Not in the top 1,000 by GitHub stars
ArabelaTso/Skills-4-SE
A curated list of 180+ useful Claude Skills for Software Engineering and resources for customizing AI for SE workflows.
History
Review weekly changes to SKILL.md before updating. Dates mark the weeks in which we observed each version; checks apply to the recorded commits.
View weekly changes
skills/abstract-domain-explorer/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Instructions only → After Instructions only
4f38503747e0 → 4f38503747e0
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Instructions only
First observation → 4f38503747e0
No earlier version was observed for comparison.
skills/abstract-invariant-generator/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Instructions only → After Instructions only
4f38503747e0 → 4f38503747e0
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Instructions only
First observation → 4f38503747e0
No earlier version was observed for comparison.
skills/abstract-state-analyzer/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Instructions only → After Instructions only
4f38503747e0 → 4f38503747e0
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Instructions only
First observation → 4f38503747e0
No earlier version was observed for comparison.
skills/abstract-trace-summarizer/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Instructions only → After Instructions only
4f38503747e0 → 4f38503747e0
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Instructions only
First observation → 4f38503747e0
No earlier version was observed for comparison.
skills/acsl-annotation-assistant/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Instructions only → After Instructions only
4f38503747e0 → 4f38503747e0
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Instructions only
First observation → 4f38503747e0
No earlier version was observed for comparison.
skills/agent-browser/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Local scripts → After Local scripts
4f38503747e0 → 4f38503747e0
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Local scripts
First observation → 4f38503747e0
No earlier version was observed for comparison.
skills/ambiguity-detector/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Instructions only → After Instructions only
4f38503747e0 → 4f38503747e0
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Instructions only
First observation → 4f38503747e0
No earlier version was observed for comparison.
skills/api-design-assistant/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Instructions only → After Instructions only
4f38503747e0 → 4f38503747e0
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Instructions only
First observation → 4f38503747e0
No earlier version was observed for comparison.
skills/api-documentation-generator/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Network or broad shell → After Network or broad shell
4f38503747e0 → 4f38503747e0
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Network or broad shell
First observation → 4f38503747e0
No earlier version was observed for comparison.
skills/assertion-synthesizer/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Instructions only → After Instructions only
4f38503747e0 → 4f38503747e0
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Instructions only
First observation → 4f38503747e0
No earlier version was observed for comparison.
skills/behavior-preservation-checker/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Network or broad shell → After Network or broad shell
4f38503747e0 → 4f38503747e0
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Network or broad shell
First observation → 4f38503747e0
No earlier version was observed for comparison.
skills/behavioral-mutation-analyzer/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Instructions only → After Instructions only
4f38503747e0 → 4f38503747e0
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Instructions only
First observation → 4f38503747e0
No earlier version was observed for comparison.
skills/bisect-aware-instrumentation/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Local scripts → After Local scripts
4f38503747e0 → 4f38503747e0
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Local scripts
First observation → 4f38503747e0
No earlier version was observed for comparison.
skills/bug-history-summarizer/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Instructions only → After Instructions only
4f38503747e0 → 4f38503747e0
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Instructions only
First observation → 4f38503747e0
No earlier version was observed for comparison.
skills/bug-localization/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Instructions only → After Instructions only
4f38503747e0 → 4f38503747e0
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Instructions only
First observation → 4f38503747e0
No earlier version was observed for comparison.
skills/bug-reproduction-test-generator/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Instructions only → After Instructions only
4f38503747e0 → 4f38503747e0
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Instructions only
First observation → 4f38503747e0
No earlier version was observed for comparison.
skills/bug-to-patch-generator/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Instructions only → After Instructions only
4f38503747e0 → 4f38503747e0
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Instructions only
First observation → 4f38503747e0
No earlier version was observed for comparison.
skills/build-ci-migration-assistant/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Local scripts → After Local scripts
4f38503747e0 → 4f38503747e0
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Local scripts
First observation → 4f38503747e0
No earlier version was observed for comparison.
skills/c-cpp-to-lean4-translator/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Instructions only → After Instructions only
4f38503747e0 → 4f38503747e0
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Instructions only
First observation → 4f38503747e0
No earlier version was observed for comparison.
skills/cd-pipeline-generator/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Network or broad shell → After Network or broad shell
4f38503747e0 → 4f38503747e0
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Network or broad shell
First observation → 4f38503747e0
No earlier version was observed for comparison.
skills/change-log-generator/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Local scripts → After Local scripts
4f38503747e0 → 4f38503747e0
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Local scripts
First observation → 4f38503747e0
No earlier version was observed for comparison.
skills/ci-pipeline-synthesizer/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Instructions only → After Instructions only
4f38503747e0 → 4f38503747e0
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Instructions only
First observation → 4f38503747e0
No earlier version was observed for comparison.
skills/code-change-summarizer/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Instructions only → After Instructions only
4f38503747e0 → 4f38503747e0
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Instructions only
First observation → 4f38503747e0
No earlier version was observed for comparison.
skills/code-comment-generator/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Network or broad shell → After Network or broad shell
4f38503747e0 → 4f38503747e0
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Network or broad shell
First observation → 4f38503747e0
No earlier version was observed for comparison.
skills/code-completion-semantic-constraints/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Instructions only → After Instructions only
4f38503747e0 → 4f38503747e0
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Instructions only
First observation → 4f38503747e0
No earlier version was observed for comparison.
skills/code-instrumentation-generator/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Instructions only → After Instructions only
4f38503747e0 → 4f38503747e0
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Instructions only
First observation → 4f38503747e0
No earlier version was observed for comparison.
skills/code-optimizer/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Instructions only → After Instructions only
4f38503747e0 → 4f38503747e0
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Instructions only
First observation → 4f38503747e0
No earlier version was observed for comparison.
skills/code-pattern-extractor/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Network or broad shell → After Network or broad shell
4f38503747e0 → 4f38503747e0
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Network or broad shell
First observation → 4f38503747e0
No earlier version was observed for comparison.
skills/code-refactoring-assistant/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Instructions only → After Instructions only
4f38503747e0 → 4f38503747e0
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Instructions only
First observation → 4f38503747e0
No earlier version was observed for comparison.
skills/code-repair-generation-combo/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Instructions only → After Instructions only
4f38503747e0 → 4f38503747e0
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Instructions only
First observation → 4f38503747e0
No earlier version was observed for comparison.
skills/code-review-assistant/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Instructions only → After Instructions only
4f38503747e0 → 4f38503747e0
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Instructions only
First observation → 4f38503747e0
No earlier version was observed for comparison.
skills/code-search-assistant/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Network or broad shell → After Network or broad shell
4f38503747e0 → 4f38503747e0
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Network or broad shell
First observation → 4f38503747e0
No earlier version was observed for comparison.
skills/code-smell-detector/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Network or broad shell → After Network or broad shell
4f38503747e0 → 4f38503747e0
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Network or broad shell
First observation → 4f38503747e0
No earlier version was observed for comparison.
skills/code-summarizer/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Instructions only → After Instructions only
4f38503747e0 → 4f38503747e0
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Instructions only
First observation → 4f38503747e0
No earlier version was observed for comparison.
skills/code-translation/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Network or broad shell → After Network or broad shell
4f38503747e0 → 4f38503747e0
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Network or broad shell
First observation → 4f38503747e0
No earlier version was observed for comparison.
skills/component-boundary-identifier/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Local scripts → After Local scripts
4f38503747e0 → 4f38503747e0
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Local scripts
First observation → 4f38503747e0
No earlier version was observed for comparison.
skills/config-consistency-checker/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Instructions only → After Instructions only
4f38503747e0 → 4f38503747e0
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Instructions only
First observation → 4f38503747e0
No earlier version was observed for comparison.
skills/configuration-generator/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Network or broad shell → After Network or broad shell
4f38503747e0 → 4f38503747e0
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Network or broad shell
First observation → 4f38503747e0
No earlier version was observed for comparison.
skills/conflict-analyzer/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Instructions only → After Instructions only
4f38503747e0 → 4f38503747e0
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Instructions only
First observation → 4f38503747e0
No earlier version was observed for comparison.
skills/containerization-assistant/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Network or broad shell → After Network or broad shell
4f38503747e0 → 4f38503747e0
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Network or broad shell
First observation → 4f38503747e0
No earlier version was observed for comparison.
skills/control-flow-abstraction-generator/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Instructions only → After Instructions only
4f38503747e0 → 4f38503747e0
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Instructions only
First observation → 4f38503747e0
No earlier version was observed for comparison.
skills/counterexample-debugger/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Instructions only → After Instructions only
4f38503747e0 → 4f38503747e0
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Instructions only
First observation → 4f38503747e0
No earlier version was observed for comparison.
skills/counterexample-explainer/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Instructions only → After Instructions only
4f38503747e0 → 4f38503747e0
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Instructions only
First observation → 4f38503747e0
No earlier version was observed for comparison.
skills/counterexample-generator/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Instructions only → After Instructions only
4f38503747e0 → 4f38503747e0
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Instructions only
First observation → 4f38503747e0
No earlier version was observed for comparison.
skills/counterexample-to-test-generator/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Local scripts → After Local scripts
4f38503747e0 → 4f38503747e0
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Local scripts
First observation → 4f38503747e0
No earlier version was observed for comparison.
skills/coverage-enhancer/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Instructions only → After Instructions only
4f38503747e0 → 4f38503747e0
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Instructions only
First observation → 4f38503747e0
No earlier version was observed for comparison.
skills/cpp-to-dafny-translator/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Instructions only → After Instructions only
4f38503747e0 → 4f38503747e0
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Instructions only
First observation → 4f38503747e0
No earlier version was observed for comparison.
skills/critical-interval-security-checker/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Local scripts → After Local scripts
4f38503747e0 → 4f38503747e0
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Local scripts
First observation → 4f38503747e0
No earlier version was observed for comparison.
skills/cve-reachability-analyzer/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Network or broad shell → After Network or broad shell
4f38503747e0 → 4f38503747e0
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Network or broad shell
First observation → 4f38503747e0
No earlier version was observed for comparison.
skills/cve-watchlist-action-recommendation-generator/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Local scripts → After Local scripts
4f38503747e0 → 4f38503747e0
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Local scripts
First observation → 4f38503747e0
No earlier version was observed for comparison.
skills/dead-code-eliminator/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Local scripts → After Local scripts
4f38503747e0 → 4f38503747e0
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Local scripts
First observation → 4f38503747e0
No earlier version was observed for comparison.
skills/dead-code-removal/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Instructions only → After Instructions only
4f38503747e0 → 4f38503747e0
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Instructions only
First observation → 4f38503747e0
No earlier version was observed for comparison.
skills/dependency-resolver/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Network or broad shell → After Network or broad shell
4f38503747e0 → 4f38503747e0
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Network or broad shell
First observation → 4f38503747e0
No earlier version was observed for comparison.
skills/deprecated-api-updater/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Network or broad shell → After Network or broad shell
4f38503747e0 → 4f38503747e0
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Network or broad shell
First observation → 4f38503747e0
No earlier version was observed for comparison.
skills/design-pattern-suggestor/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Instructions only → After Instructions only
4f38503747e0 → 4f38503747e0
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Instructions only
First observation → 4f38503747e0
No earlier version was observed for comparison.
skills/design-smell-detector/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Local scripts → After Local scripts
4f38503747e0 → 4f38503747e0
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Local scripts
First observation → 4f38503747e0
No earlier version was observed for comparison.
skills/directed-test-input-generator/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Network or broad shell → After Network or broad shell
4f38503747e0 → 4f38503747e0
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Network or broad shell
First observation → 4f38503747e0
No earlier version was observed for comparison.
skills/edge-case-generator/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Network or broad shell → After Network or broad shell
4f38503747e0 → 4f38503747e0
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Network or broad shell
First observation → 4f38503747e0
No earlier version was observed for comparison.
skills/environment-setup-assistant/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Network or broad shell → After Network or broad shell
4f38503747e0 → 4f38503747e0
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Network or broad shell
First observation → 4f38503747e0
No earlier version was observed for comparison.
skills/error-explanation-generator/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Network or broad shell → After Network or broad shell
4f38503747e0 → 4f38503747e0
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Network or broad shell
First observation → 4f38503747e0
No earlier version was observed for comparison.
skills/exploitability-analyzer/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Network or broad shell → After Network or broad shell
4f38503747e0 → 4f38503747e0
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Network or broad shell
First observation → 4f38503747e0
No earlier version was observed for comparison.
skills/failure-oriented-instrumentation/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Instructions only → After Instructions only
4f38503747e0 → 4f38503747e0
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Instructions only
First observation → 4f38503747e0
No earlier version was observed for comparison.
skills/flaky-test-detector/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Network or broad shell → After Network or broad shell
4f38503747e0 → 4f38503747e0
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Network or broad shell
First observation → 4f38503747e0
No earlier version was observed for comparison.
skills/formal-spec-generator/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Instructions only → After Instructions only
4f38503747e0 → 4f38503747e0
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Instructions only
First observation → 4f38503747e0
No earlier version was observed for comparison.
skills/framework-migration-assistant/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Local scripts → After Local scripts
4f38503747e0 → 4f38503747e0
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Local scripts
First observation → 4f38503747e0
No earlier version was observed for comparison.
skills/frontend-ui-ux/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Instructions only → After Instructions only
4f38503747e0 → 4f38503747e0
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Instructions only
First observation → 4f38503747e0
No earlier version was observed for comparison.
skills/function-class-generator/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Instructions only → After Instructions only
4f38503747e0 → 4f38503747e0
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Instructions only
First observation → 4f38503747e0
No earlier version was observed for comparison.
skills/fuzzing-input-generator/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Instructions only → After Instructions only
4f38503747e0 → 4f38503747e0
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Instructions only
First observation → 4f38503747e0
No earlier version was observed for comparison.
skills/git-bisect-assistant/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Local scripts → After Local scripts
4f38503747e0 → 4f38503747e0
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Local scripts
First observation → 4f38503747e0
No earlier version was observed for comparison.
skills/git-master/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Instructions only → After Instructions only
4f38503747e0 → 4f38503747e0
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Instructions only
First observation → 4f38503747e0
No earlier version was observed for comparison.
skills/github-triage/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Instructions only → After Instructions only
4f38503747e0 → 4f38503747e0
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Instructions only
First observation → 4f38503747e0
No earlier version was observed for comparison.
skills/imperative-to-coq-model-extractor/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Instructions only → After Instructions only
4f38503747e0 → 4f38503747e0
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Instructions only
First observation → 4f38503747e0
No earlier version was observed for comparison.
skills/incremental-java-programmer/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Instructions only → After Instructions only
4f38503747e0 → 4f38503747e0
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Instructions only
First observation → 4f38503747e0
No earlier version was observed for comparison.
skills/incremental-python-programmer/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Local scripts → After Local scripts
4f38503747e0 → 4f38503747e0
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Local scripts
First observation → 4f38503747e0
No earlier version was observed for comparison.
skills/init-deep/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Instructions only → After Instructions only
4f38503747e0 → 4f38503747e0
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Instructions only
First observation → 4f38503747e0
No earlier version was observed for comparison.
skills/integration-test-generator/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Network or broad shell → After Network or broad shell
4f38503747e0 → 4f38503747e0
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Network or broad shell
First observation → 4f38503747e0
No earlier version was observed for comparison.
skills/interface-contract-verifier/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Local scripts → After Local scripts
4f38503747e0 → 4f38503747e0
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Local scripts
First observation → 4f38503747e0
No earlier version was observed for comparison.
skills/interface-specification-generator/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Local scripts → After Local scripts
4f38503747e0 → 4f38503747e0
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Local scripts
First observation → 4f38503747e0
No earlier version was observed for comparison.
skills/interval-difference-analyzer/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Network or broad shell → After Network or broad shell
4f38503747e0 → 4f38503747e0
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Network or broad shell
First observation → 4f38503747e0
No earlier version was observed for comparison.
skills/interval-guided-regression-test-update/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Instructions only → After Instructions only
4f38503747e0 → 4f38503747e0
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Instructions only
First observation → 4f38503747e0
No earlier version was observed for comparison.
skills/interval-profiling-performance-analyzer/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Network or broad shell → After Network or broad shell
4f38503747e0 → 4f38503747e0
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Network or broad shell
First observation → 4f38503747e0
No earlier version was observed for comparison.
skills/invariant-inference/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Instructions only → After Instructions only
4f38503747e0 → 4f38503747e0
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Instructions only
First observation → 4f38503747e0
No earlier version was observed for comparison.
skills/issue-report-generator/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Instructions only → After Instructions only
4f38503747e0 → 4f38503747e0
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Instructions only
First observation → 4f38503747e0
No earlier version was observed for comparison.
skills/java-api-consistency-validator/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Local scripts → After Local scripts
4f38503747e0 → 4f38503747e0
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Local scripts
First observation → 4f38503747e0
No earlier version was observed for comparison.
skills/java-regression-test-generator/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Instructions only → After Instructions only
4f38503747e0 → 4f38503747e0
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Instructions only
First observation → 4f38503747e0
No earlier version was observed for comparison.
skills/java-test-updater/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Instructions only → After Instructions only
4f38503747e0 → 4f38503747e0
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Instructions only
First observation → 4f38503747e0
No earlier version was observed for comparison.
skills/legacy-code-summarizer/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Network or broad shell → After Network or broad shell
4f38503747e0 → 4f38503747e0
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Network or broad shell
First observation → 4f38503747e0
No earlier version was observed for comparison.
skills/lemma-discovery-assistant/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Instructions only → After Instructions only
4f38503747e0 → 4f38503747e0
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Instructions only
First observation → 4f38503747e0
No earlier version was observed for comparison.
skills/library-for-proof-advisor/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Instructions only → After Instructions only
4f38503747e0 → 4f38503747e0
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Instructions only
First observation → 4f38503747e0
No earlier version was observed for comparison.
skills/linkedin/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Network or broad shell → After Network or broad shell
4f38503747e0 → 4f38503747e0
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Network or broad shell
First observation → 4f38503747e0
No earlier version was observed for comparison.
skills/lsp-refactoring/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Instructions only → After Instructions only
4f38503747e0 → 4f38503747e0
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Instructions only
First observation → 4f38503747e0
No earlier version was observed for comparison.
skills/markdown-document-structurer/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Local scripts → After Local scripts
4f38503747e0 → 4f38503747e0
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Local scripts
First observation → 4f38503747e0
No earlier version was observed for comparison.
skills/metamorphic-property-extractor/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Instructions only → After Instructions only
4f38503747e0 → 4f38503747e0
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Instructions only
First observation → 4f38503747e0
No earlier version was observed for comparison.
skills/metamorphic-test-generator/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Local scripts → After Local scripts
4f38503747e0 → 4f38503747e0
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Local scripts
First observation → 4f38503747e0
No earlier version was observed for comparison.
skills/mocking-test-generator/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Instructions only → After Instructions only
4f38503747e0 → 4f38503747e0
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Instructions only
First observation → 4f38503747e0
No earlier version was observed for comparison.
skills/model-guided-code-repair/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Instructions only → After Instructions only
4f38503747e0 → 4f38503747e0
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Instructions only
First observation → 4f38503747e0
No earlier version was observed for comparison.
skills/modular-code-enforcement/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Instructions only → After Instructions only
4f38503747e0 → 4f38503747e0
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Instructions only
First observation → 4f38503747e0
No earlier version was observed for comparison.
skills/module-component-generator/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Instructions only → After Instructions only
4f38503747e0 → 4f38503747e0
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Instructions only
First observation → 4f38503747e0
No earlier version was observed for comparison.
skills/module-level-code-translator/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Network or broad shell → After Network or broad shell
4f38503747e0 → 4f38503747e0
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Network or broad shell
First observation → 4f38503747e0
No earlier version was observed for comparison.
skills/multi-version-behavior-comparator/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Instructions only → After Instructions only
4f38503747e0 → 4f38503747e0
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Instructions only
First observation → 4f38503747e0
No earlier version was observed for comparison.
skills/mutation-test-suite-optimizer/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Instructions only → After Instructions only
4f38503747e0 → 4f38503747e0
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Instructions only
First observation → 4f38503747e0
No earlier version was observed for comparison.
skills/nl-to-constraints/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Instructions only → After Instructions only
4f38503747e0 → 4f38503747e0
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Instructions only
First observation → 4f38503747e0
No earlier version was observed for comparison.
skills/playwright-automation/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Instructions only → After Instructions only
4f38503747e0 → 4f38503747e0
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Instructions only
First observation → 4f38503747e0
No earlier version was observed for comparison.
skills/program-correctness-prover/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Instructions only → After Instructions only
4f38503747e0 → 4f38503747e0
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Instructions only
First observation → 4f38503747e0
No earlier version was observed for comparison.
skills/program-to-model-extractor/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Instructions only → After Instructions only
4f38503747e0 → 4f38503747e0
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Instructions only
First observation → 4f38503747e0
No earlier version was observed for comparison.
skills/program-to-tlaplus-spec-generator/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Instructions only → After Instructions only
4f38503747e0 → 4f38503747e0
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Instructions only
First observation → 4f38503747e0
No earlier version was observed for comparison.
skills/proof-carrying-code-generator/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Instructions only → After Instructions only
4f38503747e0 → 4f38503747e0
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Instructions only
First observation → 4f38503747e0
No earlier version was observed for comparison.
skills/proof-failure-explainer/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Instructions only → After Instructions only
4f38503747e0 → 4f38503747e0
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Instructions only
First observation → 4f38503747e0
No earlier version was observed for comparison.
skills/proof-refactoring-assistant/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Instructions only → After Instructions only
4f38503747e0 → 4f38503747e0
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Instructions only
First observation → 4f38503747e0
No earlier version was observed for comparison.
skills/proof-skeleton-generator/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Instructions only → After Instructions only
4f38503747e0 → 4f38503747e0
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Instructions only
First observation → 4f38503747e0
No earlier version was observed for comparison.
skills/proof-trace-summarizer/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Instructions only → After Instructions only
4f38503747e0 → 4f38503747e0
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Instructions only
First observation → 4f38503747e0
No earlier version was observed for comparison.
skills/pseudocode-extractor/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Instructions only → After Instructions only
4f38503747e0 → 4f38503747e0
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Instructions only
First observation → 4f38503747e0
No earlier version was observed for comparison.
skills/pseudocode-to-java-code/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Instructions only → After Instructions only
4f38503747e0 → 4f38503747e0
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Instructions only
First observation → 4f38503747e0
No earlier version was observed for comparison.
skills/pseudocode-to-python-code/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Local scripts → After Local scripts
4f38503747e0 → 4f38503747e0
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Local scripts
First observation → 4f38503747e0
No earlier version was observed for comparison.
skills/python-api-consistency-validator/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Local scripts → After Local scripts
4f38503747e0 → 4f38503747e0
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Local scripts
First observation → 4f38503747e0
No earlier version was observed for comparison.
skills/python-regression-test-generator/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Network or broad shell → After Network or broad shell
4f38503747e0 → 4f38503747e0
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Network or broad shell
First observation → 4f38503747e0
No earlier version was observed for comparison.
skills/python-repo-quickstart/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Local scripts → After Local scripts
4f38503747e0 → 4f38503747e0
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Local scripts
First observation → 4f38503747e0
No earlier version was observed for comparison.
skills/python-test-updater/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Network or broad shell → After Network or broad shell
4f38503747e0 → 4f38503747e0
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Network or broad shell
First observation → 4f38503747e0
No earlier version was observed for comparison.
skills/python-to-dafny-translator/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Instructions only → After Instructions only
4f38503747e0 → 4f38503747e0
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Instructions only
First observation → 4f38503747e0
No earlier version was observed for comparison.
skills/python-to-lean4-translator/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Network or broad shell → After Network or broad shell
4f38503747e0 → 4f38503747e0
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Network or broad shell
First observation → 4f38503747e0
No earlier version was observed for comparison.
skills/readme-generator/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Network or broad shell → After Network or broad shell
4f38503747e0 → 4f38503747e0
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Network or broad shell
First observation → 4f38503747e0
No earlier version was observed for comparison.
skills/reference-searcher/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Instructions only → After Instructions only
4f38503747e0 → 4f38503747e0
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Instructions only
First observation → 4f38503747e0
No earlier version was observed for comparison.
skills/refinement-step-generator/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Instructions only → After Instructions only
4f38503747e0 → 4f38503747e0
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Instructions only
First observation → 4f38503747e0
No earlier version was observed for comparison.
skills/regression-consistency-checker/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Local scripts → After Local scripts
4f38503747e0 → 4f38503747e0
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Local scripts
First observation → 4f38503747e0
No earlier version was observed for comparison.
skills/regression-root-cause-analyzer/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Instructions only → After Instructions only
4f38503747e0 → 4f38503747e0
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Instructions only
First observation → 4f38503747e0
No earlier version was observed for comparison.
skills/release-change-analyzer/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Instructions only → After Instructions only
4f38503747e0 → 4f38503747e0
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Instructions only
First observation → 4f38503747e0
No earlier version was observed for comparison.
skills/release-notes-writer/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Instructions only → After Instructions only
4f38503747e0 → 4f38503747e0
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Instructions only
First observation → 4f38503747e0
No earlier version was observed for comparison.
skills/replay-oriented-instrumentation/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Instructions only → After Instructions only
4f38503747e0 → 4f38503747e0
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Instructions only
First observation → 4f38503747e0
No earlier version was observed for comparison.
skills/reproduction-trace-instrumenter/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Local scripts → After Local scripts
4f38503747e0 → 4f38503747e0
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Local scripts
First observation → 4f38503747e0
No earlier version was observed for comparison.
skills/req-to-test/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Instructions only → After Instructions only
4f38503747e0 → 4f38503747e0
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Instructions only
First observation → 4f38503747e0
No earlier version was observed for comparison.
skills/requirement-comparison-reporter/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Local scripts → After Local scripts
4f38503747e0 → 4f38503747e0
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Local scripts
First observation → 4f38503747e0
No earlier version was observed for comparison.
skills/requirement-coverage-checker/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Instructions only → After Instructions only
4f38503747e0 → 4f38503747e0
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Instructions only
First observation → 4f38503747e0
No earlier version was observed for comparison.
skills/requirement-enhancer/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Instructions only → After Instructions only
4f38503747e0 → 4f38503747e0
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Instructions only
First observation → 4f38503747e0
No earlier version was observed for comparison.
skills/requirement-summarizer/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Instructions only → After Instructions only
4f38503747e0 → 4f38503747e0
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Instructions only
First observation → 4f38503747e0
No earlier version was observed for comparison.
skills/requirement-summary/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Instructions only → After Instructions only
4f38503747e0 → 4f38503747e0
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Instructions only
First observation → 4f38503747e0
No earlier version was observed for comparison.
skills/requirement-to-tlaplus-property-generator/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Instructions only → After Instructions only
4f38503747e0 → 4f38503747e0
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Instructions only
First observation → 4f38503747e0
No earlier version was observed for comparison.
skills/rollback-strategy-advisor/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Network or broad shell → After Network or broad shell
4f38503747e0 → 4f38503747e0
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Network or broad shell
First observation → 4f38503747e0
No earlier version was observed for comparison.
skills/rtl-equivalence-checker/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Local scripts → After Local scripts
4f38503747e0 → 4f38503747e0
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Local scripts
First observation → 4f38503747e0
No earlier version was observed for comparison.
skills/rtl-property-inference/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Instructions only → After Instructions only
4f38503747e0 → 4f38503747e0
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Instructions only
First observation → 4f38503747e0
No earlier version was observed for comparison.
skills/rtl-specification-consistency-checker/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Instructions only → After Instructions only
4f38503747e0 → 4f38503747e0
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Instructions only
First observation → 4f38503747e0
No earlier version was observed for comparison.
skills/runtime-error-explainer/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Instructions only → After Instructions only
4f38503747e0 → 4f38503747e0
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Instructions only
First observation → 4f38503747e0
No earlier version was observed for comparison.
skills/scenario-generator/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Instructions only → After Instructions only
4f38503747e0 → 4f38503747e0
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Instructions only
First observation → 4f38503747e0
No earlier version was observed for comparison.
skills/security-patch-advisor/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Network or broad shell → After Network or broad shell
4f38503747e0 → 4f38503747e0
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Network or broad shell
First observation → 4f38503747e0
No earlier version was observed for comparison.
skills/security-sensitive-path-instrumenter/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Local scripts → After Local scripts
4f38503747e0 → 4f38503747e0
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Local scripts
First observation → 4f38503747e0
No earlier version was observed for comparison.
skills/semantic-bug-detector/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Instructions only → After Instructions only
4f38503747e0 → 4f38503747e0
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Instructions only
First observation → 4f38503747e0
No earlier version was observed for comparison.
skills/semantic-equivalence-verifier/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Network or broad shell → After Network or broad shell
4f38503747e0 → 4f38503747e0
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Network or broad shell
First observation → 4f38503747e0
No earlier version was observed for comparison.
skills/semantic-szz-analyzer/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Network or broad shell → After Network or broad shell
4f38503747e0 → 4f38503747e0
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Network or broad shell
First observation → 4f38503747e0
No earlier version was observed for comparison.
skills/session-handoff/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Instructions only → After Instructions only
4f38503747e0 → 4f38503747e0
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Instructions only
First observation → 4f38503747e0
No earlier version was observed for comparison.
skills/skill-creator/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Local scripts → After Local scripts
4f38503747e0 → 4f38503747e0
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Local scripts
First observation → 4f38503747e0
No earlier version was observed for comparison.
skills/smart-mutation-operator-generator/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Local scripts → After Local scripts
4f38503747e0 → 4f38503747e0
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Local scripts
First observation → 4f38503747e0
No earlier version was observed for comparison.
skills/smv-model-extractor/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Local scripts → After Local scripts
4f38503747e0 → 4f38503747e0
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Local scripts
First observation → 4f38503747e0
No earlier version was observed for comparison.
skills/specification-driven-generation/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Instructions only → After Instructions only
4f38503747e0 → 4f38503747e0
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Instructions only
First observation → 4f38503747e0
No earlier version was observed for comparison.
skills/specification-generator/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Instructions only → After Instructions only
4f38503747e0 → 4f38503747e0
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Instructions only
First observation → 4f38503747e0
No earlier version was observed for comparison.
skills/specification-to-temporal-logic-generator/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Local scripts → After Local scripts
4f38503747e0 → 4f38503747e0
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Local scripts
First observation → 4f38503747e0
No earlier version was observed for comparison.
skills/spring-mvc-to-boot-migrator/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Network or broad shell → After Network or broad shell
4f38503747e0 → 4f38503747e0
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Network or broad shell
First observation → 4f38503747e0
No earlier version was observed for comparison.
skills/state-snapshot-instrumenter/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Local scripts → After Local scripts
4f38503747e0 → 4f38503747e0
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Local scripts
First observation → 4f38503747e0
No earlier version was observed for comparison.
skills/static-bug-detector/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Instructions only → After Instructions only
4f38503747e0 → 4f38503747e0
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Instructions only
First observation → 4f38503747e0
No earlier version was observed for comparison.
skills/static-reasoning-verifier/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Local scripts → After Local scripts
4f38503747e0 → 4f38503747e0
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Local scripts
First observation → 4f38503747e0
No earlier version was observed for comparison.
skills/static-vulnerability-detector/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Network or broad shell → After Network or broad shell
4f38503747e0 → 4f38503747e0
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Network or broad shell
First observation → 4f38503747e0
No earlier version was observed for comparison.
skills/strategic-planner/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Instructions only → After Instructions only
4f38503747e0 → 4f38503747e0
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Instructions only
First observation → 4f38503747e0
No earlier version was observed for comparison.
skills/symbolic-execution-assistant/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Network or broad shell → After Network or broad shell
4f38503747e0 → 4f38503747e0
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Network or broad shell
First observation → 4f38503747e0
No earlier version was observed for comparison.
skills/system-diagram-generator/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Instructions only → After Instructions only
4f38503747e0 → 4f38503747e0
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Instructions only
First observation → 4f38503747e0
No earlier version was observed for comparison.
skills/szz-bug-identifier/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Local scripts → After Local scripts
4f38503747e0 → 4f38503747e0
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Local scripts
First observation → 4f38503747e0
No earlier version was observed for comparison.
skills/tactic-suggestion-assistant/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Instructions only → After Instructions only
4f38503747e0 → 4f38503747e0
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Instructions only
First observation → 4f38503747e0
No earlier version was observed for comparison.
skills/taint-instrumentation-assistant/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Local scripts → After Local scripts
4f38503747e0 → 4f38503747e0
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Local scripts
First observation → 4f38503747e0
No earlier version was observed for comparison.
skills/technical-debt-analyzer/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Instructions only → After Instructions only
4f38503747e0 → 4f38503747e0
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Instructions only
First observation → 4f38503747e0
No earlier version was observed for comparison.
skills/template-code-generator/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Network or broad shell → After Network or broad shell
4f38503747e0 → 4f38503747e0
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Network or broad shell
First observation → 4f38503747e0
No earlier version was observed for comparison.
skills/test-case-documentation/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Local scripts → After Local scripts
4f38503747e0 → 4f38503747e0
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Local scripts
First observation → 4f38503747e0
No earlier version was observed for comparison.
skills/test-case-reducer/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Local scripts → After Local scripts
4f38503747e0 → 4f38503747e0
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Local scripts
First observation → 4f38503747e0
No earlier version was observed for comparison.
skills/test-deduplicator/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Local scripts → After Local scripts
4f38503747e0 → 4f38503747e0
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Local scripts
First observation → 4f38503747e0
No earlier version was observed for comparison.
skills/test-driven-generation/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Instructions only → After Instructions only
4f38503747e0 → 4f38503747e0
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Instructions only
First observation → 4f38503747e0
No earlier version was observed for comparison.
skills/test-guided-bug-detector/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Instructions only → After Instructions only
4f38503747e0 → 4f38503747e0
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Instructions only
First observation → 4f38503747e0
No earlier version was observed for comparison.
skills/test-guided-debloating/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Local scripts → After Local scripts
4f38503747e0 → 4f38503747e0
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Local scripts
First observation → 4f38503747e0
No earlier version was observed for comparison.
skills/test-guided-migration-assistant/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Local scripts → After Local scripts
4f38503747e0 → 4f38503747e0
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Local scripts
First observation → 4f38503747e0
No earlier version was observed for comparison.
skills/test-oracle-generator/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Instructions only → After Instructions only
4f38503747e0 → 4f38503747e0
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Instructions only
First observation → 4f38503747e0
No earlier version was observed for comparison.
skills/test-suite-prioritizer/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Instructions only → After Instructions only
4f38503747e0 → 4f38503747e0
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Instructions only
First observation → 4f38503747e0
No earlier version was observed for comparison.
skills/time-aware-dependency-cve-scanner/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Network or broad shell → After Network or broad shell
4f38503747e0 → 4f38503747e0
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Network or broad shell
First observation → 4f38503747e0
No earlier version was observed for comparison.
skills/tlaplus-guided-code-repair/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Local scripts → After Local scripts
4f38503747e0 → 4f38503747e0
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Local scripts
First observation → 4f38503747e0
No earlier version was observed for comparison.
skills/tlaplus-model-reduction/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Instructions only → After Instructions only
4f38503747e0 → 4f38503747e0
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Instructions only
First observation → 4f38503747e0
No earlier version was observed for comparison.
skills/tlaplus-spec-generator/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Local scripts → After Local scripts
4f38503747e0 → 4f38503747e0
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Local scripts
First observation → 4f38503747e0
No earlier version was observed for comparison.
skills/trace-collection-assistant/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Local scripts → After Local scripts
4f38503747e0 → 4f38503747e0
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Local scripts
First observation → 4f38503747e0
No earlier version was observed for comparison.
skills/traceability-matrix-generator/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Instructions only → After Instructions only
4f38503747e0 → 4f38503747e0
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Instructions only
First observation → 4f38503747e0
No earlier version was observed for comparison.
skills/unit-test-generator/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Network or broad shell → After Network or broad shell
4f38503747e0 → 4f38503747e0
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Network or broad shell
First observation → 4f38503747e0
No earlier version was observed for comparison.
skills/verification-boundary-reporter/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Instructions only → After Instructions only
4f38503747e0 → 4f38503747e0
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Instructions only
First observation → 4f38503747e0
No earlier version was observed for comparison.
skills/verified-pseudocode-extractor/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Instructions only → After Instructions only
4f38503747e0 → 4f38503747e0
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Instructions only
First observation → 4f38503747e0
No earlier version was observed for comparison.
skills/verified-spec-code-mapper/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Instructions only → After Instructions only
4f38503747e0 → 4f38503747e0
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Instructions only
First observation → 4f38503747e0
No earlier version was observed for comparison.
skills/vulnerability-pattern-matcher/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Network or broad shell → After Network or broad shell
4f38503747e0 → 4f38503747e0
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Network or broad shell
First observation → 4f38503747e0
No earlier version was observed for comparison.
skills/vulnerability-root-cause-analyzer/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Instructions only → After Instructions only
4f38503747e0 → 4f38503747e0
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Instructions only
First observation → 4f38503747e0
No earlier version was observed for comparison.
260GitHub stars
1star in 7 days
188skills in this repository
0commits in 30 days
Heat
1.7- Star growth, last 7 daysNot available
- Star growth, last 24 hoursNot available
- Rank movement, last 7 daysNot available
- Commits, last 30 daysNot available
- Accounts asking about it through MCP, last 7 daysNot available
- Hot votes this weekNot available
Heat never changes the order by stars, and sponsorship never touches it. How heat works
Stars over time
30-day change not yet available: not enough history.
Individual skills in this repository
- abstract-domain-explorer
skills/abstract-domain-explorer - abstract-invariant-generator
skills/abstract-invariant-generator - abstract-state-analyzer
skills/abstract-state-analyzer - abstract-trace-summarizer
skills/abstract-trace-summarizer - acsl-annotation-assistant
skills/acsl-annotation-assistant - agent-browser
skills/agent-browser - ambiguity-detector
skills/ambiguity-detector - api-design-assistant
skills/api-design-assistant - api-documentation-generator
skills/api-documentation-generator - assertion-synthesizer
skills/assertion-synthesizer - behavior-preservation-checker
skills/behavior-preservation-checker - behavioral-mutation-analyzer
skills/behavioral-mutation-analyzer - bisect-aware-instrumentation
skills/bisect-aware-instrumentation - bug-history-summarizer
skills/bug-history-summarizer - bug-localization
skills/bug-localization - bug-reproduction-test-generator
skills/bug-reproduction-test-generator - bug-to-patch-generator
skills/bug-to-patch-generator - build-ci-migration-assistant
skills/build-ci-migration-assistant - c-cpp-to-lean4-translator
skills/c-cpp-to-lean4-translator - cd-pipeline-generator
skills/cd-pipeline-generator - change-log-generator
skills/change-log-generator - ci-pipeline-synthesizer
skills/ci-pipeline-synthesizer - code-change-summarizer
skills/code-change-summarizer - code-comment-generator
skills/code-comment-generator - code-completion-semantic-constraints
skills/code-completion-semantic-constraints - code-instrumentation-generator
skills/code-instrumentation-generator - code-optimizer
skills/code-optimizer - code-pattern-extractor
skills/code-pattern-extractor - code-refactoring-assistant
skills/code-refactoring-assistant - code-repair-generation-combo
skills/code-repair-generation-combo - code-review-assistant
skills/code-review-assistant - code-search-assistant
skills/code-search-assistant - code-smell-detector
skills/code-smell-detector - code-summarizer
skills/code-summarizer - code-translation
skills/code-translation - component-boundary-identifier
skills/component-boundary-identifier - config-consistency-checker
skills/config-consistency-checker - configuration-generator
skills/configuration-generator - conflict-analyzer
skills/conflict-analyzer - containerization-assistant
skills/containerization-assistant - control-flow-abstraction-generator
skills/control-flow-abstraction-generator - counterexample-debugger
skills/counterexample-debugger - counterexample-explainer
skills/counterexample-explainer - counterexample-generator
skills/counterexample-generator - counterexample-to-test-generator
skills/counterexample-to-test-generator - coverage-enhancer
skills/coverage-enhancer - cpp-to-dafny-translator
skills/cpp-to-dafny-translator - critical-interval-security-checker
skills/critical-interval-security-checker - cve-reachability-analyzer
skills/cve-reachability-analyzer - cve-watchlist-action-recommendation-generator
skills/cve-watchlist-action-recommendation-generator - dead-code-eliminator
skills/dead-code-eliminator - dead-code-removal
skills/dead-code-removal - dependency-resolver
skills/dependency-resolver - deprecated-api-updater
skills/deprecated-api-updater - design-pattern-suggestor
skills/design-pattern-suggestor - design-smell-detector
skills/design-smell-detector - directed-test-input-generator
skills/directed-test-input-generator - edge-case-generator
skills/edge-case-generator - environment-setup-assistant
skills/environment-setup-assistant - error-explanation-generator
skills/error-explanation-generator - exploitability-analyzer
skills/exploitability-analyzer - failure-oriented-instrumentation
skills/failure-oriented-instrumentation - flaky-test-detector
skills/flaky-test-detector - formal-spec-generator
skills/formal-spec-generator - framework-migration-assistant
skills/framework-migration-assistant - frontend-ui-ux
skills/frontend-ui-ux - function-class-generator
skills/function-class-generator - fuzzing-input-generator
skills/fuzzing-input-generator - git-bisect-assistant
skills/git-bisect-assistant - git-master
skills/git-master - github-triage
skills/github-triage - imperative-to-coq-model-extractor
skills/imperative-to-coq-model-extractor - incremental-java-programmer
skills/incremental-java-programmer - incremental-python-programmer
skills/incremental-python-programmer - init-deep
skills/init-deep - integration-test-generator
skills/integration-test-generator - interface-contract-verifier
skills/interface-contract-verifier - interface-specification-generator
skills/interface-specification-generator - interval-difference-analyzer
skills/interval-difference-analyzer - interval-guided-regression-test-update
skills/interval-guided-regression-test-update - interval-profiling-performance-analyzer
skills/interval-profiling-performance-analyzer - invariant-inference
skills/invariant-inference - issue-report-generator
skills/issue-report-generator - java-api-consistency-validator
skills/java-api-consistency-validator - java-regression-test-generator
skills/java-regression-test-generator - java-test-updater
skills/java-test-updater - legacy-code-summarizer
skills/legacy-code-summarizer - lemma-discovery-assistant
skills/lemma-discovery-assistant - library-advisor
skills/library-for-proof-advisor - linkedin
skills/linkedin - lsp-refactoring
skills/lsp-refactoring - markdown-document-structurer
skills/markdown-document-structurer - metamorphic-property-extractor
skills/metamorphic-property-extractor - metamorphic-test-generator
skills/metamorphic-test-generator - mocking-test-generator
skills/mocking-test-generator - model-guided-code-repair
skills/model-guided-code-repair - modular-code-enforcement
skills/modular-code-enforcement - module-component-generator
skills/module-component-generator - module-level-code-translator
skills/module-level-code-translator - multi-version-behavior-comparator
skills/multi-version-behavior-comparator - mutation-test-suite-optimizer
skills/mutation-test-suite-optimizer - nl-to-constraints
skills/nl-to-constraints - playwright-automation
skills/playwright-automation - program-correctness-prover
skills/program-correctness-prover - program-to-model-extractor
skills/program-to-model-extractor - program-to-tlaplus-spec-generator
skills/program-to-tlaplus-spec-generator - proof-carrying-code-generator
skills/proof-carrying-code-generator - proof-failure-explainer
skills/proof-failure-explainer - proof-refactoring-assistant
skills/proof-refactoring-assistant - proof-skeleton-generator
skills/proof-skeleton-generator - proof-trace-summarizer
skills/proof-trace-summarizer - pseudocode-extractor
skills/pseudocode-extractor - pseudocode-to-java-code
skills/pseudocode-to-java-code - pseudocode-to-python-code
skills/pseudocode-to-python-code - python-api-consistency-validator
skills/python-api-consistency-validator - python-regression-test-generator
skills/python-regression-test-generator - python-repo-quickstart
skills/python-repo-quickstart - python-test-updater
skills/python-test-updater - python-to-dafny-translator
skills/python-to-dafny-translator - python-to-lean4-translator
skills/python-to-lean4-translator - readme-generator
skills/readme-generator - reference-searcher
skills/reference-searcher - refinement-step-generator
skills/refinement-step-generator - regression-consistency-checker
skills/regression-consistency-checker - regression-root-cause-analyzer
skills/regression-root-cause-analyzer - release-change-analyzer
skills/release-change-analyzer - release-notes-writer
skills/release-notes-writer - replay-oriented-instrumentation
skills/replay-oriented-instrumentation - reproduction-trace-instrumenter
skills/reproduction-trace-instrumenter - req-to-test
skills/req-to-test - requirement-comparison-reporter
skills/requirement-comparison-reporter - requirement-coverage-checker
skills/requirement-coverage-checker - requirement-enhancer
skills/requirement-enhancer - requirement-summarizer
skills/requirement-summarizer - requirement-summary
skills/requirement-summary - requirement-to-tlaplus-property-generator
skills/requirement-to-tlaplus-property-generator - rollback-strategy-advisor
skills/rollback-strategy-advisor - rtl-equivalence-checker
skills/rtl-equivalence-checker - rtl-property-inference
skills/rtl-property-inference - rtl-specification-consistency-checker
skills/rtl-specification-consistency-checker - runtime-error-explainer
skills/runtime-error-explainer - scenario-generator
skills/scenario-generator - security-patch-advisor
skills/security-patch-advisor - security-sensitive-path-instrumenter
skills/security-sensitive-path-instrumenter - semantic-bug-detector
skills/semantic-bug-detector - semantic-equivalence-verifier
skills/semantic-equivalence-verifier - semantic-szz-analyzer
skills/semantic-szz-analyzer - session-handoff
skills/session-handoff - skill-creator
skills/skill-creator - smart-mutation-operator-generator
skills/smart-mutation-operator-generator - smv-model-extractor
skills/smv-model-extractor - specification-driven-generation
skills/specification-driven-generation - specification-generator
skills/specification-generator - specification-to-temporal-logic-generator
skills/specification-to-temporal-logic-generator - spring-mvc-to-boot-migrator
skills/spring-mvc-to-boot-migrator - state-snapshot-instrumenter
skills/state-snapshot-instrumenter - static-bug-detector
skills/static-bug-detector - static-reasoning-verifier
skills/static-reasoning-verifier - static-vulnerability-detector
skills/static-vulnerability-detector - strategic-planner
skills/strategic-planner - symbolic-execution-assistant
skills/symbolic-execution-assistant - system-diagram-generator
skills/system-diagram-generator - szz-bug-introducing-commit-identifier
skills/szz-bug-identifier - tactic-suggestion-assistant
skills/tactic-suggestion-assistant - taint-instrumentation-assistant
skills/taint-instrumentation-assistant - technical-debt-analyzer
skills/technical-debt-analyzer - template-code-generator
skills/template-code-generator - test-case-documentation
skills/test-case-documentation - test-case-reducer
skills/test-case-reducer - test-deduplicator
skills/test-deduplicator - test-driven-generation
skills/test-driven-generation - test-guided-bug-detector
skills/test-guided-bug-detector - test-guided-debloating
skills/test-guided-debloating - test-guided-migration-assistant
skills/test-guided-migration-assistant - test-oracle-generator
skills/test-oracle-generator - test-suite-prioritizer
skills/test-suite-prioritizer - time-aware-dependency-cve-scanner
skills/time-aware-dependency-cve-scanner - tlaplus-guided-code-repair
skills/tlaplus-guided-code-repair - tlaplus-model-reduction
skills/tlaplus-model-reduction - tlaplus-spec-generator
skills/tlaplus-spec-generator - trace-collection-assistant
skills/trace-collection-assistant - traceability-matrix-generator
skills/traceability-matrix-generator - unit-test-generator
skills/unit-test-generator - verification-boundary-reporter
skills/verification-boundary-reporter - verified-pseudocode-extractor
skills/verified-pseudocode-extractor - verified-spec-code-mapper
skills/verified-spec-code-mapper - vulnerability-pattern-matcher
skills/vulnerability-pattern-matcher - vulnerability-root-cause-analyzer
skills/vulnerability-root-cause-analyzer
How it works
abstract-domain-explorer
When your agent uses it
Applies abstract interpretation using different abstract domains (intervals, octagons, polyhedra, sign, congruence) to statically analyze program variables and infer invariants, value ranges, and relationships. Use when analyzing program properties, inferring loop invariants, detecting potential errors, or understanding variable relationships through static analysis.
What it loads into context
Frontmatter
75 tokensAlways available to the agent
SKILL.md
2,892 tokensWhen the skill is activated
Reference documents
4,943 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- Overview
- Analysis Workflow
- Analysis Examples
- Domain Comparison
- Choosing the Right Domain
- Constraints
- Resources
Files
SKILL.mdcore9,606 bytesreferences/abstract_domains.mddoc14,681 bytesreferences/api_reference.mddoc975 bytes
Read SKILL.md
# Abstract Domain Explorer
## Overview
This skill applies abstract interpretation to statically analyze programs using various abstract domains. It infers invariants, value ranges, and relationships between variables without executing the code. Different domains offer different trade-offs between precision and efficiency.
## Analysis Workflow
Follow these steps to analyze programs with abstract domains:
### 1. Select Appropriate Domain(s)
**Choose based on analysis goals:**
abstract-invariant-generator
When your agent uses it
Uses abstract interpretation to automatically infer loop invariants, function preconditions, and postconditions for formal verification. Generates invariants that capture program behavior and support correctness proofs in Dafny, Isabelle, Coq, and other verification systems. Use when adding formal specifications to code, generating verification conditions, inferring contracts for functions, or discovering loop invariants for proofs.
What it loads into context
Frontmatter
81 tokensAlways available to the agent
SKILL.md
2,836 tokensWhen the skill is activated
Reference documents
12,267 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- Overview
- Invariant Generation Workflow
- Complete Example
- Invariant Patterns
- Strengthening Weak Invariants
- Handling Complex Loops
- References
Files
SKILL.mdcore9,820 bytesSKILL.mdcore9,820 bytesSKILL.mdcore9,820 bytesSKILL.mdcore9,820 bytesSKILL.mdcore9,820 bytesSKILL.mdcore9,820 bytesSKILL.mdcore9,820 bytesSKILL.mdcore9,820 bytesSKILL.mdcore9,820 bytesSKILL.mdcore9,820 bytesSKILL.mdcore9,820 bytesSKILL.mdcore9,820 bytesSKILL.mdcore9,820 bytesSKILL.mdcore9,820 bytesSKILL.mdcore9,820 bytesSKILL.mdcore9,820 bytesSKILL.mdcore9,820 bytesSKILL.mdcore9,820 bytesSKILL.mdcore9,820 bytesSKILL.mdcore9,820 bytesSKILL.mdcore9,820 bytesSKILL.mdcore9,820 bytesSKILL.mdcore9,820 bytesSKILL.mdcore9,820 bytesreferences/function_contracts.mddoc9,547 bytesreferences/invariant_templates.mddoc9,494 bytesreferences/loop_invariants.mddoc8,920 bytesreferences/verification_languages.mddoc11,585 bytes
Read SKILL.md
# Abstract Invariant Generator
## Overview
This skill uses abstract interpretation to automatically infer loop invariants, function preconditions, and postconditions. It generates formal specifications that support verification and reasoning about program correctness.
## Invariant Generation Workflow
### Step 1: Identify Specification Points
Analyze the code to identify where invariants are needed:
**Loop Invariants**: For each loop
```pythonabstract-state-analyzer
When your agent uses it
Performs abstract interpretation over source code to infer possible program states, variable ranges, and data properties without executing the program. Reports potential runtime errors including out-of-bounds accesses, null dereferences, type inconsistencies, division by zero, and integer overflows. Use when analyzing code for potential runtime errors, performing static analysis, checking safety properties, or verifying program behavior without execution.
What it loads into context
Frontmatter
84 tokensAlways available to the agent
SKILL.md
2,006 tokensWhen the skill is activated
Reference documents
7,499 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- Overview
- Analysis Workflow
- Complete Example
- Language-Specific Considerations
- Handling Complexity
- References
Files
SKILL.mdcore7,185 bytesSKILL.mdcore7,185 bytesSKILL.mdcore7,185 bytesSKILL.mdcore7,185 bytesSKILL.mdcore7,185 bytesSKILL.mdcore7,185 bytesSKILL.mdcore7,185 bytesSKILL.mdcore7,185 bytesSKILL.mdcore7,185 bytesSKILL.mdcore7,185 bytesSKILL.mdcore7,185 bytesSKILL.mdcore7,185 bytesSKILL.mdcore7,185 bytesSKILL.mdcore7,185 bytesSKILL.mdcore7,185 bytesSKILL.mdcore7,185 bytesSKILL.mdcore7,185 bytesreferences/abstract_domains.mddoc5,717 bytesreferences/analysis_patterns.mddoc8,490 bytesreferences/language_specifics.mddoc8,580 bytes
Read SKILL.md
# Abstract State Analyzer
## Overview
This skill performs abstract interpretation to statically analyze source code and infer possible program states, variable ranges, and data properties. It identifies potential runtime errors without executing the program.
## Analysis Workflow
### Step 1: Parse and Understand Code Structure
Analyze the code to identify:
- Functions and their control flow
- Variable declarations and types
- Loops and conditionalsabstract-trace-summarizer
When your agent uses it
Performs abstract interpretation to produce summarized execution traces and high-level program behavior representations. Highlights key control flow paths, variable relationships, loop invariants, function summaries, and potential runtime states using abstract domains (intervals, signs, nullness, etc.). Use when analyzing program behavior, understanding execution paths, computing loop invariants, tracking variable ranges, detecting potential runtime errors, or generating program summaries without concrete execution.
What it loads into context
Frontmatter
92 tokensAlways available to the agent
SKILL.md
3,269 tokensWhen the skill is activated
Reference documents
7,176 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- Overview
- Core Workflow
- Output Format
- Analysis Techniques by Language
- Common Analysis Patterns
- Precision vs Performance Trade-offs
- Important Guidelines
- Resources
Files
SKILL.mdcore13,355 bytesSKILL.mdcore13,355 bytesSKILL.mdcore13,355 bytesSKILL.mdcore13,355 bytesreferences/abstract_interpretation.mddoc9,981 bytesreferences/examples.mddoc14,607 bytes
Read SKILL.md
# Abstract Trace Summarizer
## Overview
This skill performs abstract interpretation to analyze program behavior and produce summarized execution traces. It computes over-approximations of possible runtime states, tracks control flow paths, infers variable relationships, and generates high-level behavioral summaries without requiring concrete program execution.
## Core Workflow
### 1. Program Analysis Setup
**Initial Assessment:**
- Identify programming language and paradigm
- Determine analysis scope (function, module, program)
- Select appropriate abstract domainsacsl-annotation-assistant
When your agent uses it
Create ACSL (ANSI/ISO C Specification Language) formal annotations for C/C++ programs. Use this skill when working with formal verification, adding function contracts (requires/ensures), loop invariants, assertions, memory safety annotations, or any ACSL specifications. Supports Frama-C verification and generates comprehensive formal specifications for C/C++ code.
What it loads into context
Frontmatter
80 tokensAlways available to the agent
SKILL.md
1,768 tokensWhen the skill is activated
Reference documents
8,727 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- Core Capabilities
- Annotation Workflow
- Common ACSL Constructs
- Verification Considerations
- Output Format
- Best Practices
- Example: Complete Annotated Function
- Resources
Files
SKILL.mdcore7,004 bytesreferences/acsl_reference.mddoc8,596 bytesreferences/common_patterns.mddoc11,604 bytesreferences/frama_c_integration.mddoc10,042 bytes
Read SKILL.md
# ACSL Annotation Assistant
Generate comprehensive ACSL (ANSI/ISO C Specification Language) annotations for C/C++ programs to support formal verification with tools like Frama-C.
## Core Capabilities
### 1. Function Contracts
Add complete function specifications with preconditions and postconditions:
```c
/*@
requires \valid(array + (0..n-1));
requires n > 0;agent-browser
When your agent uses it
CLI-based browser automation with persistent page state using ref-based element interaction. Use when users ask to navigate websites, interact with web pages, fill forms, take screenshots, test web applications, or extract information from web pages.
What it loads into context
Frontmatter
51 tokensAlways available to the agent
SKILL.md
2,039 tokensWhen the skill is activated
Reference documents
0 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- Quick Start
- Core Workflow
- Commands
- Global Options
- Example: Form Submission
- Example: Authentication with Saved State
- Sessions & Persistent Profiles
- Debugging
- Installation
Files
SKILL.mdcore9,171 bytesSKILL.mdcore9,171 bytesSKILL.mdcore9,171 bytesSKILL.mdcore9,171 bytesSKILL.mdcore9,171 bytesSKILL.mdcore9,171 bytesSKILL.mdcore9,171 bytesSKILL.mdcore9,171 bytesSKILL.mdcore9,171 bytesSKILL.mdcore9,171 bytesSKILL.mdcore9,171 bytesSKILL.mdcore9,171 bytesSKILL.mdcore9,171 bytesSKILL.mdcore9,171 bytesSKILL.mdcore9,171 bytesSKILL.mdcore9,171 bytesSKILL.mdcore9,171 bytesSKILL.mdcore9,171 bytesSKILL.mdcore9,171 bytesSKILL.mdcore9,171 bytesSKILL.mdcore9,171 bytesSKILL.mdcore9,171 bytesSKILL.mdcore9,171 bytesSKILL.mdcore9,171 bytes
Read SKILL.md
# Agent Browser — CLI Browser Automation
Command-line browser automation tool with persistent page state and ref-based element interaction.
## Quick Start
```bash
agent-browser open <url> # Navigate to page
agent-browser snapshot -i # Get interactive elements with refs
agent-browser click @e1 # Click element by ref
agent-browser fill @e2 "text" # Fill input by ref
agent-browser close # Close browser
```
ambiguity-detector
When your agent uses it
Detects and analyzes ambiguous language in software requirements and user stories. Use when reviewing requirements documents, user stories, specifications, or any software requirement text to identify vague quantifiers, unclear scope, undefined terms, missing edge cases, subjective language, and incomplete specifications. Provides detailed analysis with clarifying questions and suggested improvements.
What it loads into context
Frontmatter
71 tokensAlways available to the agent
SKILL.md
2,222 tokensWhen the skill is activated
Reference documents
5,627 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- Core Capabilities
- Analysis Workflow
- Output Formats
- Best Practices
- Common Pitfalls to Avoid
- Example Analysis
- Resources
Files
SKILL.mdcore9,811 bytesassets/report_template.jsonasset3,212 bytesreferences/ambiguity_patterns.mddoc13,929 bytesreferences/question_templates.mddoc9,843 bytes
Read SKILL.md
# Ambiguity Detection in Software Requirements
You are an expert requirements analyst who identifies and resolves ambiguities in software requirements.
## Core Capabilities
This skill enables you to:
1. **Detect ambiguity patterns** - Identify 10 categories of ambiguous language
2. **Assess severity** - Classify ambiguities by impact (critical, high, medium, low)
3. **Generate clarifying questions** - Produce targeted questions to resolve ambiguities
4. **Suggest improvements** - Provide clear, testable alternatives
5. **Create reports** - Generate structured analysis with actionable recommendations
api-design-assistant
When your agent uses it
Design and review APIs with suggestions for endpoints, parameters, return types, and best practices. Use when designing new APIs from requirements, reviewing existing API designs, generating API documentation, or getting implementation guidance. Supports REST APIs with focus on endpoint structure, request/response schemas, authentication, pagination, filtering, versioning, and OpenAPI specifications. Triggers when users ask to design, review, document, or improve APIs.
What it loads into context
Frontmatter
93 tokensAlways available to the agent
SKILL.md
2,634 tokensWhen the skill is activated
Reference documents
4,458 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- Overview
- Workflow
- Example Workflows
- Tips for Effective API Design
- References
Files
SKILL.mdcore10,799 bytesreferences/best-practices.mddoc6,594 bytesreferences/openapi-template.mddoc11,444 bytes
Read SKILL.md
# API Design Assistant
## Overview
Assist with designing well-structured, RESTful APIs by suggesting endpoints, parameters, return types, and best practices. Generate OpenAPI specifications and provide implementation guidance.
## Workflow
### 1. Understand Requirements
When designing a new API or reviewing an existing one, first understand:
**For new API design:**
- What is the domain/purpose of the API?api-documentation-generator
When your agent uses it
Generate comprehensive API documentation from repository sources including OpenAPI specs, code comments, docstrings, and existing documentation. Use when documenting APIs, creating API reference guides, or summarizing API functionality from codebases. Extracts endpoint details, request/response schemas, authentication methods, and generates code examples. Triggers when users ask to document APIs, generate API docs, create API reference, or summarize API endpoints from a repository.
What it loads into context
Frontmatter
93 tokensAlways available to the agent
SKILL.md
3,103 tokensWhen the skill is activated
Reference documents
2,059 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- Overview
- Workflow
- Error Codes
Files
SKILL.mdcore13,040 bytesSKILL.mdcore13,040 bytesSKILL.mdcore13,040 bytesSKILL.mdcore13,040 bytesSKILL.mdcore13,040 bytesSKILL.mdcore13,040 bytesSKILL.mdcore13,040 bytesSKILL.mdcore13,040 bytesSKILL.mdcore13,040 bytesassets/api-doc-template.mddoc7,026 bytes
Read SKILL.md
# API Documentation Generator
## Overview
Analyze a repository to extract and generate comprehensive API documentation, including endpoints, request/response schemas, authentication, and usage examples organized in a clear, multi-file structure.
## Workflow
### 1. Discover API Information Sources
Scan the repository to identify all sources of API information:
**Primary sources (in priority order):**
assertion-synthesizer
When your agent uses it
Generate test assertions from existing code implementation. Use when the user has implementation code without tests or incomplete test coverage, and needs assertions synthesized by analyzing the code's behavior, inputs, outputs, and state changes. Supports Python (pytest/unittest), Java (JUnit/AssertJ), and JavaScript/TypeScript (Jest/Chai). Handles equality checks, collections, exceptions, and state verification.
What it loads into context
Frontmatter
90 tokensAlways available to the agent
SKILL.md
2,735 tokensWhen the skill is activated
Reference documents
0 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- Workflow
- Language-Specific Patterns
- Assertion Synthesis Strategies
- Best Practices
- Example Sessions
- Tips
Files
SKILL.mdcore11,499 bytesSKILL.mdcore11,499 bytesSKILL.mdcore11,499 bytesSKILL.mdcore11,499 bytesSKILL.mdcore11,499 bytesSKILL.mdcore11,499 bytesSKILL.mdcore11,499 bytesSKILL.mdcore11,499 bytesSKILL.mdcore11,499 bytesSKILL.mdcore11,499 bytesSKILL.mdcore11,499 bytesSKILL.mdcore11,499 bytesSKILL.mdcore11,499 bytesSKILL.mdcore11,499 bytes
Read SKILL.md
# Assertion Synthesizer
Generate comprehensive test assertions by analyzing code implementation, behavior, and expected outputs.
## Workflow
### 1. Analyze Code
Read and understand the implementation to identify testable behavior:
- **Function signatures**: Parameters, return types, side effects
- **Logic paths**: Conditionals, loops, branching behavior
- **Edge cases**: Boundary conditions, null/empty inputs, error conditions
- **State changes**: Object mutations, attribute modificationsbehavior-preservation-checker
When your agent uses it
Compare runtime behavior between original and migrated repositories to detect behavioral differences, regressions, and semantic changes. Use when validating code migrations, refactorings, language ports, framework upgrades, or any transformation that should preserve behavior. Automatically compares test results, execution traces, API responses, and observable outputs between two repository versions. Provides actionable guidance for fixing deviations and ensuring behavioral equivalence.
What it loads into context
Frontmatter
85 tokensAlways available to the agent
SKILL.md
2,111 tokensWhen the skill is activated
Reference documents
4,896 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- Overview
- Core Workflow
- Comparison Methods
- Difference Detection
- Actionable Guidance
- Report Format
- Best Practices
- Resources
Scripts executed separately
scripts/behavior_checker.pyscripts/compare_test_results.pyscripts/compare_traces.pyscripts/trace_execution.py
Files
SKILL.mdcore9,221 bytesSKILL.mdcore9,221 bytesSKILL.mdcore9,221 bytesSKILL.mdcore9,221 bytesSKILL.mdcore9,221 bytesSKILL.mdcore9,221 bytesSKILL.mdcore9,221 bytesSKILL.mdcore9,221 bytesSKILL.mdcore9,221 bytesSKILL.mdcore9,221 bytesSKILL.mdcore9,221 bytesSKILL.mdcore9,221 bytesSKILL.mdcore9,221 bytesSKILL.mdcore9,221 bytesreferences/comparison_techniques.mddoc10,547 bytesreferences/difference_patterns.mddoc10,940 bytesscripts/behavior_checker.pyruns11,417 bytesscripts/compare_test_results.pyruns9,191 bytesscripts/compare_traces.pyruns7,974 bytesscripts/trace_execution.pyruns5,415 bytes
Read SKILL.md
# Behavior Preservation Checker
## Overview
Validate that a migrated or refactored codebase preserves the original behavior by automatically comparing runtime behavior, test results, execution traces, and observable outputs between two repository versions.
## Core Workflow
### 1. Setup Repositories
Prepare both repositories for comparison:
```bash
# Clone or locate repositoriesbehavioral-mutation-analyzer
When your agent uses it
Analyzes surviving mutants from mutation testing to identify why tests failed to detect them. Takes repository code, test suite, and mutation testing results as input. Identifies root causes including insufficient coverage, equivalent mutants, weak assertions, and missed edge cases. Automatically generates actionable test improvements and new test cases. Use when analyzing mutation testing results, improving test suite effectiveness, investigating low mutation scores, generating tests to kill surviving mutants, or enhancing test quality based on mutation analysis.
What it loads into context
Frontmatter
103 tokensAlways available to the agent
SKILL.md
2,309 tokensWhen the skill is activated
Reference documents
12,547 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- Overview
- Analysis Workflow
- Mutation Operators Reference
- Tool Integration
- Practical Examples
- Best Practices
- References
Files
SKILL.mdcore10,023 bytesSKILL.mdcore10,023 bytesSKILL.mdcore10,023 bytesSKILL.mdcore10,023 bytesSKILL.mdcore10,023 bytesSKILL.mdcore10,023 bytesSKILL.mdcore10,023 bytesSKILL.mdcore10,023 bytesSKILL.mdcore10,023 bytesassets/mutation_analysis_report.mddoc11,238 bytesreferences/mutation_operators.mddoc10,237 bytesreferences/test_patterns.mddoc14,341 bytesreferences/tool_integration.mddoc12,462 bytes
Read SKILL.md
# Behavioral Mutation Analyzer
## Overview
This skill systematically analyzes surviving mutants from mutation testing to understand test suite weaknesses and automatically generate improvements. It identifies why mutants survived, categorizes root causes, and produces actionable test enhancements to increase mutation detection rates.
## Analysis Workflow
### Step 1: Input Collection and Validation
Gather required inputs and verify completeness:
**Required Inputs:**
- Repository source code (path or files)bisect-aware-instrumentation
When your agent uses it
Instrument code to support efficient git bisect by producing deterministic pass/fail signals and concise runtime summaries for each tested commit. Use when debugging regressions with git bisect, automating bisect workflows, creating bisect test scripts, handling flaky tests during bisection, or needing clear exit codes and logging for automated bisect runs. Helps identify the exact commit that introduced a bug through automated testing.
What it loads into context
Frontmatter
91 tokensAlways available to the agent
SKILL.md
2,229 tokensWhen the skill is activated
Reference documents
4,764 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- Overview
- Core Workflow
- Instrumentation Patterns
- Advanced Techniques
- Troubleshooting
- Best Practices
- Quick Reference
- Resources
Scripts executed separately
scripts/bisect_template.shscripts/bisect_wrapper.py
Files
SKILL.mdcore8,199 bytesSKILL.mdcore8,199 bytesSKILL.mdcore8,199 bytesSKILL.mdcore8,199 bytesSKILL.mdcore8,199 bytesSKILL.mdcore8,199 bytesSKILL.mdcore8,199 bytesSKILL.mdcore8,199 bytesSKILL.mdcore8,199 bytesSKILL.mdcore8,199 bytesSKILL.mdcore8,199 bytesSKILL.mdcore8,199 bytesSKILL.mdcore8,199 bytesSKILL.mdcore8,199 bytesSKILL.mdcore8,199 bytesSKILL.mdcore8,199 bytesSKILL.mdcore8,199 bytesSKILL.mdcore8,199 bytesSKILL.mdcore8,199 bytesSKILL.mdcore8,199 bytesSKILL.mdcore8,199 bytesSKILL.mdcore8,199 bytesreferences/exit_codes.mddoc8,637 bytesreferences/git_bisect_guide.mddoc8,551 bytesscripts/bisect_template.shruns3,244 bytesscripts/bisect_wrapper.pyruns8,035 bytes
Read SKILL.md
# Bisect-Aware Instrumentation
## Overview
Instrument code to support efficient git bisect operations by producing deterministic pass/fail signals and concise runtime summaries. This skill helps create robust test scripts that work reliably with `git bisect run`, handling edge cases like flaky tests, build failures, and non-deterministic behavior.
## Core Workflow
### 1. Understand the Regression
Before instrumenting, clarify:
- What behavior changed? (bug introduced, performance regression, test failure)
- What is the "good" commit? (known working state)
- What is the "bad" commit? (known broken state)bug-history-summarizer
When your agent uses it
Summarizes the complete lifecycle of a bug across code versions, tracking its introduction, detection, fixing attempts, and regression history. Use when users need to: (1) Understand how a bug evolved over time, (2) Trace when and how a bug was introduced, (3) Analyze fix attempts and their effectiveness, (4) Identify regression patterns, (5) Generate bug lifecycle reports for documentation or post-mortems. Takes a repository, bug identifier, and version history as input.
What it loads into context
Frontmatter
111 tokensAlways available to the agent
SKILL.md
1,753 tokensWhen the skill is activated
Reference documents
0 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- Workflow
- Example
- Output Format
- Git Commands Reference
- Tips for Effective Bug History Analysis
Files
SKILL.mdcore7,085 bytesSKILL.mdcore7,085 bytes
Read SKILL.md
# Bug History Summarizer
Trace and summarize the complete lifecycle of a bug across code versions.
## Workflow
Follow these steps to generate a comprehensive bug history summary:
### 1. Identify the Bug and Gather Context
Collect essential information:
- **Bug identifier**: Issue number, commit hash, or bug description
- **Repository**: Target codebase with version historybug-localization
When your agent uses it
Identify the precise location of bugs in source code, modules, and systems. Use this skill when debugging applications, investigating test failures, analyzing error reports, tracing runtime issues, or performing root cause analysis. Analyzes stack traces, error messages, failing tests, and code patterns to pinpoint buggy functions, classes, files, or modules with confidence rankings and supporting evidence.
What it loads into context
Frontmatter
81 tokensAlways available to the agent
SKILL.md
4,517 tokensWhen the skill is activated
Reference documents
0 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- Core Capabilities
- Bug Localization Workflow
- Localization Patterns
- Investigation Strategies
- Confidence Scoring
- Reporting Format
Files
SKILL.mdcore18,089 bytesSKILL.mdcore18,089 bytesSKILL.mdcore18,089 bytesSKILL.mdcore18,089 bytesSKILL.mdcore18,089 bytesSKILL.mdcore18,089 bytesSKILL.mdcore18,089 bytesSKILL.mdcore18,089 bytesSKILL.mdcore18,089 bytesSKILL.mdcore18,089 bytesSKILL.mdcore18,089 bytesSKILL.mdcore18,089 bytesSKILL.mdcore18,089 bytesSKILL.mdcore18,089 bytesSKILL.mdcore18,089 bytesSKILL.mdcore18,089 bytesSKILL.mdcore18,089 bytesSKILL.mdcore18,089 bytesSKILL.mdcore18,089 bytes
Read SKILL.md
# Bug Localization
Precisely identify the location of bugs in source code by analyzing error messages, stack traces, failing tests, and code patterns. Provides ranked suspect locations with confidence scores and evidence.
## Core Capabilities
### 1. Error Analysis
Extract information from error sources:
- **Stack traces** - Parse and analyze call stacks
- **Error messages** - Interpret exception details
- **Failing tests** - Analyze test failures and assertions
- **Crash reports** - Process crash dumps and core files
- **Log messages** - Trace execution through logsbug-reproduction-test-generator
When your agent uses it
Automatically generates executable tests that reproduce reported bugs from issue reports and code repositories. Use when users need to: (1) Create a test that reproduces a bug described in an issue report, (2) Generate failing tests from bug descriptions, stack traces, or error messages, (3) Validate bug reports by creating reproducible test cases, (4) Convert issue reports into executable regression tests. Takes a repository and issue report as input and produces test code that reliably triggers the reported bug.
What it loads into context
Frontmatter
109 tokensAlways available to the agent
SKILL.md
1,537 tokensWhen the skill is activated
Reference documents
0 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- Workflow
- Example Workflow
- Constraints
- Handling Underspecified Issues
- Tips for Effective Reproduction Tests
Files
SKILL.mdcore7,073 bytesSKILL.mdcore7,073 bytesSKILL.mdcore7,073 bytesSKILL.mdcore7,073 bytesSKILL.mdcore7,073 bytesSKILL.mdcore7,073 bytes
Read SKILL.md
# Bug Reproduction Test Generator
Generate executable tests that reproduce reported bugs based on issue reports and code repositories.
## Workflow
Follow these steps to generate a bug reproduction test:
### 1. Analyze the Issue Report
Extract key information from the issue report:
- **Symptoms**: What goes wrong? (incorrect output, exception, crash, assertion failure, unexpected behavior)
- **Affected components**: Which modules, classes, or functions are involved?bug-to-patch-generator
When your agent uses it
Generate code fixes and patches from bug reports, failing test cases, error messages, and stack traces. Use this skill when debugging code, fixing test failures, addressing GitHub issues, resolving runtime errors, or patching security vulnerabilities. Analyzes the bug context, identifies root causes, and generates precise code patches with explanations and validation steps.
What it loads into context
Frontmatter
78 tokensAlways available to the agent
SKILL.md
4,286 tokensWhen the skill is activated
Reference documents
0 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- Core Capabilities
- Bug-to-Patch Workflow
- Bug Fix Patterns
- Patch Presentation Format
- Language-Specific Fix Patterns
Files
SKILL.mdcore17,531 bytesSKILL.mdcore17,531 bytesSKILL.mdcore17,531 bytesSKILL.mdcore17,531 bytesSKILL.mdcore17,531 bytesSKILL.mdcore17,531 bytesSKILL.mdcore17,531 bytesSKILL.mdcore17,531 bytesSKILL.mdcore17,531 bytesSKILL.mdcore17,531 bytesSKILL.mdcore17,531 bytesSKILL.mdcore17,531 bytesSKILL.mdcore17,531 bytesSKILL.mdcore17,531 bytesSKILL.mdcore17,531 bytesSKILL.mdcore17,531 bytesSKILL.mdcore17,531 bytesSKILL.mdcore17,531 bytesSKILL.mdcore17,531 bytesSKILL.mdcore17,531 bytesSKILL.mdcore17,531 bytesSKILL.mdcore17,531 bytesSKILL.mdcore17,531 bytesSKILL.mdcore17,531 bytesSKILL.mdcore17,531 bytesSKILL.mdcore17,531 bytesSKILL.mdcore17,531 bytesSKILL.mdcore17,531 bytesSKILL.mdcore17,531 bytesSKILL.mdcore17,531 bytesSKILL.mdcore17,531 bytesSKILL.mdcore17,531 bytes
Read SKILL.md
# Bug-to-Patch Generator
Automatically generate code fixes from bug reports, failing tests, error messages, and stack traces. Analyzes bug context, identifies root causes, and produces verified patches.
## Core Capabilities
### 1. Bug Analysis
Understand bugs from multiple sources:
- **Failing test cases** - Analyze test failures and expected vs actual behavior
- **Error messages** - Parse exceptions, stack traces, and error logs
- **Bug reports** - Process issue descriptions, reproduction steps, and screenshots
- **Crash dumps** - Interpret segmentation faults, core dumps, and memory errors
- **Runtime errors** - Handle assertion failures, type errors, and logic bugsbuild-ci-migration-assistant
When your agent uses it
Automatically migrates build systems and CI/CD configurations to target platforms. Use when modernizing build infrastructure, switching CI/CD providers, or standardizing across projects. Supports common migration paths including Maven↔Gradle, npm↔Yarn, Travis CI→GitHub Actions, CircleCI→GitHub Actions, Jenkins→GitLab CI, and GitLab CI→GitHub Actions. Analyzes existing configuration, generates equivalent target configuration, maps dependencies and commands, and provides validation and migration documentation.
What it loads into context
Frontmatter
111 tokensAlways available to the agent
SKILL.md
2,170 tokensWhen the skill is activated
Reference documents
4,066 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- Workflow
- Common Migration Paths
- Migration Checklist
- Validation Strategies
- Common Patterns
- Troubleshooting
- Best Practices
- References
- Tips
Files
SKILL.mdcore9,142 bytesSKILL.mdcore9,142 bytesSKILL.mdcore9,142 bytesSKILL.mdcore9,142 bytesSKILL.mdcore9,142 bytesreferences/build-systems.mddoc6,200 bytesreferences/ci-platforms.mddoc8,297 bytes
Read SKILL.md
# Build/CI Migration Assistant
Automatically migrate build systems and CI/CD configurations to target platforms while preserving functionality.
## Workflow
### 1. Analyze Source Configuration
Identify the current build system or CI/CD platform:
**Build Systems:**
- Maven (pom.xml)
- Gradle (build.gradle, build.gradle.kts)
- npm (package.json)c-cpp-to-lean4-translator
When your agent uses it
Translate C or C++ programs into equivalent Lean4 code, preserving program semantics and ensuring the generated code is well-typed, executable, and can run successfully. Use when the user asks to convert C/C++ code to Lean4, port C/C++ programs to Lean4, translate imperative code to functional Lean4, or create Lean4 versions of C/C++ algorithms.
What it loads into context
Frontmatter
89 tokensAlways available to the agent
SKILL.md
2,768 tokensWhen the skill is activated
Reference documents
2,534 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- Overview
- Translation Workflow
- Common Translation Patterns
- Examples
- Best Practices
- Limitations and Considerations
- Resources
Files
SKILL.mdcore9,931 bytesSKILL.mdcore9,931 bytesreferences/translation_patterns.mddoc7,707 bytes
Read SKILL.md
# C/C++ to Lean4 Translator
## Overview
Transform C or C++ programs into equivalent Lean4 code that preserves the original semantics while leveraging Lean4's functional programming paradigm, strong type system, and proof capabilities.
## Translation Workflow
### Step 1: Analyze Input Code
Understand the C/C++ program structure and semantics:
1. **Identify program components:**
- Functions and their signaturescd-pipeline-generator
When your agent uses it
Generate GitHub Actions deployment workflows for automated deployment to staging and production environments on cloud platforms (AWS, GCP, Azure). Use when setting up continuous deployment pipelines, creating deployment automation, or configuring multi-environment deployment strategies. Includes templates for environment-specific deployments with approval gates, secrets management, and rollback capabilities.
What it loads into context
Frontmatter
71 tokensAlways available to the agent
SKILL.md
1,197 tokensWhen the skill is activated
Reference documents
0 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- Overview
- Workflow
- Template Features
- Security Best Practices
- Customization Examples
- Tips
Files
SKILL.mdcore5,256 bytesassets/deploy-aws.ymlasset2,784 bytesassets/deploy-azure.ymlasset2,795 bytesassets/deploy-gcp.ymlasset2,411 bytes
Read SKILL.md
# CD Pipeline Generator
## Overview
Generate production-ready GitHub Actions deployment workflows that automate deployments to staging and production environments with environment protection rules, approval gates, and secrets management.
## Workflow
### 1. Identify Deployment Target
Determine the cloud platform and deployment method:
- **AWS**: ECS, Elastic Beanstalk, EC2, Lambda
- **GCP**: Cloud Run, App Engine, Compute Engine, Cloud Functions
- **Azure**: App Service, Container Instances, Functionschange-log-generator
When your agent uses it
Automatically generates change logs from git commits, patches, and pull requests. Use when preparing software releases, creating version summaries, or maintaining CHANGELOG.md files. Analyzes commit messages (including conventional commits), diff/patch files, and PR data to produce categorized Markdown change logs organized by type (Features, Bug Fixes, Breaking Changes, etc.). Ideal for release notes, version updates, and automated changelog maintenance.
What it loads into context
Frontmatter
92 tokensAlways available to the agent
SKILL.md
5,318 tokensWhen the skill is activated
Reference documents
0 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- Core Capabilities
- Change Log Generation Workflow
- Quick Templates
- Automation Scripts
- Best Practices
- Resources
- Quick Reference
- Common Patterns
Files
SKILL.mdcore20,209 bytesSKILL.mdcore20,209 bytesSKILL.mdcore20,209 bytesSKILL.mdcore20,209 bytesSKILL.mdcore20,209 bytesSKILL.mdcore20,209 bytesSKILL.mdcore20,209 bytesSKILL.mdcore20,209 bytesSKILL.mdcore20,209 bytesSKILL.mdcore20,209 bytesSKILL.mdcore20,209 bytesSKILL.mdcore20,209 bytesSKILL.mdcore20,209 bytesSKILL.mdcore20,209 bytesSKILL.mdcore20,209 bytesSKILL.mdcore20,209 bytesSKILL.mdcore20,209 bytesSKILL.mdcore20,209 bytes
Read SKILL.md
# Change Log Generator
Automatically generate comprehensive change logs from git history and code changes.
## Core Capabilities
This skill helps create change logs by:
1. **Analyzing git commits** - Parse commit messages for changes
2. **Processing conventional commits** - Extract structured information from standardized commits
3. **Examining diffs/patches** - Understand code changes from git diff output
4. **Categorizing changes** - Automatically group by type (features, fixes, docs, etc.)
5. **Formatting output** - Generate Markdown change logs following best practices
ci-pipeline-synthesizer
When your agent uses it
Generate GitHub Actions CI/CD pipeline configurations for automated building and testing of library and package projects. Use when creating or updating CI workflows for npm packages, Python packages, Go modules, Rust crates, or other library projects that need automated build and test pipelines. Includes templates for common package ecosystems with best practices for dependency caching, matrix testing, and artifact publishing.
What it loads into context
Frontmatter
83 tokensAlways available to the agent
SKILL.md
937 tokensWhen the skill is activated
Reference documents
0 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- Overview
- Workflow
- Template Features
- Customization Examples
- Tips
Files
SKILL.mdcore3,874 bytesassets/github-actions-go.ymlasset635 bytesassets/github-actions-nodejs.ymlasset644 bytesassets/github-actions-python.ymlasset726 bytesassets/github-actions-rust.ymlasset1,147 bytes
Read SKILL.md
# CI Pipeline Synthesizer
## Overview
Generate production-ready GitHub Actions workflow files for library and package projects with automated build and test stages, dependency caching, and multi-version testing matrices.
## Workflow
### 1. Identify Project Type
Determine the package ecosystem by examining project files:
- **Node.js/npm**: `package.json` present
- **Python**: `setup.py`, `pyproject.toml`, or `requirements.txt` present
- **Go**: `go.mod` presentcode-change-summarizer
When your agent uses it
Generates clear and structured pull request descriptions from code changes. Use when Claude needs to: (1) Create PR descriptions from git diffs or code changes, (2) Summarize what changed and why, (3) Document breaking changes with migration guides, (4) Add technical details and design decisions, (5) Provide testing instructions, (6) Enhance descriptions with security, performance, and architecture notes, (7) Document dependency changes. Takes code changes as input, outputs comprehensive PR description in Markdown.
What it loads into context
Frontmatter
115 tokensAlways available to the agent
SKILL.md
3,326 tokensWhen the skill is activated
Reference documents
1,855 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- Workflow
- Output Format
- Best Practices
- Common Scenarios
- Troubleshooting
Files
SKILL.mdcore14,523 bytesreferences/pr-templates.mddoc7,600 bytes
Read SKILL.md
# Code Change Summarizer
Generate clear, structured pull request descriptions from code changes.
## Workflow
### 1. Analyze Code Changes
**Gather code changes:**
- Git diff output
- Modified files list
- Commit messages
- Related issue numbers
code-comment-generator
When your agent uses it
Generates meaningful comments and documentation for code to improve maintenance and readability. Use when adding documentation to Python or Java code, including function/method docstrings, class documentation, inline explanations for complex logic, and code annotations (TODO, FIXME). Analyzes existing comment style in the codebase to match conventions. Produces clear, concise comments that explain the "why" not just the "what", following best practices for each language.
What it loads into context
Frontmatter
94 tokensAlways available to the agent
SKILL.md
4,447 tokensWhen the skill is activated
Reference documents
8,508 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- Core Capabilities
- Comment Generation Workflow
- Comment Quality Guidelines
- Language-Specific Guidelines
- Resources
- Best Practices Summary
Files
SKILL.mdcore18,348 bytesSKILL.mdcore18,348 bytesSKILL.mdcore18,348 bytesSKILL.mdcore18,348 bytesSKILL.mdcore18,348 bytesSKILL.mdcore18,348 bytesSKILL.mdcore18,348 bytesSKILL.mdcore18,348 bytesSKILL.mdcore18,348 bytesSKILL.mdcore18,348 bytesSKILL.mdcore18,348 bytesSKILL.mdcore18,348 bytesSKILL.mdcore18,348 bytesSKILL.mdcore18,348 bytesreferences/comment_examples.mddoc23,962 bytesreferences/style_guides.mddoc15,079 bytes
Read SKILL.md
# Code Comment Generator
Generate meaningful, maintainable comments and documentation for your code.
## Core Capabilities
This skill helps you create effective code documentation by:
1. **Analyzing code context** - Understanding what the code does and why
2. **Matching existing style** - Following comment conventions in your codebase
3. **Writing clear documentation** - Creating function/method/class documentation
4. **Adding inline explanations** - Explaining complex logic and algorithms
5. **Inserting code annotations** - Adding TODO, FIXME, and optimization notes
code-completion-semantic-constraints
When your agent uses it
Automatically complete partial code snippets while satisfying semantic constraints including variable types, invariants, pre/post-conditions, interface contracts, and expected input/output behavior. Use when users provide incomplete code with specific requirements like "complete this function that takes a list and returns sorted unique elements" or "fill in this method body that must maintain the invariant that x stays positive" or "implement this interface method with these type constraints." Produces compilable, executable code with tests and a constraint satisfaction report.
What it loads into context
Frontmatter
109 tokensAlways available to the agent
SKILL.md
930 tokensWhen the skill is activated
Reference documents
0 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- Overview
- Workflow
- Examples
- Output Format
- Language Support
Files
SKILL.mdcore4,715 bytesSKILL.mdcore4,715 bytes
Read SKILL.md
# Code Completion with Semantic Constraints
## Overview
Complete partial code snippets while satisfying specified semantic constraints. Produces compilable code, verification tests, and a detailed report explaining how each constraint was satisfied.
## Workflow
### 1. Parse Input
Extract and categorize the provided information:
**Partial Code**: Identify the incomplete code structure (function signature, class skeleton, method stub, etc.)
code-instrumentation-generator
When your agent uses it
Automatically instruments source code to collect runtime information such as function calls, branch decisions, variable values, and execution traces while preserving original program semantics. Use when users need to: (1) Add logging or tracing to code for debugging, (2) Collect runtime execution data for analysis, (3) Monitor function calls and control flow, (4) Track variable values during execution, (5) Generate execution traces for testing or profiling. Supports Python, Java, JavaScript, and C/C++ with configurable instrumentation levels.
What it loads into context
Frontmatter
114 tokensAlways available to the agent
SKILL.md
2,066 tokensWhen the skill is activated
Reference documents
0 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- Workflow
- Language-Specific Patterns
- Branch Instrumentation Example
- Configuration-Based Instrumentation
- Output Format
- Best Practices
- Advanced Features
- Constraints
Files
SKILL.mdcore9,157 bytesSKILL.mdcore9,157 bytesSKILL.mdcore9,157 bytesSKILL.mdcore9,157 bytesSKILL.mdcore9,157 bytesSKILL.mdcore9,157 bytesSKILL.mdcore9,157 bytesSKILL.mdcore9,157 bytesSKILL.mdcore9,157 bytesSKILL.mdcore9,157 bytes
Read SKILL.md
# Code Instrumentation Generator
Automatically instrument source code to collect runtime information while preserving program semantics.
## Workflow
Follow these steps to instrument code:
### 1. Analyze the Source Code
Understand the code structure and identify instrumentation points:
- **Language detection**: Identify the programming language
- **Code structure**: Parse functions, classes, branches, loopscode-optimizer
When your agent uses it
Analyzes and optimizes code for better performance, memory usage, and efficiency. Use when code is slow, memory-intensive, or inefficient. Supports Python and Java optimization including execution speed improvements, memory reduction, database query optimization, and I/O efficiency. Provides before/after examples with detailed explanations of why optimizations work, complexity analysis, and measurable performance improvements.
What it loads into context
Frontmatter
81 tokensAlways available to the agent
SKILL.md
3,209 tokensWhen the skill is activated
Reference documents
0 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- Core Capabilities
- Optimization Workflow
- Common Optimizations
- Optimization Process
- Best Practices
- Resources
- Quick Reference
Files
SKILL.mdcore12,583 bytesSKILL.mdcore12,583 bytesSKILL.mdcore12,583 bytesSKILL.mdcore12,583 bytesSKILL.mdcore12,583 bytesSKILL.mdcore12,583 bytesSKILL.mdcore12,583 bytesSKILL.mdcore12,583 bytesSKILL.mdcore12,583 bytesSKILL.mdcore12,583 bytesSKILL.mdcore12,583 bytesSKILL.mdcore12,583 bytesSKILL.mdcore12,583 bytesSKILL.mdcore12,583 bytesSKILL.mdcore12,583 bytesSKILL.mdcore12,583 bytes
Read SKILL.md
# Code Optimizer
Improve code performance, memory usage, and efficiency through systematic optimization.
## Core Capabilities
This skill helps optimize code by:
1. **Analyzing performance bottlenecks** - Identifying slow or inefficient code
2. **Suggesting optimizations** - Providing concrete improvements with examples
3. **Explaining trade-offs** - Describing benefits and potential drawbacks
4. **Measuring impact** - Estimating performance gains
5. **Preserving correctness** - Ensuring optimizations don't change behavior
code-pattern-extractor
When your agent uses it
Analyze codebases to identify reusable code patterns, duplications, and implementation patterns for future development. Use when refactoring code, identifying technical debt, finding opportunities for abstraction, or documenting common patterns in a directory or module. Outputs pattern catalogs, refactoring suggestions, and reusable template code.
What it loads into context
Frontmatter
66 tokensAlways available to the agent
SKILL.md
1,333 tokensWhen the skill is activated
Reference documents
0 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- Overview
- Workflow
- Output Structure
- Pattern Detection Heuristics
- Tips
Files
SKILL.mdcore6,175 bytes
Read SKILL.md
# Code Pattern Extractor
## Overview
Systematically analyze code in directories or modules to identify recurring patterns, code duplication, and implementation patterns that can be abstracted into reusable components, utilities, or design patterns.
## Workflow
### 1. Define Analysis Scope
Identify the code to analyze:
- **Directory/module**: Analyze all files in a specific directory
- **File set**: Analyze a specific set of related files
- **Component**: Analyze files related to a specific feature or componentcode-refactoring-assistant
When your agent uses it
Suggest and apply code refactorings to improve readability, maintainability, and code quality. Use this skill when improving existing code structure, eliminating code smells, applying design patterns, simplifying complex logic, extracting duplicated code, renaming for clarity, or preparing code for new features. Provides specific before/after examples, explains benefits, identifies risks, and ensures behavior preservation through tests.
What it loads into context
Frontmatter
85 tokensAlways available to the agent
SKILL.md
5,968 tokensWhen the skill is activated
Reference documents
0 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- Core Capabilities
- Refactoring Workflow
- Common Refactoring Patterns
- Refactoring Safety Guidelines
- Refactoring Anti-Patterns
- Best Practices
- Language-Specific Patterns
Files
SKILL.mdcore25,357 bytesSKILL.mdcore25,357 bytesSKILL.mdcore25,357 bytesSKILL.mdcore25,357 bytesSKILL.mdcore25,357 bytesSKILL.mdcore25,357 bytesSKILL.mdcore25,357 bytesSKILL.mdcore25,357 bytesSKILL.mdcore25,357 bytesSKILL.mdcore25,357 bytesSKILL.mdcore25,357 bytesSKILL.mdcore25,357 bytesSKILL.mdcore25,357 bytesSKILL.mdcore25,357 bytesSKILL.mdcore25,357 bytesSKILL.mdcore25,357 bytesSKILL.mdcore25,357 bytesSKILL.mdcore25,357 bytesSKILL.mdcore25,357 bytesSKILL.mdcore25,357 bytesSKILL.mdcore25,357 bytesSKILL.mdcore25,357 bytesSKILL.mdcore25,357 bytesSKILL.mdcore25,357 bytesSKILL.mdcore25,357 bytesSKILL.mdcore25,357 bytesSKILL.mdcore25,357 bytesSKILL.mdcore25,357 bytesSKILL.mdcore25,357 bytesSKILL.mdcore25,357 bytesSKILL.mdcore25,357 bytesSKILL.mdcore25,357 bytesSKILL.mdcore25,357 bytesSKILL.mdcore25,357 bytesSKILL.mdcore25,357 bytesSKILL.mdcore25,357 bytesSKILL.mdcore25,357 bytesSKILL.mdcore25,357 bytes
Read SKILL.md
# Code Refactoring Assistant
Systematically improve code structure and quality through targeted refactorings. Identifies opportunities, suggests improvements, and applies changes while preserving behavior.
## Core Capabilities
### 1. Code Smell Detection
Identify refactoring opportunities:
- **Long methods/functions** - Functions doing too much
- **Large classes** - Classes with too many responsibilities
- **Duplicate code** - Repeated logic across codebase
- **Long parameter lists** - Functions with many parameters
- **Primitive obsession** - Using primitives instead of objectscode-repair-generation-combo
When your agent uses it
Automatically repair buggy code and generate comprehensive tests for Python, Java, and C++ programs. Use when users need to fix logic errors or runtime errors in functions, modules, or repositories. Accepts specifications via natural language descriptions, existing test cases, or input/output examples. Generates corrected code, creates or updates tests to verify correctness and prevent regressions, and produces a detailed report explaining the bug, fix, and testing strategy. Triggers on requests like "fix this bug", "repair this code", "debug this function", or "this code is broken".
What it loads into context
Frontmatter
123 tokensAlways available to the agent
SKILL.md
1,169 tokensWhen the skill is activated
Reference documents
1,529 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- Workflow
- Example Usage
- Language-Specific Notes
- Resources
Files
SKILL.mdcore5,193 bytesassets/bug-fix-report-template.mddoc887 bytesreferences/cpp-testing.mddoc2,260 bytesreferences/java-testing.mddoc1,917 bytesreferences/python-testing.mddoc1,251 bytes
Read SKILL.md
# Code Repair + Generation Combo
Automatically diagnose and repair buggy code while generating comprehensive tests to verify correctness and prevent regressions.
## Workflow
Follow this systematic approach for bug fixing and test generation:
### 1. Understand the Bug
**Read the buggy code** - Use Read tool to examine the problematic code thoroughly.
**Analyze the specification** - Understand expected behavior from:
- Natural language description from usercode-review-assistant
When your agent uses it
Conduct comprehensive code reviews identifying bugs, security issues, performance problems, code quality concerns, and best practice violations. Use when reviewing pull requests, examining code changes, evaluating new code, assessing code quality, or providing feedback on implementations. Analyzes code for correctness, security vulnerabilities, performance bottlenecks, maintainability issues, test coverage, documentation quality, and adherence to coding standards. Produces structured markdown reviews with categorized findings, severity ratings, specific examples, and actionable recommendations. Triggers when users ask to review code, check pull requests, evaluate implementations, find bugs, or assess code quality.
What it loads into context
Frontmatter
129 tokensAlways available to the agent
SKILL.md
2,773 tokensWhen the skill is activated
Reference documents
0 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- Overview
- Review Categories
- Review Workflow
- Review Template
- 🟡 Important Issues
- 🔵 Minor Issues
- 💡 Suggestions
- ✅ Positive Observations
- Questions for Author
- Recommendations
- Security Checklist
- Performance Review Points
- Code Quality Standards
- Testing Review
- Example Reviews
Files
SKILL.mdcore11,963 bytesSKILL.mdcore11,963 bytesSKILL.mdcore11,963 bytesSKILL.mdcore11,963 bytesSKILL.mdcore11,963 bytesSKILL.mdcore11,963 bytesSKILL.mdcore11,963 bytesSKILL.mdcore11,963 bytes
Read SKILL.md
# Code Review Assistant
## Overview
Perform thorough, constructive code reviews that identify issues, suggest improvements, and ensure code quality, security, and maintainability.
## Review Categories
Examine code across these dimensions:
### 1. 🐛 Correctness & Bugs
- Logic errors
- Edge case handling
- Null/undefined checkscode-search-assistant
When your agent uses it
Search code repositories for code related to a given code snippet, ranking results by call chain similarity, textual similarity, and functional similarity. Use when finding related code, locating similar implementations, discovering code dependencies, or identifying code that performs similar operations. Outputs ranked file lists with matching code snippets and relevance scores.
What it loads into context
Frontmatter
69 tokensAlways available to the agent
SKILL.md
1,662 tokensWhen the skill is activated
Reference documents
0 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- Overview
- Workflow
- Tips
Files
SKILL.mdcore7,444 bytes
Read SKILL.md
# Code Search Assistant
## Overview
Search codebases to find code related to a given snippet using multi-dimensional similarity analysis: call chain patterns, textual structure, and functional behavior. Results are ranked and presented with matching code snippets.
## Workflow
### 1. Analyze Input Snippet
Extract key characteristics from the provided code snippet:
**Structural elements**:
- Function/method calls madecode-smell-detector
When your agent uses it
Identify and report code smells indicating poor design or maintainability issues in Python code, including duplicate code, magic numbers, hardcoded values, God classes, feature envy, inappropriate intimacy, data clumps, primitive obsession, and long parameter lists. Use when conducting code quality audits, preparing for refactoring, improving codebase maintainability, or performing design reviews. Produces markdown reports with severity ratings, locations, descriptions, and specific refactoring recommendations with before/after examples. Triggers when users ask to find code smells, identify design issues, suggest refactorings, improve code quality, or detect maintainability problems.
What it loads into context
Frontmatter
133 tokensAlways available to the agent
SKILL.md
3,641 tokensWhen the skill is activated
Reference documents
5,289 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- Overview
- Workflow
- Code Smell Analysis Report
- Summary
- 🔴 High Severity Smells
- 🟡 Medium Severity Smells
- 🔵 Low Severity Smells
- Recommendations
- Tips for Effective Smell Detection
- Common False Positives
- Reference
Scripts executed separately
scripts/detect_smells.py
Files
SKILL.mdcore15,742 bytesSKILL.mdcore15,742 bytesSKILL.mdcore15,742 bytesSKILL.mdcore15,742 bytesSKILL.mdcore15,742 bytesSKILL.mdcore15,742 bytesSKILL.mdcore15,742 bytesSKILL.mdcore15,742 bytesSKILL.mdcore15,742 bytesSKILL.mdcore15,742 bytesSKILL.mdcore15,742 bytesSKILL.mdcore15,742 bytesreferences/refactoring-patterns.mddoc5,988 bytesreferences/smell-patterns.mddoc16,756 bytesscripts/detect_smells.pyruns8,064 bytes
Read SKILL.md
# Code Smell Detector
## Overview
Identify code quality and design smells in Python codebases, then provide specific refactoring recommendations to improve maintainability and design.
## Workflow
### 1. Understand the Analysis Scope
Define what to analyze:
**Questions to ask:**
- What directory or files should be analyzed?code-summarizer
When your agent uses it
Generate concise summaries of source code at multiple scales. Use when users ask to summarize, explain, or understand code - whether it's a single function, a class, a module, or an entire codebase. Handles function-level code by explaining intention and core logic, and large codebases by providing high-level overviews with drill-down capabilities for specific modules.
What it loads into context
Frontmatter
79 tokensAlways available to the agent
SKILL.md
1,775 tokensWhen the skill is activated
Reference documents
0 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- Overview
- Workflow Decision Tree
- Small-Scale Code Summarization
- Large-Scale Code Summarization
- Best Practices
- Common Scenarios
- Output Format Guidelines
- Limitations and Considerations
Files
SKILL.mdcore8,282 bytesSKILL.mdcore8,282 bytesSKILL.mdcore8,282 bytesSKILL.mdcore8,282 bytes
Read SKILL.md
# Code Summarizer
Generate clear, concise summaries of source code at any scale - from individual functions to entire codebases.
## Overview
This skill helps analyze and summarize code by adapting the level of detail to the code's scale:
- **Small-scale code** (functions, classes, small files): Provide focused summaries of intention and implementation
- **Large-scale code** (modules, packages, entire repositories): Provide hierarchical summaries with progressive drill-down
## Workflow Decision Tree
```code-translation
When your agent uses it
Convert code between programming languages while preserving functionality and semantics. Use when: (1) Translating functions, classes, or modules between languages (Python, JavaScript/TypeScript, Java, Go, Rust, C/C++), (2) Migrating entire projects to a different language, (3) Need idiomatic translation that follows target language conventions, (4) Converting between different paradigms (OOP to functional, etc.), (5) Porting legacy code to modern languages. Provides language-specific patterns, idiomatic translation guides, and project migration strategies.
What it loads into context
Frontmatter
123 tokensAlways available to the agent
SKILL.md
3,008 tokensWhen the skill is activated
Reference documents
8,035 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- Translation Workflow
- Quick Translation Examples
- Common Translation Patterns
- Translation Decision Tree
- Language-Specific Guidance
- Best Practices
- Translation Checklist
- Common Pitfalls
- Example: Complete Translation
Files
SKILL.mdcore12,385 bytesSKILL.mdcore12,385 bytesSKILL.mdcore12,385 bytesSKILL.mdcore12,385 bytesSKILL.mdcore12,385 bytesSKILL.mdcore12,385 bytesSKILL.mdcore12,385 bytesSKILL.mdcore12,385 bytesSKILL.mdcore12,385 bytesSKILL.mdcore12,385 bytesSKILL.mdcore12,385 bytesSKILL.mdcore12,385 bytesSKILL.mdcore12,385 bytesSKILL.mdcore12,385 bytesSKILL.mdcore12,385 bytesreferences/idiomatic_guide.mddoc9,961 bytesreferences/language_patterns.mddoc8,293 bytesreferences/project_migration.mddoc12,406 bytes
Read SKILL.md
# Code Translation
Convert code between programming languages while preserving functionality, adapting to target language idioms and best practices.
## Translation Workflow
### 1. Analyze Source Code
Understand what the code does:
- Core functionality and algorithms
- Dependencies and external libraries
- Language-specific features used
- Performance characteristics
component-boundary-identifier
When your agent uses it
Identifies boundaries between modules or components in software systems through static code analysis and dependency detection. Use when Claude needs to analyze software architecture, identify module boundaries, detect boundary violations, find circular dependencies, or assess component coupling. Supports Python (packages and imports) and Java (packages and dependencies). Trigger when users ask to "identify boundaries", "find component boundaries", "detect boundary violations", "analyze module structure", "check architecture", or "find circular dependencies".
What it loads into context
Frontmatter
103 tokensAlways available to the agent
SKILL.md
1,987 tokensWhen the skill is activated
Reference documents
3,313 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- Quick Start
- What This Skill Does
- Analysis Methods
- Architectural Patterns
- Language-Specific Guidance
- Workflow
- Violation Severity Levels
- Detection Patterns
- Best Practices
- Example Usage Patterns
- Automated Analysis
Scripts executed separately
scripts/analyze_boundaries.py
Files
SKILL.mdcore9,823 bytesSKILL.mdcore9,823 bytesSKILL.mdcore9,823 bytesSKILL.mdcore9,823 bytesSKILL.mdcore9,823 bytesSKILL.mdcore9,823 bytesSKILL.mdcore9,823 bytesreferences/boundary-indicators.mddoc7,156 bytesreferences/violation-patterns.mddoc8,305 bytesscripts/analyze_boundaries.pyruns7,598 bytes
Read SKILL.md
# Component Boundary Identifier
Identify and analyze boundaries between software components to ensure proper architectural separation.
## Quick Start
When a user requests boundary analysis:
1. **Understand the goal**: Identify boundaries, detect violations, or both
2. **Analyze structure**: Examine package/module organization and dependencies
3. **Identify boundaries**: Determine component boundaries based on structure
4. **Detect violations**: Find improper cross-boundary dependencies
5. **Report findings**: Present boundaries and violations with severity levels
config-consistency-checker
When your agent uses it
Automatically analyzes configuration files to detect inconsistencies, conflicts, missing keys, and divergent values across environments, versions, or modules. Use when managing multi-environment configurations, detecting config drift, validating configuration changes, or ensuring consistency across microservices. Supports JSON, YAML, TOML, INI, XML, .env, and properties files. Identifies security issues like hardcoded secrets and provides actionable resolution guidance.
What it loads into context
Frontmatter
92 tokensAlways available to the agent
SKILL.md
1,133 tokensWhen the skill is activated
Reference documents
0 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- Workflow
- Quick Examples
- Detection Patterns
- Report Format
- Best Practices
- Common Scenarios
- Tips
Files
SKILL.mdcore4,856 bytes
Read SKILL.md
# Config Consistency Checker
Automatically detect inconsistencies, conflicts, and mismatches in configuration files across environments and modules.
## Workflow
### 1. Parse Configuration Files
Read and parse configuration files in various formats:
- JSON (.json)
- YAML (.yml, .yaml)
- TOML (.toml)
- INI (.ini)
- XML (.xml)configuration-generator
When your agent uses it
Generate configuration files for applications, services, and infrastructure. Use when: (1) Setting up new projects (package.json, requirements.txt, tsconfig.json), (2) Creating Docker or Kubernetes configurations, (3) Configuring CI/CD pipelines (GitHub Actions, GitLab CI, CircleCI), (4) Setting up web servers (Nginx, Apache), (5) Defining infrastructure as code (Terraform, CloudFormation), (6) Generating linter/formatter configs (ESLint, Prettier, Black). Provides templates and custom-generated configs for diverse tech stacks.
What it loads into context
Frontmatter
128 tokensAlways available to the agent
SKILL.md
2,901 tokensWhen the skill is activated
Reference documents
6,382 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- Quick Start
- Common Configuration Types
- Configuration Decision Tree
- Generation Approaches
- Best Practices
- Common Patterns
- Complete Example
- Troubleshooting
- Reference Materials
Files
SKILL.mdcore11,172 bytesSKILL.mdcore11,172 bytesSKILL.mdcore11,172 bytesSKILL.mdcore11,172 bytesSKILL.mdcore11,172 bytesSKILL.mdcore11,172 bytesSKILL.mdcore11,172 bytesSKILL.mdcore11,172 bytesSKILL.mdcore11,172 bytesSKILL.mdcore11,172 bytesSKILL.mdcore11,172 bytesSKILL.mdcore11,172 bytesassets/docker-compose.ymlasset1,418 bytesassets/github-actions-workflow.ymlasset3,476 bytesassets/kubernetes-deployment.yamlasset1,742 bytesreferences/app_configs.mddoc8,451 bytesreferences/infra_configs.mddoc13,439 bytes
Read SKILL.md
# Configuration Generator
Generate configuration files for applications, services, and infrastructure across various formats and frameworks.
## Quick Start
### Use Built-in Templates
Access ready-to-use configuration templates from assets:
```bash
# Docker Compose
cat assets/docker-compose.yml
conflict-analyzer
When your agent uses it
Identifies and analyzes conflicts in software requirements including logical contradictions, technical incompatibilities, resource constraints, timeline issues, data conflicts, and stakeholder priority mismatches. Use when reviewing requirement sets, specifications, user stories, or project plans to detect conflicts that could block implementation or cause rework. Provides detailed conflict analysis with resolution strategies and impact assessment.
What it loads into context
Frontmatter
76 tokensAlways available to the agent
SKILL.md
2,920 tokensWhen the skill is activated
Reference documents
4,754 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- Core Capabilities
- Analysis Workflow
- Output Formats
- Best Practices
- Common Pitfalls to Avoid
- Example Analysis
- Resources
Files
SKILL.mdcore13,296 bytesassets/conflict_report_template.jsonasset5,751 bytesreferences/conflict_patterns.mddoc11,687 bytesreferences/resolution_strategies.mddoc9,361 bytes
Read SKILL.md
# Requirement Conflict Analysis
You are an expert requirements analyst who identifies and resolves conflicts between software requirements.
## Core Capabilities
This skill enables you to:
1. **Detect conflicts** - Identify 8 types of requirement conflicts
2. **Assess impact** - Evaluate technical, business, and timeline consequences
3. **Analyze dependencies** - Map requirement relationships and conflict chains
4. **Recommend resolutions** - Suggest appropriate resolution strategies
5. **Generate reports** - Create structured conflict analysis with actionable recommendations
containerization-assistant
When your agent uses it
Generate Dockerfiles, Docker Compose configurations, and Kubernetes manifests for containerizing applications. Use when: (1) Creating Dockerfiles for Node.js, Python, Java, Go, or other applications, (2) Setting up multi-service environments with Docker Compose, (3) Generating Kubernetes deployments, services, and ingress configurations, (4) Optimizing container images for production, (5) Implementing containerization best practices. Provides both ready-to-use templates and custom-generated configurations based on project requirements.
What it loads into context
Frontmatter
110 tokensAlways available to the agent
SKILL.md
2,891 tokensWhen the skill is activated
Reference documents
4,143 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- Quick Start
- Available Templates
- Generation Workflow
- Common Scenarios
- Dockerfile Best Practices
- Kubernetes Deployment
- Configuration Management
- Troubleshooting
- Reference Documentation
- Advanced Topics
Scripts executed separately
assets/Dockerfile.go
Files
SKILL.mdcore11,607 bytesSKILL.mdcore11,607 bytesSKILL.mdcore11,607 bytesSKILL.mdcore11,607 bytesSKILL.mdcore11,607 bytesSKILL.mdcore11,607 bytesSKILL.mdcore11,607 bytesSKILL.mdcore11,607 bytesSKILL.mdcore11,607 bytesassets/.env.exampleasset314 bytesassets/Dockerfile.goruns692 bytesassets/Dockerfile.javaasset738 bytesassets/Dockerfile.nodejsasset720 bytesassets/Dockerfile.pythonasset786 bytesassets/docker-compose.ymlasset1,558 bytesreferences/dockerfile_best_practices.mddoc5,593 bytesreferences/kubernetes_patterns.mddoc9,218 bytes
Read SKILL.md
# Containerization Assistant
Generate production-ready Docker and Kubernetes configurations for your applications.
## Quick Start
### Generate a Dockerfile
**For existing templates**:
```bash
# Node.js application
cp assets/Dockerfile.nodejs ./Dockerfile
# Python applicationcontrol-flow-abstraction-generator
When your agent uses it
Generate abstract Control Flow Graph (CFG) representations of programs showing loops, branches, and function calls for static analysis or verification. Use when users need to: (1) Visualize program control flow structure, (2) Generate CFGs for static analysis tools, (3) Create control flow abstractions for formal verification, (4) Analyze program paths and reachability, (5) Document program structure. Supports both function-level (intraprocedural) and program-level (interprocedural) analysis with multiple output formats (textual, DOT/Graphviz, JSON).
What it loads into context
Frontmatter
126 tokensAlways available to the agent
SKILL.md
3,151 tokensWhen the skill is activated
Reference documents
3,318 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- Overview
- How to Use
- CFG Generation Workflow
- Example: Simple Conditional
- Example: While Loop
- Example: Nested Control Flow
- Example: Function Calls (Interprocedural)
- Output Formats
- Analysis Levels
- CFG Properties
- Common Patterns
- References
- Tips
Files
SKILL.mdcore11,732 bytesSKILL.mdcore11,732 bytesSKILL.mdcore11,732 bytesSKILL.mdcore11,732 bytesSKILL.mdcore11,732 bytesSKILL.mdcore11,732 bytesSKILL.mdcore11,732 bytesSKILL.mdcore11,732 bytesSKILL.mdcore11,732 bytesSKILL.mdcore11,732 bytesSKILL.mdcore11,732 bytesSKILL.mdcore11,732 bytesSKILL.mdcore11,732 bytesreferences/cfg_patterns.mddoc10,269 bytes
Read SKILL.md
# Control Flow Abstraction Generator
Generate abstract Control Flow Graph representations of programs.
## Overview
This skill analyzes program code and generates Control Flow Graphs (CFGs) that abstract the program's control flow structure. CFGs show how execution flows through the program via nodes (statements, conditions) and edges (control transfers), making them suitable for static analysis, formal verification, and program understanding.
## How to Use
Provide:
1. **Program code**: Function or program to analyze
2. **Analysis scope**: Function-level or program-level
3. **Output format** (optional): Textual, DOT, JSON, or multiplecounterexample-debugger
When your agent uses it
Debug proof failures using counterexamples from Nitpick (Isabelle) or QuickChick (Coq) to identify specification errors, missing preconditions, and proof strategy issues. Use when: (1) A proof attempt fails and you need to understand why, (2) Counterexamples are generated by Nitpick or QuickChick, (3) Specifications may be incorrect or incomplete, (4) Theorems need validation before proving, (5) Missing preconditions or lemmas need identification, or (6) Proof failures need explanation and correction suggestions. Supports both Isabelle/HOL and Coq equally.
What it loads into context
Frontmatter
132 tokensAlways available to the agent
SKILL.md
1,759 tokensWhen the skill is activated
Reference documents
6,507 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- Workflow
- Counterexample Analysis Patterns
- Tool-Specific Guidance
- Common Root Causes
- Debugging Checklist
- Examples
- Tips
Files
SKILL.mdcore7,575 bytesreferences/examples.mddoc10,129 bytesreferences/nitpick_guide.mddoc5,260 bytesreferences/quickchick_guide.mddoc7,128 bytes
Read SKILL.md
# Counterexample-Guided Proof Debugger
Analyze counterexamples from Nitpick or QuickChick to explain proof failures and suggest corrections to specifications or proofs.
## Workflow
### 1. Receive Counterexample Information
Identify what information is provided:
- **Counterexample output**: From Nitpick or QuickChick
- **Failed theorem**: The statement that couldn't be proven
- **Proof attempt**: Any partial proof or tactics tried
- **Context**: Definitions and lemmas involved
counterexample-explainer
When your agent uses it
Explain why counterexamples violate specifications by analyzing formal specifications (temporal logic, invariants, pre/postconditions, code contracts), informal requirements (user stories, acceptance criteria), test specifications (assertions, property-based tests), and providing step-by-step traces showing state changes, comparing expected vs actual behavior, identifying root causes, and assessing violation impact. Use when debugging test failures, understanding model checker output, explaining runtime assertion violations, analyzing static analysis warnings, or teaching specification concepts. Produces structured markdown explanations with traces, comparisons, state diagrams, and cause chains. Triggers when users ask why something failed, explain a violation, understand a counterexample, debug a specification, or analyze why a test fails.
What it loads into context
Frontmatter
151 tokensAlways available to the agent
SKILL.md
3,405 tokensWhen the skill is activated
Reference documents
5,431 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- Overview
- Workflow
- Impact
- Related Issues
- Impact
- Impact
Files
SKILL.mdcore14,151 bytesSKILL.mdcore14,151 bytesSKILL.mdcore14,151 bytesSKILL.mdcore14,151 bytesSKILL.mdcore14,151 bytesSKILL.mdcore14,151 bytesSKILL.mdcore14,151 bytesSKILL.mdcore14,151 bytesSKILL.mdcore14,151 bytesSKILL.mdcore14,151 bytesSKILL.mdcore14,151 bytesSKILL.mdcore14,151 bytesreferences/explanation-patterns.mddoc13,416 bytesreferences/specification-types.mddoc8,089 bytes
Read SKILL.md
# Counterexample Explainer
## Overview
Analyze counterexamples that violate specifications and produce clear, structured explanations showing step-by-step how and why the violation occurs, with root cause analysis and impact assessment.
## Workflow
### 1. Understand the Specification
Identify what property is being checked.
**Questions to ask:**
- What is the specification or requirement?counterexample-generator
When your agent uses it
Generate concrete counterexamples when formal verification, assertions, or specifications fail. Use this skill when debugging failed proofs, understanding why verification fails, creating minimal reproducing examples, analyzing assertion violations, investigating invariant breaks, or diagnosing specification mismatches. Produces concrete input values, execution traces, and state information that demonstrate the failure.
What it loads into context
Frontmatter
72 tokensAlways available to the agent
SKILL.md
4,970 tokensWhen the skill is activated
Reference documents
0 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- Core Capabilities
- Counterexample Generation Workflow
- Counterexample Generation Techniques
- Counterexample Report Template
- Example Complete Report
Files
SKILL.mdcore18,480 bytesSKILL.mdcore18,480 bytesSKILL.mdcore18,480 bytesSKILL.mdcore18,480 bytesSKILL.mdcore18,480 bytesSKILL.mdcore18,480 bytesSKILL.mdcore18,480 bytesSKILL.mdcore18,480 bytesSKILL.mdcore18,480 bytesSKILL.mdcore18,480 bytesSKILL.mdcore18,480 bytesSKILL.mdcore18,480 bytesSKILL.mdcore18,480 bytesSKILL.mdcore18,480 bytesSKILL.mdcore18,480 bytesSKILL.mdcore18,480 bytesSKILL.mdcore18,480 bytesSKILL.mdcore18,480 bytesSKILL.mdcore18,480 bytesSKILL.mdcore18,480 bytesSKILL.mdcore18,480 bytesSKILL.mdcore18,480 bytesSKILL.mdcore18,480 bytesSKILL.mdcore18,480 bytesSKILL.mdcore18,480 bytesSKILL.mdcore18,480 bytesSKILL.mdcore18,480 bytesSKILL.mdcore18,480 bytesSKILL.mdcore18,480 bytesSKILL.mdcore18,480 bytesSKILL.mdcore18,480 bytesSKILL.mdcore18,480 bytesSKILL.mdcore18,480 bytesSKILL.mdcore18,480 bytesSKILL.mdcore18,480 bytes
Read SKILL.md
# Counterexample Generator
Systematically generate counterexamples that demonstrate why verification fails. Provides concrete input values, execution traces, and diagnostic information to help understand and fix specification or implementation issues.
## Core Capabilities
### 1. Precondition Violation Detection
Generate inputs that violate preconditions:
- **Invalid parameter values** - Out-of-range inputs
- **Null/undefined references** - Missing required objects
- **State violations** - Invalid object states
- **Type mismatches** - Incorrect types
- **Constraint violations** - Broken business rulescounterexample-to-test-generator
When your agent uses it
Automatically generates executable test cases from model checking counterexample traces. Translates abstract counterexample states and transitions into concrete test inputs, execution steps, and assertions that reproduce property violations. Use when working with model checker outputs (SPIN, CBMC, NuSMV, TLA+, Java PathFinder, etc.) and needing to create regression tests, validate bug fixes, or reproduce verification failures in executable test suites.
What it loads into context
Frontmatter
92 tokensAlways available to the agent
SKILL.md
1,369 tokensWhen the skill is activated
Reference documents
2,259 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- Overview
- Workflow
- Example Workflow
- Best Practices
- Common Challenges
- References
Scripts executed separately
assets/test_templates/python_pytest_template.py
Files
SKILL.mdcore6,289 bytesassets/test_templates/README.mddoc1,830 bytesassets/test_templates/c_gtest_template.casset2,096 bytesassets/test_templates/cpp_gtest_template.cppasset3,384 bytesassets/test_templates/csharp_nunit_template.csasset4,323 bytesassets/test_templates/java_junit_template.javaasset3,035 bytesassets/test_templates/python_pytest_template.pyruns3,460 bytesreferences/model_checker_formats.mddoc6,499 bytes
Read SKILL.md
# Counterexample To Test Generator
## Overview
This skill transforms counterexample traces from model checkers into executable test cases that reliably reproduce property violations. It bridges formal verification and testing by mapping abstract states to concrete values and generating runnable tests with clear traceability from counterexample steps to test logic.
## Workflow
### Step 1: Analyze Inputs
Gather and understand the counterexample trace and program:
1. **Identify the model checker format**: Determine which tool produced the counterexample (SPIN, CBMC, NuSMV, TLA+, JPF, etc.). See [references/model_checker_formats.md](references/model_checker_formats.md) for format details.
coverage-enhancer
When your agent uses it
Analyze existing test suites and source code to suggest additional unit tests that improve test coverage. Use this skill when working with test files and source code to identify untested code paths, missing edge cases, uncovered branches, untested error conditions, and gaps in test coverage. Supports major testing frameworks (pytest, Jest, JUnit, Go testing, etc.) and generates targeted test suggestions based on coverage analysis.
What it loads into context
Frontmatter
88 tokensAlways available to the agent
SKILL.md
4,182 tokensWhen the skill is activated
Reference documents
0 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- Core Capabilities
- Coverage Analysis Workflow
- Coverage Analysis Patterns
- Coverage Metrics
- Integration with Coverage Tools
- Test Suggestion Template
- Language-Specific Patterns
- Example: Complete Coverage Analysis
Files
SKILL.mdcore17,774 bytesSKILL.mdcore17,774 bytesSKILL.mdcore17,774 bytesSKILL.mdcore17,774 bytesSKILL.mdcore17,774 bytesSKILL.mdcore17,774 bytesSKILL.mdcore17,774 bytesSKILL.mdcore17,774 bytesSKILL.mdcore17,774 bytesSKILL.mdcore17,774 bytesSKILL.mdcore17,774 bytesSKILL.mdcore17,774 bytesSKILL.mdcore17,774 bytesSKILL.mdcore17,774 bytesSKILL.mdcore17,774 bytesSKILL.mdcore17,774 bytesSKILL.mdcore17,774 bytesSKILL.mdcore17,774 bytesSKILL.mdcore17,774 bytesSKILL.mdcore17,774 bytesSKILL.mdcore17,774 bytesSKILL.mdcore17,774 bytesSKILL.mdcore17,774 bytesSKILL.mdcore17,774 bytesSKILL.mdcore17,774 bytesSKILL.mdcore17,774 bytesSKILL.mdcore17,774 bytesSKILL.mdcore17,774 bytesSKILL.mdcore17,774 bytesSKILL.mdcore17,774 bytesSKILL.mdcore17,774 bytesSKILL.mdcore17,774 bytesSKILL.mdcore17,774 bytesSKILL.mdcore17,774 bytesSKILL.mdcore17,774 bytesSKILL.mdcore17,774 bytesSKILL.mdcore17,774 bytesSKILL.mdcore17,774 bytesSKILL.mdcore17,774 bytesSKILL.mdcore17,774 bytes
Read SKILL.md
# Coverage Enhancer
Analyze existing tests and source code to identify coverage gaps, then suggest specific additional tests to improve overall test coverage and code quality.
## Core Capabilities
### 1. Coverage Gap Analysis
Identify untested areas in source code:
- **Uncovered lines** - Code never executed by tests
- **Uncovered branches** - Conditional paths not tested
- **Uncovered functions** - Methods/functions without tests
- **Missing error handling tests** - Exception paths not verified
- **Untested edge cases** - Boundary conditions not coveredcpp-to-dafny-translator
When your agent uses it
Translate C/C++ programs to equivalent Dafny code while preserving semantics and ensuring verification. Use when users ask to convert, translate, or port C/C++ code to Dafny, or when they need to formally verify C/C++ algorithms using Dafny's verification capabilities. Handles functions, structs, pointers, arrays, memory management, and ensures the generated Dafny code is well-typed, executable, verifiable, and can successfully run.
What it loads into context
Frontmatter
100 tokensAlways available to the agent
SKILL.md
3,048 tokensWhen the skill is activated
Reference documents
7,765 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- Overview
- Translation Workflow
- Core Translation Principles
- Type Mapping Reference
- Translation Patterns
- Handling Common Challenges
- Translation Process
- Example Translation
- Best Practices
- Verification Checklist
- Additional Resources
Files
SKILL.mdcore11,462 bytesreferences/memory_patterns.mddoc8,406 bytesreferences/type_mappings.mddoc7,373 bytesreferences/verification_guide.mddoc10,478 bytes
Read SKILL.md
# C/C++ to Dafny Translator
Translate C/C++ programs into equivalent, verifiable Dafny code while preserving program semantics and ensuring memory safety.
## Overview
This skill provides systematic guidance for translating C/C++ code to Dafny, handling memory management, pointer semantics, type conversions, and ensuring well-typed, verifiable output with appropriate specifications.
## Translation Workflow
```
C/C++ Input → Analyze Structure → Map Types & Memory → Translate → Add Specifications → Verify
├─ Identify types, pointers, memory patterns
├─ Map C/C++ constructs to Dafny equivalentscritical-interval-security-checker
When your agent uses it
Analyzes code to identify security-critical time intervals and timing vulnerabilities in authentication, authorization, and time-sensitive security operations. Use this skill when reviewing code for proper timeout enforcement, token expiration, session management, rate limiting, password reset validity, or any time-sensitive security mechanism. Detects missing expiration checks, excessive timeout values, lack of rate limiting, client-side only validation, hardcoded timeouts, and timing attack vulnerabilities. Triggers when users ask to check security timeouts, verify token expiration handling, audit session timeout implementation, review rate limiting, or analyze time-based security controls.
What it loads into context
Frontmatter
128 tokensAlways available to the agent
SKILL.md
1,668 tokensWhen the skill is activated
Reference documents
5,057 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- Workflow
- Quick Reference
- Helper Script
- Best Practices
Scripts executed separately
scripts/check_intervals.py
Files
SKILL.mdcore7,269 bytesSKILL.mdcore7,269 bytesSKILL.mdcore7,269 bytesSKILL.mdcore7,269 bytesSKILL.mdcore7,269 bytesSKILL.mdcore7,269 bytesSKILL.mdcore7,269 bytesSKILL.mdcore7,269 bytesSKILL.mdcore7,269 bytesSKILL.mdcore7,269 bytesSKILL.mdcore7,269 bytesSKILL.mdcore7,269 bytesSKILL.mdcore7,269 bytesSKILL.mdcore7,269 bytesreferences/time_intervals.mddoc9,506 bytesreferences/vulnerability_patterns.mddoc11,765 bytesscripts/check_intervals.pyruns13,432 bytes
Read SKILL.md
# Critical Interval Security Checker
Analyze code to identify security-critical time intervals and timing vulnerabilities that could compromise security.
## Workflow
### 1. Identify Security-Critical Operations
Look for code that handles:
- **Authentication**: Login, logout, token generation
- **Session management**: Session creation, validation, expiration
- **Password operations**: Reset tokens, change requests
- **Rate limiting**: Login attempts, API calls, password resets
- **Token operations**: JWT, OAuth tokens, API keyscve-reachability-analyzer
When your agent uses it
Analyze CVE reachability in software repositories by examining how vulnerable dependencies are imported and used. Determines whether vulnerable components, classes, or functions are reachable from project code through call chain analysis, reflection detection, dynamic loading patterns, and configuration-gated behavior. Classifies each CVE as likely reachable, possibly reachable, or likely unreachable with supporting evidence. Use when analyzing security vulnerabilities in dependencies, performing post-disclosure CVE triage, assessing vulnerability impact, or when users ask to analyze CVE reachability, check if vulnerabilities are exploitable, or evaluate dependency security risks.
What it loads into context
Frontmatter
126 tokensAlways available to the agent
SKILL.md
2,698 tokensWhen the skill is activated
Reference documents
5,676 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- Overview
- Workflow
- Output Format
Files
SKILL.mdcore12,522 bytesreferences/cve_analysis.mddoc8,857 bytesreferences/language_guide.mddoc8,201 bytesreferences/reachability_patterns.mddoc7,337 bytes
Read SKILL.md
# Post-Disclosure CVE Reachability Analyzer
## Overview
This skill performs static analysis of software repositories to determine whether disclosed CVEs in dependencies are reachable from the project's code. It analyzes import patterns, call chains, dynamic invocation, and configuration to classify each CVE's reachability with evidence-based justification.
## Workflow
### Step 1: Gather Input Information
Collect and validate the required information:
1. **Repository analysis**:
- Identify programming language(s)cve-watchlist-action-recommendation-generator
When your agent uses it
Generate prioritized CVE watchlists and actionable security recommendations for repositories. Use when analyzing CVE scan results, creating security reports, prioritizing vulnerability remediation, or generating security gate reports for CI/CD. Takes CVE scan results (JSON/SARIF from npm audit, pip-audit, Snyk), reachability analysis, and cutoff date as input. Combines severity, reachability, exploitability, and dependency criticality to rank CVEs by practical risk. Outputs markdown reports with concrete next-step guidance (immediate upgrade, monitor, ignore with justification, apply mitigation) suitable for issue trackers, security reviews, and CI security gates.
What it loads into context
Frontmatter
142 tokensAlways available to the agent
SKILL.md
1,735 tokensWhen the skill is activated
Reference documents
5,320 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- Workflow
- Input Formats
- Example Output
Scripts executed separately
scripts/calculate_risk_score.pyscripts/parse_scan_results.py
Files
SKILL.mdcore6,676 bytesSKILL.mdcore6,676 bytesSKILL.mdcore6,676 bytesSKILL.mdcore6,676 bytesassets/report_template.mddoc6,632 bytesreferences/action_guidelines.mddoc8,399 bytesreferences/risk_scoring.mddoc5,490 bytesscripts/calculate_risk_score.pyruns8,621 bytesscripts/parse_scan_results.pyruns8,404 bytes
Read SKILL.md
# CVE Watchlist & Action Recommendation Generator
Generate prioritized CVE watchlists with actionable security recommendations for development and security teams.
## Workflow
### 1. Gather Input Data
Collect required inputs:
**Required:**
- Repository name/path
- CVE scan results (JSON/SARIF format from npm audit, pip-audit, Snyk, etc.)
- Cutoff date (YYYY-MM-DD) for filtering new CVEsdead-code-eliminator
When your agent uses it
Identify and analyze unused or redundant code including unused functions/methods, unused variables/imports, unreachable code, and redundant conditions. Use when cleaning up codebases, improving maintainability, reducing technical debt, or conducting code quality audits. Analyzes Python code using AST analysis and produces markdown reports listing dead code locations with line numbers, severity ratings, and recommendations. Triggers when users ask to find dead code, remove unused code, identify unused imports, find unreachable code, or clean up redundant logic.
What it loads into context
Frontmatter
111 tokensAlways available to the agent
SKILL.md
3,099 tokensWhen the skill is activated
Reference documents
2,121 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- Overview
- Workflow
- Dead Code Analysis Report
- Summary
- 🔴 High Priority Issues
- 🟡 Medium Priority Issues
- 🔵 Low Priority Issues
- ⚪ Needs Verification
- Recommendations
- Detailed Findings
- Tips for Effective Dead Code Analysis
- Common False Positives
- Reference
Scripts executed separately
scripts/find_unused_functions.pyscripts/find_unused_imports.py
Files
SKILL.mdcore13,279 bytesSKILL.mdcore13,279 bytesSKILL.mdcore13,279 bytesSKILL.mdcore13,279 bytesSKILL.mdcore13,279 bytesSKILL.mdcore13,279 bytesSKILL.mdcore13,279 bytesSKILL.mdcore13,279 bytesSKILL.mdcore13,279 bytesSKILL.mdcore13,279 bytesSKILL.mdcore13,279 bytesSKILL.mdcore13,279 bytesSKILL.mdcore13,279 bytesSKILL.mdcore13,279 bytesSKILL.mdcore13,279 bytesSKILL.mdcore13,279 bytesSKILL.mdcore13,279 bytesSKILL.mdcore13,279 bytesSKILL.mdcore13,279 bytesSKILL.mdcore13,279 bytesSKILL.mdcore13,279 bytesSKILL.mdcore13,279 bytesreferences/dead-code-patterns.mddoc9,174 bytesscripts/find_unused_functions.pyruns4,530 bytesscripts/find_unused_imports.pyruns4,954 bytes
Read SKILL.md
# Dead Code Eliminator
## Overview
Systematically identify unused or redundant code in Python codebases to improve maintainability, reduce confusion, and eliminate technical debt.
## Workflow
### 1. Understand the Scope
Define what to analyze:
**Questions to ask:**
- What directory or files should be analyzed?dead-code-removal
When your agent uses it
Dead code removal via parallel scanning, reference verification, batch execution, and atomic commits. You are the ORCHESTRATOR — you scan, verify, batch, then delegate ALL removals.
What it loads into context
Frontmatter
48 tokensAlways available to the agent
SKILL.md
1,616 tokensWhen the skill is activated
Reference documents
0 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- PHASE 1: SCAN — Find Dead Code Candidates
- PHASE 2: VERIFY — Reference Confirmation (Zero False Positives)
- PHASE 3: BATCH — Group by File for Conflict-Free Parallelism
- PHASE 4: EXECUTE — Apply Removals
- PHASE 5: FINAL VERIFICATION
- SCOPE CONTROL
- ABORT CONDITIONS
Files
SKILL.mdcore6,584 bytesSKILL.mdcore6,584 bytesSKILL.mdcore6,584 bytesSKILL.mdcore6,584 bytes
Read SKILL.md
# Dead Code Removal
Dead code removal via massively parallel scanning and execution. You are the ORCHESTRATOR — you scan, verify, batch, then execute all removals with atomic commits.
**Rules:**
- **Reference verification is law.** Verify with grep/language tools before ANY removal decision.
- **Never remove entry points.** Main entry files, test files, config files — off-limits.
**False-positive guards — NEVER mark as dead:**
- Symbols in entry point files or barrel `index` re-exports
- Symbols referenced in test files (tests are valid consumers)
- Symbols with `@public` / `@api` doc tags
- Hook factories (`createXXXHook`), tool factories (`createXXXTool`), plugin definitions
- Command templates, skill definitions, config objectsdependency-resolver
When your agent uses it
Identify, analyze, and manage software dependencies before deployment. Use this skill when preparing applications for deployment, resolving dependency conflicts, updating dependencies, auditing security vulnerabilities, managing package versions, or troubleshooting dependency-related issues. Supports multiple package managers (npm, pip, maven, cargo, go mod, composer) and provides actionable recommendations for dependency management.
What it loads into context
Frontmatter
76 tokensAlways available to the agent
SKILL.md
4,353 tokensWhen the skill is activated
Reference documents
0 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- Core Capabilities
- Dependency Resolution Workflow
- Dependency Management Patterns
- Version Constraint Syntax
- Dependency Commands Reference
- Pre-Deployment Checklist
- Common Issues and Solutions
- Best Practices
- Ecosystem-Specific Guides
Files
SKILL.mdcore16,096 bytesSKILL.mdcore16,096 bytesSKILL.mdcore16,096 bytesSKILL.mdcore16,096 bytesSKILL.mdcore16,096 bytesSKILL.mdcore16,096 bytesSKILL.mdcore16,096 bytesSKILL.mdcore16,096 bytesSKILL.mdcore16,096 bytesSKILL.mdcore16,096 bytesSKILL.mdcore16,096 bytesSKILL.mdcore16,096 bytesSKILL.mdcore16,096 bytesSKILL.mdcore16,096 bytesSKILL.mdcore16,096 bytesSKILL.mdcore16,096 bytesSKILL.mdcore16,096 bytesSKILL.mdcore16,096 bytesSKILL.mdcore16,096 bytesSKILL.mdcore16,096 bytesSKILL.mdcore16,096 bytesSKILL.mdcore16,096 bytesSKILL.mdcore16,096 bytesSKILL.mdcore16,096 bytesSKILL.mdcore16,096 bytesSKILL.mdcore16,096 bytesSKILL.mdcore16,096 bytes
Read SKILL.md
# Dependency Resolver
Analyze, manage, and resolve software dependencies to ensure safe and successful deployments. Identifies conflicts, security vulnerabilities, version mismatches, and missing dependencies.
## Core Capabilities
### 1. Dependency Analysis
Examine project dependencies:
- **Direct dependencies** - Packages explicitly required
- **Transitive dependencies** - Dependencies of dependencies
- **Dev dependencies** - Development-only packages
- **Peer dependencies** - Required by packages but not auto-installed
- **Optional dependencies** - Non-critical packagesdeprecated-api-updater
When your agent uses it
Identify and replace deprecated API usage in source code with modern alternatives. Use when: (1) Modernizing legacy codebases, (2) Upgrading framework versions (React, Django, Spring, etc.), (3) Fixing deprecation warnings in build output, (4) Preparing for major version upgrades, (5) Ensuring code uses current best practices. Supports Python, JavaScript/TypeScript, Java, and other major languages with both AST-based detection and pattern matching for accurate identification and automated replacement with validation.
What it loads into context
Frontmatter
115 tokensAlways available to the agent
SKILL.md
2,595 tokensWhen the skill is activated
Reference documents
5,704 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- Quick Start
- Supported Languages
- Detection Methods
- Workflow
- Best Practices
- Common Scenarios
- Limitations and Caveats
- Troubleshooting
- Reference Documentation
- Advanced Usage
Scripts executed separately
scripts/detect_deprecated_apis.pyscripts/replace_deprecated_apis.py
Files
SKILL.mdcore11,135 bytesSKILL.mdcore11,135 bytesSKILL.mdcore11,135 bytesSKILL.mdcore11,135 bytesSKILL.mdcore11,135 bytesSKILL.mdcore11,135 bytesSKILL.mdcore11,135 bytesSKILL.mdcore11,135 bytesSKILL.mdcore11,135 bytesSKILL.mdcore11,135 bytesSKILL.mdcore11,135 bytesSKILL.mdcore11,135 bytesSKILL.mdcore11,135 bytesSKILL.mdcore11,135 bytesSKILL.mdcore11,135 bytesSKILL.mdcore11,135 bytesSKILL.mdcore11,135 bytesSKILL.mdcore11,135 bytesSKILL.mdcore11,135 bytesSKILL.mdcore11,135 bytesreferences/java_deprecations.mddoc9,911 bytesreferences/javascript_deprecations.mddoc8,591 bytesreferences/python_deprecations.mddoc5,336 bytesscripts/detect_deprecated_apis.pyruns12,808 bytesscripts/replace_deprecated_apis.pyruns10,077 bytes
Read SKILL.md
# Deprecated API Updater
Identify and replace deprecated API usage with modern alternatives automatically.
## Quick Start
### Detect Deprecated APIs
Scan code to identify deprecated API usage:
```bash
# Scan a single file
python scripts/detect_deprecated_apis.py src/app.py
design-pattern-suggestor
When your agent uses it
Recommends appropriate software design patterns based on problem descriptions, requirements, or code scenarios. Use when designing software architecture, refactoring code, solving common design problems, or choosing between design approaches. Analyzes the problem context and suggests suitable creational, structural, behavioral, architectural, or concurrency patterns with implementation guidance and trade-off analysis.
What it loads into context
Frontmatter
78 tokensAlways available to the agent
SKILL.md
2,488 tokensWhen the skill is activated
Reference documents
3,923 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- Core Capabilities
- Pattern Suggestion Workflow
- Quick Pattern Matching
- Anti-Pattern Detection
- Example Consultations
- Resources
- Best Practices
Files
SKILL.mdcore11,880 bytesSKILL.mdcore11,880 bytesSKILL.mdcore11,880 bytesreferences/pattern_catalog.mddoc11,446 bytesreferences/selection_guide.mddoc7,510 bytes
Read SKILL.md
# Design Pattern Suggestor
You are an expert software architect who recommends appropriate design patterns for software problems.
## Core Capabilities
This skill enables you to:
1. **Analyze problems** - Understand design challenges and requirements
2. **Suggest patterns** - Recommend appropriate design patterns
3. **Explain rationale** - Justify why patterns fit the problem
4. **Provide implementation** - Show code examples and structure
5. **Compare alternatives** - Evaluate trade-offs between pattern choices
6. **Detect anti-patterns** - Identify and warn against poor design choicesdesign-smell-detector
When your agent uses it
Identify design quality issues in code including high coupling, low cohesion, God classes, long methods, and other code smells. Use when: (1) Reviewing code architecture and design quality, (2) Identifying refactoring opportunities, (3) Detecting God classes or classes with too many responsibilities, (4) Finding high coupling or low cohesion issues, (5) Analyzing code maintainability and technical debt. Detects coupling smells, cohesion problems, complexity issues, size violations, and encapsulation problems with actionable refactoring suggestions.
What it loads into context
Frontmatter
119 tokensAlways available to the agent
SKILL.md
3,108 tokensWhen the skill is activated
Reference documents
5,089 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- Quick Start
- Design Smells Detected
- Detection Workflow
- Common Design Smells
- Refactoring Strategies
- Metrics and Thresholds
- Design Smell Catalog
- Best Practices
- Common Scenarios
- Integration with Development Workflow
- Troubleshooting
- Reference Documentation
Scripts executed separately
scripts/detect_smells.py
Files
SKILL.mdcore12,910 bytesSKILL.mdcore12,910 bytesSKILL.mdcore12,910 bytesSKILL.mdcore12,910 bytesSKILL.mdcore12,910 bytesSKILL.mdcore12,910 bytesSKILL.mdcore12,910 bytesSKILL.mdcore12,910 bytesSKILL.mdcore12,910 bytesSKILL.mdcore12,910 bytesSKILL.mdcore12,910 bytesSKILL.mdcore12,910 bytesSKILL.mdcore12,910 bytesSKILL.mdcore12,910 bytesSKILL.mdcore12,910 bytesSKILL.mdcore12,910 bytesSKILL.mdcore12,910 bytesSKILL.mdcore12,910 bytesSKILL.mdcore12,910 bytesSKILL.mdcore12,910 bytesreferences/refactoring_strategies.mddoc11,493 bytesreferences/smell_catalog.mddoc10,487 bytesscripts/detect_smells.pyruns12,138 bytes
Read SKILL.md
# Design Smell Detector
Identify and address design quality issues in code through automated smell detection and refactoring guidance.
## Quick Start
### Detect Design Smells
```bash
# Analyze a single file
python scripts/detect_smells.py src/app.py
# Analyze entire directory
python scripts/detect_smells.py src/directed-test-input-generator
When your agent uses it
Generate targeted test inputs to reach specific code paths and hard-to-reach behaviors in Python code. Use when: (1) Targeting uncovered branches or specific execution paths, (2) Need coverage-guided test generation, (3) Want to leverage LLM understanding of code semantics for meaningful test inputs, (4) Testing boundary conditions and edge cases systematically, (5) Combining symbolic reasoning with fuzzing. Provides path analysis, constraint solving, coverage-guided strategies, and LLM-driven semantic generation for comprehensive test input creation.
What it loads into context
Frontmatter
116 tokensAlways available to the agent
SKILL.md
2,921 tokensWhen the skill is activated
Reference documents
6,117 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- Overview
- Quick Start
- Core Techniques
- Common Use Cases
- Advanced Strategies
- Reference Documentation
- Best Practices
- Tools Reference
Scripts executed separately
scripts/input_generator.pyscripts/path_analyzer.py
Files
SKILL.mdcore12,077 bytesSKILL.mdcore12,077 bytesSKILL.mdcore12,077 bytesSKILL.mdcore12,077 bytesSKILL.mdcore12,077 bytesSKILL.mdcore12,077 bytesSKILL.mdcore12,077 bytesSKILL.mdcore12,077 bytesSKILL.mdcore12,077 bytesSKILL.mdcore12,077 bytesSKILL.mdcore12,077 bytesSKILL.mdcore12,077 bytesSKILL.mdcore12,077 bytesSKILL.mdcore12,077 bytesSKILL.mdcore12,077 bytesSKILL.mdcore12,077 bytesSKILL.mdcore12,077 bytesSKILL.mdcore12,077 bytesSKILL.mdcore12,077 bytesSKILL.mdcore12,077 bytesSKILL.mdcore12,077 bytesreferences/coverage_strategies.mddoc14,741 bytesreferences/llm_patterns.mddoc12,642 bytesscripts/__pycache__/path_analyzer.cpython-36.pycasset7,510 bytesscripts/input_generator.pyruns9,983 bytesscripts/path_analyzer.pyruns8,485 bytes
Read SKILL.md
# Directed Test Input Generator
Generate test inputs that target specific code paths and hard-to-reach behaviors using program analysis, coverage feedback, and LLM-driven semantic understanding.
## Overview
Directed test input generation combines multiple techniques to create test inputs that explore specific execution paths:
1. **Path Analysis**: Extract control flow paths and their constraints
2. **Constraint Solving**: Generate inputs satisfying path conditions
3. **Coverage Guidance**: Use coverage feedback to iteratively reach new paths
4. **LLM Semantic Understanding**: Leverage code understanding for meaningful inputs
## Quick Startedge-case-generator
When your agent uses it
Automatically identify potential boundary and exception cases from requirements, specifications, or existing code, and generate comprehensive test cases targeting boundary conditions, edge cases, and uncommon scenarios. Use this skill when analyzing programs, code repositories, functions, or APIs to discover and test corner cases, null handling, overflow conditions, empty inputs, concurrent access patterns, and other exceptional scenarios that are often missed in standard testing.
What it loads into context
Frontmatter
86 tokensAlways available to the agent
SKILL.md
4,274 tokensWhen the skill is activated
Reference documents
17,237 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- Core Capabilities
- Edge Case Analysis Workflow
- Edge Case Categories
- Test Generation Patterns
- Common Edge Case Checklist
- Language-Specific Patterns
- Best Practices
- Example: Complete Edge Case Analysis
Files
SKILL.mdcore17,507 bytesSKILL.mdcore17,507 bytesSKILL.mdcore17,507 bytesSKILL.mdcore17,507 bytesSKILL.mdcore17,507 bytesSKILL.mdcore17,507 bytesSKILL.mdcore17,507 bytesSKILL.mdcore17,507 bytesSKILL.mdcore17,507 bytesreferences/c_cpp_edge_cases.mddoc15,249 bytesreferences/java_edge_cases.mddoc20,078 bytesreferences/javascript_edge_cases.mddoc17,805 bytesreferences/python_edge_cases.mddoc13,432 bytes
Read SKILL.md
# Edge Case Generator
Systematically identify boundary conditions, edge cases, and exceptional scenarios, then generate comprehensive tests to validate software behavior under uncommon conditions.
## Core Capabilities
### 1. Edge Case Identification
Analyze code, specifications, or requirements to identify:
- **Boundary values**: Min/max limits, zero, empty, first/last elements
- **Null and undefined**: Missing data, null pointers, undefined references
- **Type boundaries**: Integer overflow, floating-point precision, type mismatches
- **Collection edge cases**: Empty collections, single element, duplicatesenvironment-setup-assistant
When your agent uses it
Generate setup scripts and instructions for development environments across platforms. Use when: (1) Setting up new development machines (Python, Node.js, Docker, databases), (2) Creating automated setup scripts for team onboarding, (3) Need cross-platform setup instructions (macOS, Linux, Windows), (4) Installing development tools and dependencies, (5) Configuring version managers and package managers. Provides executable setup scripts, platform-specific guides, and tool installation instructions.
What it loads into context
Frontmatter
104 tokensAlways available to the agent
SKILL.md
2,950 tokensWhen the skill is activated
Reference documents
4,730 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- Quick Start
- Common Setup Scenarios
- Setup Script Templates
- Platform-Specific Guidance
- Development Tools
- Workflow
- Best Practices
- Common Patterns
- Troubleshooting
- Complete Example
Scripts executed separately
scripts/setup_docker.shscripts/setup_nodejs.shscripts/setup_python.sh
Files
SKILL.mdcore11,924 bytesSKILL.mdcore11,924 bytesSKILL.mdcore11,924 bytesSKILL.mdcore11,924 bytesSKILL.mdcore11,924 bytesSKILL.mdcore11,924 bytesSKILL.mdcore11,924 bytesSKILL.mdcore11,924 bytesSKILL.mdcore11,924 bytesSKILL.mdcore11,924 bytesSKILL.mdcore11,924 bytesSKILL.mdcore11,924 bytesSKILL.mdcore11,924 bytesSKILL.mdcore11,924 bytesSKILL.mdcore11,924 bytesSKILL.mdcore11,924 bytesSKILL.mdcore11,924 bytesSKILL.mdcore11,924 bytesSKILL.mdcore11,924 bytesSKILL.mdcore11,924 bytesSKILL.mdcore11,924 bytesSKILL.mdcore11,924 bytesSKILL.mdcore11,924 bytesSKILL.mdcore11,924 bytesSKILL.mdcore11,924 bytesSKILL.mdcore11,924 bytesSKILL.mdcore11,924 bytesSKILL.mdcore11,924 bytesSKILL.mdcore11,924 bytesSKILL.mdcore11,924 bytesreferences/platform_instructions.mddoc8,090 bytesreferences/tool_guides.mddoc8,867 bytesscripts/setup_docker.shruns3,170 bytesscripts/setup_nodejs.shruns2,212 bytesscripts/setup_python.shruns2,611 bytes
Read SKILL.md
# Environment Setup Assistant
Generate automated setup scripts and detailed instructions for development environments across multiple platforms.
## Quick Start
### Generate Setup Script
Specify your requirements and get an automated setup script:
```bash
# Example: Python development environment
bash scripts/setup_python.sh
error-explanation-generator
When your agent uses it
Explains test failures and provides actionable debugging guidance. Use when tests fail (unit, integration, E2E), builds fail, or code throws errors. Analyzes error messages, stack traces, and test output to identify root causes and suggest concrete fixes. Handles pytest, jest, junit, mocha, vitest, selenium, cypress, playwright, and other testing frameworks across Python, JavaScript/TypeScript, Java, Go, and other languages.
What it loads into context
Frontmatter
101 tokensAlways available to the agent
SKILL.md
3,546 tokensWhen the skill is activated
Reference documents
6,294 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- Core Capabilities
- Error Analysis Workflow
- Verification
- Prevention
- Verification
- Prevention
- Verification
- Prevention
- Verification
- Debugging Steps
- Prevention
- Verification
- Debugging Steps
- Prevention
- Quick Reference: Error Categories
- Resources
- Best Practices
Files
SKILL.mdcore15,072 bytesSKILL.mdcore15,072 bytesSKILL.mdcore15,072 bytesSKILL.mdcore15,072 bytesSKILL.mdcore15,072 bytesSKILL.mdcore15,072 bytesSKILL.mdcore15,072 bytesSKILL.mdcore15,072 bytesSKILL.mdcore15,072 bytesSKILL.mdcore15,072 bytesSKILL.mdcore15,072 bytesSKILL.mdcore15,072 bytesSKILL.mdcore15,072 bytesSKILL.mdcore15,072 bytesSKILL.mdcore15,072 bytesreferences/debugging_strategies.mddoc12,820 bytesreferences/error_patterns.mddoc12,230 bytes
Read SKILL.md
# Error Explanation Generator
Analyze test failures and provide clear explanations with actionable fixes.
## Core Capabilities
This skill helps debug failed tests by:
1. **Parsing error messages** - Extract key information from test output
2. **Identifying root causes** - Determine why tests fail
3. **Explaining clearly** - Translate technical errors into understandable language
4. **Providing fixes** - Suggest concrete, actionable solutions
5. **Recognizing patterns** - Detect common error categories across frameworks
exploitability-analyzer
When your agent uses it
Analyze detected vulnerabilities to assess realistic exploitability by examining control flow, input sources, sanitization logic, and execution context. Use when users need to: (1) Determine if a vulnerability is actually exploitable in practice, (2) Assess severity and impact of security issues, (3) Prioritize vulnerability remediation, (4) Understand attack vectors and exploitation conditions, (5) Generate exploitability reports with proof-of-concept scenarios. Focuses on injection vulnerabilities (SQL, command, XSS, path traversal, LDAP) with detailed analysis of reachability, controllability, sanitization, and impact.
What it loads into context
Frontmatter
131 tokensAlways available to the agent
SKILL.md
3,370 tokensWhen the skill is activated
Reference documents
3,035 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- Overview
- How to Use
- Analysis Workflow
- Example: SQL Injection (Critical)
- Example: Command Injection (High)
- Example: XSS (Medium)
- Example: Path Traversal (Low)
- Exploitability Rating Scale
- Report Format
- References
- Tips
Files
SKILL.mdcore14,150 bytesSKILL.mdcore14,150 bytesSKILL.mdcore14,150 bytesSKILL.mdcore14,150 bytesSKILL.mdcore14,150 bytesSKILL.mdcore14,150 bytesSKILL.mdcore14,150 bytesSKILL.mdcore14,150 bytesSKILL.mdcore14,150 bytesSKILL.mdcore14,150 bytesSKILL.mdcore14,150 bytesreferences/assessment_criteria.mddoc11,733 bytes
Read SKILL.md
# Exploitability Analyzer
Assess whether detected vulnerabilities are realistically exploitable.
## Overview
This skill analyzes security vulnerabilities to determine if they're actually exploitable in practice. It examines control flow to assess reachability, traces input sources to evaluate controllability, analyzes sanitization logic, and considers execution context to provide realistic exploitability assessments with severity ratings.
## How to Use
Provide:
1. **Vulnerable code**: The code containing the vulnerability
2. **Vulnerability type**: SQL injection, XSS, command injection, etc.
3. **Context**: Surrounding code, input sources, sanitization functionsfailure-oriented-instrumentation
When your agent uses it
Selectively instruments code to capture runtime data for debugging failures and bugs. Use when investigating crashes, exceptions, unexpected behavior, test failures, or performance issues. Analyzes stack traces and error messages to identify suspicious code regions, then adds targeted logging, tracing, and assertions to capture variable values, execution paths, timing, and conditional branches. Supports Python, JavaScript/TypeScript, Java, and C/C++.
What it loads into context
Frontmatter
93 tokensAlways available to the agent
SKILL.md
1,804 tokensWhen the skill is activated
Reference documents
4,009 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- Workflow
- Quick Start Examples
- Instrumentation Guidelines
- Language-Specific References
- Tips
Files
SKILL.mdcore8,487 bytesSKILL.mdcore8,487 bytesreferences/c-cpp.mddoc4,801 bytesreferences/java.mddoc4,701 bytesreferences/javascript.mddoc4,111 bytesreferences/python.mddoc3,140 bytes
Read SKILL.md
# Failure-Oriented Instrumentation
Strategically instrument code to capture high-signal runtime data for debugging failures, focusing only on suspicious regions rather than comprehensive instrumentation.
## Workflow
### 1. Analyze the Failure
Gather and analyze failure information:
- Error message and exception type
- Stack trace showing call chain
- Failure location (file, line, function)
- Reproduction steps or test case
- Expected vs actual behaviorflaky-test-detector
When your agent uses it
Identifies non-deterministic or unreliable tests through static code analysis and test result analysis. Use when Claude needs to find flaky tests, analyze test reliability, or investigate intermittent test failures. Supports Python (pytest, unittest) and Java (JUnit, TestNG) test frameworks. Trigger when users mention "flaky tests", "intermittent failures", "non-deterministic tests", "unreliable tests", or ask to "find flaky tests", "analyze test stability", or "why tests fail randomly".
What it loads into context
Frontmatter
113 tokensAlways available to the agent
SKILL.md
1,898 tokensWhen the skill is activated
Reference documents
3,938 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- Quick Start
- What Makes Tests Flaky
- Detection Methods
- Framework-Specific Guidance
- Workflow
- Example Usage Patterns
- Best Practices
Scripts executed separately
scripts/analyze_test_results.py
Files
SKILL.mdcore8,055 bytesSKILL.mdcore8,055 bytesreferences/flaky-patterns.mddoc6,686 bytesreferences/remediation-strategies.mddoc9,291 bytesscripts/analyze_test_results.pyruns5,212 bytes
Read SKILL.md
# Flaky Test Detector
Identify and fix non-deterministic tests that intermittently fail without code changes.
## Quick Start
When a user reports flaky tests or asks for test reliability analysis:
1. **Identify the approach**: Determine if analyzing code patterns or test execution results
2. **Analyze for flakiness**: Look for common flaky patterns in test code or execution history
3. **Report findings**: List identified flaky tests with specific issues
4. **Suggest fixes**: Provide concrete remediation strategies
## What Makes Tests Flakyformal-spec-generator
When your agent uses it
Generate formal specifications (definitions, predicates, invariants, pre/post-conditions) in Isabelle/HOL or Coq from informal requirements, source code, pseudocode, or mathematical descriptions. Use when users need to: (1) Formalize algorithms or data structures, (2) Create function specifications with contracts, (3) Generate predicates and properties for verification, (4) Translate informal requirements into formal logic, (5) Specify invariants for loops or data structures, or (6) Create formal definitions for mathematical concepts. Supports both Isabelle/HOL and Coq equally.
What it loads into context
Frontmatter
124 tokensAlways available to the agent
SKILL.md
1,281 tokensWhen the skill is activated
Reference documents
3,724 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- Workflow
- Key Principles
- Common Patterns
- Examples
- Tips
Files
SKILL.mdcore6,042 bytesSKILL.mdcore6,042 bytesSKILL.mdcore6,042 bytesreferences/coq_patterns.mddoc2,836 bytesreferences/examples.mddoc7,343 bytesreferences/isabelle_patterns.mddoc2,657 bytes
Read SKILL.md
# Formal Specification Generator
Generate formal specifications in Isabelle/HOL or Coq from informal descriptions, source code, or mathematical statements.
## Workflow
### 1. Understand the Input
Identify what type of input is provided:
- **Informal requirements**: Natural language descriptions (e.g., "a function that sorts a list")
- **Source code**: Existing implementations in Python, C, Java, or other languages
- **Pseudocode**: Algorithmic descriptions with semi-formal structure
- **Mathematical definitions**: Properties or theorems to formalize
framework-migration-assistant
When your agent uses it
Automatically migrate Python web applications between frameworks (Flask → FastAPI, Django → FastAPI). Use when you need to migrate an existing web application to a modern framework while preserving functionality. The skill analyzes the codebase, updates routes, handlers, configuration, dependency injection patterns, and tests. Creates git commits for each migration phase and generates a comprehensive summary of all changes. Supports automatic dependency updates, code transformations, and test adaptations.
What it loads into context
Frontmatter
96 tokensAlways available to the agent
SKILL.md
1,727 tokensWhen the skill is activated
Reference documents
6,420 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- Overview
- Quick Start
- Supported Migration Paths
- Migration Process
- Using the Migration Scripts
- Post-Migration Steps
- Reference Documentation
- Example Applications
- Migration Summary
- Tips
- Troubleshooting
Scripts executed separately
assets/example_fastapi_app.pyassets/example_flask_app.pyscripts/migrate.pyscripts/migrate_config.pyscripts/migrate_dependencies.pyscripts/migrate_routes.pyscripts/migrate_tests.py
Files
SKILL.mdcore7,647 bytesSKILL.mdcore7,647 bytesSKILL.mdcore7,647 bytesSKILL.mdcore7,647 bytesSKILL.mdcore7,647 bytesSKILL.mdcore7,647 bytesSKILL.mdcore7,647 bytesSKILL.mdcore7,647 bytesSKILL.mdcore7,647 bytesSKILL.mdcore7,647 bytesSKILL.mdcore7,647 bytesSKILL.mdcore7,647 bytesSKILL.mdcore7,647 bytesassets/example_fastapi_app.pyruns4,047 bytesassets/example_flask_app.pyruns2,672 bytesreferences/framework_comparison.mddoc7,846 bytesreferences/migration_guide.mddoc7,553 bytesreferences/migration_patterns.mddoc11,177 bytesscripts/migrate.pyruns12,869 bytesscripts/migrate_config.pyruns5,188 bytesscripts/migrate_dependencies.pyruns4,748 bytesscripts/migrate_routes.pyruns5,856 bytesscripts/migrate_tests.pyruns5,045 bytes
Read SKILL.md
# Framework Migration Assistant
## Overview
This skill automatically migrates Python web applications between frameworks, transforming code, configuration, and tests while preserving existing functionality. It handles route migration, request/response patterns, dependency injection, configuration updates, and test adaptations, committing changes incrementally with detailed summaries.
## Quick Start
### Basic Usage
```bash
# Navigate to your repository
cd /path/to/your/repo
frontend-ui-ux
When your agent uses it
Designer-turned-developer who crafts stunning UI/UX even without design mockups. Use for any frontend implementation requiring visual design decisions, aesthetic direction, or pixel-perfect UI work.
What it loads into context
Frontmatter
45 tokensAlways available to the agent
SKILL.md
676 tokensWhen the skill is activated
Reference documents
0 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- When to Use This Skill
- Design Process
- Aesthetic Guidelines
- Anti-Patterns (Never Do)
- Execution
- Example
Files
SKILL.mdcore3,246 bytes
Read SKILL.md
# Frontend UI/UX Designer
You are a designer who learned to code. You see what pure developers miss — spacing, color harmony, micro-interactions, that indefinable "feel" that makes interfaces memorable.
## When to Use This Skill
- Implementing UI without design mockups
- Making visual design decisions (typography, color, layout)
- Creating visually striking, production-grade interfaces
- Improving existing UI aesthetics and interactions
## Design Process
Before coding, commit to a bold aesthetic direction:function-class-generator
When your agent uses it
Generate complete, production-ready functions and classes from formal specifications, design descriptions, type signatures, or natural language requirements. Use this skill when implementing APIs from specifications, creating data structures from schemas, building classes from UML diagrams, generating code from contracts, or translating design documents into code. Supports multiple programming languages and follows language-specific best practices.
What it loads into context
Frontmatter
75 tokensAlways available to the agent
SKILL.md
6,032 tokensWhen the skill is activated
Reference documents
0 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- Core Capabilities
- Code Generation Workflow
- Generation Patterns
- Language-Specific Templates
- Best Practices
- Common Patterns
Files
SKILL.mdcore26,439 bytesSKILL.mdcore26,439 bytesSKILL.mdcore26,439 bytesSKILL.mdcore26,439 bytesSKILL.mdcore26,439 bytesSKILL.mdcore26,439 bytesSKILL.mdcore26,439 bytesSKILL.mdcore26,439 bytes
Read SKILL.md
# Function/Class Generator
Transform formal specifications, design descriptions, and requirements into complete, well-structured, production-ready code. Generates functions, classes, interfaces, and data structures with proper error handling, documentation, and tests.
## Core Capabilities
### 1. Specification Parsing
Understand specifications from multiple sources:
- **Type signatures** - Function signatures with input/output types
- **Formal specifications** - Pre/postconditions, invariants, contracts
- **API documentation** - OpenAPI, Swagger, JSON Schema
- **UML diagrams** - Class diagrams, sequence diagrams
- **Natural language** - Requirements and design descriptionsfuzzing-input-generator
When your agent uses it
Generate randomized and edge-case inputs to detect unexpected failures, bugs, and security vulnerabilities through fuzz testing. Use when creating test cases for robustness testing, generating adversarial inputs, testing error handling, finding edge cases, or security testing. Produces Python test code with fuzzing inputs for strings, numbers, and structured data focusing on edge cases, invalid inputs, and random valid inputs. Triggers when users ask to generate fuzz tests, create randomized test inputs, test edge cases, find bugs through fuzzing, or generate adversarial test cases.
What it loads into context
Frontmatter
117 tokensAlways available to the agent
SKILL.md
4,580 tokensWhen the skill is activated
Reference documents
2,236 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- Overview
- Workflow
- Example Workflows
- Tips for Effective Fuzzing
- Reference
Files
SKILL.mdcore19,540 bytesSKILL.mdcore19,540 bytesSKILL.mdcore19,540 bytesSKILL.mdcore19,540 bytesSKILL.mdcore19,540 bytesSKILL.mdcore19,540 bytesSKILL.mdcore19,540 bytesSKILL.mdcore19,540 bytesSKILL.mdcore19,540 bytesSKILL.mdcore19,540 bytesSKILL.mdcore19,540 bytesSKILL.mdcore19,540 bytesSKILL.mdcore19,540 bytesSKILL.mdcore19,540 bytesSKILL.mdcore19,540 bytesSKILL.mdcore19,540 bytesSKILL.mdcore19,540 bytesreferences/fuzzing-patterns.mddoc7,649 bytes
Read SKILL.md
# Fuzzing Input Generator
## Overview
Generate comprehensive fuzz testing inputs to uncover bugs, crashes, and security vulnerabilities by systematically testing functions with edge cases, invalid inputs, and randomized data.
## Workflow
### 1. Analyze the Target Function
Understand what needs to be fuzzed:
**Identify input types:**
- Strings (text, paths, URLs, etc.)git-bisect-assistant
When your agent uses it
Automatically performs git bisect to identify the first bad commit that introduced a bug or failure. Use when debugging regressions, tracking down when a test started failing, or identifying which commit broke functionality. Handles flaky tests with retry logic and provides comprehensive reports with bisect logs and confidence levels.
What it loads into context
Frontmatter
68 tokensAlways available to the agent
SKILL.md
1,148 tokensWhen the skill is activated
Reference documents
0 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- Quick Start
- Workflow
- Parameters
- Handling Flaky Tests
- Test Command Guidelines
- Output Report
- Common Scenarios
- Tips
- Troubleshooting
Scripts executed separately
scripts/git_bisect_runner.py
Files
SKILL.mdcore4,775 bytesSKILL.mdcore4,775 bytesSKILL.mdcore4,775 bytesSKILL.mdcore4,775 bytesSKILL.mdcore4,775 bytesSKILL.mdcore4,775 bytesSKILL.mdcore4,775 bytesSKILL.mdcore4,775 bytesscripts/git_bisect_runner.pyruns8,214 bytes
Read SKILL.md
# Git Bisect Assistant
Automates the git bisect process to efficiently identify the first bad commit responsible for a bug or test failure.
## Quick Start
Basic usage pattern:
```bash
python scripts/git_bisect_runner.py \
--good <known-good-commit> \
--bad <known-bad-commit> \
--test "<test-command>"
```git-master
When your agent uses it
Git expert combining atomic commits, rebase/squash, and history search (blame, bisect, log -S). Use for any git operations requiring structured commit strategies, history rewriting, or code archaeology. Triggers: 'commit', 'rebase', 'squash', 'who wrote', 'when was X added', 'find the commit that'.
What it loads into context
Frontmatter
83 tokensAlways available to the agent
SKILL.md
7,133 tokensWhen the skill is activated
Reference documents
0 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- MODE DETECTION (FIRST STEP)
- CORE PRINCIPLE: MULTIPLE COMMITS BY DEFAULT (NON-NEGOTIABLE)
- PHASE 0: Parallel Context Gathering (MANDATORY FIRST STEP)
- PHASE 1: Style Detection (BLOCKING - MUST OUTPUT BEFORE PROCEEDING)
- PHASE 2: Branch Context Analysis
- PHASE 3: Atomic Unit Planning (BLOCKING - MUST OUTPUT BEFORE PROCEEDING)
- PHASE 4: Commit Strategy Decision
- PHASE 5: Commit Execution
- PHASE 6: Verification & Cleanup
- PHASE R1: Rebase Context Analysis
- PHASE R2: Rebase Execution
- PHASE R3: Post-Rebase Verification
- PHASE R4: Rebase Report
- PHASE H1: Determine Search Type
- PHASE H2: Execute Search
- PHASE H3: Present Results
- Quick Reference: History Search Commands
- Anti-Patterns (ALL MODES)
- FINAL CHECK BEFORE EXECUTION (BLOCKING)
Files
SKILL.mdcore25,836 bytesSKILL.mdcore25,836 bytesSKILL.mdcore25,836 bytesSKILL.mdcore25,836 bytesSKILL.mdcore25,836 bytesSKILL.mdcore25,836 bytesSKILL.mdcore25,836 bytesSKILL.mdcore25,836 bytesSKILL.mdcore25,836 bytesSKILL.mdcore25,836 bytesSKILL.mdcore25,836 bytesSKILL.mdcore25,836 bytesSKILL.mdcore25,836 bytesSKILL.mdcore25,836 bytesSKILL.mdcore25,836 bytesSKILL.mdcore25,836 bytesSKILL.mdcore25,836 bytes
Read SKILL.md
# Git Master
You are a Git expert combining three specializations:
1. **Commit Architect**: Atomic commits, dependency ordering, style detection
2. **Rebase Surgeon**: History rewriting, conflict resolution, branch cleanup
3. **History Archaeologist**: Finding when/where specific changes were introduced
---
## MODE DETECTION (FIRST STEP)
Analyze the user's request to determine operation mode:
| User Request Pattern | Mode | Jump To |github-triage
When your agent uses it
Unified GitHub triage for issues AND PRs. Classifies open items, answers questions from codebase, analyzes bugs, reviews PRs, and produces a structured triage report. Triggers: 'triage', 'triage issues', 'triage PRs', 'github triage'.
What it loads into context
Frontmatter
71 tokensAlways available to the agent
SKILL.md
3,142 tokensWhen the skill is activated
Reference documents
0 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- ARCHITECTURE
- PHASE 1: FETCH ALL OPEN ITEMS
- PHASE 2: CLASSIFY EACH ITEM
- PHASE 3: PROCESS EACH ITEM
- PHASE 4: COLLECT RESULTS
- PHASE 5: FINAL SUMMARY
- ANTI-PATTERNS
- QUICK START
Files
SKILL.mdcore11,953 bytesSKILL.mdcore11,953 bytes
Read SKILL.md
# GitHub Triage — Unified Issue & PR Processor
You are a GitHub triage orchestrator. You fetch all open issues and PRs, classify each one, then process each item in parallel. Each item gets analyzed, actioned (comment/close/merge/report), and results are tracked.
---
## ARCHITECTURE
```
1 issue or PR = 1 parallel task
```
| Rule | Value |
|------|-------|imperative-to-coq-model-extractor
When your agent uses it
Extract abstract mathematical models from imperative code (C, C++, Python, Java, etc.) suitable for formal reasoning in Coq. Use when the user asks to model imperative code in Coq, create Coq specifications from imperative programs, extract mathematical models for verification, or translate imperative algorithms to Coq for formal reasoning and proof.
What it loads into context
Frontmatter
78 tokensAlways available to the agent
SKILL.md
2,754 tokensWhen the skill is activated
Reference documents
3,568 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- Overview
- Extraction Workflow
- Common Extraction Patterns
- Examples
- Best Practices
- Key Differences: Imperative vs Coq Model
- Limitations and Considerations
- Resources
Files
SKILL.mdcore10,418 bytesSKILL.mdcore10,418 bytesSKILL.mdcore10,418 bytesreferences/extraction_patterns.mddoc11,397 bytes
Read SKILL.md
# Imperative to Coq Model Extractor
## Overview
Extract abstract mathematical models from imperative code that can be used for formal reasoning and verification in Coq. This skill transforms imperative programs into functional Coq definitions with explicit state modeling, enabling formal proofs about program behavior.
## Extraction Workflow
### Step 1: Analyze Imperative Code
Understand the program structure and semantics:
1. **Identify components:**
- Functions and their signaturesincremental-java-programmer
When your agent uses it
Incrementally implement new features in Java repositories from natural language descriptions. Use when adding functionality to existing Java codebases (Maven or Gradle projects). Takes a feature description as input and outputs modified repository with implementation code, corresponding JUnit tests, and verification that all tests pass. Supports method additions, new class creation, and method modifications with proper Java conventions.
What it loads into context
Frontmatter
81 tokensAlways available to the agent
SKILL.md
2,409 tokensWhen the skill is activated
Reference documents
0 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- Overview
- Workflow
- Implementation Patterns
- Tips
Files
SKILL.mdcore11,090 bytesSKILL.mdcore11,090 bytesSKILL.mdcore11,090 bytes
Read SKILL.md
# Incremental Java Programmer
## Overview
Implement new features in Java repositories by analyzing the codebase, generating implementation code, creating comprehensive tests, and ensuring all tests pass before completion.
## Workflow
### 1. Analyze Repository Structure
Understand the Java project structure and build system:
**Identify build system**:
- Maven: Look for `pom.xml` in root directoryincremental-python-programmer
When your agent uses it
Takes a Python repository and natural language feature description as input, implements the feature with proper code placement, generates comprehensive tests, and ensures all tests pass. Use when Claude needs to: (1) Add new features to existing Python projects, (2) Implement functions, classes, or modules based on requirements, (3) Modify existing code to add functionality, (4) Generate unit and integration tests for new code, (5) Fix failing tests after implementation, (6) Ensure code follows existing patterns and conventions.
What it loads into context
Frontmatter
114 tokensAlways available to the agent
SKILL.md
3,123 tokensWhen the skill is activated
Reference documents
3,825 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- Workflow
- Implementation Guidelines
- Common Scenarios
- Troubleshooting
- Best Practices
Scripts executed separately
scripts/analyze_repo_structure.py
Files
SKILL.mdcore14,237 bytesSKILL.mdcore14,237 bytesSKILL.mdcore14,237 bytesSKILL.mdcore14,237 bytesSKILL.mdcore14,237 bytesSKILL.mdcore14,237 bytesSKILL.mdcore14,237 bytesSKILL.mdcore14,237 bytesSKILL.mdcore14,237 bytesSKILL.mdcore14,237 bytesreferences/implementation-patterns.mddoc7,936 bytesreferences/testing-strategies.mddoc8,778 bytesscripts/analyze_repo_structure.pyruns6,492 bytes
Read SKILL.md
# Incremental Python Programmer
Implement new features in Python repositories with automated testing and validation.
## Workflow
### 1. Understand the Feature Request
**Parse the request:**
- Identify what functionality is being requested
- Determine scope (function, class, module, or modification)
- Understand expected behavior and inputs/outputs
- Note any specific requirements or constraints
init-deep
When your agent uses it
Generates hierarchical context files (CLAUDE.md) throughout a project directory tree, providing AI agents with directory-specific knowledge for better code understanding. Use when setting up a new project for AI-assisted development.
What it loads into context
Frontmatter
48 tokensAlways available to the agent
SKILL.md
893 tokensWhen the skill is activated
Reference documents
0 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- When to Use This Skill
- What This Skill Does
- Options
- Example
Files
SKILL.mdcore3,703 bytesSKILL.mdcore3,703 bytes
Read SKILL.md
# Init Deep — Hierarchical Context Generator
Automatically generates layered context files throughout a project's directory tree, giving AI agents directory-specific knowledge without loading the entire codebase into context.
## When to Use This Skill
- Setting up a new project for AI-assisted development
- Onboarding AI agents to an existing codebase
- After major restructuring when context files are outdated
- When AI agents lack understanding of project-specific conventions
## What This Skill Does
### Conceptintegration-test-generator
When your agent uses it
Generate integration tests for multiple interacting components in Python. Use when testing interactions between: (1) Multiple services or APIs (REST/GraphQL endpoints, microservices), (2) Database operations with repositories/ORMs (SQLAlchemy, Django ORM), (3) External services (payment gateways, email services, third-party APIs), (4) Message queues and event-driven systems, (5) Full stack workflows (API + database + business logic). Provides test structure templates, fixtures, test data builders, and patterns for pytest-based integration testing.
What it loads into context
Frontmatter
118 tokensAlways available to the agent
SKILL.md
1,816 tokensWhen the skill is activated
Reference documents
4,807 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- When to Use Integration Tests
- Test Structure
- Common Integration Test Patterns
- Detailed Patterns and Examples
- Best Practices
- Quick Reference
Files
SKILL.mdcore8,272 bytesSKILL.mdcore8,272 bytesSKILL.mdcore8,272 bytesSKILL.mdcore8,272 bytesSKILL.mdcore8,272 bytesSKILL.mdcore8,272 bytesSKILL.mdcore8,272 bytesSKILL.mdcore8,272 bytesSKILL.mdcore8,272 bytesSKILL.mdcore8,272 bytesSKILL.mdcore8,272 bytesSKILL.mdcore8,272 bytesSKILL.mdcore8,272 bytesSKILL.mdcore8,272 bytesreferences/patterns.mddoc11,715 bytesreferences/test_data.mddoc10,600 bytes
Read SKILL.md
# Integration Test Generator
Generate comprehensive integration tests for Python applications that test multiple interacting components together.
## When to Use Integration Tests
Integration tests verify that multiple components work correctly together:
- **Service Integration**: REST/GraphQL APIs communicating with each other
- **Database Integration**: Repositories, ORM models, transaction handling
- **External Services**: Payment gateways, email services, third-party APIs
- **Event-Driven**: Message queues, event publishers/consumers
- **Full Stack**: Complete workflows through multiple layers (API → business logic → database)
interface-contract-verifier
When your agent uses it
Verify that interface and class contracts (preconditions, postconditions, invariants) are preserved across program versions. Use when validating refactorings, checking API compatibility, verifying design-by-contract implementations, or ensuring behavioral contracts remain intact after code changes. Automatically detects contract violations, identifies affected methods and classes, and provides actionable guidance for resolving violations while maintaining program correctness.
What it loads into context
Frontmatter
81 tokensAlways available to the agent
SKILL.md
533 tokensWhen the skill is activated
Reference documents
489 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- Overview
- Core Workflow
- Contract Types
- Verification Rules
- Violation Types
- Resolution Guidance
- Resources
Scripts executed separately
scripts/contract_extractor.pyscripts/contract_verifier.py
Files
SKILL.mdcore2,704 bytesSKILL.mdcore2,704 bytesSKILL.mdcore2,704 bytesSKILL.mdcore2,704 bytesSKILL.mdcore2,704 bytesSKILL.mdcore2,704 bytesreferences/design_by_contract.mddoc2,175 bytesscripts/contract_extractor.pyruns5,309 bytesscripts/contract_verifier.pyruns10,029 bytes
Read SKILL.md
# Interface Contract Verifier
## Overview
Verify that formal or structured contracts (preconditions, postconditions, invariants) defined in interfaces and classes are preserved when updating to a new program version.
## Core Workflow
### 1. Extract Contracts
Extract contracts from both versions:
```bash
python scripts/contract_extractor.py --program old_version --output old_contracts.jsoninterface-specification-generator
When your agent uses it
What it loads into context
Frontmatter
46 tokensAlways available to the agent
SKILL.md
832 tokensWhen the skill is activated
Reference documents
4,541 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- Overview
- Structuring This Skill
- [TODO: Replace with the first main section based on chosen structure]
- Resources
Scripts executed separately
scripts/example.pyscripts/validate_openapi.py
Files
SKILL.mdcore4,056 bytesassets/example_asset.txtdoc865 bytesassets/openapi-template.yamlasset2,382 bytesreferences/api_reference.mddoc984 bytesreferences/openapi-patterns.mddoc14,415 bytesreferences/validation-rules.mddoc4,196 bytesscripts/example.pyruns625 bytesscripts/validate_openapi.pyruns5,146 bytes
Read SKILL.md
# Interface Specification Generator
## Overview
[TODO: 1-2 sentences explaining what this skill enables]
## Structuring This Skill
[TODO: Choose the structure that best fits this skill's purpose. Common patterns:
**1. Workflow-Based** (best for sequential processes)
- Works well when there are clear step-by-step procedures
- Example: DOCX skill with "Workflow Decision Tree" → "Reading" → "Creating" → "Editing"
- Structure: ## Overview → ## Workflow Decision Tree → ## Step 1 → ## Step 2...interval-difference-analyzer
When your agent uses it
Analyze differences in program intervals between two versions of a program (old and new) to identify added, removed, or modified intervals. Use when comparing program versions, analyzing variable ranges, detecting behavioral changes in numeric computations, validating refactorings, or assessing migration impacts. Supports optional test suite integration to validate interval changes. Generates comprehensive reports highlighting intervals requiring further testing or verification.
What it loads into context
Frontmatter
84 tokensAlways available to the agent
SKILL.md
1,508 tokensWhen the skill is activated
Reference documents
4,917 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- Overview
- Core Workflow
- What Are Program Intervals?
- Interval Extraction Methods
- Interval Comparison
- Behavioral Change Detection
- Testing Recommendations
- Report Format
- Integration with Test Suites
- Best Practices
- Resources
Scripts executed separately
scripts/compare_intervals.pyscripts/interval_analyzer.py
Files
SKILL.mdcore6,546 bytesSKILL.mdcore6,546 bytesSKILL.mdcore6,546 bytesSKILL.mdcore6,546 bytesSKILL.mdcore6,546 bytesSKILL.mdcore6,546 bytesSKILL.mdcore6,546 bytesSKILL.mdcore6,546 bytesSKILL.mdcore6,546 bytesSKILL.mdcore6,546 bytesSKILL.mdcore6,546 bytesSKILL.mdcore6,546 bytesreferences/abstract_interpretation.mddoc8,555 bytesreferences/interval_analysis.mddoc7,916 bytesscripts/compare_intervals.pyruns12,838 bytesscripts/interval_analyzer.pyruns8,597 bytes
Read SKILL.md
# Interval Difference Analyzer
## Overview
Analyze differences in program intervals (variable value ranges) between two versions of a program to detect behavioral changes, identify potential bugs, and guide testing efforts.
## Core Workflow
### 1. Setup Program Versions
Prepare both program versions for analysis:
```bash
OLD_VERSION=/path/to/old/programinterval-guided-regression-test-update
When your agent uses it
Automatically updates regression tests based on interval analysis to maintain coverage of key program intervals. Use when code changes affect value ranges, conditionals, or control flow, and existing tests need updating to maintain interval coverage. Analyzes interval information from updated code, identifies coverage gaps, adjusts test inputs and assertions, removes redundant tests, and generates new tests for uncovered intervals. Supports Python, Java, JavaScript, and C/C++ with various test frameworks (pytest, JUnit, Jest, Google Test).
What it loads into context
Frontmatter
111 tokensAlways available to the agent
SKILL.md
2,633 tokensWhen the skill is activated
Reference documents
4,726 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- Core Concept
- Workflow
- Quick Start Examples
- Update Strategies
- Coverage Analysis
- Best Practices
- Common Scenarios
- Troubleshooting
- References
- Tips
Files
SKILL.mdcore10,750 bytesSKILL.mdcore10,750 bytesSKILL.mdcore10,750 bytesSKILL.mdcore10,750 bytesSKILL.mdcore10,750 bytesSKILL.mdcore10,750 bytesSKILL.mdcore10,750 bytesSKILL.mdcore10,750 bytesSKILL.mdcore10,750 bytesSKILL.mdcore10,750 bytesSKILL.mdcore10,750 bytesSKILL.mdcore10,750 bytesSKILL.mdcore10,750 bytesSKILL.mdcore10,750 bytesSKILL.mdcore10,750 bytesSKILL.mdcore10,750 bytesSKILL.mdcore10,750 bytesSKILL.mdcore10,750 bytesSKILL.mdcore10,750 bytesSKILL.mdcore10,750 bytesreferences/interval-analysis.mddoc7,625 bytesreferences/test-update-strategies.mddoc9,768 bytes
Read SKILL.md
# Interval-Guided Regression Test Update
Automatically update regression tests to maintain interval coverage when program code changes.
## Core Concept
**Intervals** represent ranges of values that variables can take during execution. When code changes, intervals may be added, removed, or modified. This skill ensures regression tests continue to cover all important intervals.
**Example:**
```python
# Old code
def process(x):
if x < 10:
return x * 2interval-profiling-performance-analyzer
When your agent uses it
Profile programs at the function/method level to identify performance hotspots, bottlenecks, and optimization opportunities. Records execution time, memory usage, and call frequency for each interval. Generates actionable recommendations and visualizations. Use when users need to (1) analyze program performance, (2) identify slow functions or bottlenecks, (3) optimize execution time or memory usage, (4) profile Python, Java, or C/C++ programs with test cases or workload scenarios, or (5) generate performance reports with flame graphs and recommendations.
What it loads into context
Frontmatter
120 tokensAlways available to the agent
SKILL.md
1,480 tokensWhen the skill is activated
Reference documents
3,240 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- Workflow
- Common Patterns
- Important Notes
- Troubleshooting
- Resources
Scripts executed separately
scripts/generate_visualization.pyscripts/profile_cpp.pyscripts/profile_java.pyscripts/profile_python.py
Files
SKILL.mdcore6,733 bytesSKILL.mdcore6,733 bytesSKILL.mdcore6,733 bytesSKILL.mdcore6,733 bytesSKILL.mdcore6,733 bytesSKILL.mdcore6,733 bytesUSAGE.txtdoc1,093 bytesreferences/optimization-patterns.mddoc7,978 bytesreferences/profiling-tools.mddoc4,578 bytesscripts/generate_visualization.pyruns9,132 bytesscripts/profile_cpp.pyruns8,027 bytesscripts/profile_java.pyruns6,207 bytesscripts/profile_python.pyruns5,434 bytes
Read SKILL.md
# Interval Profiling & Performance Analyzer
Profile programs to identify performance bottlenecks and generate optimization recommendations with visualizations.
## Workflow
### 1. Understand Requirements
Clarify the profiling task:
- **Target program:** Which file/executable to profile?
- **Language:** Python, Java, or C/C++?
- **Test scenarios:** What workload or test cases to run?
- **Focus area:** CPU time, memory usage, or both?
invariant-inference
When your agent uses it
Automatically infer loop invariants for code verification and correctness proofs. Use when analyzing loops to identify properties that hold throughout execution, generating assertions for verification, proving loop correctness, or documenting loop behavior. Supports Python, Java, C/C++, and language-agnostic analysis. Generates invariants as code assertions (assert statements). Triggers when users ask to infer invariants, find loop properties, generate loop assertions, prove loop correctness, or verify loop behavior.
What it loads into context
Frontmatter
98 tokensAlways available to the agent
SKILL.md
3,228 tokensWhen the skill is activated
Reference documents
1,747 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- Overview
- Workflow
- Example Workflows
- Tips for Effective Invariant Inference
- Reference
Files
SKILL.mdcore12,391 bytesSKILL.mdcore12,391 bytesSKILL.mdcore12,391 bytesSKILL.mdcore12,391 bytesSKILL.mdcore12,391 bytesSKILL.mdcore12,391 bytesSKILL.mdcore12,391 bytesSKILL.mdcore12,391 bytesSKILL.mdcore12,391 bytesSKILL.mdcore12,391 bytesSKILL.mdcore12,391 bytesSKILL.mdcore12,391 bytesSKILL.mdcore12,391 bytesSKILL.mdcore12,391 bytesSKILL.mdcore12,391 bytesSKILL.mdcore12,391 bytesSKILL.mdcore12,391 bytesSKILL.mdcore12,391 bytesSKILL.mdcore12,391 bytesSKILL.mdcore12,391 bytesSKILL.mdcore12,391 bytesSKILL.mdcore12,391 bytesSKILL.mdcore12,391 bytesSKILL.mdcore12,391 bytesreferences/invariant-patterns.mddoc5,991 bytes
Read SKILL.md
# Invariant Inference
## Overview
Analyze loops and automatically infer invariants—properties that remain true throughout loop execution. Generate these as code assertions for verification and correctness proofs.
## Workflow
### 1. Identify the Loop
First, locate and understand the loop to analyze:
**Loop types to recognize:**
- `for` loops with index variablesissue-report-generator
When your agent uses it
Automatically generate clear, actionable issue reports from failing tests and repository analysis. Analyze test failures to understand expected vs. actual behavior, identify affected code components, and produce well-structured Markdown reports suitable for GitHub Issues or similar trackers. Use when a test fails, when debugging issues, or when the user asks to create an issue report, generate a bug report, or document a test failure.
What it loads into context
Frontmatter
86 tokensAlways available to the agent
SKILL.md
3,285 tokensWhen the skill is activated
Reference documents
3,650 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- Overview
- Report Generation Workflow
- Report Templates
- Examples
- Analysis
- Test Details
- Expected Behavior
- Actual Behavior
- Affected Code
- Analysis
- Test Details
- Analysis
- Test Details
- Constraints and Requirements
- Best Practices
- Quality Checklist
- Resources
Files
SKILL.mdcore13,856 bytesSKILL.mdcore13,856 bytesSKILL.mdcore13,856 bytesSKILL.mdcore13,856 bytesSKILL.mdcore13,856 bytesSKILL.mdcore13,856 bytesreferences/report_patterns.mddoc15,359 bytes
Read SKILL.md
# Issue Report Generator
## Overview
Generate comprehensive, developer-friendly issue reports from failing tests. Analyze test failures, identify affected code, infer root causes when possible, and produce structured Markdown reports ready for issue tracking systems.
## Report Generation Workflow
### Step 1: Analyze the Failing Test
Understand what the test is checking and why it fails:
1. **Identify the test:**
- Test file pathjava-api-consistency-validator
When your agent uses it
Validate API consistency between two versions of Java libraries. Use when you need to compare API behavior, signatures, and exceptions between Java library versions to identify breaking changes, incompatible modifications, and behavior differences. The skill performs static analysis of Java code, compares method signatures, class definitions, interface changes, parameter types, return types, exception declarations, and generates a detailed JSON report with breaking changes, warnings, and migration guidance. Supports Java libraries and packages.
What it loads into context
Frontmatter
99 tokensAlways available to the agent
SKILL.md
560 tokensWhen the skill is activated
Reference documents
0 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- Overview
- Quick Start
- What Gets Validated
- Validation Report
- Usage
- Tips
Scripts executed separately
scripts/validate.py
Files
SKILL.mdcore2,639 bytesSKILL.mdcore2,639 bytesSKILL.mdcore2,639 bytesscripts/validate.pyruns9,219 bytes
Read SKILL.md
# Java API Consistency Validator
## Overview
This skill validates API consistency between two versions of Java libraries by comparing signatures, behavior, and exceptions. It identifies breaking changes, incompatible modifications, and provides detailed reports to guide safe API migration or upgrade.
## Quick Start
```bash
# Compare two versions of a Java library
python scripts/validate.py /path/to/old_version /path/to/new_version
# Specify output file
python scripts/validate.py old_lib/ new_lib/ --output report.jsonjava-regression-test-generator
When your agent uses it
Automatically generate regression tests for Java codebases by analyzing changes between old and new code versions. Use when users need to: (1) Generate tests after refactoring or code changes, (2) Ensure previously tested behavior still works in new versions, (3) Cover modified or newly added code paths, (4) Migrate existing tests to work with updated APIs or signatures, (5) Maintain test coverage during code evolution. Supports JUnit and TestNG frameworks with unit tests, parameterized tests, and exception testing patterns.
What it loads into context
Frontmatter
116 tokensAlways available to the agent
SKILL.md
3,499 tokensWhen the skill is activated
Reference documents
5,903 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- Overview
- How to Use
- Test Generation Workflow
- Example: Parameter Added
- Example: New Method Added
- Example: Return Type Changed
- Output Format
- References
- Tips
Files
SKILL.mdcore16,011 bytesreferences/change_patterns.mddoc11,254 bytesreferences/test_patterns.mddoc13,765 bytes
Read SKILL.md
# Java Regression Test Generator
Automatically generate regression tests for Java code based on version changes.
## Overview
This skill analyzes changes between old and new versions of Java code and generates regression tests that ensure previously tested behavior still works while covering new or modified functionality. It preserves correctness guarantees from existing tests and suggests updates when old tests become invalid.
## How to Use
Provide:
1. **Old version**: The previous version of Java code
2. **New version**: The updated version of Java code
3. **Existing tests**: Test classes or methods for the old versionjava-test-updater
When your agent uses it
Update Java test classes and methods to work with new code versions after refactoring or modifications. Use when code changes break existing tests due to signature changes, refactoring, or behavior modifications. Takes old and new code versions plus old tests as input, and outputs updated tests that compile and pass against the new code. Handles method signature changes, class refactoring, assertion updates, and mock modifications.
What it loads into context
Frontmatter
87 tokensAlways available to the agent
SKILL.md
2,735 tokensWhen the skill is activated
Reference documents
0 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- Overview
- Workflow
- Update Patterns
- Tips
Files
SKILL.mdcore11,862 bytesSKILL.mdcore11,862 bytesSKILL.mdcore11,862 bytes
Read SKILL.md
# Java Test Updater
## Overview
Automatically update Java test code to align with changes in production code, ensuring tests compile and pass after refactoring, signature changes, or behavior modifications.
## Workflow
### 1. Analyze Code Changes
Compare old and new versions of the production code to identify changes:
**Read both versions**:
- Old code version (before changes)legacy-code-summarizer
When your agent uses it
Produces comprehensive summaries and insights about legacy codebases to help understand unfamiliar code. Use when onboarding to a new project, planning refactoring efforts, assessing code for acquisition/migration, or generating documentation for undocumented systems. Analyzes architecture, dependencies, code quality issues, and test coverage. Creates high-level overviews with architecture diagrams, key components, entry points, and actionable insights for understanding and improving legacy code.
What it loads into context
Frontmatter
93 tokensAlways available to the agent
SKILL.md
5,265 tokensWhen the skill is activated
Reference documents
10,187 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- Core Capabilities
- Code Analysis Workflow
- Appendix
- Best Practices
- Resources
- Quick Reference
Files
SKILL.mdcore22,068 bytesSKILL.mdcore22,068 bytesSKILL.mdcore22,068 bytesSKILL.mdcore22,068 bytesSKILL.mdcore22,068 bytesSKILL.mdcore22,068 bytesSKILL.mdcore22,068 bytesSKILL.mdcore22,068 bytesSKILL.mdcore22,068 bytesSKILL.mdcore22,068 bytesSKILL.mdcore22,068 bytesSKILL.mdcore22,068 bytesSKILL.mdcore22,068 bytesSKILL.mdcore22,068 bytesSKILL.mdcore22,068 bytesSKILL.mdcore22,068 bytesSKILL.mdcore22,068 bytesSKILL.mdcore22,068 bytesSKILL.mdcore22,068 bytesSKILL.mdcore22,068 bytesreferences/architecture_patterns.mddoc12,235 bytesreferences/code_quality_checklist.mddoc12,657 bytesreferences/dependency_analysis.mddoc14,733 bytes
Read SKILL.md
# Legacy Code Summarizer
Analyze and summarize legacy codebases to quickly understand their structure, quality, and improvement opportunities.
## Core Capabilities
This skill helps understand legacy code by:
1. **Mapping architecture** - Identify key components, layers, and relationships
2. **Analyzing dependencies** - Understand module coupling and import patterns
3. **Detecting quality issues** - Find code smells, technical debt, and outdated patterns
4. **Assessing test coverage** - Identify testing gaps and untested code
5. **Generating documentation** - Create actionable summaries for teams
lemma-discovery-assistant
When your agent uses it
Analyze failed or stuck proofs and propose auxiliary lemmas to help complete the proof in Isabelle/HOL or Coq. Use when encountering proof failures, stuck proof states, unprovable subgoals, or when needing to strengthen induction hypotheses. Identifies missing lemmas, suggests proof strategies, and generates helper lemmas with appropriate statements and proof sketches. Supports inductive proofs, case analysis, rewriting, and complex proof obligations.
What it loads into context
Frontmatter
95 tokensAlways available to the agent
SKILL.md
2,831 tokensWhen the skill is activated
Reference documents
9,302 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- Overview
- When Proofs Get Stuck
- Lemma Discovery Process
- Lemma Patterns by Proof Type
- Framework-Specific Guidance
- Common Lemma Categories
- Example: Complete Lemma Discovery
- Lemma Discovery Strategies
- Best Practices
- Troubleshooting
- Additional Resources
Files
SKILL.mdcore10,955 bytesreferences/coq_lemmas.mddoc9,950 bytesreferences/isabelle_lemmas.mddoc9,317 bytesreferences/proof_patterns.mddoc10,418 bytes
Read SKILL.md
# Lemma Discovery Assistant
Analyze stuck or failed proofs and propose auxiliary lemmas that can help complete the proof.
## Overview
When proofs fail or get stuck, the issue is often a missing auxiliary lemma. This skill helps identify what lemmas are needed by:
1. Analyzing the current proof state and goal
2. Identifying gaps in reasoning
3. Proposing auxiliary lemmas with precise statements
4. Suggesting proof strategies for the lemmas
5. Explaining how the lemmas help the main proof
library-advisor
When your agent uses it
Recommend relevant Isabelle/HOL or Coq standard library theories, lemmas, and tactics based on proof goals. Use when: (1) Users need library lemmas for their proof, (2) Proof goals match standard library patterns, (3) Users ask what libraries to import, (4) Specific lemmas are needed for list/set/arithmetic operations, (5) Users are stuck and need to know what library support exists, or (6) Guidance on find_theorems/Search commands is needed. Supports both Isabelle/HOL and Coq standard libraries.
What it loads into context
Frontmatter
122 tokensAlways available to the agent
SKILL.md
2,050 tokensWhen the skill is activated
Reference documents
7,516 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- Workflow
- Domain-Specific Recommendations
- Recommendation Patterns
- Search Strategies
- Common Recommendations by Goal Type
- Examples
- Tips
Files
SKILL.mdcore7,272 bytesreferences/coq_library.mddoc7,562 bytesreferences/examples.mddoc8,066 bytesreferences/isabelle_library.mddoc6,168 bytes
Read SKILL.md
# Library Usage Advisor
Recommend relevant libraries, lemmas, and theories from Isabelle/HOL or Coq standard libraries based on proof goals.
## Workflow
### 1. Analyze the Proof Goal
Examine the goal to identify:
- **Domain**: Lists, sets, arithmetic, logic, etc.
- **Operations**: Specific functions or operators involved
- **Pattern**: Commutativity, associativity, distributivity, etc.
- **Complexity**: Simple property vs. complex relationship
When your agent uses it
General-purpose LinkedIn automation – fetch profiles, search people and companies, send messages, manage connections, create posts, and more. Use when the user wants to interact with LinkedIn.
What it loads into context
Frontmatter
43 tokensAlways available to the agent
SKILL.md
4,166 tokensWhen the skill is activated
Reference documents
0 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- Authentication
- Global Flags
- Output Format
- Commands
- Important Behavior
Files
SKILL.mdcore16,499 bytesSKILL.mdcore16,499 bytesSKILL.mdcore16,499 bytesSKILL.mdcore16,499 bytesSKILL.mdcore16,499 bytesSKILL.mdcore16,499 bytesSKILL.mdcore16,499 bytesSKILL.mdcore16,499 bytesSKILL.mdcore16,499 bytesSKILL.mdcore16,499 bytesSKILL.mdcore16,499 bytesSKILL.mdcore16,499 bytesSKILL.mdcore16,499 bytesSKILL.mdcore16,499 bytesSKILL.mdcore16,499 bytesSKILL.mdcore16,499 bytesSKILL.mdcore16,499 bytesSKILL.mdcore16,499 bytesSKILL.mdcore16,499 bytesSKILL.mdcore16,499 bytesSKILL.mdcore16,499 bytesSKILL.mdcore16,499 bytesSKILL.mdcore16,499 bytesSKILL.mdcore16,499 bytesSKILL.mdcore16,499 bytesSKILL.mdcore16,499 bytesSKILL.mdcore16,499 bytesSKILL.mdcore16,499 bytesSKILL.mdcore16,499 bytesSKILL.mdcore16,499 bytesSKILL.mdcore16,499 bytesSKILL.mdcore16,499 bytesSKILL.mdcore16,499 bytesSKILL.mdcore16,499 bytesSKILL.mdcore16,499 bytesSKILL.mdcore16,499 bytesSKILL.mdcore16,499 bytesSKILL.mdcore16,499 bytesSKILL.mdcore16,499 bytesSKILL.mdcore16,499 bytesSKILL.mdcore16,499 bytesSKILL.mdcore16,499 bytesSKILL.mdcore16,499 bytesSKILL.mdcore16,499 bytesSKILL.mdcore16,499 bytes
Read SKILL.md
# LinkedIn Skill
You have access to `linkedin` – a CLI tool for LinkedIn automation. Use it to fetch profiles, search people and companies, send messages, manage connections, create posts, react, comment, and more.
Each command sends a request to Linked API, which runs a real cloud browser to perform the action on LinkedIn. Operations are **not instant** – expect 30 seconds to several minutes depending on complexity.
If `linkedin` is not available, install it:
```bash
npm install -g @linkedapi/linkedin-cli
```
## Authentication
lsp-refactoring
When your agent uses it
Intelligent code refactoring using IDE-level tools (rename, find-references, go-to-definition), AST-aware pattern matching, and TDD verification. Use for safe, large-scale refactoring with precision.
What it loads into context
Frontmatter
49 tokensAlways available to the agent
SKILL.md
1,098 tokensWhen the skill is activated
Reference documents
0 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- When to Use This Skill
- What This Skill Does
- Approach by Language
- Anti-Patterns
- Example
Files
SKILL.mdcore4,293 bytesSKILL.mdcore4,293 bytesSKILL.mdcore4,293 bytesSKILL.mdcore4,293 bytesSKILL.mdcore4,293 bytes
Read SKILL.md
# LSP Refactoring
Refactoring workflow that combines language server capabilities with code search and test-driven verification for safe, precise code transformations.
## When to Use This Skill
- Renaming symbols across an entire workspace
- Extracting functions, classes, or modules
- Moving code between files with automatic reference updates
- Large-scale pattern-based code transformations
- Any refactoring where manual find-replace is error-prone
## What This Skill Does
markdown-document-structurer
When your agent uses it
Reorganizes markdown documents into well-structured, consistent format while preserving content and improving readability. Use when Claude needs to: (1) Fix heading hierarchy issues (skipped levels, multiple h1s), (2) Generate or update table of contents, (3) Standardize formatting (lists, code blocks, emphasis, links), (4) Improve grammar and spelling, (5) Add missing standard sections (installation, usage, etc.), (6) Remove redundant or duplicate content, (7) Restructure technical docs, READMEs, or long-form content for better organization and flow.
What it loads into context
Frontmatter
132 tokensAlways available to the agent
SKILL.md
1,978 tokensWhen the skill is activated
Reference documents
1,939 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- Workflow
- Document Type Guidelines
- Formatting Standards
- Content Preservation Rules
- Handling Redundancy
- Table of Contents Generation
- Grammar and Spelling
- Output Format
- Best Practices
Scripts executed separately
scripts/analyze_structure.py
Files
SKILL.mdcore8,802 bytesSKILL.mdcore8,802 bytesSKILL.mdcore8,802 bytesreferences/document-patterns.mddoc4,697 bytesreferences/markdown-best-practices.mddoc3,220 bytesscripts/analyze_structure.pyruns8,640 bytes
Read SKILL.md
# Markdown Document Structurer
Reorganize and improve markdown documents while preserving content integrity.
## Workflow
### 1. Analyze Current Structure
**Automated analysis:**
```bash
python scripts/analyze_structure.py <markdown_file>
```
**Manual analysis:**metamorphic-property-extractor
When your agent uses it
Automatically identify metamorphic properties (symmetry, linearity, additivity, input invariances) from programs or functions. Use when generating metamorphic tests, discovering program properties, validating transformations, or creating test oracles without explicit specifications. Analyzes control flow, data flow, and sample executions to output structured properties for metamorphic test generation and verification.
What it loads into context
Frontmatter
81 tokensAlways available to the agent
SKILL.md
300 tokensWhen the skill is activated
Reference documents
0 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- Overview
- Core Workflow
- Metamorphic Properties
- Resources
Files
SKILL.mdcore1,323 bytesSKILL.mdcore1,323 bytesSKILL.mdcore1,323 bytes
Read SKILL.md
# Metamorphic Property Extractor
## Overview
Automatically identify metamorphic properties from programs to enable metamorphic testing without explicit test oracles.
## Core Workflow
### 1. Extract Properties
```bash
python scripts/property_extractor.py --program function.py --output properties.json
```
metamorphic-test-generator
When your agent uses it
Generate test cases using metamorphic testing by applying transformations based on metamorphic properties. Use when you need to expand test suites, test programs without oracles, validate mathematical or algorithmic properties, or detect subtle bugs through input-output relationships. The skill takes a program, original test cases, and metamorphic properties as input, generates new test cases by applying transformations, executes tests, verifies outputs satisfy properties, reports violations and anomalies, and outputs an expanded test suite with property coverage summary. Supports multiple programming languages and property types.
What it loads into context
Frontmatter
113 tokensAlways available to the agent
SKILL.md
646 tokensWhen the skill is activated
Reference documents
1,881 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- Overview
- Quick Start
- What Gets Generated
- Common Metamorphic Properties
- Test Generation Report
- Usage
- Tips
Scripts executed separately
assets/example-program.pyscripts/generate.py
Files
README.mddoc3,486 bytesSKILL.mdcore3,192 bytesSKILL.mdcore3,192 bytesSKILL.mdcore3,192 bytesassets/example-program.pyruns759 bytesassets/properties-template.jsonasset241 bytesassets/test-cases-template.jsonasset327 bytesreferences/properties.mddoc4,134 bytesscripts/generate.pyruns21,611 bytes
Read SKILL.md
# Metamorphic Test Generator
## Overview
This skill generates test cases using metamorphic testing, applying transformations based on metamorphic properties to expand test suites and detect bugs through input-output relationships.
## Quick Start
```bash
# Generate metamorphic tests
python scripts/generate.py program.py --tests tests/ --properties properties.json
# Use specific metamorphic properties
python scripts/generate.py program.py --tests tests/ --properties "permutation,addition"mocking-test-generator
When your agent uses it
Generate unit tests with proper mocking for Python (unittest.mock/pytest) or Java (Mockito/JUnit) code. Use when users request test generation, unit tests with mocks, or testing code that has external dependencies like database calls, API requests, file I/O, or network operations. Automatically identifies dependencies to mock and creates executable, maintainable test code.
What it loads into context
Frontmatter
80 tokensAlways available to the agent
SKILL.md
1,386 tokensWhen the skill is activated
Reference documents
2,048 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- Workflow
- Step 1: Analyze the Code
- Step 2: Select Framework
- Step 3: Generate Mocks
- Step 4: Write Tests
- Step 5: Add Documentation
- Output Format
- Example Usage
- Framework-Specific Notes
- Common Patterns
Files
SKILL.mdcore6,296 bytesSKILL.mdcore6,296 bytesreferences/java_patterns.mddoc6,307 bytesreferences/python_patterns.mddoc3,136 bytes
Read SKILL.md
# Mocking Test Generator
Generate unit tests with proper mocking of external dependencies for Python and Java code.
## Workflow
1. **Analyze the code** - Identify external dependencies, side effects, and testable units
2. **Select framework** - Determine Python (unittest.mock/pytest) or Java (Mockito/JUnit)
3. **Generate mocks** - Create mock objects for external dependencies
4. **Write tests** - Generate executable test code with assertions
5. **Add documentation** - Include clear comments explaining mocks and test logic
## Step 1: Analyze the Code
model-guided-code-repair
When your agent uses it
Automatically repair code violations of temporal properties using model-checking counterexamples as guidance. Use when working with formal verification results, temporal logic property violations (LTL, CTL), model checking counterexamples, or when asked to repair property violations, fix counterexamples, repair temporal properties, fix model checking violations, or repair code based on counterexamples. Applicable to concurrent systems, state machines, synchronization issues, safety/liveness properties, and resource management violations.
What it loads into context
Frontmatter
101 tokensAlways available to the agent
SKILL.md
1,343 tokensWhen the skill is activated
Reference documents
1,484 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- Overview
- Repair Workflow
- Output Format
- Common Scenarios
- Tips for Effective Repairs
- Integration with Model Checkers
Files
SKILL.mdcore6,756 bytesSKILL.mdcore6,756 bytesSKILL.mdcore6,756 bytesSKILL.mdcore6,756 bytesSKILL.mdcore6,756 bytesreferences/temporal_logic_patterns.mddoc5,809 bytes
Read SKILL.md
# Model-Guided Code Repair
## Overview
This skill enables automatic repair of code that violates temporal properties by analyzing model-checking counterexamples. It reasons about the root cause of violations at the model level, proposes minimal and semantically justified code modifications, and validates repairs through re-verification or test generation.
## Repair Workflow
Follow this sequential process when repairing temporal property violations:
### 1. Analyze Input
Gather and understand three required inputs:
modular-code-enforcement
When your agent uses it
Enforces strict modular code architecture: SRP, no monolithic index files, no catch-all utils, 200 LOC hard limit. This rule is NON-NEGOTIABLE. Violations BLOCK all further work until resolved.
What it loads into context
Frontmatter
55 tokensAlways available to the agent
SKILL.md
1,297 tokensWhen the skill is activated
Reference documents
0 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- Rule 1: index files are ENTRY POINTS, NOT dumping grounds
- Rule 2: No Catch-All Files — utils/helpers/service are CODE SMELLS
- Rule 3: Single Responsibility Principle — ABSOLUTE
- Rule 4: 200 LOC Hard Limit — CODE SMELL DETECTOR
- How to Apply
Files
SKILL.mdcore5,558 bytesSKILL.mdcore5,558 bytesSKILL.mdcore5,558 bytesSKILL.mdcore5,558 bytes
Read SKILL.md
# Modular Code Architecture — Zero Tolerance Policy
This rule is NON-NEGOTIABLE. Violations BLOCK all further work until resolved.
## Rule 1: index files are ENTRY POINTS, NOT dumping grounds
`index` files (`index.ts`, `__init__.py`, `index.js`, etc.) MUST ONLY contain:
- Re-exports (`export { ... } from "./module"`)
- Factory function calls that compose modules
- Top-level wiring/registration (hook registration, plugin setup)
`index` files MUST NEVER contain:
- Business logic implementation
- Helper/utility functionsmodule-component-generator
When your agent uses it
Generates complete modules and components from interface contracts and specifications. Use when Claude needs to build larger software components, implement interfaces, create service layers, or generate complete modules with multiple related classes. Supports Python (with type hints and protocols) and Java (with interfaces and abstract classes). Trigger when users request "implement this interface", "generate a module for", "create a service layer", "build a component that implements", or provide interface definitions that need implementation.
What it loads into context
Frontmatter
99 tokensAlways available to the agent
SKILL.md
1,779 tokensWhen the skill is activated
Reference documents
7,000 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- Quick Start
- What This Skill Generates
- Generation Scope
- Language-Specific Guidance
- Workflow
- Design Patterns
- Best Practices
- Example Usage Patterns
- Quality Checklist
Files
SKILL.mdcore9,051 bytesreferences/documentation-patterns.mddoc8,205 bytesreferences/java-patterns.mddoc13,754 bytesreferences/python-patterns.mddoc10,307 bytes
Read SKILL.md
# Module/Component Generator
Generate complete, production-ready modules and components from interface contracts and specifications.
## Quick Start
When a user provides an interface contract or requests a module:
1. **Understand the contract**: Analyze the interface, abstract class, or specification
2. **Determine scope**: Clarify if generating single implementation or full module
3. **Select patterns**: Choose appropriate design patterns and structure
4. **Generate code**: Create implementation with proper structure and documentation
5. **Add documentation**: Include comprehensive docstrings and usage examples
module-level-code-translator
When your agent uses it
Translate source code between programming languages at function, class, and module levels while preserving behavior and generating verification tests. Use when translating code from one language to another (e.g., "translate this Python module to JavaScript", "convert this Java class to C#", "port this code to Go and generate tests"), migrating codebases between languages, or creating equivalent implementations across different technology stacks. Handles idiom adaptation, standard library mappings, and test generation.
What it loads into context
Frontmatter
100 tokensAlways available to the agent
SKILL.md
1,506 tokensWhen the skill is activated
Reference documents
2,476 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- Translation Workflow
- Output Format
- Language-Specific Considerations
- Resources
- Best Practices
Scripts executed separately
assets/test_template_go.goassets/test_template_javascript.jsassets/test_template_python.py
Files
SKILL.mdcore7,557 bytesSKILL.mdcore7,557 bytesSKILL.mdcore7,557 bytesSKILL.mdcore7,557 bytesSKILL.mdcore7,557 bytesSKILL.mdcore7,557 bytesassets/test_template_go.goruns1,318 bytesassets/test_template_java.javaasset1,273 bytesassets/test_template_javascript.jsruns927 bytesassets/test_template_python.pyruns1,012 bytesreferences/language_mappings.mddoc2,308 bytesreferences/stdlib_mappings.mddoc2,951 bytesreferences/testing_frameworks.mddoc3,293 bytes
Read SKILL.md
# Module-Level Code Translator
Translate source code between programming languages while preserving behavior, adapting idioms, and generating verification tests.
## Translation Workflow
Follow this sequential process for code translation:
### 1. Analyze Source Code
Before translating, thoroughly understand the source code:
- **Identify scope**: Determine if translating functions, classes, or entire modules
- **Map dependencies**: List all imports, external libraries, and dependenciesmulti-version-behavior-comparator
When your agent uses it
Compare behavior across multiple versions of programs or repositories. Use when you need to analyze how functionality changes between versions, identify regressions, compare outputs and exceptions, or validate upgrades. The skill compares execution behavior, test results, outputs, exceptions, and observable states across versions, generating detailed reports showing behavioral divergences, potential regressions, added/removed functionality, and areas requiring validation. Supports multiple programming languages and can work with test suites or execution traces.
What it loads into context
Frontmatter
102 tokensAlways available to the agent
SKILL.md
446 tokensWhen the skill is activated
Reference documents
0 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- Overview
- Quick Start
- What Gets Compared
- Comparison Report
- Usage
- Tips
Files
SKILL.mdcore2,127 bytesSKILL.mdcore2,127 bytesSKILL.mdcore2,127 bytesSKILL.mdcore2,127 bytesSKILL.mdcore2,127 bytesSKILL.mdcore2,127 bytes
Read SKILL.md
# Multi-Version Behavior Comparator
## Overview
This skill compares behavior across multiple versions of programs, identifying functional changes, regressions, and behavioral divergences to guide safe upgrades and validation.
## Quick Start
```bash
# Compare two versions
python scripts/compare.py v1.0/ v2.0/
# Compare multiple versions with test suite
python scripts/compare.py v1.0/ v2.0/ v3.0/ --tests tests/mutation-test-suite-optimizer
When your agent uses it
Optimize test suites using mutation testing to maximize mutation kill rate with minimal tests. Use when you need to reduce test suite size while maintaining quality, identify redundant tests, improve mutation coverage, or validate test effectiveness. The skill analyzes test coverage, execution intervals, and redundancy using mutation operators, selects or generates a minimal subset of tests that maximizes mutation kill rate, and outputs an optimized test suite with detailed reports showing killed and surviving mutants. Supports multiple programming languages and mutation testing frameworks.
What it loads into context
Frontmatter
105 tokensAlways available to the agent
SKILL.md
620 tokensWhen the skill is activated
Reference documents
0 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- Overview
- Quick Start
- What Gets Optimized
- Mutation Operators
- Optimization Report
- Usage
- Tips
Files
SKILL.mdcore2,843 bytesSKILL.mdcore2,843 bytesSKILL.mdcore2,843 bytesSKILL.mdcore2,843 bytesSKILL.mdcore2,843 bytesSKILL.mdcore2,843 bytes
Read SKILL.md
# Mutation Test Suite Optimizer
## Overview
This skill optimizes test suites using mutation testing, selecting a minimal subset of tests that maximizes mutation kill rate while reducing execution time and redundancy.
## Quick Start
```bash
# Optimize test suite with mutation testing
python scripts/optimize.py /path/to/repo --tests tests/
# Use specific mutation operators
python scripts/optimize.py repo/ --tests tests/ --operators AOR,ROR,CORnl-to-constraints
When your agent uses it
Transforms natural language requirements (user stories, verbal descriptions, business rules) into formal specifications and constraints. Use when converting informal requirements into structured, testable specifications with explicit constraints. Outputs in multiple formats including BDD-style Given-When-Then, JSON Schema, and structured plain text requirements documents.
What it loads into context
Frontmatter
69 tokensAlways available to the agent
SKILL.md
2,049 tokensWhen the skill is activated
Reference documents
1,428 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- Core Capabilities
- Workflow
- Handling Ambiguity
- Best Practices
- Signal Words Reference
- Output Selection
- Resources
Files
SKILL.mdcore9,253 bytesassets/specification_schema.jsonasset4,142 bytesreferences/constraint_patterns.mddoc5,833 bytes
Read SKILL.md
# Natural Language to Constraints/Specifications
You are an expert requirements engineer who transforms informal natural language into precise, structured specifications and constraints.
## Core Capabilities
This skill enables you to:
1. **Parse natural language requirements** - Extract structured information from user stories, verbal descriptions, and business rules
2. **Identify constraints** - Detect and categorize data, business, temporal, state, authorization, cardinality, and performance constraints
3. **Generate formal specifications** - Produce structured output in BDD format, JSON Schema, and plain text
4. **Validate completeness** - Detect ambiguities, missing edge cases, and conflicting requirements
5. **Create test scenarios** - Derive testable scenarios from requirements
playwright-automation
When your agent uses it
Browser automation via Playwright for web testing, screenshots, form filling, scraping, and verification. Use when tasks require navigating websites, interacting with web pages, or testing web applications.
What it loads into context
Frontmatter
44 tokensAlways available to the agent
SKILL.md
816 tokensWhen the skill is activated
Reference documents
0 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- When to Use This Skill
- Approach Selection
- Core Workflow
- Key Patterns
- Workflow Loop
- Tips
Files
SKILL.mdcore3,723 bytesSKILL.mdcore3,723 bytes
Read SKILL.md
# Playwright Automation
Browser automation skill using Playwright for web testing, verification, data extraction, and interactive workflows. Maintains persistent page state across script executions.
## When to Use This Skill
- Testing web applications (navigation, forms, assertions)
- Taking screenshots for visual verification
- Scraping web content or extracting data
- Automating browser workflows (login, form submission)
- Verifying UI changes after code modifications
## Approach Selection
program-correctness-prover
When your agent uses it
Generate Isabelle or Coq proofs establishing partial or total correctness of imperative programs from code and formal specifications. Use when users need to: (1) Prove program correctness using Hoare logic, (2) Generate verification conditions from pre/postconditions, (3) Construct loop invariants and termination arguments, (4) Verify imperative programs with assignments, conditionals, and loops. Supports both partial correctness (if terminates, postcondition holds) and total correctness (terminates and postcondition holds) for both Isabelle/HOL and Coq.
What it loads into context
Frontmatter
120 tokensAlways available to the agent
SKILL.md
3,038 tokensWhen the skill is activated
Reference documents
6,286 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- Overview
- How to Use
- Verification Workflow
- Example: Sum of Array
- Example: Maximum of Two Numbers
- Common Patterns
- Correctness Types
- References
- Tips
Files
SKILL.mdcore10,026 bytesreferences/hoare_logic.mddoc7,257 bytesreferences/verification_patterns.mddoc10,051 bytes
Read SKILL.md
# Program Correctness Prover
Generate formal proofs establishing correctness of imperative programs.
## Overview
This skill takes imperative program code with formal specifications (preconditions and postconditions) and generates complete correctness proofs in Isabelle or Coq using Hoare logic. It handles loop invariant generation, verification condition generation, and proof construction for both partial and total correctness.
## How to Use
Provide:
1. **Program code**: Imperative program (assignments, conditionals, loops)
2. **Specification**: Precondition and postcondition
3. **Target system**: Isabelle or Coqprogram-to-model-extractor
When your agent uses it
Extract abstract mathematical models from functional code (Haskell, OCaml, F#) for formal reasoning in Isabelle/HOL. Use when users need to: (1) Convert functional programs to Isabelle definitions, (2) Extract high-level algorithm essence from implementation code, (3) Generate formal specifications and properties from code, (4) Create verification-ready models that capture mathematical properties while abstracting away implementation details. Focuses on structural recursion, algebraic data types, higher-order functions, and invariant extraction.
What it loads into context
Frontmatter
112 tokensAlways available to the agent
SKILL.md
1,503 tokensWhen the skill is activated
Reference documents
2,946 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- Overview
- Extraction Workflow
- Common Extraction Patterns
- Abstraction Guidelines
- Example: Complete Extraction
- References
- Tips
Files
SKILL.mdcore6,230 bytesSKILL.mdcore6,230 bytesreferences/extraction_patterns.mddoc5,832 bytesreferences/isabelle_syntax.mddoc4,619 bytes
Read SKILL.md
# Program-to-Model Extractor
Extract high-level mathematical models from functional code for formal reasoning in Isabelle/HOL.
## Overview
This skill transforms functional programs (Haskell, OCaml, F#) into abstract mathematical models suitable for formal verification in Isabelle/HOL. The extraction focuses on the algorithm's mathematical essence—capturing core properties, invariants, and structural patterns while abstracting away language-specific implementation details.
## Extraction Workflow
### 1. Analyze the Source Code
Identify key elements:
- **Data structures**: Algebraic types, lists, trees, custom typesprogram-to-tlaplus-spec-generator
When your agent uses it
Automatically generate TLA+ specifications from program code, repositories, or system implementations. Use when asked to generate TLA+ spec, create TLA+ specification from code, convert program to TLA+, formalize system in TLA+, extract TLA+ model from code, or when working with formal specification of concurrent systems, distributed systems, protocols, algorithms, or state machines that need to be verified.
What it loads into context
Frontmatter
93 tokensAlways available to the agent
SKILL.md
1,870 tokensWhen the skill is activated
Reference documents
4,285 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- Overview
- Generation Workflow
- Output Format
- Common Patterns
- Abstraction Guidelines
- Tips for Effective Specs
- Language-Specific Considerations
Files
SKILL.mdcore8,571 bytesSKILL.mdcore8,571 bytesSKILL.mdcore8,571 bytesassets/template.tlaasset3,087 bytesreferences/language_patterns.mddoc7,993 bytesreferences/tlaplus_syntax.mddoc6,075 bytes
Read SKILL.md
# Program to TLA+ Spec Generator
## Overview
This skill enables automatic generation of TLA+ specifications from source code. It analyzes program structure, identifies state variables and transitions, and produces well-formed TLA+ modules with proper syntax and semantics.
## Generation Workflow
Follow this sequential process to generate TLA+ specifications from code:
### 1. Analyze Input Program
Read and understand the source code:
proof-carrying-code-generator
When your agent uses it
Generate executable code together with formal proofs certifying safety and correctness properties in Isabelle/HOL or Coq. Use when building verified software, safety-critical systems, or when formal guarantees are required. Produces code with accompanying proofs for memory safety, bounds checking, functional correctness, invariant preservation, and termination. Supports extraction to OCaml/Haskell/SML and integration with existing codebases.
What it loads into context
Frontmatter
87 tokensAlways available to the agent
SKILL.md
2,989 tokensWhen the skill is activated
Reference documents
10,896 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- Overview
- PCC Generation Workflow
- Core Approaches
- Safety Properties
- Correctness Properties
- Framework-Specific Guidance
- Common Safety Properties
- Complete Example: Verified Binary Search
- Best Practices
- Verification Checklist
- Integration Patterns
- Additional Resources
Files
SKILL.mdcore11,746 bytesreferences/coq_pcc.mddoc13,495 bytesreferences/isabelle_pcc.mddoc12,794 bytesreferences/safety_properties.mddoc11,887 bytes
Read SKILL.md
# Proof-Carrying Code Generator
Generate executable code bundled with formal proofs that certify key safety and correctness properties.
## Overview
Proof-carrying code (PCC) is executable code accompanied by formal proofs that certify specific properties. This skill helps generate:
1. **Verified implementations** with correctness proofs
2. **Safety certificates** for memory safety, bounds checking, null safety
3. **Functional specifications** with pre/postconditions
4. **Invariant proofs** for data structure integrity
5. **Extracted code** from verified specifications
proof-failure-explainer
When your agent uses it
Analyze and explain why Isabelle or Coq proofs fail, identifying the root cause such as type mismatches, missing assumptions, incorrect goals, unification failures, or inapplicable tactics. Use when the user encounters proof failures, error messages in formal verification, stuck proof states, or asks why their Isabelle/Coq proof doesn't work.
What it loads into context
Frontmatter
78 tokensAlways available to the agent
SKILL.md
2,613 tokensWhen the skill is activated
Reference documents
3,297 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- Overview
- Analysis Workflow
- Common Failure Patterns
- Examples
- Diagnostic Questions
- Best Practices
- Debugging Tools
- Resources
Files
SKILL.mdcore9,929 bytesreferences/failure_patterns.mddoc11,169 bytes
Read SKILL.md
# Proof Failure Explainer
## Overview
Diagnose and explain proof failures in Isabelle and Coq by analyzing proof states, error messages, and goal structures. This skill helps identify root causes and suggests fixes for common proof problems.
## Analysis Workflow
### Step 1: Gather Context
Collect information about the failure:
1. **Proof state:**
- Current goal(s)proof-refactoring-assistant
When your agent uses it
Restructure and improve Isabelle or Coq proofs to enhance readability, modularity, and maintainability without changing semantics. Use when proofs are long and monolithic, have repeated patterns, use unclear naming, lack documentation, or when the user asks to refactor, clean up, improve, or reorganize their formal proofs.
What it loads into context
Frontmatter
74 tokensAlways available to the agent
SKILL.md
3,147 tokensWhen the skill is activated
Reference documents
4,470 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- Overview
- Refactoring Workflow
- Common Refactoring Patterns
- Examples
- Refactoring Guidelines
- Best Practices
- Anti-Patterns to Avoid
- Refactoring Checklist
- Resources
Files
SKILL.mdcore12,085 bytesreferences/refactoring_patterns.mddoc14,564 bytes
Read SKILL.md
# Proof Refactoring Assistant
## Overview
Improve proof quality by restructuring Isabelle and Coq proofs for better readability, modularity, and maintainability while preserving semantics. This skill applies proven refactoring patterns to make proofs easier to understand and maintain.
## Refactoring Workflow
### Step 1: Analyze Current Proof
Identify code smells and improvement opportunities:
1. **Structure issues:**
- Long, monolithic proofs (>20 lines)proof-skeleton-generator
When your agent uses it
Generate structured proof skeletons with tactics, strategies, and intermediate lemmas for theorems in Isabelle/HOL or Coq. Use when users need to: (1) Create proof outlines for theorem statements, (2) Generate proof structure with tactic placeholders, (3) Identify key lemmas needed for a proof, (4) Plan proof strategies (induction, case analysis, forward/backward reasoning), (5) Scaffold proofs with intermediate steps and subgoals, or (6) Convert theorem statements into detailed proof templates. Supports both Isabelle/HOL and Coq equally.
What it loads into context
Frontmatter
127 tokensAlways available to the agent
SKILL.md
1,791 tokensWhen the skill is activated
Reference documents
5,889 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- Workflow
- Key Principles
- Proof Strategy Selection Guide
- Common Patterns
- Tips
Files
SKILL.mdcore7,265 bytesreferences/coq_tactics.mddoc5,367 bytesreferences/examples.mddoc10,108 bytesreferences/isabelle_tactics.mddoc3,949 bytes
Read SKILL.md
# Proof Skeleton Generator
Generate structured proof skeletons with tactics, proof strategies, and key lemmas for theorems in Isabelle/HOL or Coq.
## Workflow
### 1. Analyze the Theorem Statement
Examine the theorem to understand:
- **Quantifiers**: Universal (∀/forall) or existential (∃/exists)
- **Logical structure**: Implications, conjunctions, disjunctions
- **Data types involved**: Lists, natural numbers, custom types
- **Complexity**: Simple equality vs. complex property
proof-trace-summarizer
When your agent uses it
Summarize long Isabelle or Coq proof scripts into high-level logical steps and reasoning flow. Use when users need to: (1) Understand the structure of a complex proof, (2) Document proof strategies for others, (3) Extract the key reasoning steps from verbose proof scripts, (4) Create readable proof outlines from detailed tactical proofs. Produces hierarchical outlines with moderate detail showing proof structure, main cases, key lemmas, and reasoning flow for both Isabelle/Isar and Coq proofs.
What it loads into context
Frontmatter
114 tokensAlways available to the agent
SKILL.md
2,658 tokensWhen the skill is activated
Reference documents
4,620 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- Overview
- How to Use
- Summarization Workflow
- Example: Isabelle Induction Proof
- Example: Coq Case Analysis
- Example: Complex Nested Proof
- Common Proof Patterns
- Handling Different Proof Lengths
- Quality Guidelines
- References
- Tips
Files
SKILL.mdcore9,769 bytesreferences/summarization_patterns.mddoc7,419 bytesreferences/tactic_interpretation.mddoc9,289 bytes
Read SKILL.md
# Proof Trace Summarizer
Summarize long proof scripts into high-level logical steps and reasoning flow.
## Overview
This skill transforms verbose Isabelle or Coq proof scripts into clear, hierarchical summaries that capture the essential reasoning structure. It identifies proof patterns (induction, case analysis, equational reasoning), extracts key steps, and presents them in a readable outline format.
## How to Use
Provide a proof script with:
1. **System**: Isabelle or Coq
2. **Proof script**: The complete proof to summarize
3. **Context** (optional): Theorem statement, definitions, or backgroundpseudocode-extractor
When your agent uses it
Extract programming-language-agnostic pseudocode from source code in any language, preserving control flow and logical structure while filtering out implementation details. Use when the user asks to convert code to pseudocode, abstract code logic, understand code structure without syntax, create language-independent documentation, or analyze algorithmic flow without language-specific details.
What it loads into context
Frontmatter
73 tokensAlways available to the agent
SKILL.md
1,659 tokensWhen the skill is activated
Reference documents
0 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- Overview
- Extraction Process
- Examples
- Best Practices
- Common Patterns
Files
SKILL.mdcore7,510 bytesSKILL.mdcore7,510 bytesSKILL.mdcore7,510 bytesSKILL.mdcore7,510 bytes
Read SKILL.md
# Pseudocode Extractor
## Overview
Transform source code from any programming language into clear, language-agnostic pseudocode that captures the essential logic and control flow while removing syntax-specific details.
## Extraction Process
### 1. Analyze Input Code
First, identify the programming language and understand the code structure:
- Recognize functions, classes, methods, and modules
- Identify control flow structures (loops, conditionals, error handling)
- Note data structures and their relationshipspseudocode-to-java-code
When your agent uses it
Converts pseudocode descriptions and algorithm specifications into complete, executable Java code. Use this skill when you need to implement algorithms from pseudocode, translate algorithm descriptions to Java, generate Java code from specifications, convert textbook algorithms to working code, or create executable implementations from high-level descriptions. Preserves logic and control flow while handling Java idioms, data structures, and includes test cases for verification.
What it loads into context
Frontmatter
87 tokensAlways available to the agent
SKILL.md
1,752 tokensWhen the skill is activated
Reference documents
1,667 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- Overview
- Workflow
- Common Conversions
- Use Cases
- Best Practices
- Advanced Features
- Limitations
- Resources
Files
SKILL.mdcore7,592 bytesSKILL.mdcore7,592 bytesassets/java_template.javaasset361 bytesreferences/mapping_patterns.mddoc5,969 bytes
Read SKILL.md
# Pseudocode to Java Code
## Overview
This skill converts pseudocode descriptions and algorithm specifications into complete, executable Java programs. It preserves the original logic and control flow, applies appropriate Java idioms and data structures, and generates test cases to verify correctness.
## Workflow
### 1. Provide Pseudocode Input
Give the pseudocode or algorithm specification. Formats accepted:
- Structured pseudocode with keywords (IF, FOR, WHILE, etc.)
- Algorithm descriptions in plain text
- Textbook-style algorithm specificationspseudocode-to-python-code
When your agent uses it
Convert pseudocode, algorithm descriptions, or specifications into complete, executable Python code. Handles natural language descriptions, structured pseudocode, and formal algorithm specifications. Generates production-ready code with type hints, docstrings, error handling, and test cases. Use when users need to (1) convert pseudocode to Python, (2) implement algorithms from descriptions, (3) translate algorithm specifications to code, (4) generate Python implementations from textbook pseudocode, or (5) create executable code from high-level algorithm designs.
What it loads into context
Frontmatter
113 tokensAlways available to the agent
SKILL.md
2,473 tokensWhen the skill is activated
Reference documents
4,094 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- Workflow
- Common Patterns
- Important Notes
- Resources
Scripts executed separately
assets/template.py
Files
SKILL.mdcore10,354 bytesSKILL.mdcore10,354 bytesSKILL.mdcore10,354 bytesSKILL.mdcore10,354 bytesSKILL.mdcore10,354 bytesSKILL.mdcore10,354 bytesSKILL.mdcore10,354 bytesSKILL.mdcore10,354 bytesSKILL.mdcore10,354 bytesassets/template.pyruns1,343 bytesreferences/pseudocode-patterns.mddoc6,979 bytesreferences/python-idioms.mddoc8,013 bytes
Read SKILL.md
# Pseudocode to Python Code
Convert pseudocode and algorithm descriptions into complete, executable Python code with proper structure, documentation, and tests.
## Workflow
### 1. Understand the Input
Identify the input format and extract the algorithm logic:
**Natural language description:**
- Example: "Sort an array using bubble sort"
- Extract: Algorithm name, input/output, basic steps
python-api-consistency-validator
When your agent uses it
Validate API consistency between two versions of Python libraries. Use when you need to compare API behavior, signatures, and exceptions between library versions to identify breaking changes, incompatible modifications, and behavior differences. The skill performs static analysis of Python code, compares function signatures, class definitions, parameter types, return types, and generates a detailed JSON report with breaking changes, warnings, and migration guidance. Supports Python libraries and packages.
What it loads into context
Frontmatter
92 tokensAlways available to the agent
SKILL.md
511 tokensWhen the skill is activated
Reference documents
0 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- Overview
- Quick Start
- What Gets Validated
- Validation Report
- Usage
- Tips
Scripts executed separately
scripts/validate.py
Files
SKILL.mdcore2,435 bytesSKILL.mdcore2,435 bytesSKILL.mdcore2,435 bytesscripts/validate.pyruns10,322 bytes
Read SKILL.md
# Python API Consistency Validator
## Overview
This skill validates API consistency between two versions of Python libraries by comparing signatures, behavior, and exceptions. It identifies breaking changes, incompatible modifications, and provides detailed reports to guide safe API migration or upgrade.
## Quick Start
```bash
# Compare two versions of a Python library
python scripts/validate.py /path/to/old_version /path/to/new_version
# Specify output file
python scripts/validate.py old_lib/ new_lib/ --output report.jsonpython-regression-test-generator
When your agent uses it
Automatically generates regression tests for Python codebases by analyzing changes between old and new code versions and their existing tests. Migrates tests to work with new code, generates tests for new functionality, and creates mocks for external dependencies. Supports unittest and pytest frameworks. Use when refactoring code, adding features, or ensuring backward compatibility.
What it loads into context
Frontmatter
74 tokensAlways available to the agent
SKILL.md
3,664 tokensWhen the skill is activated
Reference documents
5,165 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- Overview
- Test Generation Workflow
- Complete Example
- Framework-Specific Examples
- Test Generation Guidelines
- Constraints
- Output Format
- Resources
Files
SKILL.mdcore16,419 bytesSKILL.mdcore16,419 bytesSKILL.mdcore16,419 bytesSKILL.mdcore16,419 bytesSKILL.mdcore16,419 bytesSKILL.mdcore16,419 bytesSKILL.mdcore16,419 bytesSKILL.mdcore16,419 bytesSKILL.mdcore16,419 bytesSKILL.mdcore16,419 bytesSKILL.mdcore16,419 bytesSKILL.mdcore16,419 bytesSKILL.mdcore16,419 bytesSKILL.mdcore16,419 bytesSKILL.mdcore16,419 bytesSKILL.mdcore16,419 bytesSKILL.mdcore16,419 bytesreferences/api_reference.mddoc983 bytesreferences/test_generation_patterns.mddoc20,460 bytes
Read SKILL.md
# Python Regression Test Generator
## Overview
This skill automatically generates regression tests for Python code by analyzing differences between old and new versions, migrating existing tests, and creating new tests for modified or added functionality. It ensures previously tested behavior still works while covering new code paths.
## Test Generation Workflow
Follow these steps to generate regression tests:
### 1. Analyze Code Changes
**Compare old and new versions to identify:**
python-repo-quickstart
When your agent uses it
Quickly analyzes Python repositories to understand their purpose, structure, and setup requirements. Use when Claude needs to onboard to a new Python codebase, understand project structure, identify entry points, determine dependencies, or generate setup instructions. Trigger when users ask to "analyze this Python repo", "understand this codebase", "how do I run this project", "what does this repo do", or provide a Python repository path for quick start guidance.
What it loads into context
Frontmatter
100 tokensAlways available to the agent
SKILL.md
1,854 tokensWhen the skill is activated
Reference documents
1,055 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- Quick Start
- What This Skill Analyzes
- Analysis Workflow
- Output Format
- Example Usage Patterns
- Best Practices
- Automated Analysis
Scripts executed separately
scripts/analyze_repo.py
Files
SKILL.mdcore7,836 bytesSKILL.mdcore7,836 bytesSKILL.mdcore7,836 bytesSKILL.mdcore7,836 bytesSKILL.mdcore7,836 bytesSKILL.mdcore7,836 bytesSKILL.mdcore7,836 bytesSKILL.mdcore7,836 bytesSKILL.mdcore7,836 bytesSKILL.mdcore7,836 bytesSKILL.mdcore7,836 bytesSKILL.mdcore7,836 bytesSKILL.mdcore7,836 bytesSKILL.mdcore7,836 bytesreferences/python-patterns.mddoc3,688 bytesscripts/analyze_repo.pyruns5,250 bytes
Read SKILL.md
# Python Repository Quick Start
Rapidly analyze and understand Python repositories to get started quickly.
## Quick Start
When a user provides a Python repository:
1. **Scan repository structure**: Identify key files and directories
2. **Determine project type**: Web app, CLI tool, library, data science, etc.
3. **Find entry points**: Locate main execution files
4. **Identify dependencies**: Find requirements and dependency management
5. **Extract setup instructions**: Determine how to install and run
6. **Summarize functionality**: Understand what the project doespython-test-updater
When your agent uses it
Updates Python test code to work with new versions of the code being tested. Use when Claude needs to: (1) Update tests after code changes, (2) Fix broken tests due to signature changes, (3) Update assertions to match new behavior, (4) Add test cases for new functionality, (5) Analyze code differences and their test impact, (6) Run tests and fix failures based on error messages. Takes old code, new code, and old tests as input, outputs updated tests that pass.
What it loads into context
Frontmatter
114 tokensAlways available to the agent
SKILL.md
2,671 tokensWhen the skill is activated
Reference documents
2,305 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- Workflow
- Common Update Patterns
- Best Practices
- Troubleshooting
- Example Workflow
- Output Format
Scripts executed separately
scripts/analyze_code_diff.py
Files
SKILL.mdcore10,799 bytesSKILL.mdcore10,799 bytesSKILL.mdcore10,799 bytesSKILL.mdcore10,799 bytesSKILL.mdcore10,799 bytesSKILL.mdcore10,799 bytesSKILL.mdcore10,799 bytesSKILL.mdcore10,799 bytesSKILL.mdcore10,799 bytesSKILL.mdcore10,799 bytesSKILL.mdcore10,799 bytesSKILL.mdcore10,799 bytesSKILL.mdcore10,799 bytesSKILL.mdcore10,799 bytesSKILL.mdcore10,799 bytesSKILL.mdcore10,799 bytesSKILL.mdcore10,799 bytesSKILL.mdcore10,799 bytesSKILL.mdcore10,799 bytesSKILL.mdcore10,799 bytesSKILL.mdcore10,799 bytesSKILL.mdcore10,799 bytesSKILL.mdcore10,799 bytesSKILL.mdcore10,799 bytesreferences/test-update-patterns.mddoc9,083 bytesscripts/analyze_code_diff.pyruns8,320 bytes
Read SKILL.md
# Python Test Updater
Update Python tests to work correctly with new code versions.
## Workflow
### 1. Understand the Inputs
**Gather required inputs:**
- Old version of Python code (file or content)
- New version of Python code (file or content)
- Old test module or test functions (file or content)
**Verify inputs:**python-to-dafny-translator
When your agent uses it
Translate Python programs into equivalent Dafny code, preserving program semantics and ensuring the generated code is well-typed, executable, and verifiable. Use when the user asks to convert Python code to Dafny, port Python programs to Dafny, add formal verification to Python code, or create Dafny versions of Python algorithms with specifications.
What it loads into context
Frontmatter
78 tokensAlways available to the agent
SKILL.md
3,400 tokensWhen the skill is activated
Reference documents
3,392 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- Overview
- Translation Workflow
- Common Translation Patterns
- Examples
- Best Practices
- Key Differences: Python vs Dafny
- Limitations and Considerations
- Resources
Files
SKILL.mdcore12,586 bytesSKILL.mdcore12,586 bytesSKILL.mdcore12,586 bytesSKILL.mdcore12,586 bytesSKILL.mdcore12,586 bytesSKILL.mdcore12,586 bytesSKILL.mdcore12,586 bytesSKILL.mdcore12,586 bytesSKILL.mdcore12,586 bytesSKILL.mdcore12,586 bytesSKILL.mdcore12,586 bytesSKILL.mdcore12,586 bytesSKILL.mdcore12,586 bytesSKILL.mdcore12,586 bytesSKILL.mdcore12,586 bytesreferences/translation_patterns.mddoc10,908 bytes
Read SKILL.md
# Python to Dafny Translator
## Overview
Transform Python programs into equivalent Dafny code that preserves the original semantics while adding formal specifications and leveraging Dafny's verification capabilities.
## Translation Workflow
### Step 1: Analyze Python Code
Understand the Python program structure and semantics:
1. **Identify program components:**
- Functions and their signaturespython-to-lean4-translator
When your agent uses it
Translate Python programs to equivalent Lean4 code while preserving semantics and ensuring type safety. Use when users ask to convert, translate, or port Python code to Lean4, or when they need to verify Python algorithms using Lean4's theorem proving capabilities. Handles functions, classes, data structures, control flow, and ensures the generated Lean4 code is well-typed, executable, and can successfully run.
What it loads into context
Frontmatter
91 tokensAlways available to the agent
SKILL.md
2,225 tokensWhen the skill is activated
Reference documents
6,082 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- Overview
- Translation Workflow
- Core Translation Principles
- Type Mapping Reference
- Translation Patterns
- Handling Common Challenges
- Translation Process
- Required Imports
- Example Translation
- Best Practices
- Verification Checklist
- Additional Resources
Files
SKILL.mdcore8,739 bytesSKILL.mdcore8,739 bytesSKILL.mdcore8,739 bytesSKILL.mdcore8,739 bytesSKILL.mdcore8,739 bytesSKILL.mdcore8,739 bytesSKILL.mdcore8,739 bytesSKILL.mdcore8,739 bytesSKILL.mdcore8,739 bytesSKILL.mdcore8,739 bytesSKILL.mdcore8,739 bytesreferences/advanced_features.mddoc7,073 bytesreferences/common_patterns.mddoc7,377 bytesreferences/type_mappings.mddoc5,236 bytes
Read SKILL.md
# Python to Lean4 Translator
Translate Python programs into equivalent, executable Lean4 code while preserving program semantics and ensuring type safety.
## Overview
This skill provides systematic guidance for translating Python code to Lean4, handling type inference, function translations, data structures, control flow, and ensuring well-typed, executable output.
## Translation Workflow
```
Python Input → Analyze Structure → Map Types → Translate Constructs → Verify → Output Lean4
├─ Identify types and signatures
├─ Map Python constructs to Lean4 equivalentsreadme-generator
When your agent uses it
Generate comprehensive, user-friendly README.md files for code repositories. Use when creating documentation for new projects, updating existing READMEs, or improving project onboarding. Produces READMEs with project introduction, prerequisites, environment setup, executable usage instructions, and repository structure overview. Supports application projects, libraries, and research codebases.
What it loads into context
Frontmatter
73 tokensAlways available to the agent
SKILL.md
2,441 tokensWhen the skill is activated
Reference documents
0 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- Overview
- Workflow
- README Quality Guidelines
- Tips
Files
SKILL.mdcore10,356 bytesSKILL.mdcore10,356 bytesSKILL.mdcore10,356 bytesSKILL.mdcore10,356 bytesSKILL.mdcore10,356 bytesSKILL.mdcore10,356 bytesSKILL.mdcore10,356 bytesSKILL.mdcore10,356 bytesSKILL.mdcore10,356 bytesSKILL.mdcore10,356 bytesSKILL.mdcore10,356 bytesSKILL.mdcore10,356 bytesSKILL.mdcore10,356 bytesSKILL.mdcore10,356 bytesSKILL.mdcore10,356 bytesSKILL.mdcore10,356 bytesSKILL.mdcore10,356 bytesSKILL.mdcore10,356 bytesSKILL.mdcore10,356 bytes
Read SKILL.md
# README Generator
## Overview
Analyze a code repository and generate a comprehensive, reproducible README.md that enables users to quickly understand, set up, and use the project with clear instructions and executable examples.
## Workflow
### 1. Analyze Repository Structure
Explore the repository to understand its organization and purpose:
**Key files to examine**:
- `package.json`, `pyproject.toml`, `Cargo.toml`, `go.mod` - Project metadatareference-searcher
When your agent uses it
Systematic external reference searching across documentation, open-source repositories, and web resources. Use when working with unfamiliar libraries, APIs, or when needing production-quality implementation examples.
What it loads into context
Frontmatter
41 tokensAlways available to the agent
SKILL.md
872 tokensWhen the skill is activated
Reference documents
0 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- When to Use This Skill
- What This Skill Does
- Anti-Patterns
- Example
Files
SKILL.mdcore4,127 bytesSKILL.mdcore4,127 bytesSKILL.mdcore4,127 bytesSKILL.mdcore4,127 bytesSKILL.mdcore4,127 bytesSKILL.mdcore4,127 bytesSKILL.mdcore4,127 bytes
Read SKILL.md
# Reference Searcher
Structured methodology for searching external references — official docs, open-source implementations, and web resources — to inform development decisions.
## When to Use This Skill
- Working with unfamiliar libraries or frameworks
- Needing production-quality implementation examples
- Debugging unexpected behavior from external dependencies
- Finding best practices for specific patterns (auth, caching, etc.)
- Evaluating library choices with real-world usage data
## What This Skill Does
refinement-step-generator
When your agent uses it
Generate systematic refinement steps from high-level specifications to concrete implementations in Isabelle/HOL or Coq, preserving correctness obligations at each step. Use when working with formal verification, program refinement, proof development, or when translating abstract specifications into executable code while maintaining formal guarantees. Supports data refinement (abstract types → concrete structures), algorithmic refinement (specifications → algorithms), and stepwise refinement with proof obligations.
What it loads into context
Frontmatter
87 tokensAlways available to the agent
SKILL.md
2,246 tokensWhen the skill is activated
Reference documents
9,057 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- Overview
- Refinement Workflow
- Core Refinement Types
- Refinement Process
- Framework-Specific Guidance
- Common Refinement Patterns
- Example: Complete Refinement
- Best Practices
- Verification Checklist
- Additional Resources
Files
SKILL.mdcore9,252 bytesreferences/coq_refinement.mddoc11,062 bytesreferences/isabelle_refinement.mddoc9,707 bytesreferences/refinement_patterns.mddoc10,144 bytes
Read SKILL.md
# Refinement Step Generator
Generate systematic refinement steps that transform high-level specifications into concrete, executable implementations while preserving correctness through formal proofs.
## Overview
Refinement is the process of transforming abstract specifications into concrete implementations through a series of correctness-preserving steps. Each refinement step:
1. Makes the specification more concrete (closer to executable code)
2. Preserves correctness through formal proof obligations
3. Maintains a clear abstraction relation between levels
4. Can be verified independently
This skill provides guidance for generating refinement steps in Isabelle/HOL and Coq.regression-consistency-checker
When your agent uses it
Checks whether a new version of a repository preserves the behavior observed by tests on the old version. Use this skill when comparing two versions of code to detect regressions, verify refactoring safety, validate bug fixes don't break existing functionality, or ensure backward compatibility. Detects differences in function outputs, exceptions, observable states, and performance between versions. Generates reports highlighting potential regressions (critical, high, medium, low severity), improvements, and areas requiring verification. Triggers when users ask to check for regressions between versions, compare test behavior across versions, verify behavior preservation, or validate that changes don't break existing tests.
What it loads into context
Frontmatter
133 tokensAlways available to the agent
SKILL.md
1,908 tokensWhen the skill is activated
Reference documents
2,670 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- Workflow
- Quick Reference
- Helper Script
- Best Practices
Scripts executed separately
scripts/compare_results.py
Files
SKILL.mdcore8,385 bytesSKILL.mdcore8,385 bytesSKILL.mdcore8,385 bytesSKILL.mdcore8,385 bytesSKILL.mdcore8,385 bytesSKILL.mdcore8,385 bytesSKILL.mdcore8,385 bytesSKILL.mdcore8,385 bytesSKILL.mdcore8,385 bytesSKILL.mdcore8,385 bytesSKILL.mdcore8,385 bytesSKILL.mdcore8,385 bytesSKILL.mdcore8,385 bytesSKILL.mdcore8,385 bytesreferences/detection_strategies.mddoc11,616 bytesscripts/compare_results.pyruns12,086 bytes
Read SKILL.md
# Regression Consistency Checker
Check whether a new version of a repository preserves the behavior observed by tests on the old version.
## Workflow
### 1. Prepare Versions
**Set up old version**:
```bash
# Tag or note the old version
git tag old-version
# Or checkout specific commitregression-root-cause-analyzer
When your agent uses it
Locate root causes of failing regression tests by analyzing code changes, error messages, and test dependencies. Use when regression tests start failing after code changes, investigating test failures in CI/CD, debugging flaky tests, or understanding why previously passing tests now fail. Analyzes git diffs, stack traces, test output, and dependency changes to produce structured markdown reports ranking likely causes. Triggers when users ask to find why tests are failing, debug regression failures, investigate test breakage, or analyze failing test suites.
What it loads into context
Frontmatter
112 tokensAlways available to the agent
SKILL.md
3,260 tokensWhen the skill is activated
Reference documents
1,659 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- Overview
- Workflow
- Root Cause Analysis: [Test Name]
- Alternative Hypotheses
- Reproduction Steps
- Verification Steps
- Investigation Strategies
- Common Investigation Commands
- Example Workflows
- Tips for Effective Analysis
- Reference
Files
SKILL.mdcore13,632 bytesSKILL.mdcore13,632 bytesSKILL.mdcore13,632 bytesSKILL.mdcore13,632 bytesSKILL.mdcore13,632 bytesSKILL.mdcore13,632 bytesSKILL.mdcore13,632 bytesSKILL.mdcore13,632 bytesSKILL.mdcore13,632 bytesSKILL.mdcore13,632 bytesSKILL.mdcore13,632 bytesSKILL.mdcore13,632 bytesSKILL.mdcore13,632 bytesSKILL.mdcore13,632 bytesSKILL.mdcore13,632 bytesSKILL.mdcore13,632 bytesreferences/failure-patterns.mddoc7,014 bytes
Read SKILL.md
# Regression Root Cause Analyzer
## Overview
Systematically investigate failing regression tests to identify root causes by analyzing code changes, error messages, test dependencies, and common failure patterns.
## Workflow
### 1. Gather Initial Information
Collect essential details about the test failure:
**Test failure details:**
- Which test(s) are failing?release-change-analyzer
When your agent uses it
Compares HEAD with the latest published version to analyze real changes, group by type, and recommend version bumps. Use before publishing a release to understand what actually changed.
What it loads into context
Frontmatter
42 tokensAlways available to the agent
SKILL.md
659 tokensWhen the skill is activated
Reference documents
0 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- When to Use This Skill
- What This Skill Does
- Version Bump Decision
- Anti-Patterns
- Example
Files
SKILL.mdcore2,743 bytesSKILL.mdcore2,743 bytesSKILL.mdcore2,743 bytes
Read SKILL.md
# Release Change Analyzer
Analyzes unpublished changes by comparing HEAD with the latest published version. Reads actual diffs instead of just copying commit messages.
## When to Use This Skill
- Before publishing a new release
- Deciding between major/minor/patch version bump
- Writing accurate release notes based on real code changes
- Reviewing what changed since last deployment
## What This Skill Does
### Step 1: Identify Published Versionrelease-notes-writer
When your agent uses it
Automatically generate user-facing release notes from git commits, pull requests, changelogs, and code changes. Use when preparing software releases, creating version announcements, documenting what changed between versions, or communicating updates to users. Analyzes commit messages, PR descriptions, and code diffs to produce categorized markdown release notes organized by New Features, Improvements, Bug Fixes, and Breaking Changes. Focuses on user-visible changes while filtering out internal/technical details. Triggers when users ask to generate release notes, create changelog, write version announcement, or summarize changes for a release.
What it loads into context
Frontmatter
126 tokensAlways available to the agent
SKILL.md
2,272 tokensWhen the skill is activated
Reference documents
0 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- Overview
- Workflow
- Template Structure
- Tips for Effective Release Notes
Files
SKILL.mdcore9,280 bytesSKILL.mdcore9,280 bytesSKILL.mdcore9,280 bytesSKILL.mdcore9,280 bytesSKILL.mdcore9,280 bytesSKILL.mdcore9,280 bytesSKILL.mdcore9,280 bytesSKILL.mdcore9,280 bytes
Read SKILL.md
# Release Notes Writer
## Overview
Generate polished, user-facing release notes from git history, pull requests, and code changes, automatically categorizing and summarizing changes in a clear, accessible format.
## Workflow
### 1. Gather Release Information
Collect the scope and sources for the release notes:
**Define the release scope:**
- What version is being released? (e.g., v2.1.0)replay-oriented-instrumentation
When your agent uses it
Instruments programs to record execution information for deterministic replay debugging. Use when debugging hard-to-reproduce bugs (race conditions, timing issues, intermittent failures, heisenbugs), reproducing production failures, or analyzing complex execution sequences. Records non-deterministic events (I/O, threading, randomness, time) to enable exact replay of program executions. Supports Python, JavaScript, Java, and C/C++ with both custom instrumentation and existing replay tools.
What it loads into context
Frontmatter
99 tokensAlways available to the agent
SKILL.md
2,174 tokensWhen the skill is activated
Reference documents
3,795 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- Core Concept
- Workflow
- Quick Start by Language
- Common Scenarios
- Recording Strategies
- Replay Verification
- References
- Tips
Files
SKILL.mdcore9,799 bytesSKILL.mdcore9,799 bytesSKILL.mdcore9,799 bytesSKILL.mdcore9,799 bytesSKILL.mdcore9,799 bytesSKILL.mdcore9,799 bytesSKILL.mdcore9,799 bytesSKILL.mdcore9,799 bytesreferences/non-determinism.mddoc3,511 bytesreferences/python-replay.mddoc5,933 bytesreferences/replay-tools.mddoc6,524 bytes
Read SKILL.md
# Replay-Oriented Instrumentation
Instrument programs to capture execution information that enables deterministic replay, making it possible to reproduce and debug failures that are difficult to reproduce normally.
## Core Concept
Deterministic replay works by:
1. **Recording**: Capture all non-deterministic inputs during execution
2. **Replaying**: Re-execute the program using recorded inputs to reproduce exact behavior
3. **Debugging**: Use replay to analyze failures with time-travel debugging
## Workflow
### 1. Identify Non-Determinism Sourcesreproduction-trace-instrumenter
When your agent uses it
Instruments programs to capture execution traces specifically for reproducing reported bugs, enabling consistent replay and diagnosis of failures. Use this skill when you need to reproduce a bug, capture execution traces for debugging, instrument code to record program behavior, generate replay scripts for bug reproduction, diagnose hard-to-reproduce failures, or perform deterministic replay of program execution. Triggers when users ask to instrument code for tracing, capture execution traces, reproduce bugs, generate replay scripts, or enable deterministic debugging.
What it loads into context
Frontmatter
105 tokensAlways available to the agent
SKILL.md
2,078 tokensWhen the skill is activated
Reference documents
1,647 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- Overview
- Workflow
- Configuration
- Instrumentation Levels
- Common Use Cases
- Trace Format
- Best Practices
- Limitations
- Advanced Topics
- Resources
Scripts executed separately
scripts/python_instrumenter.pyscripts/replay_generator.py
Files
SKILL.mdcore9,447 bytesSKILL.mdcore9,447 bytesSKILL.mdcore9,447 bytesSKILL.mdcore9,447 bytesSKILL.mdcore9,447 bytesSKILL.mdcore9,447 bytesSKILL.mdcore9,447 bytesSKILL.mdcore9,447 bytesSKILL.mdcore9,447 bytesSKILL.mdcore9,447 bytesSKILL.mdcore9,447 bytesSKILL.mdcore9,447 bytesSKILL.mdcore9,447 bytesassets/trace_config_template.jsonasset987 bytesreferences/instrumentation_techniques.mddoc6,974 bytesscripts/python_instrumenter.pyruns11,799 bytesscripts/replay_generator.pyruns6,929 bytes
Read SKILL.md
# Reproduction Trace Instrumenter
## Overview
This skill instruments source code to capture detailed execution traces for bug reproduction. It records function calls, variable values, control flow, and program state, then generates replay scripts to deterministically reproduce the bug for diagnosis.
## Workflow
### 1. Identify the Bug Context
Before instrumentation, understand:
- What is the bug or failure being investigated?
- Which code paths are likely involved?
- What inputs trigger the bug?req-to-test
When your agent uses it
Generates comprehensive test scenarios from requirements including BDD/Gherkin scenarios, unit tests, integration tests, and end-to-end test cases. Use when converting requirements, user stories, or specifications into testable scenarios with full coverage including happy paths, error cases, edge cases, and boundary conditions. Outputs structured test suites ready for implementation.
What it loads into context
Frontmatter
74 tokensAlways available to the agent
SKILL.md
2,673 tokensWhen the skill is activated
Reference documents
3,911 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- Core Capabilities
- Workflow
- Best Practices
- Common Patterns
- Output Formats
- Resources
Files
SKILL.mdcore11,595 bytesassets/test_suite_template.jsonasset4,095 bytesreferences/coverage_checklist.mddoc6,771 bytesreferences/test_patterns.mddoc9,996 bytes
Read SKILL.md
# Requirement to Test Scenario Generation
You are an expert test engineer who transforms requirements into comprehensive, executable test scenarios.
## Core Capabilities
This skill enables you to:
1. **Analyze requirements** - Extract testable behaviors and conditions from requirements
2. **Generate BDD scenarios** - Create Given-When-Then scenarios in Gherkin format
3. **Design unit tests** - Generate function-level test cases with assertions
4. **Create integration tests** - Design tests for system interactions and APIs
5. **Build E2E tests** - Develop complete user journey test scenarios
6. **Ensure coverage** - Generate happy path, error cases, edge cases, and boundariesrequirement-comparison-reporter
When your agent uses it
Compares old and new requirement documents, analyzes code repository impact, and generates detailed modification plans. Use when Claude needs to: (1) Compare requirement versions and identify changes, (2) Map requirement changes to code components, (3) Identify components to modify, delete, or add, (4) Analyze dependencies and integration points, (5) Assess test impact, (6) Generate comprehensive modification plans in Markdown format. Supports text/Markdown requirements and analyzes feature-level, functional, and API changes.
What it loads into context
Frontmatter
112 tokensAlways available to the agent
SKILL.md
2,572 tokensWhen the skill is activated
Reference documents
4,374 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- Workflow
- Output Format
- Best Practices
- Common Scenarios
- Troubleshooting
Scripts executed separately
scripts/analyze_code_impact.py
Files
SKILL.mdcore12,239 bytesSKILL.mdcore12,239 bytesSKILL.mdcore12,239 bytesreferences/analysis-patterns.mddoc8,486 bytesreferences/report-template.mddoc10,266 bytesscripts/analyze_code_impact.pyruns9,333 bytes
Read SKILL.md
# Requirement Comparison Reporter
Generate detailed modification plans by comparing requirement documents and analyzing code impact.
## Workflow
### 1. Understand the Inputs
**Gather required inputs:**
- Old requirement document (path or content)
- New requirement document (path or content)
- Repository path
**Verify inputs:**requirement-coverage-checker
When your agent uses it
Verify that design documents, code implementations, and tests fully cover all specified requirements. Use this skill when validating requirement traceability, conducting design reviews, assessing implementation completeness, checking test coverage against requirements, performing compliance audits, or identifying missing functionality. Produces coverage reports showing which requirements are satisfied, partially satisfied, or missing.
What it loads into context
Frontmatter
74 tokensAlways available to the agent
SKILL.md
637 tokensWhen the skill is activated
Reference documents
0 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- Core Capabilities
- Coverage Checking Workflow
- Best Practices
Files
SKILL.mdcore3,225 bytesSKILL.mdcore3,225 bytes
Read SKILL.md
# Requirement Coverage Checker
Systematically verify that design and implementation cover all specified requirements. Identifies gaps, ensures traceability, and validates that every requirement has corresponding design elements, code, and tests.
## Core Capabilities
### 1. Requirement Extraction
Parse and identify requirements from documents:
- **Functional requirements** - Feature specifications
- **Non-functional requirements** - Performance, security, usability
- **Business rules** - Constraints and policies
- **User stories** - As-a/I-want/So-that format
- **Use cases** - Actor-goal scenariosrequirement-enhancer
When your agent uses it
Iteratively enhance user requirements into clear, complete, actionable specifications through analysis and clarification. Use when: (1) Users provide initial requirements that need refinement, (2) Requirements are vague, incomplete, or ambiguous, (3) Creating formal specifications from informal descriptions, (4) Identifying missing constraints, edge cases, or acceptance criteria, (5) Clarifying assumptions and implicit dependencies, or (6) Preparing requirements for design, implementation, or verification. Operates interactively: analyze → ask clarifying questions → refine based on responses.
What it loads into context
Frontmatter
118 tokensAlways available to the agent
SKILL.md
1,937 tokensWhen the skill is activated
Reference documents
4,963 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- Core Principles
- Enhancement Workflow
- Analysis Framework
- Common Ambiguity Patterns
- Requirement Categories
- Labeling Conventions
- Output Format
- Interactive Loop
- Quality Checks
- Examples
- Tips
Files
SKILL.mdcore8,824 bytesreferences/analysis_framework.mddoc5,929 bytesreferences/examples.mddoc15,419 bytes
Read SKILL.md
# Requirement Enhancer
Transform initial requirements into clear, complete, actionable specifications through iterative analysis and refinement.
## Core Principles
### Preserve Intent
- Maintain the user's original goals and vision
- Do not change fundamental requirements without confirmation
- Clarify rather than assume
### Iterative Refinement
- Analyze → Ask → Refine → Repeat
- Ask targeted questions to fill gapsrequirement-summarizer
When your agent uses it
Extract and summarize core features, constraints, and priorities from requirement documents. Use when analyzing PRDs, RFCs, business requirements, user stories, epics, or any requirement documentation to identify must-have features, technical constraints, priority levels (P0/P1/P2/MoSCoW), and key decision points. Triggers when users ask to summarize, analyze, extract, or understand requirements from documents.
What it loads into context
Frontmatter
92 tokensAlways available to the agent
SKILL.md
1,517 tokensWhen the skill is activated
Reference documents
0 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- Overview
- Workflow
- Best Practices
- Example Usage
- Tips for Effective Summarization
Files
SKILL.mdcore7,018 bytesSKILL.mdcore7,018 bytesSKILL.mdcore7,018 bytesSKILL.mdcore7,018 bytes
Read SKILL.md
# Requirement Summarizer
## Overview
Extract and organize the essential information from requirement documents into a structured markdown summary that highlights core features, constraints, and priorities.
## Workflow
Follow these steps to summarize requirement documents:
### 1. Read and Understand the Document
First, read the entire requirement document to understand its structure and content:
requirement-summary
When your agent uses it
Generate concise, structured summaries of requirements for quick team understanding. Use when analyzing requirements from text documents (MD, TXT, DOCX) or technical specifications to create bullet-point summaries that highlight core functionality and dependencies/constraints. Ideal for sprint planning, stakeholder updates, team onboarding, or any situation requiring rapid comprehension of requirement documents.
What it loads into context
Frontmatter
72 tokensAlways available to the agent
SKILL.md
791 tokensWhen the skill is activated
Reference documents
0 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- Overview
- Workflow
- Example
- Tips
Files
SKILL.mdcore4,087 bytes
Read SKILL.md
# Requirement Summary
## Overview
Generate structured, bullet-point summaries (5-7 items) from requirement documents that enable teams to quickly grasp core functionality and critical constraints without reading full specifications.
## Workflow
### 1. Analyze the Requirement Document
Read the provided requirement document thoroughly to identify:
- Core functionality and features being requested
- Technical dependencies and system constraints
- Integration points with existing systemsrequirement-to-tlaplus-property-generator
When your agent uses it
Automatically derives TLA+ properties (invariants, safety, liveness) from natural-language requirements or structured requirement documents. Resolves ambiguities, asks clarifying questions for underspecified requirements, and outputs TLA+-compatible property definitions with semantic explanations. Use when translating system requirements, specifications, or behavioral constraints into formal TLA+ temporal logic properties for verification with TLC model checker.
What it loads into context
Frontmatter
88 tokensAlways available to the agent
SKILL.md
1,763 tokensWhen the skill is activated
Reference documents
7,168 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- Overview
- Workflow
- Common Requirement Patterns
- Handling Complex Requirements
- Best Practices
- Common Pitfalls
- Output Format
- References
Files
SKILL.mdcore7,619 bytesreferences/clarification_patterns.mddoc10,441 bytesreferences/requirement_patterns.mddoc8,838 bytesreferences/tlaplus_syntax.mddoc7,428 bytes
Read SKILL.md
# Requirement to TLA+ Property Generator
## Overview
This skill transforms natural-language requirements into formal TLA+ properties, enabling rigorous verification of system specifications. It handles invariants, safety properties, and liveness properties, resolving ambiguities and seeking clarification when needed.
## Workflow
### Step 1: Analyze the Requirement
Parse and understand the input requirement:
1. **Identify requirement type**:
- Invariant: "The system always maintains property P"rollback-strategy-advisor
When your agent uses it
Suggests rollback strategies for failed deployments across different platforms and failure types. Use when deployments fail and need to be reverted, including application code rollbacks, database migration reversions, infrastructure changes, and configuration updates. Supports Docker/Docker Compose environments with step-by-step procedural guidance for safe and effective rollback execution.
What it loads into context
Frontmatter
71 tokensAlways available to the agent
SKILL.md
3,733 tokensWhen the skill is activated
Reference documents
6,756 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- Core Capabilities
- Rollback Strategy Workflow
- Quick Reference
- Resources
- Best Practices
Files
SKILL.mdcore15,943 bytesSKILL.mdcore15,943 bytesSKILL.mdcore15,943 bytesSKILL.mdcore15,943 bytesSKILL.mdcore15,943 bytesSKILL.mdcore15,943 bytesSKILL.mdcore15,943 bytesSKILL.mdcore15,943 bytesSKILL.mdcore15,943 bytesSKILL.mdcore15,943 bytesSKILL.mdcore15,943 bytesSKILL.mdcore15,943 bytesSKILL.mdcore15,943 bytesSKILL.mdcore15,943 bytesSKILL.mdcore15,943 bytesSKILL.mdcore15,943 bytesSKILL.mdcore15,943 bytesSKILL.mdcore15,943 bytesSKILL.mdcore15,943 bytesreferences/database_rollback_patterns.mddoc13,247 bytesreferences/platform_guides.mddoc12,205 bytes
Read SKILL.md
# Rollback Strategy Advisor
Provide safe and effective rollback strategies for failed deployments.
## Core Capabilities
This skill helps recover from failed deployments by:
1. **Assessing failure impact** - Identifying what failed and what needs rollback
2. **Recommending rollback strategy** - Choosing the appropriate approach based on failure type
3. **Providing step-by-step guidance** - Clear procedural instructions for execution
4. **Validating rollback success** - Ensuring system returns to stable state
5. **Preventing data loss** - Protecting critical data during rollback operations
rtl-equivalence-checker
When your agent uses it
Hardware verification tool for checking functional equivalence between two RTL designs (Verilog). Use when users need to: (1) Verify if two RTL versions are functionally equivalent, (2) Compare original vs. refactored RTL code, (3) Validate design changes or optimizations, (4) Identify semantic vs. cosmetic differences, (5) Generate counterexamples for non-equivalent designs. Analyzes interface alignment, state variables, logic differences, and produces detailed equivalence verdicts with plain language explanations. Particularly effective for design verification, code reviews, and regression testing of RTL modifications.
What it loads into context
Frontmatter
131 tokensAlways available to the agent
SKILL.md
2,068 tokensWhen the skill is activated
Reference documents
3,427 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- Overview
- Workflow
- Analysis Process
- Output Format
- Common Use Cases
- Difference Types
- Interpreting Results
- Advanced Options
- Integration with Formal Tools
- Limitations
- Tips
- Common Issues
- References
- Scripts
Scripts executed separately
scripts/check_equivalence.pyscripts/counterexample_generator.pyscripts/equivalence_analyzer.pyscripts/rtl_parser.py
Files
SKILL.mdcore9,976 bytesSKILL.mdcore9,976 bytesSKILL.mdcore9,976 bytesSKILL.mdcore9,976 bytesSKILL.mdcore9,976 bytesSKILL.mdcore9,976 bytesSKILL.mdcore9,976 bytesSKILL.mdcore9,976 bytesreferences/equivalence_patterns.mddoc7,017 bytesreferences/formal_tools.mddoc5,481 bytesscripts/check_equivalence.pyruns7,651 bytesscripts/counterexample_generator.pyruns8,605 bytesscripts/equivalence_analyzer.pyruns12,012 bytesscripts/rtl_parser.pyruns6,401 bytes
Read SKILL.md
# RTL Equivalence Checker
Verify functional equivalence between two RTL designs with detailed analysis and counterexample generation.
## Overview
This skill compares two Verilog RTL designs to determine if they are functionally equivalent. It aligns interfaces and state variables, distinguishes semantic differences from cosmetic refactoring, and generates minimal counterexample traces when designs differ.
## Workflow
### 1. Basic Equivalence Check
Compare two RTL designs:
rtl-property-inference
When your agent uses it
Automatically infer formal correctness properties from Verilog/SystemVerilog RTL code and generate SystemVerilog Assertions (SVA). Identifies control-flow invariants (mutual exclusion, valid-ready handshakes, pipeline ordering, safety properties), liveness expectations, and temporal properties. Use when working with RTL designs that need formal property generation, when adding assertions to existing RTL, or when users ask to infer properties, generate assertions, or create formal specifications from hardware designs.
What it loads into context
Frontmatter
101 tokensAlways available to the agent
SKILL.md
1,924 tokensWhen the skill is activated
Reference documents
3,366 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- Overview
- Workflow
- Output Format
Files
SKILL.mdcore8,782 bytesreferences/common_patterns.mddoc6,184 bytesreferences/sva_syntax.mddoc5,950 bytes
Read SKILL.md
# RTL Property Inference
## Overview
This skill analyzes Verilog/SystemVerilog RTL code and automatically infers implicit correctness properties, generating formal SystemVerilog Assertions (SVA). The skill identifies common hardware patterns and generates appropriate safety, liveness, and fairness properties with clear explanations.
## Workflow
### Step 1: Parse and Understand RTL Structure
Analyze the input RTL code to extract key components:
1. **Identify signals and their roles**:
- Clock and reset signalsrtl-specification-consistency-checker
When your agent uses it
Check behavioral consistency between high-level hardware specifications and RTL implementations. Use when asked to check RTL consistency, verify RTL against spec, check hardware specification compliance, validate RTL implementation, find spec violations in RTL, check behavioral consistency, or when working with hardware designs that need verification against protocol specifications, timing requirements, or functional specifications in Verilog, VHDL, or SystemVerilog.
What it loads into context
Frontmatter
88 tokensAlways available to the agent
SKILL.md
1,980 tokensWhen the skill is activated
Reference documents
5,414 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- Overview
- Consistency Checking Workflow
- Report Structure
- Common Verification Patterns
- HDL-Specific Considerations
- Tips for Effective Checking
- Reference Materials
Files
SKILL.mdcore9,086 bytesreferences/common_violations.mddoc10,855 bytesreferences/hdl_patterns.mddoc9,851 bytes
Read SKILL.md
# RTL-Specification Consistency Checker
## Overview
This skill enables systematic checking of behavioral consistency between high-level hardware specifications and RTL implementations. It extracts requirements from specifications, maps them to RTL logic, and classifies each requirement as satisfied, violated, underspecified, or uncheckable.
## Consistency Checking Workflow
Follow this sequential process to check RTL-specification consistency:
### 1. Parse and Understand Inputs
Read and analyze both the specification and RTL code:
runtime-error-explainer
When your agent uses it
Explains runtime errors and compilation failures with actionable debugging guidance. Use when Python or Java code throws runtime exceptions (NullPointerException, TypeError, AttributeError, etc.), compilation errors (syntax errors, type mismatches, import failures), or dependency issues. Analyzes error messages, stack traces, and code context to identify root causes and provide concrete fixes with examples. Distinct from test-related errors - focuses on errors during normal code execution and build processes.
What it loads into context
Frontmatter
102 tokensAlways available to the agent
SKILL.md
4,476 tokensWhen the skill is activated
Reference documents
9,239 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- Core Capabilities
- Error Analysis Workflow
- Verification
- Prevention
- Verification
- Prevention
- Verification
- Prevention
- Verification
- Prevention
- Verification
- Prevention
- Verification
- Prevention
- Verification
- Prevention
- Quick Reference: Error Categories
- Resources
- Best Practices
Files
SKILL.mdcore19,011 bytesSKILL.mdcore19,011 bytesSKILL.mdcore19,011 bytesSKILL.mdcore19,011 bytesSKILL.mdcore19,011 bytesSKILL.mdcore19,011 bytesSKILL.mdcore19,011 bytesSKILL.mdcore19,011 bytesSKILL.mdcore19,011 bytesSKILL.mdcore19,011 bytesSKILL.mdcore19,011 bytesSKILL.mdcore19,011 bytesSKILL.mdcore19,011 bytesSKILL.mdcore19,011 bytesSKILL.mdcore19,011 bytesSKILL.mdcore19,011 bytesSKILL.mdcore19,011 bytesSKILL.mdcore19,011 bytesSKILL.mdcore19,011 bytesSKILL.mdcore19,011 bytesSKILL.mdcore19,011 bytesSKILL.mdcore19,011 bytesSKILL.mdcore19,011 bytesSKILL.mdcore19,011 bytesSKILL.mdcore19,011 bytesSKILL.mdcore19,011 bytesSKILL.mdcore19,011 bytesSKILL.mdcore19,011 bytesSKILL.mdcore19,011 bytesreferences/debugging_guide.mddoc14,846 bytesreferences/error_catalog.mddoc20,435 bytes
Read SKILL.md
# Runtime Error Explainer
Analyze runtime and compilation errors with clear explanations and actionable fixes.
## Core Capabilities
This skill helps debug runtime and compilation errors by:
1. **Parsing error output** - Extract key information from error messages and stack traces
2. **Identifying root causes** - Determine why errors occur during execution or compilation
3. **Explaining clearly** - Translate technical errors into understandable language
4. **Providing fixes** - Suggest concrete code changes with before/after examples
5. **Preventing recurrence** - Recommend best practices to avoid similar errors
scenario-generator
When your agent uses it
Generate comprehensive test scenarios, user stories, and acceptance criteria from requirements and specifications. Use this skill when planning testing efforts, writing user stories, creating test cases, documenting acceptance criteria, exploring edge cases, designing test coverage, or translating requirements into actionable scenarios. Supports BDD (Given-When-Then), Gherkin syntax, user story format, and test case documentation.
What it loads into context
Frontmatter
82 tokensAlways available to the agent
SKILL.md
6,028 tokensWhen the skill is activated
Reference documents
0 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- Core Capabilities
- Scenario Generation Workflow
- Scenario Generation Patterns
- Scenario Templates
- Best Practices
- Common Scenario Types
- Gherkin Best Practices
Files
SKILL.mdcore25,480 bytes
Read SKILL.md
# Scenario Generator
Systematically generate test scenarios, user stories, and acceptance criteria from requirements. Ensures comprehensive coverage of functional paths, edge cases, and error conditions.
## Core Capabilities
### 1. User Story Generation
Create well-formed user stories:
- **As-a/I-want/So-that format** - Standard user story structure
- **Acceptance criteria** - Clear success conditions
- **Edge cases** - Boundary conditions and exceptions
- **Non-functional requirements** - Performance, security, usability
- **Story prioritization** - Business value assessmentsecurity-patch-advisor
When your agent uses it
Proposes secure remediation strategies for detected security vulnerabilities including buffer overflows, injection risks, insecure deserialization, improper authentication, and unsafe cryptographic usage. Provides recommended security checks, safer API alternatives, design-level changes, code examples, trade-off analysis, and prioritized remediation plans. Does NOT automatically modify code unless explicitly requested.
What it loads into context
Frontmatter
74 tokensAlways available to the agent
SKILL.md
3,017 tokensWhen the skill is activated
Reference documents
7,834 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- Overview
- When to Use This Skill
- Core Workflow
- Vulnerability Categories
- Output Format
- Important Guidelines
- Example Interaction
- Alternative Approaches
- Design-Level Improvements
- Verification & Testing
- Priority Recommendation
- Additional Resources
Files
SKILL.mdcore14,246 bytesSKILL.mdcore14,246 bytesSKILL.mdcore14,246 bytesSKILL.mdcore14,246 bytesSKILL.mdcore14,246 bytesreferences/examples.mddoc21,859 bytesreferences/remediation_strategies.mddoc11,744 bytes
Read SKILL.md
# Security Patch Advisor
## Overview
This skill analyzes security vulnerabilities and provides comprehensive remediation strategies without automatically modifying code. It offers multiple remediation approaches with detailed trade-off analysis, code examples, and implementation guidance for vulnerabilities categorized by CWE (Common Weakness Enumeration) and severity.
## When to Use This Skill
Use this skill when you need:
- Remediation strategies for detected security vulnerabilities
- Safer API alternatives for insecure code patterns
- Design-level security improvements
- Multiple remediation approaches with trade-offs
- Code examples showing before/after fixessecurity-sensitive-path-instrumenter
When your agent uses it
Instruments authentication, authorization, and input-handling code paths to monitor security-relevant events and states at runtime. Use this skill when developers need to add security monitoring and logging to their code, including tracking authentication attempts (login/logout), authorization decisions (access control checks), input validation failures, session management events, and other security-critical operations. Supports Python, JavaScript/TypeScript, and Java with structured logging patterns. Triggers when users ask to add security instrumentation, monitor security events, log authentication/authorization, track security-sensitive operations, or add security observability to their codebase.
What it loads into context
Frontmatter
128 tokensAlways available to the agent
SKILL.md
884 tokensWhen the skill is activated
Reference documents
4,179 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- Workflow
- Quick Reference
- Helper Script
- Important Reminders
Scripts executed separately
scripts/generate_instrumentation.py
Files
SKILL.mdcore4,407 bytesSKILL.mdcore4,407 bytesSKILL.mdcore4,407 bytesSKILL.mdcore4,407 bytesreferences/best_practices.mddoc2,644 bytesreferences/language_patterns.mddoc15,467 bytesreferences/security_events.mddoc2,413 bytesscripts/generate_instrumentation.pyruns6,261 bytes
Read SKILL.md
# Security-Sensitive Path Instrumenter
Add structured logging instrumentation to security-critical code paths for runtime monitoring of authentication, authorization, input validation, session management, and other security-relevant events.
## Workflow
1. **Identify security-sensitive code paths** - Locate authentication, authorization, input validation, or session management code that needs instrumentation
2. **Determine event types** - Classify the security events to monitor (see [security_events.md](references/security_events.md) for taxonomy)
3. **Review best practices** - Check [best_practices.md](references/best_practices.md) for what to log and what to avoid (never log passwords, secrets, or sensitive PII)
4. **Select language patterns** - Use [language_patterns.md](references/language_patterns.md) for language-specific instrumentation code (Python, JavaScript/TypeScript, Java)
semantic-bug-detector
When your agent uses it
Detect semantic-level bugs by analyzing whether code behavior matches its intended purpose inferred from function/variable names, comments, docstrings, and documentation. Use when users need to: (1) Find logic errors where implementation contradicts stated intent, (2) Identify off-by-one errors and boundary mismatches, (3) Detect inverted logic or wrong operators, (4) Catch missing edge case handling, (5) Verify code matches its documentation. Highlights mismatches between intent and implementation across multiple programming languages.
What it loads into context
Frontmatter
111 tokensAlways available to the agent
SKILL.md
2,673 tokensWhen the skill is activated
Reference documents
2,453 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- Overview
- How to Use
- Detection Workflow
- Example: Off-by-One Error
- Example: Inverted Logic
- Example: Boundary Mismatch
- Example: Wrong Operator
- Example: Missing Edge Case
- Common Bug Categories
- Detection Strategies
- Multi-Language Support
- Report Format
- References
- Tips
Files
SKILL.mdcore11,167 bytesSKILL.mdcore11,167 bytesSKILL.mdcore11,167 bytesSKILL.mdcore11,167 bytesSKILL.mdcore11,167 bytesSKILL.mdcore11,167 bytesSKILL.mdcore11,167 bytesreferences/bug_patterns.mddoc9,159 bytes
Read SKILL.md
# Semantic Bug Detector
Detect bugs where code behavior doesn't match its intended purpose.
## Overview
This skill analyzes code to find semantic bugs—errors where the implementation contradicts the intent expressed through names, comments, and documentation. Unlike syntax errors or type errors, semantic bugs are logically valid code that does the wrong thing.
## How to Use
Provide code with any of:
1. **Function/variable names** that express intent
2. **Comments** describing what code should do
3. **Docstrings** specifying behaviorsemantic-equivalence-verifier
When your agent uses it
Analyzes and verifies semantic equivalence between two functions, classes, or modules by examining control flow, data flow, and observable behavior. Use when comparing code implementations (refactored vs original, different implementations of same functionality, migration verification), determining if two code artifacts produce identical behavior, identifying behavioral differences between code versions, or validating that code changes preserve semantics. Supports formal reasoning and symbolic execution approaches.
What it loads into context
Frontmatter
91 tokensAlways available to the agent
SKILL.md
1,272 tokensWhen the skill is activated
Reference documents
6,757 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- Overview
- Verification Workflow
- Analysis Techniques by Language
- Common Equivalence Patterns
- Practical Examples
- References
Files
SKILL.mdcore6,116 bytesSKILL.mdcore6,116 bytesassets/equivalence_report_template.mddoc6,262 bytesreferences/formal_verification.mddoc3,936 bytesreferences/language_patterns.mddoc9,372 bytesreferences/symbolic_execution.mddoc7,513 bytes
Read SKILL.md
# Semantic Equivalence Verifier
## Overview
This skill enables rigorous analysis of semantic equivalence between two code artifacts (functions, classes, or modules). It systematically compares control flow, data flow, and observable behavior to determine if implementations are functionally identical, and provides actionable guidance for achieving equivalence when differences exist.
## Verification Workflow
### Step 1: Input Specification
Clearly identify the two code artifacts to compare:
```
Artifact A: [function/class/module name and location]semantic-szz-analyzer
When your agent uses it
Identify bug-introducing commits using semantic analysis that extends traditional SZZ algorithm. Distinguishes semantic changes from refactorings or code movements using control-flow and data-flow similarity analysis. Use when analyzing bug-fix commits to trace back to bug-introducing changes, investigating software evolution, conducting empirical studies on defect prediction, or reducing false positives in bug localization. Supports git repositories and provides explanations for why commits are identified as bug-introducing.
What it loads into context
Frontmatter
100 tokensAlways available to the agent
SKILL.md
1,273 tokensWhen the skill is activated
Reference documents
5,818 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- Overview
- Core Capabilities
- Workflow
- Usage Examples
- Advanced Features
- References
- Output Format
Scripts executed separately
scripts/batch_analyze.pyscripts/semantic_analyzer.pyscripts/semantic_szz.py
Files
README.mddoc3,463 bytesSKILL.mdcore5,625 bytesSKILL.mdcore5,625 bytesSKILL.mdcore5,625 bytesSKILL.mdcore5,625 bytesSKILL.mdcore5,625 bytesSKILL.mdcore5,625 bytesSKILL.mdcore5,625 bytesSKILL.mdcore5,625 bytesbug_fixes.txt.exampleasset202 bytesreferences/language_support.mddoc8,665 bytesreferences/semantic_analysis.mddoc7,638 bytesreferences/szz_algorithm.mddoc4,432 bytesscripts/batch_analyze.pyruns5,610 bytesscripts/semantic_analyzer.pyruns9,642 bytesscripts/semantic_szz.pyruns6,626 bytes
Read SKILL.md
# Semantic SZZ Analyzer
## Overview
Semantic SZZ Analyzer extends the traditional SZZ (Sliwerski-Zimmermann-Zeller) algorithm by incorporating semantic analysis to identify bug-introducing commits more accurately. It distinguishes actual semantic changes from refactorings or code movements by analyzing control-flow and data-flow similarity across versions.
## Core Capabilities
### 1. Semantic Change Detection
Analyze commits to distinguish between:
- **Semantic changes**: Modifications that alter program behavior
- **Refactorings**: Code restructuring without behavior changes
- **Code movements**: Relocations of code blocks without semantic impactsession-handoff
When your agent uses it
Creates structured context summaries for continuing work across AI sessions. Use when ending a session to enable seamless continuation in a new session without losing context.
What it loads into context
Frontmatter
36 tokensAlways available to the agent
SKILL.md
717 tokensWhen the skill is activated
Reference documents
0 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- When to Use This Skill
- What This Skill Does
- Tips
- Example
Files
SKILL.mdcore2,974 bytes
Read SKILL.md
# Session Handoff
Generates a detailed handoff document capturing the current state of work, enabling seamless continuation in a fresh AI session.
## When to Use This Skill
- Ending a long coding session that will continue later
- Switching between AI tools or models mid-task
- Context window approaching limits, need a fresh session
- Handing off work to a teammate (human or AI)
## What This Skill Does
Generate a structured handoff document with:skill-creator
When your agent uses it
Guide for creating effective skills. This skill should be used when users want to create a new skill (or update an existing skill) that extends Claude's capabilities with specialized knowledge, workflows, or tool integrations.
What it loads into context
Frontmatter
56 tokensAlways available to the agent
SKILL.md
3,729 tokensWhen the skill is activated
Reference documents
535 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- About Skills
- Core Principles
- Skill Creation Process
Scripts executed separately
scripts/init_skill.pyscripts/package_skill.pyscripts/quick_validate.py
Files
LICENSE.txtdoc11,357 bytesSKILL.mdcore18,086 bytesreferences/output-patterns.mddoc1,813 bytesreferences/workflows.mddoc818 bytesscripts/__pycache__/quick_validate.cpython-36.pycasset2,741 bytesscripts/init_skill.pyruns10,865 bytesscripts/package_skill.pyruns3,288 bytesscripts/quick_validate.pyruns3,972 bytes
Read SKILL.md
# Skill Creator
This skill provides guidance for creating effective skills.
## About Skills
Skills are modular, self-contained packages that extend Claude's capabilities by providing
specialized knowledge, workflows, and tools. Think of them as "onboarding guides" for specific
domains or tasks—they transform Claude from a general-purpose agent into a specialized agent
equipped with procedural knowledge that no model can fully possess.
### What Skills Provide
1. Specialized workflows - Multi-step procedures for specific domainssmart-mutation-operator-generator
When your agent uses it
Analyzes a repository and its test suite to generate customized mutation operators tailored to the project. Use this skill when setting up mutation testing, improving test quality, or generating project-specific mutants. Considers language constructs, business logic patterns, API calls, data types, and code complexity to produce effective mutation operators that maximize test sensitivity while avoiding trivial or equivalent mutations. Generates prioritized operator sets (high/medium/low value) with impact summaries. Triggers when users ask to generate mutation operators, customize mutation testing, analyze code for mutation opportunities, or create project-specific mutants.
What it loads into context
Frontmatter
125 tokensAlways available to the agent
SKILL.md
1,613 tokensWhen the skill is activated
Reference documents
2,132 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- Workflow
- Quick Reference
- Best Practices
- Helper Script
Scripts executed separately
scripts/generate_operators.py
Files
SKILL.mdcore6,636 bytesSKILL.mdcore6,636 bytesSKILL.mdcore6,636 bytesSKILL.mdcore6,636 bytesSKILL.mdcore6,636 bytesSKILL.mdcore6,636 bytesSKILL.mdcore6,636 bytesSKILL.mdcore6,636 bytesSKILL.mdcore6,636 bytesreferences/standard_operators.mddoc7,092 bytesscripts/generate_operators.pyruns10,558 bytes
Read SKILL.md
# Smart Mutation Operator Generator
Generate customized mutation operators tailored to a specific codebase to maximize mutation testing effectiveness.
## Workflow
### 1. Analyze Codebase
**Run analysis script**:
```bash
# Analyze entire repository
python scripts/generate_operators.py /path/to/repo
# Analyze single filesmv-model-extractor
When your agent uses it
Automatically extract abstract finite-state models in SMV/NuSMV format from source code (C/C++, Java, Python) for formal model checking. Use when users need to: (1) Generate SMV models from program code for verification, (2) Extract state-transition models from protocol implementations, (3) Analyze control flow and data flow to construct formal models, (4) Create models for checking safety and liveness properties, (5) Convert imperative code to declarative state machines. Particularly effective for protocol implementations, concurrent systems, and control logic with clear state transitions.
What it loads into context
Frontmatter
127 tokensAlways available to the agent
SKILL.md
1,691 tokensWhen the skill is activated
Reference documents
2,538 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- Overview
- Workflow
- Common Use Cases
- Advanced Options
- Tips
- Common Issues
- References
- Scripts
Scripts executed separately
scripts/cfg_analyzer.pyscripts/extract_model.pyscripts/language_parser.pyscripts/smv_generator.py
Files
SKILL.mdcore7,359 bytesSKILL.mdcore7,359 bytesSKILL.mdcore7,359 bytesSKILL.mdcore7,359 bytesSKILL.mdcore7,359 bytesSKILL.mdcore7,359 bytesSKILL.mdcore7,359 bytesSKILL.mdcore7,359 bytesSKILL.mdcore7,359 bytesSKILL.mdcore7,359 bytesreferences/extraction_patterns.mddoc6,440 bytesreferences/smv_syntax.mddoc3,396 bytesscripts/cfg_analyzer.pyruns5,523 bytesscripts/extract_model.pyruns3,169 bytesscripts/language_parser.pyruns7,744 bytesscripts/smv_generator.pyruns6,676 bytes
Read SKILL.md
# SMV Model Extractor
Automatically extract abstract finite-state models from source code for formal verification with NuSMV model checker.
## Overview
This skill transforms imperative programs (C/C++, Java, Python) into declarative SMV models suitable for model checking. It analyzes control flow, data flow, and program variables to construct states and transitions, applying appropriate abstraction to make models tractable while preserving properties of interest.
## Workflow
### 1. Analyze Source Code
Read and understand the program structure:
specification-driven-generation
When your agent uses it
Generate implementation code and tests from written specifications. Use when the user provides specifications (natural language descriptions, formal specs, requirements documents, API specs) and asks Claude to implement the described functionality. Supports data structures, algorithms, classes, functions, and includes automatic test generation to validate implementation against specification.
What it loads into context
Frontmatter
67 tokensAlways available to the agent
SKILL.md
1,950 tokensWhen the skill is activated
Reference documents
0 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- Workflow
- Specification Analysis
- Best Practices
- Common Patterns
- Example Session
- Tips
Files
SKILL.mdcore9,481 bytesSKILL.mdcore9,481 bytesSKILL.mdcore9,481 bytesSKILL.mdcore9,481 bytesSKILL.mdcore9,481 bytesSKILL.mdcore9,481 bytesSKILL.mdcore9,481 bytes
Read SKILL.md
# Specification-Driven Generation
Generate implementation code and validation tests from written specifications through a systematic specification-to-code workflow.
## Workflow
### 1. Analyze Specification
Read and extract requirements from the specification:
- Identify functional requirements (what the code must do)
- Extract input/output contracts (parameters, return types, constraints)
- Note edge cases, error conditions, and validation rules
- Understand performance requirements or complexity constraintsspecification-generator
When your agent uses it
Generate formal specifications including preconditions, postconditions, invariants, and contracts from code or requirements. Use this skill when documenting APIs, creating formal verification annotations, defining function contracts, specifying class invariants, writing design-by-contract code, or preparing code for formal verification. Supports multiple specification languages including JML, ACSL, Dafny, Eiffel contracts, and documentation annotations.
What it loads into context
Frontmatter
82 tokensAlways available to the agent
SKILL.md
5,712 tokensWhen the skill is activated
Reference documents
0 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- Core Capabilities
- Specification Generation Workflow
- Specification Patterns
- Specification Templates
- Best Practices
- Common Specification Elements
- Verification Considerations
Files
SKILL.mdcore24,258 bytesSKILL.mdcore24,258 bytesSKILL.mdcore24,258 bytesSKILL.mdcore24,258 bytesSKILL.mdcore24,258 bytesSKILL.mdcore24,258 bytesSKILL.mdcore24,258 bytesSKILL.mdcore24,258 bytesSKILL.mdcore24,258 bytesSKILL.mdcore24,258 bytesSKILL.mdcore24,258 bytesSKILL.mdcore24,258 bytesSKILL.mdcore24,258 bytesSKILL.mdcore24,258 bytesSKILL.mdcore24,258 bytesSKILL.mdcore24,258 bytesSKILL.mdcore24,258 bytesSKILL.mdcore24,258 bytesSKILL.mdcore24,258 bytesSKILL.mdcore24,258 bytesSKILL.mdcore24,258 bytesSKILL.mdcore24,258 bytesSKILL.mdcore24,258 bytes
Read SKILL.md
# Specification Generator
Systematically generate formal specifications from code and requirements. Produces preconditions, postconditions, invariants, and behavioral contracts that enable verification, documentation, and design-by-contract programming.
## Core Capabilities
### 1. Precondition Generation
Define required conditions before execution:
- **Parameter validation** - Valid ranges, types, states
- **Object state requirements** - Required object states
- **Resource availability** - Files exist, connections open
- **Authorization checks** - Permission requirements
- **Null safety** - Non-null parameter requirementsspecification-to-temporal-logic-generator
When your agent uses it
Translate natural-language requirements or structured specification documents into formal temporal logic properties (LTL, CTL, safety/liveness properties). Use when users need to formalize requirements for model checking, formal verification, or property specification. Handles embedded/real-time systems, hardware verification, concurrent systems, and reactive systems. Resolves ambiguities, asks clarifying questions when needed, and outputs machine-checkable formulas with explanations. Supports multiple output formats (SPIN, NuSMV, Uppaal, TLA+, Maude).
What it loads into context
Frontmatter
115 tokensAlways available to the agent
SKILL.md
1,485 tokensWhen the skill is activated
Reference documents
5,419 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- Workflow
- Output Format
- Examples
- Resources
Scripts executed separately
scripts/convert_format.pyscripts/validate_formula.py
Files
SKILL.mdcore6,133 bytesSKILL.mdcore6,133 bytesSKILL.mdcore6,133 bytesreferences/ambiguity_resolution.mddoc6,148 bytesreferences/ctl_patterns.mddoc4,597 bytesreferences/ltl_patterns.mddoc3,146 bytesreferences/tool_syntax.mddoc5,729 bytesscripts/convert_format.pyruns6,029 bytesscripts/validate_formula.pyruns5,608 bytes
Read SKILL.md
# Specification-to-Temporal-Logic Generator
Translate natural-language requirements into formal temporal logic properties for model checking and formal verification.
## Workflow
### 1. Parse Input Requirements
Extract requirements from natural language text, structured documents, or semi-formal notations.
Identify key elements:
- **Events/Actions**: What happens (e.g., "request", "response", "button_press")
- **States/Conditions**: System states (e.g., "authenticated", "locked", "idle")
- **Temporal relationships**: When things happen (e.g., "always", "eventually", "before")spring-mvc-to-boot-migrator
When your agent uses it
Automatically migrate Spring MVC applications to Spring Boot. Use when you need to modernize a Spring MVC project to Spring Boot while preserving functionality. The skill analyzes the codebase, updates build configuration (Maven/Gradle), migrates annotations, converts XML configuration to Java/properties, updates controllers and tests, and creates the Spring Boot main application class. Creates git commits for each migration phase and generates a comprehensive summary. Supports both Maven and Gradle projects.
What it loads into context
Frontmatter
105 tokensAlways available to the agent
SKILL.md
2,026 tokensWhen the skill is activated
Reference documents
4,647 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- Overview
- Quick Start
- Supported Migration Paths
- Migration Process
- Using the Migration Scripts
- Post-Migration Steps
- Reference Documentation
- Example Code
- Migration Summary
- Tips
- Troubleshooting
- Benefits of Migration
Scripts executed separately
scripts/migrate.pyscripts/migrate_annotations.pyscripts/migrate_build.pyscripts/migrate_config.pyscripts/migrate_tests.py
Files
SKILL.mdcore8,974 bytesSKILL.mdcore8,974 bytesSKILL.mdcore8,974 bytesSKILL.mdcore8,974 bytesSKILL.mdcore8,974 bytesSKILL.mdcore8,974 bytesSKILL.mdcore8,974 bytesSKILL.mdcore8,974 bytesSKILL.mdcore8,974 bytesSKILL.mdcore8,974 bytesSKILL.mdcore8,974 bytesassets/UserController_After.javaasset1,095 bytesassets/UserController_Before.javaasset1,412 bytesreferences/framework_comparison.mddoc8,407 bytesreferences/migration_guide.mddoc11,558 bytesscripts/migrate.pyruns13,143 bytesscripts/migrate_annotations.pyruns8,131 bytesscripts/migrate_build.pyruns8,989 bytesscripts/migrate_config.pyruns5,126 bytesscripts/migrate_tests.pyruns6,098 bytes
Read SKILL.md
# Spring MVC to Spring Boot Migrator
## Overview
This skill automatically migrates Spring MVC applications to Spring Boot, transforming build configuration, annotations, XML configuration, controllers, and tests while preserving existing functionality. It handles Maven and Gradle projects, creates incremental git commits, and generates detailed migration summaries.
## Quick Start
### Basic Usage
```bash
# Navigate to your Spring MVC project
cd /path/to/spring-mvc-project
state-snapshot-instrumenter
When your agent uses it
Instrument programs (Python, C/C++, Java) to capture snapshots of key program states at runtime, including variables, memory, and call stacks. Use when you need to debug complex issues, reproduce test cases, prepare traces for formal verification, or analyze program execution. Supports manual instrumentation points, automatic function/method instrumentation, and conditional triggers. Outputs structured JSON snapshots for debugging, replay, and verification workflows.
What it loads into context
Frontmatter
92 tokensAlways available to the agent
SKILL.md
2,010 tokensWhen the skill is activated
Reference documents
4,919 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- Overview
- Quick Start
- Instrumentation Modes
- Core Operations
- Use Cases
- Reference Documentation
- Example Programs
- Output Format
- Tips
Scripts executed separately
assets/example_python.pyscripts/analyze_snapshots.pyscripts/instrument_c.pyscripts/instrument_java.pyscripts/instrument_python.pyscripts/snapshot_runtime.py
Files
SKILL.mdcore8,875 bytesSKILL.mdcore8,875 bytesSKILL.mdcore8,875 bytesSKILL.mdcore8,875 bytesSKILL.mdcore8,875 bytesSKILL.mdcore8,875 bytesSKILL.mdcore8,875 bytesSKILL.mdcore8,875 bytesSKILL.mdcore8,875 bytesSKILL.mdcore8,875 bytesSKILL.mdcore8,875 bytesSKILL.mdcore8,875 bytesSKILL.mdcore8,875 bytesSKILL.mdcore8,875 bytesSKILL.mdcore8,875 bytesSKILL.mdcore8,875 bytesSKILL.mdcore8,875 bytesSKILL.mdcore8,875 bytesassets/example_c.casset445 bytesassets/example_java.javaasset553 bytesassets/example_python.pyruns422 bytesassets/snapshot_schema.jsonasset3,119 bytesreferences/instrumentation_guide.mddoc6,355 bytesreferences/snapshot_format.mddoc5,766 bytesreferences/use_cases.mddoc8,298 bytesscripts/SnapshotRuntime.javaasset7,924 bytesscripts/analyze_snapshots.pyruns6,096 bytesscripts/instrument_c.pyruns5,379 bytesscripts/instrument_java.pyruns5,017 bytesscripts/instrument_python.pyruns5,826 bytesscripts/snapshot_runtime.casset4,887 bytesscripts/snapshot_runtime.hasset1,347 bytesscripts/snapshot_runtime.pyruns4,837 bytes
Read SKILL.md
# State Snapshot Instrumenter
## Overview
This skill instruments programs to capture snapshots of key program states at runtime. Snapshots include variable values, memory state, call stacks, and execution context, saved in structured JSON format for analysis, debugging, reproduction, and verification.
## Quick Start
### Basic Workflow
1. **Add snapshot markers** to your code (manual mode) or use automatic instrumentation
2. **Run the instrumenter** to generate instrumented code
3. **Execute the instrumented program** to capture snapshots
4. **Analyze snapshots** to understand program behaviorstatic-bug-detector
When your agent uses it
Analyze source code statically to detect potential functional bugs including null dereferences, incorrect condition checks, unreachable code, inconsistent state updates, logic errors, resource leaks, and type mismatches. Report suspicious code locations with detailed explanations, severity levels, and confidence assessments. Use when reviewing code for bugs, performing code audits, or when the user asks to find bugs, detect issues, analyze code for problems, or perform static analysis.
What it loads into context
Frontmatter
95 tokensAlways available to the agent
SKILL.md
3,201 tokensWhen the skill is activated
Reference documents
4,130 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- Overview
- Bug Detection Workflow
- Bug Categories
- Examples
Files
SKILL.mdcore13,812 bytesSKILL.mdcore13,812 bytesSKILL.mdcore13,812 bytesSKILL.mdcore13,812 bytesSKILL.mdcore13,812 bytesSKILL.mdcore13,812 bytesSKILL.mdcore13,812 bytesSKILL.mdcore13,812 bytesSKILL.mdcore13,812 bytesSKILL.mdcore13,812 bytesSKILL.mdcore13,812 bytesreferences/detection_patterns.mddoc16,442 bytes
Read SKILL.md
# Static Bug Detector
## Overview
Perform static analysis on source code to identify potential functional bugs. Detect common bug patterns, analyze control flow and data flow, and report suspicious locations with explanations, severity levels, and confidence assessments.
## Bug Detection Workflow
### Step 1: Understand the Code
Analyze the code structure and semantics:
1. **Identify language:**
- Determine programming languagestatic-reasoning-verifier
When your agent uses it
Verify code correctness statically against specifications using type checking, contract verification, and formal methods. Use when: (1) Verifying type safety and null safety in Python, Java, or C/C++ code, (2) Checking design-by-contract specifications (preconditions, postconditions, invariants), (3) Validating code against formal specifications, (4) Ensuring code quality and correctness before runtime, (5) Finding potential bugs through static analysis. Supports Python (mypy, contracts), Java (javac, JML), and provides verification scripts and contract specification guidelines.
What it loads into context
Frontmatter
129 tokensAlways available to the agent
SKILL.md
2,923 tokensWhen the skill is activated
Reference documents
3,905 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- Quick Start
- Verification Types
- Verification Workflow
- Python Verification
- Java Verification
- Common Verification Patterns
- Best Practices
- Troubleshooting
- Reference Documentation
- Integration with Development Workflow
Scripts executed separately
scripts/verify_java.pyscripts/verify_python.py
Files
SKILL.mdcore11,713 bytesSKILL.mdcore11,713 bytesSKILL.mdcore11,713 bytesSKILL.mdcore11,713 bytesSKILL.mdcore11,713 bytesSKILL.mdcore11,713 bytesSKILL.mdcore11,713 bytesSKILL.mdcore11,713 bytesSKILL.mdcore11,713 bytesSKILL.mdcore11,713 bytesSKILL.mdcore11,713 bytesSKILL.mdcore11,713 bytesSKILL.mdcore11,713 bytesSKILL.mdcore11,713 bytesSKILL.mdcore11,713 bytesSKILL.mdcore11,713 bytesSKILL.mdcore11,713 bytesSKILL.mdcore11,713 bytesSKILL.mdcore11,713 bytesSKILL.mdcore11,713 bytesSKILL.mdcore11,713 bytesSKILL.mdcore11,713 bytesSKILL.mdcore11,713 bytesSKILL.mdcore11,713 bytesSKILL.mdcore11,713 bytesSKILL.mdcore11,713 bytesSKILL.mdcore11,713 bytesSKILL.mdcore11,713 bytesreferences/java_jml.mddoc7,626 bytesreferences/python_contracts.mddoc7,945 bytesscripts/verify_java.pyruns10,010 bytesscripts/verify_python.pyruns10,143 bytes
Read SKILL.md
# Static Reasoning Verifier
Verify code correctness statically against specifications through type checking, contract verification, and formal reasoning.
## Quick Start
### Verify Python Code
```bash
# Type checking and contract verification
python scripts/verify_python.py src/app.py
# Strict mode (enforce all type annotations)
python scripts/verify_python.py src/ --strictstatic-vulnerability-detector
When your agent uses it
Statically analyze code to detect security vulnerabilities including buffer overflows, injection risks (SQL, command, XSS), insecure deserialization, improper authentication, hard-coded credentials, and unsafe cryptography. Use when: (1) Performing security code review, (2) Analyzing code for OWASP Top 10 vulnerabilities, (3) Identifying CWE-classified weaknesses, (4) Generating security audit reports, (5) Reviewing code before deployment, or (6) Assessing third-party code security. Findings categorized by CWE ID and severity (Critical/High/Medium/Low).
What it loads into context
Frontmatter
130 tokensAlways available to the agent
SKILL.md
1,999 tokensWhen the skill is activated
Reference documents
5,345 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- Analysis Workflow
- Detection Heuristics
- CWE Reference
- Report Format
- Examples
- Analysis Tips
Files
SKILL.mdcore7,818 bytesSKILL.mdcore7,818 bytesSKILL.mdcore7,818 bytesSKILL.mdcore7,818 bytesSKILL.mdcore7,818 bytesSKILL.mdcore7,818 bytesSKILL.mdcore7,818 bytesSKILL.mdcore7,818 bytesSKILL.mdcore7,818 bytesSKILL.mdcore7,818 bytesSKILL.mdcore7,818 bytesreferences/cwe_patterns.mddoc10,542 bytesreferences/examples.mddoc10,657 bytes
Read SKILL.md
# Static Vulnerability Detector
Analyze code for security vulnerabilities with CWE classification and severity assessment.
## Analysis Workflow
### 1. Code Scanning
Systematically examine code for vulnerability patterns:
**Memory Safety** (C/C++):
- Buffer overflows (CWE-119)
- Out-of-bounds access (CWE-125)
- Use-after-free (CWE-416)strategic-planner
When your agent uses it
Interview-based strategic planning for complex software tasks. Conducts structured requirements gathering, gap analysis, and generates detailed work plans before implementation begins.
What it loads into context
Frontmatter
35 tokensAlways available to the agent
SKILL.md
839 tokensWhen the skill is activated
Reference documents
0 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- When to Use This Skill
- What This Skill Does
- Example
- Tips
Files
SKILL.mdcore4,018 bytes
Read SKILL.md
# Strategic Planner
An intelligent interviewer that helps think through complex software tasks before writing code. Separates planning from execution to prevent cognitive drift and scope creep.
## When to Use This Skill
- Multi-day or multi-step implementation projects
- Critical production changes requiring careful planning
- Complex refactoring with behavior preservation needs
- Any task where "just start coding" leads to rework
## What This Skill Does
### Phase 1: Interview — Requirements Gatheringsymbolic-execution-assistant
When your agent uses it
Performs symbolic execution to detect potential errors by exploring execution paths, solving path constraints, and generating test inputs. Use when you need to analyze code for bugs like null dereferences, division by zero, buffer overflows, or assertion violations. Also use to generate test inputs that exercise different code paths, find edge cases, or explore all reachable program states. Supports Python, Java, and C/C++ through manual symbolic execution techniques and integration with tools like KLEE, angr, Z3, and Symbolic PathFinder.
What it loads into context
Frontmatter
125 tokensAlways available to the agent
SKILL.md
3,395 tokensWhen the skill is activated
Reference documents
8,551 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- What is Symbolic Execution?
- Workflow
- Symbolic Execution Tools
- Handling Path Explosion
- Tips
- Common Use Cases
- References
Files
SKILL.mdcore13,911 bytesSKILL.mdcore13,911 bytesSKILL.mdcore13,911 bytesSKILL.mdcore13,911 bytesSKILL.mdcore13,911 bytesSKILL.mdcore13,911 bytesSKILL.mdcore13,911 bytesSKILL.mdcore13,911 bytesSKILL.mdcore13,911 bytesSKILL.mdcore13,911 bytesSKILL.mdcore13,911 bytesSKILL.mdcore13,911 bytesSKILL.mdcore13,911 bytesSKILL.mdcore13,911 bytesSKILL.mdcore13,911 bytesSKILL.mdcore13,911 bytesreferences/constraint_solving.mddoc10,795 bytesreferences/path_exploration.mddoc9,906 bytesreferences/tool_integration.mddoc10,208 bytes
Read SKILL.md
# Symbolic Execution Assistant
Perform symbolic execution analysis to detect errors and generate test inputs by exploring program paths with symbolic variables.
## What is Symbolic Execution?
Symbolic execution executes code with **symbolic values** (representing any possible value) instead of concrete values. This allows exploring multiple execution paths simultaneously and detecting errors that might only occur with specific inputs.
**Key Concepts:**
- **Symbolic variables**: Variables with unknown values (e.g., α, β instead of 5, 10)
- **Path constraints**: Conditions accumulated along each execution path
- **Path explosion**: Number of paths grows exponentially with branches
- **Constraint solver**: Tool (like Z3) that finds concrete values satisfying constraints
system-diagram-generator
When your agent uses it
Creates visual representations of system structure including architecture diagrams, data flow diagrams, deployment diagrams, and sequence diagrams. Use when Claude needs to visualize system components, infrastructure, data flows, or interactions. Supports Mermaid (recommended for Markdown/GitHub), PlantUML (for detailed UML), and Graphviz/DOT (for complex networks). Trigger when users request diagrams, visualizations, or ask to "show", "diagram", "visualize", or "map out" system architecture, infrastructure, data flows, or component interactions.
What it loads into context
Frontmatter
114 tokensAlways available to the agent
SKILL.md
1,273 tokensWhen the skill is activated
Reference documents
1,867 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- Quick Start
- Format Selection
- Diagram Types
- Best Practices
- Workflow
- Example Usage Patterns
Files
SKILL.mdcore6,047 bytesreferences/graphviz-patterns.mddoc3,112 bytesreferences/mermaid-patterns.mddoc2,130 bytesreferences/plantuml-patterns.mddoc2,251 bytes
Read SKILL.md
# System Diagram Generator
Generate clear, accurate visual representations of system structure using text-based diagram formats.
## Quick Start
When a user requests a system diagram:
1. **Understand the system**: Ask clarifying questions about components, relationships, and scope
2. **Choose the format**: Select based on user preference or context (default to Mermaid for versatility)
3. **Select diagram type**: Match the visualization to the information being conveyed
4. **Generate the diagram**: Create the diagram code with clear labels and structure
5. **Provide context**: Include a brief explanation of what the diagram shows
szz-bug-introducing-commit-identifier
When your agent uses it
Identifies bug-introducing commits using SZZ-style analysis based on bug-fixing commits, commit history, and code blame information. Use this skill when you need to trace bugs back to their origin, identify which commits introduced bugs, analyze bug-fix commits to find root causes, perform software repository mining for bug analysis, or conduct empirical studies on software defects. Triggers when users ask to find bug-introducing commits, identify when a bug was introduced, trace bug origins, perform SZZ analysis, or analyze bug-fixing commits.
What it loads into context
Frontmatter
125 tokensAlways available to the agent
SKILL.md
1,365 tokensWhen the skill is activated
Reference documents
952 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- Overview
- Workflow
- Understanding Confidence Scores
- False Positive Filtering
- Common Use Cases
- Limitations and Considerations
- Advanced Usage
- Resources
Scripts executed separately
scripts/szz_analyzer.py
Files
SKILL.mdcore6,126 bytesSKILL.mdcore6,126 bytesSKILL.mdcore6,126 bytesSKILL.mdcore6,126 bytesSKILL.mdcore6,126 bytesreferences/szz_algorithm.mddoc4,364 bytesscripts/szz_analyzer.pyruns10,591 bytes
Read SKILL.md
# SZZ Bug-Introducing Commit Identifier
## Overview
This skill performs SZZ (Śliwerski-Zimmermann-Zeller) algorithm analysis to identify bug-introducing commits in git repositories. Given a bug-fixing commit, it traces modified lines back through version history using git blame to find candidate commits that originally introduced the buggy code.
## Workflow
### 1. Identify the Bug-Fixing Commit
Start by identifying the commit that fixes the bug. This can be obtained from:
- Commit hash provided by the user
- Issue tracker references (e.g., "fixes #123")
- Commit message analysis (e.g., "fix:", "bug:")tactic-suggestion-assistant
When your agent uses it
Analyze proof states in Isabelle or Coq and suggest applicable tactics to make progress. Use when users need help with: (1) Choosing the next tactic in an interactive proof, (2) Understanding what tactics apply to their current goal, (3) Getting unstuck in a proof, (4) Learning which tactics work for specific goal structures (conjunctions, implications, induction, etc.). Provides 3-5 ranked tactic suggestions with explanations for intermediate-level proofs in both Isabelle/Isar and Coq.
What it loads into context
Frontmatter
114 tokensAlways available to the agent
SKILL.md
2,069 tokensWhen the skill is activated
Reference documents
7,175 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- Overview
- How to Use
- Analysis Process
- Suggestion Format
- Example: Isabelle Proof State
- Example: Coq Proof State
- Common Situations
- References
- Tips for Effective Suggestions
Files
SKILL.mdcore8,002 bytesreferences/coq_tactics.mddoc7,874 bytesreferences/isabelle_tactics.mddoc6,231 bytesreferences/proof_patterns.mddoc10,356 bytes
Read SKILL.md
# Tactic Suggestion Assistant
Analyze proof states and suggest applicable tactics to make progress in Isabelle or Coq.
## Overview
This skill helps you navigate interactive proofs by analyzing the current proof state and suggesting 3-5 ranked tactics that can make progress. It works with both Isabelle/Isar and Coq, providing system-specific suggestions with explanations.
## How to Use
Provide the current proof state including:
1. **System**: Isabelle or Coq
2. **Goal**: The current goal to prove
3. **Context**: Available hypotheses/assumptions (if any)taint-instrumentation-assistant
When your agent uses it
Instruments code to track the flow of untrusted or sensitive data at runtime, enabling detection of injection vulnerabilities, data leaks, and privilege violations. Use when users need to: (1) Track untrusted input propagation through code, (2) Detect SQL injection, XSS, or command injection vulnerabilities, (3) Identify sensitive data leaks, (4) Monitor privilege escalation paths, (5) Perform dynamic taint analysis for security testing. Supports Python, Java, JavaScript, and C/C++ with configurable taint sources and sinks.
What it loads into context
Frontmatter
122 tokensAlways available to the agent
SKILL.md
2,868 tokensWhen the skill is activated
Reference documents
189 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- Workflow
- Language-Specific Patterns
- Common Vulnerability Patterns
- Taint Policy Configuration
- Output Format
- Best Practices
- Advanced Features
- Constraints
Scripts executed separately
scripts/example.py
Files
SKILL.mdcore11,637 bytesSKILL.mdcore11,637 bytesSKILL.mdcore11,637 bytesSKILL.mdcore11,637 bytesSKILL.mdcore11,637 bytesSKILL.mdcore11,637 bytesSKILL.mdcore11,637 bytesSKILL.mdcore11,637 bytesSKILL.mdcore11,637 bytesSKILL.mdcore11,637 bytesSKILL.mdcore11,637 bytesSKILL.mdcore11,637 bytesSKILL.mdcore11,637 bytesSKILL.mdcore11,637 bytesSKILL.mdcore11,637 bytesSKILL.mdcore11,637 bytesSKILL.mdcore11,637 bytesassets/example_asset.txtdoc865 bytesreferences/api_reference.mddoc982 bytesscripts/example.pyruns621 bytes
Read SKILL.md
# Taint Instrumentation Assistant
Instrument code to track untrusted and sensitive data flow for security vulnerability detection.
## Workflow
Follow these steps to add taint tracking instrumentation:
### 1. Identify Taint Sources and Sinks
Define what data to track and where violations occur:
**Taint sources** (untrusted/sensitive data origins):
- User input (HTTP parameters, form data, command-line args)technical-debt-analyzer
When your agent uses it
Detect and analyze areas with high maintenance cost, poor design, or accumulated technical debt. Use this skill when reviewing codebases for quality issues, planning refactoring efforts, conducting code audits, assessing project health, identifying maintenance hotspots, or prioritizing technical improvements. Analyzes code smells, architectural issues, dependency problems, test quality, documentation gaps, and provides actionable recommendations with priority rankings.
What it loads into context
Frontmatter
87 tokensAlways available to the agent
SKILL.md
6,442 tokensWhen the skill is activated
Reference documents
0 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- Core Capabilities
- Technical Debt Analysis Workflow
- Technical Debt Remediation Plan
- Code Quality Metrics
- Technical Debt Report Template
- Best Practices
- Common Anti-Patterns
Files
SKILL.mdcore27,844 bytesSKILL.mdcore27,844 bytesSKILL.mdcore27,844 bytesSKILL.mdcore27,844 bytesSKILL.mdcore27,844 bytesSKILL.mdcore27,844 bytesSKILL.mdcore27,844 bytesSKILL.mdcore27,844 bytesSKILL.mdcore27,844 bytesSKILL.mdcore27,844 bytesSKILL.mdcore27,844 bytesSKILL.mdcore27,844 bytesSKILL.mdcore27,844 bytesSKILL.mdcore27,844 bytesSKILL.mdcore27,844 bytesSKILL.mdcore27,844 bytesSKILL.mdcore27,844 bytesSKILL.mdcore27,844 bytes
Read SKILL.md
# Technical Debt Analyzer
Systematically identify, categorize, and prioritize technical debt across codebases. Provides actionable insights into code quality, architectural issues, and maintenance risks.
## Core Capabilities
### 1. Code Quality Analysis
Identify code-level technical debt:
- **Code smells** - Long methods, large classes, duplicated code
- **Complexity metrics** - Cyclomatic complexity, nesting depth
- **Naming issues** - Poor variable/function names, inconsistent conventions
- **Dead code** - Unused functions, unreachable code, commented code
- **Magic numbers** - Hard-coded values without explanationtemplate-code-generator
When your agent uses it
Generate boilerplate code and project templates/skeletons automatically. Use when: (1) Creating new projects from scratch (React app, FastAPI backend, Express API), (2) Generating repetitive code patterns (CRUD endpoints, models, controllers), (3) Scaffolding components, services, or modules, (4) Creating test boilerplate, (5) Setting up monorepo structures. Provides project templates and code generation patterns for common development tasks.
What it loads into context
Frontmatter
102 tokensAlways available to the agent
SKILL.md
2,221 tokensWhen the skill is activated
Reference documents
7,425 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- Quick Start
- Project Templates
- Code Generation Patterns
- Generation Workflow
- Best Practices
- Common Scenarios
- Reference Documentation
Scripts executed separately
assets/react-app/package.json
Files
SKILL.mdcore9,397 bytesSKILL.mdcore9,397 bytesSKILL.mdcore9,397 bytesSKILL.mdcore9,397 bytesSKILL.mdcore9,397 bytesSKILL.mdcore9,397 bytesSKILL.mdcore9,397 bytesassets/react-app/package.jsonruns484 bytesreferences/code_patterns.mddoc10,983 bytesreferences/template_patterns.mddoc17,698 bytes
Read SKILL.md
# Template Code Generator
Generate boilerplate code and complete project skeletons automatically, accelerating development with battle-tested templates.
## Quick Start
### Generate Complete Projects
**React Application**:
```bash
# Use assets/react-app as template base
# Includes: Vite, TypeScript, React Router, standard structure
```
test-case-documentation
When your agent uses it
Generate comprehensive test case documentation from test code, test framework output, existing test docs, and source code context. Use when documenting test suites, creating test specifications, generating test coverage reports, onboarding developers to testing practices, or preparing QA documentation. Analyzes test functions (pytest, unittest) to extract test names, docstrings, assertions, and organization, then produces structured markdown with both overview-level summaries and detailed test case specifications including purpose, preconditions, steps, expected results, and test data. Triggers when users ask to document tests, generate test specifications, create test reports, summarize test coverage, or explain what tests do.
What it loads into context
Frontmatter
136 tokensAlways available to the agent
SKILL.md
3,152 tokensWhen the skill is activated
Reference documents
2,405 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- Overview
- Workflow
- Automation Opportunities
- Reference
Scripts executed separately
scripts/extract_tests.py
Files
SKILL.mdcore13,508 bytesSKILL.mdcore13,508 bytesSKILL.mdcore13,508 bytesSKILL.mdcore13,508 bytesSKILL.mdcore13,508 bytesSKILL.mdcore13,508 bytesSKILL.mdcore13,508 bytesSKILL.mdcore13,508 bytesSKILL.mdcore13,508 bytesSKILL.mdcore13,508 bytesSKILL.mdcore13,508 bytesSKILL.mdcore13,508 bytesSKILL.mdcore13,508 bytesSKILL.mdcore13,508 bytesSKILL.mdcore13,508 bytesSKILL.mdcore13,508 bytesSKILL.mdcore13,508 bytesSKILL.mdcore13,508 bytesSKILL.mdcore13,508 bytesSKILL.mdcore13,508 bytesSKILL.mdcore13,508 bytesSKILL.mdcore13,508 bytesreferences/documentation-templates.mddoc9,930 bytesscripts/extract_tests.pyruns7,993 bytes
Read SKILL.md
# Test Case Documentation
## Overview
Generate comprehensive, structured documentation for test suites by analyzing test code, framework output, and source context to produce both overview summaries and detailed test case specifications.
## Workflow
### 1. Understand Documentation Needs
Determine what documentation is needed:
**Questions to ask:**
- What test suites need documentation?test-case-reducer
When your agent uses it
Automatically reduces bug-triggering test cases to minimal form while preserving the failure. Use when debugging with large, complex test cases that need simplification, reproducing bugs with minimal examples, or creating regression tests from verbose failure scenarios. Takes a failing test and systematically removes unnecessary inputs, steps, assertions, and code using delta debugging and other reduction algorithms. Supports unit tests, integration tests, input files, and multiple programming languages (Python, JavaScript, Java, C/C++).
What it loads into context
Frontmatter
104 tokensAlways available to the agent
SKILL.md
2,257 tokensWhen the skill is activated
Reference documents
3,836 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- Core Concept
- Workflow
- Quick Start Examples
- Using the Reduction Script
- Manual Reduction Workflow
- Language-Specific Guidance
- Common Scenarios
- Best Practices
- Troubleshooting
- References
- Tips
Scripts executed separately
scripts/reduce_test.py
Files
SKILL.mdcore9,875 bytesSKILL.mdcore9,875 bytesSKILL.mdcore9,875 bytesSKILL.mdcore9,875 bytesSKILL.mdcore9,875 bytesSKILL.mdcore9,875 bytesSKILL.mdcore9,875 bytesSKILL.mdcore9,875 bytesSKILL.mdcore9,875 bytesSKILL.mdcore9,875 bytesSKILL.mdcore9,875 bytesSKILL.mdcore9,875 bytesSKILL.mdcore9,875 bytesSKILL.mdcore9,875 bytesSKILL.mdcore9,875 bytesSKILL.mdcore9,875 bytesSKILL.mdcore9,875 bytesreferences/algorithms.mddoc7,071 bytesreferences/language-specific.mddoc8,459 bytesscripts/reduce_test.pyruns10,640 bytes
Read SKILL.md
# Test Case Reducer
Automatically reduce bug-triggering test cases to minimal form while guaranteeing the reduced test still reproduces the same failure.
## Core Concept
Test case reduction works by:
1. **Identify**: Parse the test case and identify reducible elements
2. **Remove**: Systematically try removing elements (lines, statements, inputs)
3. **Validate**: Run the test after each removal to verify failure is preserved
4. **Iterate**: Continue until no further reduction is possible
## Workflow
test-deduplicator
When your agent uses it
Analyzes test suites to identify redundant and duplicate test cases using coverage analysis, semantic similarity, and execution results. Use this skill when you need to reduce test suite size, identify redundant tests, optimize test execution time, analyze test coverage overlap, find tests with identical behavior, or improve test suite maintainability. Triggers when users ask to deduplicate tests, find redundant test cases, reduce test suite size, identify duplicate tests, or optimize test coverage.
What it loads into context
Frontmatter
101 tokensAlways available to the agent
SKILL.md
2,125 tokensWhen the skill is activated
Reference documents
1,899 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- Overview
- Workflow
- Analysis Types
- Configuration
- Common Use Cases
- Understanding Results
- Best Practices
- Limitations
- Resources
Scripts executed separately
scripts/coverage_analyzer.pyscripts/deduplicator.pyscripts/semantic_analyzer.py
Files
SKILL.mdcore9,437 bytesSKILL.mdcore9,437 bytesSKILL.mdcore9,437 bytesSKILL.mdcore9,437 bytesSKILL.mdcore9,437 bytesassets/deduplication_config.jsonasset1,584 bytesreferences/deduplication_methodology.mddoc7,961 bytesscripts/coverage_analyzer.pyruns10,525 bytesscripts/deduplicator.pyruns12,011 bytesscripts/semantic_analyzer.pyruns10,568 bytes
Read SKILL.md
# Test Deduplicator
## Overview
This skill analyzes test suites to identify redundant or duplicate tests by examining code coverage, semantic similarity, and execution behavior. It groups equivalent tests, explains deduplication rationale, and recommends which tests can be safely removed while preserving overall test effectiveness.
## Workflow
### 1. Collect Test Coverage Data
First, gather coverage information for each test in the suite.
**For Python projects with pytest:**
```bashtest-driven-generation
When your agent uses it
Generate implementation code that passes existing unit tests. Use when the user provides test files (Python pytest/unittest, Java JUnit/TestNG) and asks Claude to implement the code to make those tests pass. Supports full TDD workflow - analyzing tests, generating implementation, running tests, debugging failures, and iterating until all tests pass.
What it loads into context
Frontmatter
75 tokensAlways available to the agent
SKILL.md
1,030 tokensWhen the skill is activated
Reference documents
0 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- Workflow
- Best Practices
- Example Session
- Language-Specific Notes
Files
SKILL.mdcore4,541 bytesSKILL.mdcore4,541 bytesSKILL.mdcore4,541 bytesSKILL.mdcore4,541 bytesSKILL.mdcore4,541 bytes
Read SKILL.md
# Test-Driven Generation
Generate implementation code that satisfies existing unit tests through an iterative test-driven development workflow.
## Workflow
### 1. Analyze Tests
Read and understand the provided test file(s):
- Identify what functions/classes/methods need to be implemented
- Extract input/output expectations from assertions
- Note edge cases, error conditions, and special behaviors
- Understand dependencies and importstest-guided-bug-detector
When your agent uses it
Analyze failing tests to detect functional bugs in code. Takes repository and failing test output as input, analyzes execution behavior, assertions, and stack traces to identify suspicious code regions and root causes. Use when debugging test failures, investigating regression bugs, or understanding why tests fail. Explains the bug mechanism, identifies affected code, and suggests fixes based on test expectations vs actual behavior.
What it loads into context
Frontmatter
86 tokensAlways available to the agent
SKILL.md
2,884 tokensWhen the skill is activated
Reference documents
5,482 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- Overview
- Bug Detection Workflow
- Analysis Process
- Common Bug Patterns
- Failure Type Analysis
- Example Analysis
- Bug Mechanism
- Execution Trace
- Suspicious Code Regions
- Recommended Fix
- Verification
- Related Issues
- Additional Resources
Files
SKILL.mdcore11,051 bytesSKILL.mdcore11,051 bytesSKILL.mdcore11,051 bytesSKILL.mdcore11,051 bytesSKILL.mdcore11,051 bytesSKILL.mdcore11,051 bytesSKILL.mdcore11,051 bytesSKILL.mdcore11,051 bytesSKILL.mdcore11,051 bytesSKILL.mdcore11,051 bytesSKILL.mdcore11,051 bytesreferences/analysis_strategies.mddoc6,869 bytesreferences/bug_patterns.mddoc8,881 bytesreferences/failure_types.mddoc6,332 bytes
Read SKILL.md
# Test-Guided Bug Detector
Analyze failing tests to detect and explain functional bugs in code.
## Overview
When tests fail, they provide valuable clues about bugs in the code. This skill analyzes:
1. **Test failure output** - Error messages, stack traces, assertion failures
2. **Test expectations** - What the test expects to happen
3. **Actual behavior** - What actually happened
4. **Code execution path** - Which code was executed
5. **Suspicious patterns** - Common bug patterns that match the failure
test-guided-debloating
When your agent uses it
Removes unnecessary code from a repository while preserving exactly the behavior exercised by a given test suite. Use this skill when you need to debloat, slim down, or remove unused code from a codebase based on test coverage. The skill analyzes which code elements (files, classes, functions, methods, branches, imports) are exercised by tests, identifies unreachable or unused code, and safely removes it while ensuring all tests continue to pass. Triggers when users ask to remove unused code, debloat based on tests, eliminate dead code guided by test coverage, or slim down a repository to only test-required functionality.
What it loads into context
Frontmatter
132 tokensAlways available to the agent
SKILL.md
1,310 tokensWhen the skill is activated
Reference documents
3,244 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- Workflow
- Key Principles
- Common Pitfalls
- Helper Script
Scripts executed separately
scripts/analyze_coverage.py
Files
SKILL.mdcore5,889 bytesSKILL.mdcore5,889 bytesSKILL.mdcore5,889 bytesSKILL.mdcore5,889 bytesSKILL.mdcore5,889 bytesSKILL.mdcore5,889 bytesSKILL.mdcore5,889 bytesSKILL.mdcore5,889 bytesSKILL.mdcore5,889 bytesSKILL.mdcore5,889 bytesSKILL.mdcore5,889 bytesSKILL.mdcore5,889 bytesSKILL.mdcore5,889 bytesSKILL.mdcore5,889 bytesreferences/coverage_tools.mddoc7,199 bytesreferences/debloating_strategy.mddoc5,772 bytesscripts/analyze_coverage.pyruns9,033 bytes
Read SKILL.md
# Test-Guided Debloating
Remove unnecessary code from a repository while preserving exactly the behavior exercised by a given test suite.
## Workflow
### 1. Understand Requirements
**Inputs needed**:
- Target repository path
- Test command to run the test suite
- Programming language/framework
**Clarify scope**:test-guided-migration-assistant
When your agent uses it
Automatically updates a codebase to a new language version, framework version, or library update while ensuring all tests still pass. Use this skill when migrating Python 2→3, upgrading framework versions (React, Django, Angular), updating dependencies, or performing any version migration where tests define correct behavior. The skill analyzes failing tests caused by migration, categorizes errors (import errors, API changes, type errors, behavior changes), proposes systematic fixes, and verifies that test-observable behavior remains unchanged. Triggers when users ask to migrate code versions, upgrade dependencies while keeping tests passing, update framework versions, or perform test-guided version migrations.
What it loads into context
Frontmatter
139 tokensAlways available to the agent
SKILL.md
1,735 tokensWhen the skill is activated
Reference documents
3,309 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- Workflow
- Key Principles
- Common Migration Patterns
- Helper Script
- Rollback Strategy
Scripts executed separately
scripts/analyze_test_failures.py
Files
SKILL.mdcore7,319 bytesSKILL.mdcore7,319 bytesSKILL.mdcore7,319 bytesSKILL.mdcore7,319 bytesSKILL.mdcore7,319 bytesSKILL.mdcore7,319 bytesSKILL.mdcore7,319 bytesSKILL.mdcore7,319 bytesSKILL.mdcore7,319 bytesSKILL.mdcore7,319 bytesSKILL.mdcore7,319 bytesSKILL.mdcore7,319 bytesSKILL.mdcore7,319 bytesSKILL.mdcore7,319 bytesSKILL.mdcore7,319 bytesreferences/migration_scenarios.mddoc5,845 bytesreferences/migration_strategy.mddoc8,266 bytesscripts/analyze_test_failures.pyruns9,220 bytes
Read SKILL.md
# Test-Guided Migration Assistant
Automatically update a codebase to a new language version, framework version, or library update while ensuring all tests continue to pass.
## Workflow
### 1. Establish Baseline
Before starting migration, establish the current state:
```bash
# Run full test suite
<test_command>
test-oracle-generator
When your agent uses it
Generates automated test oracles to verify correct software behavior. Creates assertion-based oracles (expected values), property-based oracles (invariants), differential oracles (comparing implementations), and metamorphic oracles (input transformations). Use when you need to generate assertions for test cases, identify invariants that should always hold, compare new vs legacy implementations, create metamorphic test relationships, validate function correctness, or improve test coverage with better verification strategies. Supports Python (pytest, unittest, hypothesis) and Java (JUnit, property testing).
What it loads into context
Frontmatter
128 tokensAlways available to the agent
SKILL.md
3,336 tokensWhen the skill is activated
Reference documents
5,085 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- Oracle Types
- Workflow
- Oracle Selection Guide
- Tips
- Common Patterns
Files
SKILL.mdcore14,181 bytesSKILL.mdcore14,181 bytesSKILL.mdcore14,181 bytesSKILL.mdcore14,181 bytesSKILL.mdcore14,181 bytesSKILL.mdcore14,181 bytesSKILL.mdcore14,181 bytesSKILL.mdcore14,181 bytesSKILL.mdcore14,181 bytesSKILL.mdcore14,181 bytesSKILL.mdcore14,181 bytesreferences/metamorphic_patterns.mddoc10,696 bytesreferences/property_patterns.mddoc8,452 bytes
Read SKILL.md
# Test Oracle Generator
Generate automated test oracles to verify correct software behavior across multiple oracle types.
## Oracle Types
1. **Assertion-based**: Compare actual vs expected output
2. **Property-based**: Verify invariants that should always hold
3. **Differential**: Compare new implementation against reference
4. **Metamorphic**: Test input-output transformations
## Workflow
### Step 1: Analyze the Function Under Testtest-suite-prioritizer
When your agent uses it
Analyzes test suites and suggests optimal test execution order based on code change impact and project requirements. Use when optimizing CI/CD pipelines, deciding which tests to run before committing, or selecting critical tests under time constraints. Prioritizes tests by analyzing recently modified files, test dependencies, and coverage overlap. Outputs detailed rankings with priority scores and reasoning to help teams run the most impactful tests first.
What it loads into context
Frontmatter
89 tokensAlways available to the agent
SKILL.md
3,624 tokensWhen the skill is activated
Reference documents
6,774 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- Core Capabilities
- Test Prioritization Workflow
- Time Estimates
- Recommendations
- Prioritization Strategies
- Analyzing Different Project Types
- Best Practices
- Example Scenarios
- Resources
- Quick Reference
Files
SKILL.mdcore15,150 bytesSKILL.mdcore15,150 bytesSKILL.mdcore15,150 bytesSKILL.mdcore15,150 bytesSKILL.mdcore15,150 bytesSKILL.mdcore15,150 bytesSKILL.mdcore15,150 bytesSKILL.mdcore15,150 bytesSKILL.mdcore15,150 bytesSKILL.mdcore15,150 bytesSKILL.mdcore15,150 bytesSKILL.mdcore15,150 bytesreferences/framework_guides.mddoc11,748 bytesreferences/prioritization_algorithms.mddoc15,875 bytes
Read SKILL.md
# Test Suite Prioritizer
Intelligently prioritize test execution based on code changes and project impact.
## Core Capabilities
This skill helps optimize test execution by:
1. **Analyzing code changes** - Identifying which files were modified
2. **Mapping test coverage** - Determining which tests cover changed code
3. **Calculating priority scores** - Ranking tests by impact and relevance
4. **Generating execution order** - Creating an optimized test run sequence
5. **Providing reasoning** - Explaining why each test is prioritized
time-aware-dependency-cve-scanner
When your agent uses it
Scan repositories for newly disclosed CVEs in dependencies after a specific cutoff date. Takes a repository path, cutoff date (YYYY-MM-DD), and optional parameters for transitive dependencies. Parses dependency manifests (package.json, pom.xml, requirements.txt, go.mod, Cargo.toml) and lockfiles to extract exact versions. Queries vulnerability databases (OSV.dev, NVD, GitHub Advisory) to identify CVEs disclosed strictly after the cutoff date. Distinguishes between newly disclosed CVEs and previously known CVEs. Use when: (1) Performing security audits to find new vulnerabilities since last review, (2) Checking if new CVEs affect a historical codebase version, (3) Generating compliance reports showing vulnerability status at specific dates, (4) Tracking security posture changes over time. Supports npm, Maven, pip, Go modules, Cargo, and other major ecosystems.
What it loads into context
Frontmatter
190 tokensAlways available to the agent
SKILL.md
2,038 tokensWhen the skill is activated
Reference documents
3,515 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- Quick Start
- Workflow
- Use Cases
- Advanced Options
- Understanding Results
- Troubleshooting
- Dependencies
Scripts executed separately
scripts/parse_dependencies.pyscripts/query_cves.pyscripts/scan_repository.py
Files
SKILL.mdcore8,409 bytesSKILL.mdcore8,409 bytesSKILL.mdcore8,409 bytesSKILL.mdcore8,409 bytesSKILL.mdcore8,409 bytesSKILL.mdcore8,409 bytesSKILL.mdcore8,409 bytesSKILL.mdcore8,409 bytesSKILL.mdcore8,409 bytesSKILL.mdcore8,409 bytesSKILL.mdcore8,409 bytesSKILL.mdcore8,409 bytesSKILL.mdcore8,409 bytesreferences/dependency_formats.mddoc6,175 bytesreferences/vulnerability_databases.mddoc6,219 bytesscripts/parse_dependencies.pyruns9,687 bytesscripts/query_cves.pyruns9,193 bytesscripts/scan_repository.pyruns8,206 bytes
Read SKILL.md
# Time-Aware Dependency CVE Scanner
Scan repositories for newly disclosed CVEs affecting dependencies after a specific cutoff date. This skill helps track when vulnerabilities were introduced and distinguish between pre-existing and newly disclosed security issues.
## Quick Start
**Basic scan**:
```bash
python scripts/scan_repository.py /path/to/repo 2023-01-01
```
**Scan only direct dependencies**:
```bash
python scripts/scan_repository.py /path/to/repo 2023-01-01 --no-transitivetlaplus-guided-code-repair
When your agent uses it
Automatically repair C/C++ code violations detected by TLA+ model checking. Takes a program, TLA+ specification, and TLC counterexample trace as input, then generates minimal code modifications to eliminate the violation. Use when: (1) TLC model checker reports an invariant violation, deadlock, or temporal property failure, (2) You have a counterexample trace and need to fix the corresponding code, (3) You need to understand how a TLA+ violation maps to program-level bugs, (4) You want to validate repairs by re-running TLC. Supports safety properties (invariants), liveness properties (temporal logic), and deadlock detection.
What it loads into context
Frontmatter
147 tokensAlways available to the agent
SKILL.md
1,414 tokensWhen the skill is activated
Reference documents
3,205 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- Repair Workflow
- Quick Reference
Scripts executed separately
scripts/parse_tlc_trace.pyscripts/run_tlc.py
Files
SKILL.mdcore5,973 bytesSKILL.mdcore5,973 bytesSKILL.mdcore5,973 bytesSKILL.mdcore5,973 bytesreferences/repair_patterns.mddoc6,201 bytesreferences/tlaplus_to_cpp_mapping.mddoc6,797 bytesscripts/parse_tlc_trace.pyruns4,072 bytesscripts/run_tlc.pyruns3,945 bytes
Read SKILL.md
# TLA+ Guided Code Repair
Automatically repair C/C++ code based on TLA+ model checking violations. This skill analyzes TLC counterexamples, identifies root causes in the implementation, and generates semantically justified repairs.
## Repair Workflow
Follow this sequential process when given a TLA+ violation:
### 1. Parse the Counterexample
Use `scripts/parse_tlc_trace.py` to extract structured information from TLC output:
```bash
python scripts/parse_tlc_trace.py trace.txttlaplus-model-reduction
When your agent uses it
Automatically simplify and minimize TLA+ specifications by reducing redundant state variables, merging equivalent actions, and minimizing invariants while preserving specified properties. Use when working with TLA+ specifications that need optimization, simplification, or reduction. Triggers when users ask to minimize, reduce, simplify, or optimize TLA+ specs, or when they want to remove redundancy from formal specifications while maintaining semantic equivalence.
What it loads into context
Frontmatter
91 tokensAlways available to the agent
SKILL.md
1,301 tokensWhen the skill is activated
Reference documents
489 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- Overview
- Workflow
- Example Usage
- Important Notes
- References
Files
SKILL.mdcore6,296 bytesreferences/reduction_techniques.mddoc2,538 bytes
Read SKILL.md
# TLA+ Model Reduction (Spec Minimizer)
## Overview
This skill analyzes TLA+ specifications and produces minimized versions by eliminating redundancies while preserving all specified properties. The reduction process analyzes reachability, dependency relations, and property relevance to ensure semantic equivalence between the original and reduced specifications.
## Workflow
### Step 1: Input Analysis
Parse and understand the input TLA+ specification:
1. **Identify components**:
- State variables (VARIABLES declaration)tlaplus-spec-generator
When your agent uses it
Automatically generate TLA+ specifications from source code (C/C++, Python) for formal verification of distributed systems. Use when users need to: (1) Generate TLA+ specs from program implementations, (2) Model distributed systems, consensus protocols, or concurrent algorithms, (3) Extract state variables, actions, and invariants from code, (4) Create formal specifications for model checking with TLC, (5) Verify safety and liveness properties of distributed systems. Particularly effective for message-passing systems, replication protocols, consensus algorithms, and distributed transactions.
What it loads into context
Frontmatter
123 tokensAlways available to the agent
SKILL.md
2,176 tokensWhen the skill is activated
Reference documents
4,965 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- Overview
- Workflow
- Abstraction Levels
- Common Use Cases
- Advanced Options
- Refining Generated Specs
- Tips
- Common Issues
- References
- Scripts
- External Tools
Scripts executed separately
scripts/generate_spec.pyscripts/program_analyzer.pyscripts/tlaplus_generator.py
Files
SKILL.mdcore9,310 bytesSKILL.mdcore9,310 bytesSKILL.mdcore9,310 bytesSKILL.mdcore9,310 bytesSKILL.mdcore9,310 bytesSKILL.mdcore9,310 bytesSKILL.mdcore9,310 bytesSKILL.mdcore9,310 bytesSKILL.mdcore9,310 bytesSKILL.mdcore9,310 bytesreferences/distributed_patterns.mddoc9,367 bytesreferences/tlaplus_syntax.mddoc6,016 bytesscripts/generate_spec.pyruns3,597 bytesscripts/program_analyzer.pyruns8,465 bytesscripts/tlaplus_generator.pyruns11,871 bytes
Read SKILL.md
# TLA+ Spec Generator
Automatically generate TLA+ specifications from program implementations for formal verification of distributed systems.
## Overview
This skill transforms imperative programs (C/C++, Python) into declarative TLA+ specifications. It analyzes program structure to identify state variables, actions, and system behavior, then generates well-structured TLA+ modules suitable for model checking with TLC.
## Workflow
### 1. Analyze Source Code
Generate TLA+ specification from source files:
trace-collection-assistant
When your agent uses it
Collect, normalize, and structure execution traces from instrumented programs (strace, ltrace) into JSON format for downstream analysis. Use when working with system call traces, library call traces, or execution logs that need to be analyzed for debugging, test case reproduction, or verification. Supports parsing strace/ltrace output, filtering noise, extracting debug information, and preparing traces for bug analysis or reproduction workflows.
What it loads into context
Frontmatter
91 tokensAlways available to the agent
SKILL.md
1,240 tokensWhen the skill is activated
Reference documents
2,379 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- Overview
- Quick Start
- Core Operations
- Use Cases
- Reference Documentation
- Output Format
- Tips
Scripts executed separately
scripts/extract_debug_info.pyscripts/filter_trace.pyscripts/parse_ltrace.pyscripts/parse_strace.py
Files
SKILL.mdcore5,539 bytesSKILL.mdcore5,539 bytesSKILL.mdcore5,539 bytesSKILL.mdcore5,539 bytesSKILL.mdcore5,539 bytesSKILL.mdcore5,539 bytesSKILL.mdcore5,539 bytesSKILL.mdcore5,539 bytesSKILL.mdcore5,539 bytesassets/schema_template.jsonasset3,129 bytesreferences/analysis_guide.mddoc4,320 bytesreferences/json_schema.mddoc2,216 bytesreferences/trace_formats.mddoc2,587 bytesscripts/extract_debug_info.pyruns6,579 bytesscripts/filter_trace.pyruns4,020 bytesscripts/parse_ltrace.pyruns3,324 bytesscripts/parse_strace.pyruns3,390 bytes
Read SKILL.md
# Trace Collection Assistant
## Overview
This skill helps collect, normalize, and structure execution traces produced by instrumented programs (strace, ltrace), making them suitable for downstream analysis such as debugging, reproduction, or verification. It converts raw trace output into structured JSON format and provides tools for filtering, cleaning, and extracting relevant information.
## Quick Start
### Basic Workflow
1. **Parse raw traces** - Convert strace/ltrace output to JSON
2. **Filter and clean** - Remove noise and focus on relevant calls
3. **Extract debug info** - Identify errors, file operations, network activity
traceability-matrix-generator
When your agent uses it
Builds traceability matrices connecting requirements to design documents to source code implementation, tracking the complete development lifecycle. Use when you need to verify implementation completeness, ensure all requirements are implemented in code, generate compliance documentation, audit requirement coverage, identify orphaned code, or create traceability reports for stakeholders. Supports parsing requirements from Markdown, Word, and PDFs; extracting design from architecture docs and API specs; and scanning source code for implementations. Outputs to Markdown tables, Excel/CSV, and HTML visualizations.
What it loads into context
Frontmatter
122 tokensAlways available to the agent
SKILL.md
4,461 tokensWhen the skill is activated
Reference documents
5,703 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- What is a Traceability Matrix?
- Workflow
- Complete Example
- Tips
- Common Use Cases
- References
Files
SKILL.mdcore19,924 bytesSKILL.mdcore19,924 bytesSKILL.mdcore19,924 bytesSKILL.mdcore19,924 bytesSKILL.mdcore19,924 bytesSKILL.mdcore19,924 bytesSKILL.mdcore19,924 bytesSKILL.mdcore19,924 bytesSKILL.mdcore19,924 bytesSKILL.mdcore19,924 bytesSKILL.mdcore19,924 bytesSKILL.mdcore19,924 bytesSKILL.mdcore19,924 bytesSKILL.mdcore19,924 bytesSKILL.mdcore19,924 bytesSKILL.mdcore19,924 bytesSKILL.mdcore19,924 bytesSKILL.mdcore19,924 bytesreferences/code_scanning.mddoc13,493 bytesreferences/extraction_patterns.mddoc10,625 bytes
Read SKILL.md
# Traceability Matrix Generator
Build comprehensive traceability matrices linking requirements → design → implementation across the software development lifecycle.
## What is a Traceability Matrix?
A traceability matrix documents relationships between:
- **Requirements**: What the system must do (user stories, specs, features)
- **Design**: How the system will be structured (architecture, APIs, components)
- **Implementation**: Where requirements are coded (functions, classes, modules)
**Benefits:**
- Ensure all requirements are implemented
- Identify missing implementations or testsunit-test-generator
When your agent uses it
Automatically generates comprehensive unit tests for functions, classes, and modules. Use when you need to create tests for Python (pytest, unittest) or Java (JUnit, TestNG) code. Generates tests with comprehensive coverage including happy paths, edge cases, and error conditions. Analyzes existing test patterns in the codebase to match style and conventions. Supports mocking, parameterized tests, fixtures, and follows best practices for each framework.
What it loads into context
Frontmatter
94 tokensAlways available to the agent
SKILL.md
2,723 tokensWhen the skill is activated
Reference documents
8,671 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- Core Capabilities
- Test Generation Workflow
- Advanced Patterns
- Framework-Specific Guidance
- Best Practices
- Resources
- Quick Reference
Files
SKILL.mdcore11,452 bytesSKILL.mdcore11,452 bytesSKILL.mdcore11,452 bytesSKILL.mdcore11,452 bytesSKILL.mdcore11,452 bytesSKILL.mdcore11,452 bytesSKILL.mdcore11,452 bytesreferences/assertion_guide.mddoc12,900 bytesreferences/test_patterns.mddoc24,965 bytes
Read SKILL.md
# Unit Test Generator
Automatically generate comprehensive unit tests for your code.
## Core Capabilities
This skill helps you generate high-quality unit tests by:
1. **Analyzing source code** - Understanding function/class behavior and contracts
2. **Identifying test cases** - Determining happy paths, edge cases, and error conditions
3. **Matching style** - Following existing test patterns and conventions in your codebase
4. **Generating tests** - Creating complete, runnable test code
5. **Explaining coverage** - Documenting what each test validates
verification-boundary-reporter
When your agent uses it
Analyze formal verification artifacts (Isabelle, Coq, Dafny, etc.) and produce structured reports identifying the precise boundary between verified, assumed, and unverified components. Use when assessing verification coverage, understanding trust boundaries, auditing formal proofs, or documenting verification scope. Reports explicitly list verified code, assumptions, axioms, trusted computing base, and unverified components. Conservative and explicit about verification status without attempting to repair or mask gaps.
What it loads into context
Frontmatter
97 tokensAlways available to the agent
SKILL.md
2,929 tokensWhen the skill is activated
Reference documents
10,919 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- Overview
- Analysis Workflow
- Component Classification
- Analysis Process
- Report Structure
- Framework-Specific Analysis
- Common Patterns
- Example Analysis
- Best Practices
- Red Flags
- Reporting Principles
- Additional Resources
Files
SKILL.mdcore13,101 bytesreferences/boundary_patterns.mddoc10,830 bytesreferences/coq_analysis.mddoc10,909 bytesreferences/dafny_analysis.mddoc10,825 bytesreferences/isabelle_analysis.mddoc9,795 bytes
Read SKILL.md
# Verification Boundary Reporter
Analyze formal verification artifacts and produce clear reports on what is verified, what is assumed, and what remains unverified.
## Overview
When working with formally verified code, it's critical to understand exactly what guarantees the verification provides and where the boundaries lie. This skill analyzes verification artifacts and produces structured reports that:
1. **Identify verified components** - Code with completed proofs
2. **List assumptions and axioms** - What is taken on trust
3. **Document the trusted computing base (TCB)** - External dependencies
4. **Highlight unverified components** - Gaps in verification coverage
5. **Explain verification limitations** - Why certain parts aren't verified
verified-pseudocode-extractor
When your agent uses it
Extract language-agnostic pseudocode from formally verified programs (Isabelle/HOL, Coq) while preserving verified control flow, data dependencies, and algorithmic logic. Use when: (1) Users have verified code and need readable pseudocode, (2) Documenting verified algorithms for broader audiences, (3) Translating verified implementations to other languages, (4) Creating algorithm specifications from verified code, (5) Preserving verification guarantees in pseudocode form, or (6) Abstracting proof-heavy code to essential logic. Maintains semantic faithfulness to verified implementation.
What it loads into context
Frontmatter
128 tokensAlways available to the agent
SKILL.md
1,997 tokensWhen the skill is activated
Reference documents
5,160 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- Core Principles
- Workflow
- Extraction Patterns
- Verification Annotations
- What to Preserve vs. Remove
- Output Format
- Quality Checks
- Examples
- Tips
Files
SKILL.mdcore8,335 bytesSKILL.mdcore8,335 bytesreferences/examples.mddoc12,275 bytesreferences/extraction_patterns.mddoc7,697 bytes
Read SKILL.md
# Verified Pseudocode Extractor
Extract language-agnostic pseudocode from formally verified programs while preserving verified properties and algorithmic structure.
## Core Principles
### Semantic Faithfulness
- Preserve exact control flow from verified code
- Maintain all data dependencies
- Keep algorithmic logic intact
- Do not introduce new behavior
- Do not omit verified steps
### Verification Preservationverified-spec-code-mapper
When your agent uses it
Establish explicit traceability between formal specifications (preconditions, postconditions, invariants) and verified code components with their correctness proofs. Produce structured Markdown mapping reports showing verification coverage and proof evidence. Use when auditing formal verification, documenting verified systems, establishing traceability for certification, or when the user asks to map specifications to code, generate verification reports, or analyze verification coverage in Coq, Dafny, Isabelle, or other proof assistants.
What it loads into context
Frontmatter
97 tokensAlways available to the agent
SKILL.md
3,505 tokensWhen the skill is activated
Reference documents
4,136 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- Overview
- Mapping Workflow
- Mapping Patterns
- Examples
- Specifications
- Verification Evidence
- Coverage Summary
- Specifications
- Verification Evidence
- Assumptions
- Coverage Summary
- Constraints and Requirements
- Best Practices
- Report Format Guidelines
- Resources
Files
SKILL.mdcore14,189 bytesreferences/mapping_patterns.mddoc15,102 bytes
Read SKILL.md
# Verified Spec-Code Mapper
## Overview
Establish explicit, evidence-based traceability between formal specifications and verified code components. Generate structured reports that map each specification to its implementation and correctness proofs, supporting verification auditing, documentation, and reproducibility.
## Mapping Workflow
### Step 1: Identify Specifications
Locate all formal specifications in the codebase:
1. **Preconditions:**
- Coq: `forall ... -> P -> ...` (hypothesis before conclusion)vulnerability-pattern-matcher
When your agent uses it
Detects security vulnerabilities by matching code against known vulnerability patterns, insecure coding idioms, and CVE-style patterns. Explains why patterns are risky and under what conditions they are exploitable. Use when analyzing code for security issues, reviewing for common vulnerabilities, or assessing exploitability of suspicious code patterns.
What it loads into context
Frontmatter
69 tokensAlways available to the agent
SKILL.md
2,396 tokensWhen the skill is activated
Reference documents
4,265 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- Overview
- Detection Workflow
- Detection Examples
- Confidence Levels
- Constraints
- Report Format
- Resources
Files
SKILL.mdcore11,070 bytesSKILL.mdcore11,070 bytesSKILL.mdcore11,070 bytesSKILL.mdcore11,070 bytesSKILL.mdcore11,070 bytesSKILL.mdcore11,070 bytesSKILL.mdcore11,070 bytesSKILL.mdcore11,070 bytesSKILL.mdcore11,070 bytesreferences/api_reference.mddoc980 bytesreferences/vulnerability_patterns.mddoc17,382 bytes
Read SKILL.md
# Vulnerability Pattern Matcher
## Overview
This skill detects security vulnerabilities by matching code against a comprehensive database of known vulnerability patterns, insecure coding idioms, and historical CVE-style patterns. It identifies risky code, explains why each pattern is dangerous, assesses exploitability conditions, and provides severity ratings with confidence levels.
## Detection Workflow
Follow these steps to detect and assess vulnerabilities:
### 1. Analyze Code Structure
**Identify key security-relevant elements:**
- User input sources (request parameters, form data, file uploads)vulnerability-root-cause-analyzer
When your agent uses it
Analyze vulnerable code to identify underlying root causes such as violated assumptions, incorrect invariants, missing validation checks, or unsafe component interactions. Use when investigating security vulnerabilities, CVEs, exploit code, or security audit findings. Infers why the vulnerability exists beyond surface symptoms, identifies systemic issues, and explains the chain of failures that enable exploitation.
What it loads into context
Frontmatter
78 tokensAlways available to the agent
SKILL.md
2,718 tokensWhen the skill is activated
Reference documents
3,447 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- Overview
- Root Cause Analysis Workflow
- Analysis Process
- Root Cause Categories
- Vulnerability Patterns
- Example Analysis
- Invariant Violations
- Missing Checks
- Component Interaction Analysis
- Exploitation Chain
- Systemic Issues
- Recommended Fixes
- Prevention Strategies
- Related Vulnerabilities
- Additional Resources
Files
SKILL.mdcore12,505 bytesSKILL.mdcore12,505 bytesreferences/analysis_strategies.mddoc6,693 bytesreferences/root_causes.mddoc3,743 bytesreferences/vulnerability_patterns.mddoc5,198 bytes
Read SKILL.md
# Vulnerability Root Cause Analyzer
Analyze vulnerable code to identify the underlying root causes that enable security vulnerabilities.
## Overview
Security vulnerabilities are symptoms of deeper issues in code design and implementation. This skill analyzes vulnerable code to identify:
1. **Violated assumptions** - What the code assumes but doesn't verify
2. **Incorrect invariants** - Properties that should hold but don't
3. **Missing checks** - Validation that should exist but is absent
4. **Unsafe interactions** - How components interact unsafely
5. **Design flaws** - Architectural issues that enable vulnerabilities
Skills included
- abstract-domain-explorer
- abstract-invariant-generator
- abstract-state-analyzer
- abstract-trace-summarizer
- acsl-annotation-assistant
- agent-browser
- ambiguity-detector
- api-design-assistant
- api-documentation-generator
- assertion-synthesizer
- behavior-preservation-checker
- behavioral-mutation-analyzer
- bisect-aware-instrumentation
- bug-history-summarizer
- bug-localization
- bug-reproduction-test-generator
- bug-to-patch-generator
- build-ci-migration-assistant
- c-cpp-to-lean4-translator
- cd-pipeline-generator
- change-log-generator
- ci-pipeline-synthesizer
- code-change-summarizer
- code-comment-generator
- code-completion-semantic-constraints
- code-instrumentation-generator
- code-optimizer
- code-pattern-extractor
- code-refactoring-assistant
- code-repair-generation-combo
- code-review-assistant
- code-search-assistant
- code-smell-detector
- code-summarizer
- code-translation
- component-boundary-identifier
- config-consistency-checker
- configuration-generator
- conflict-analyzer
- containerization-assistant
- control-flow-abstraction-generator
- counterexample-debugger
- counterexample-explainer
- counterexample-generator
- counterexample-to-test-generator
- coverage-enhancer
- cpp-to-dafny-translator
- critical-interval-security-checker
- cve-reachability-analyzer
- cve-watchlist-action-recommendation-generator
- dead-code-eliminator
- dead-code-removal
- dependency-resolver
- deprecated-api-updater
- design-pattern-suggestor
- design-smell-detector
- directed-test-input-generator
- edge-case-generator
- environment-setup-assistant
- error-explanation-generator
- exploitability-analyzer
- failure-oriented-instrumentation
- flaky-test-detector
- formal-spec-generator
- framework-migration-assistant
- frontend-ui-ux
- function-class-generator
- fuzzing-input-generator
- git-bisect-assistant
- git-master
- github-triage
- imperative-to-coq-model-extractor
- incremental-java-programmer
- incremental-python-programmer
- init-deep
- integration-test-generator
- interface-contract-verifier
- interface-specification-generator
- interval-difference-analyzer
- interval-guided-regression-test-update
- interval-profiling-performance-analyzer
- invariant-inference
- issue-report-generator
- java-api-consistency-validator
- java-regression-test-generator
- java-test-updater
- legacy-code-summarizer
- lemma-discovery-assistant
- library-advisor
- lsp-refactoring
- markdown-document-structurer
- metamorphic-property-extractor
- metamorphic-test-generator
- mocking-test-generator
- model-guided-code-repair
- modular-code-enforcement
- module-component-generator
- module-level-code-translator
- multi-version-behavior-comparator
- mutation-test-suite-optimizer
- nl-to-constraints
- playwright-automation
- program-correctness-prover
- program-to-model-extractor
- program-to-tlaplus-spec-generator
- proof-carrying-code-generator
- proof-failure-explainer
- proof-refactoring-assistant
- proof-skeleton-generator
- proof-trace-summarizer
- pseudocode-extractor
- pseudocode-to-java-code
- pseudocode-to-python-code
- python-api-consistency-validator
- python-regression-test-generator
- python-repo-quickstart
- python-test-updater
- python-to-dafny-translator
- python-to-lean4-translator
- readme-generator
- reference-searcher
- refinement-step-generator
- regression-consistency-checker
- regression-root-cause-analyzer
- release-change-analyzer
- release-notes-writer
- replay-oriented-instrumentation
- reproduction-trace-instrumenter
- req-to-test
- requirement-comparison-reporter
- requirement-coverage-checker
- requirement-enhancer
- requirement-summarizer
- requirement-summary
- requirement-to-tlaplus-property-generator
- rollback-strategy-advisor
- rtl-equivalence-checker
- rtl-property-inference
- rtl-specification-consistency-checker
- runtime-error-explainer
- scenario-generator
- security-patch-advisor
- security-sensitive-path-instrumenter
- semantic-bug-detector
- semantic-equivalence-verifier
- semantic-szz-analyzer
- session-handoff
- skill-creator
- smart-mutation-operator-generator
- smv-model-extractor
- specification-driven-generation
- specification-generator
- specification-to-temporal-logic-generator
- spring-mvc-to-boot-migrator
- state-snapshot-instrumenter
- static-bug-detector
- static-reasoning-verifier
- static-vulnerability-detector
- strategic-planner
- symbolic-execution-assistant
- system-diagram-generator
- szz-bug-introducing-commit-identifier
- tactic-suggestion-assistant
- taint-instrumentation-assistant
- technical-debt-analyzer
- template-code-generator
- test-case-documentation
- test-case-reducer
- test-deduplicator
- test-driven-generation
- test-guided-bug-detector
- test-guided-debloating
- test-guided-migration-assistant
- test-oracle-generator
- test-suite-prioritizer
- time-aware-dependency-cve-scanner
- tlaplus-guided-code-repair
- tlaplus-model-reduction
- tlaplus-spec-generator
- trace-collection-assistant
- traceability-matrix-generator
- unit-test-generator
- verification-boundary-reporter
- verified-pseudocode-extractor
- verified-spec-code-mapper
- vulnerability-pattern-matcher
- vulnerability-root-cause-analyzer
Repository facts
- License
- Apache-2.0
- Created
- Feb 14, 2026
- Last pushed
- Aug 21, 2026
- Forks
- 26
- Open issues
- 0
- Project activity
- Slowing
Before you install
Network or broad shellAutomated signals, not a guarantee
Checked Nov 6, 2026
Not fully analyzed: some files were too long, unreadable or missing. This never lowers the level.
Show 1,482 notes
skills/abstract-invariant-generator/SKILL.md:1Analysis incomplete: Referenced executable target unavailable; not analyzedskills/abstract-invariant-generator/SKILL.md:1Analysis incomplete: Referenced executable target unavailable; not analyzedskills/abstract-invariant-generator/SKILL.md:1Analysis incomplete: Referenced executable target unavailable; not analyzedskills/abstract-invariant-generator/SKILL.md:1Analysis incomplete: Referenced executable target unavailable; not analyzedskills/abstract-invariant-generator/SKILL.md:1Analysis incomplete: Referenced executable target unavailable; not analyzedskills/abstract-invariant-generator/SKILL.md:1Analysis incomplete: Referenced executable target unavailable; not analyzedskills/abstract-invariant-generator/SKILL.md:1Analysis incomplete: Referenced executable target unavailable; not analyzedskills/abstract-invariant-generator/SKILL.md:1Analysis incomplete: Referenced executable target unavailable; not analyzedskills/abstract-invariant-generator/SKILL.md:1Analysis incomplete: Referenced executable target unavailable; not analyzedskills/abstract-invariant-generator/SKILL.md:1Analysis incomplete: Referenced executable target unavailable; not analyzedskills/abstract-invariant-generator/SKILL.md:1Analysis incomplete: Referenced executable target unavailable; not analyzedskills/abstract-invariant-generator/SKILL.md:1Analysis incomplete: Referenced executable target unavailable; not analyzedskills/abstract-invariant-generator/SKILL.md:1Analysis incomplete: Referenced executable target unavailable; not analyzedskills/abstract-invariant-generator/SKILL.md:1Analysis incomplete: Referenced executable target unavailable; not analyzedskills/abstract-invariant-generator/SKILL.md:1Analysis incomplete: Referenced executable target unavailable; not analyzedskills/abstract-invariant-generator/SKILL.md:1Analysis incomplete: Referenced executable target unavailable; not analyzedskills/abstract-invariant-generator/SKILL.md:1Analysis incomplete: Referenced executable target unavailable; not analyzedskills/abstract-invariant-generator/SKILL.md:1Analysis incomplete: Referenced executable target unavailable; not analyzedskills/abstract-invariant-generator/SKILL.md:1Analysis incomplete: Referenced executable target unavailable; not analyzedskills/abstract-invariant-generator/SKILL.md:1Analysis incomplete: Referenced executable target unavailable; not analyzed
- No broad tool permissions
- 140 dangerous shell commandsin 39 files: environment-setup-assistant/references/tool_guides.md:22 environment-setup-assistant/references/platform_instructions.md:21 environment-setup-assistant/scripts/setup_docker.sh:40 and 36 more
- 662 network referencesin 109 files: linkedin/SKILL.md:22 environment-setup-assistant/references/platform_instructions.md:21 environment-setup-assistant/references/tool_guides.md:22 and 106 more
- 3 obfuscation signalsin 2 files: fuzzing-input-generator/references/fuzzing-patterns.md:375 critical-interval-security-checker/references/vulnerability_patterns.md:188
- No instruction overrides
- 111 executable scriptsin 111 files: behavior-preservation-checker/scripts/behavior_checker.py:1 behavior-preservation-checker/scripts/compare_test_results.py:1 behavior-preservation-checker/scripts/compare_traces.py:1 and 108 more
- 88 references to secretsin 41 files: code-comment-generator/references/comment_examples.md:152 readme-generator/SKILL.md:129 code-translation/references/project_migration.md:354 and 38 more
- No requests to vote in Hot
Show all 1,004 signals by file
skills/agent-browser/SKILL.md
- Access to secretsline 143
[Credential-related source omitted] - Access to secretsline 144
[Credential-related source omitted] - Access to secretsline 145
[Credential-related source omitted] - Dangerous shell operationline 182
agent-browser eval "document.title" # Run JavaScript - Network accessline 199
agent-browser open https://example.com/form - Network accessline 213
# Login once agent-browser open https://app.example.com/login - Network accessline 214
agent-browser open https://app.example.com/login - Network accessline 222
# Later sessions: load saved state agent-browser state load auth.json agent-browser open https://app.example.com/dashboard - Network accessline 224
agent-browser open https://app.example.com/dashboard - Network accessline 264
# Verify agent-browser open https://example.com --headed - Network accessline 265
agent-browser open https://example.com --headed - Network accessline 268
Run `agent-browser --help` for all commands. Repo: https://github.com/vercel-labs/agent-browser - Network accessline 270
**Inspired by:** [oh-my-opencode](https://github.com/code-yeongyu/oh-my-opencode) agent-browser skill
skills/ambiguity-detector/references/ambiguity_patterns.md
- Network accessline 315
[Credential-related source omitted]
skills/api-design-assistant/references/openapi-template.md
- Network accessline 17
servers: - url: https://api.example.com/v1 - Network accessline 18
- url: https://api.example.com/v1 - Network accessline 19
description: Production server - url: https://staging-api.example.com/v1 description: Staging server - Network accessline 20
- url: https://staging-api.example.com/v1 - Network accessline 435
flows: authorizationCode: authorizationUrl: https://example.com/oauth/authorize - Network accessline 436
authorizationCode: authorizationUrl: https://example.com/oauth/authorize tokenUrl: https://example.com/oauth/token - Network accessline 437
authorizationUrl: https://example.com/oauth/authorize - Network accessline 438
tokenUrl: https://example.com/oauth/token - Network accessline 453
servers: - url: https://api.example.com/v1 - Network accessline 454
- url: https://api.example.com/v1
skills/api-documentation-generator/SKILL.md
- Network accessline 151
## Base URL https://api.example.com/v1 - Network accessline 152
https://api.example.com/v1 - Network accessline 250
curl -X POST "https://api.example.com/v1/users" \ - Network accessline 262
response = requests.post( - Network accessline 263
"https://api.example.com/v1/users", - Network accessline 350
curl -X POST "https://api.example.com/v1/users" \ - Network accessline 359
# Create user response = requests.post( - Network accessline 360
response = requests.post( - Network accessline 361
"https://api.example.com/v1/users", - Network accessline 372
# Get user details response = requests.get( - Network accessline 373
response = requests.get( - Network accessline 374
f"https://api.example.com/v1/users/{user_id}", - Network accessline 447
7. Create schemas.md with all data models 8. Create errors.md with error codes 9. Add code examples in curl and Python - Network accessline 449
9. Add code examples in curl and Python
skills/api-documentation-generator/assets/api-doc-template.md
- Network accessline 10
https://api.example.com/v1 - Network accessline 71
curl -X GET "https://api.example.com/v1/resource?page=1&limit=20" \ - Network accessline 142
curl -X POST "https://api.example.com/v1/resource" \ - Network accessline 381
curl -X POST "https://api.example.com/v1/resource" \ - Network accessline 404
curl -X GET "https://api.example.com/v1/resource/456" \
skills/behavior-preservation-checker/SKILL.md
- Network accessline 120
# Test API endpoints python scripts/compare_api_outputs.py \ --original-url http://localhost:8000 \ - Network accessline 121
python scripts/compare_api_outputs.py --original-url http://localhost:8000 - Network accessline 122
--original-url http://localhost:8000 \ - Network accessline 123
--migrated-url http://localhost:8001 \
skills/behavior-preservation-checker/references/comparison_techniques.md
skills/behavior-preservation-checker/references/difference_patterns.md
skills/behavior-preservation-checker/scripts/behavior_checker.py
- Executable scriptline 1
#!/usr/bin/env python3
skills/behavior-preservation-checker/scripts/compare_test_results.py
- Executable scriptline 1
#!/usr/bin/env python3
skills/behavior-preservation-checker/scripts/compare_traces.py
- Executable scriptline 1
#!/usr/bin/env python3
skills/behavior-preservation-checker/scripts/trace_execution.py
- Executable scriptline 1
#!/usr/bin/env python3
skills/bisect-aware-instrumentation/SKILL.md
- Dangerous shell operationline 89
rm -rf /tmp/test_cache
skills/bisect-aware-instrumentation/references/git_bisect_guide.md
- Dangerous shell operationline 296
rm -rf /tmp/cache - Access to secretsline 351
[Credential-related source omitted] - Network accessline 421
- Git bisect documentation: https://git-scm.com/docs/git-bisect - Network accessline 422
- Pro Git book chapter: https://git-scm.com/book/en/v2/Git-Tools-Debugging-with-Git - Network accessline 423
- Git bisect examples: https://github.com/git/git/tree/master/contrib/examples
skills/bisect-aware-instrumentation/scripts/bisect_template.sh
skills/bisect-aware-instrumentation/scripts/bisect_wrapper.py
- Executable scriptline 1
#!/usr/bin/env python3
skills/build-ci-migration-assistant/references/build-systems.md
- Network accessline 59
<repository> <id>central</id> <url>https://repo.maven.apache.org/maven2</url> - Network accessline 60
<id>central</id> <url>https://repo.maven.apache.org/maven2</url> </repository> - Network accessline 61
<url>https://repo.maven.apache.org/maven2</url> - Dangerous shell operationline 191
rm -f $(OBJS) $(TARGET)
skills/build-ci-migration-assistant/references/ci-platforms.md
skills/c-cpp-to-lean4-translator/SKILL.md
- Network accessline 439
- **Translation patterns:** See [translation_patterns.md](references/translation_patterns.md) for comprehensive pattern catalog - **Lean4 documentation:** https://lean-lang.org/documentation/ - Network accessline 440
- **Lean4 documentation:** https://lean-lang.org/documentation/ - Network accessline 441
- **Lean4 standard library:** https://github.com/leanprover/lean4/tree/master/src/Init
skills/cd-pipeline-generator/SKILL.md
skills/change-log-generator/SKILL.md
- Network accessline 265
The format is based on [Keep a Changelog](https://keepachangelog.com/), - Network accessline 266
and this project adheres to [Semantic Versioning](https://semver.org/). - Network accessline 446
[Full Changelog](https://github.com/user/repo/compare/v1.2.0...v1.3.0) - Network accessline 557
[Full Changelog](https://github.com/user/repo/compare/v1.2.0...v1.3.0) - Network accessline 587
The format is based on [Keep a Changelog](https://keepachangelog.com/), - Network accessline 588
and this project adheres to [Semantic Versioning](https://semver.org/). - Network accessline 598
[Full Changelog](https://github.com/user/repo/compare/v1.2.0...v1.3.0) | [Release Notes](link) - Dangerous shell operationline 722
rm "$file"
skills/ci-pipeline-synthesizer/SKILL.md
- Network accessline 114
- Use `actions/cache` for dependencies to reduce build times - Keep matrix versions current with language support policies - Add status badges to README.md: `` - Network accessline 116
- Add status badges to README.md: ``
skills/code-comment-generator/references/comment_examples.md
- Access to secretsline 152
[Credential-related source omitted] - Access to secretsline 158
[Credential-related source omitted] - Access to secretsline 164
[Credential-related source omitted] - Access to secretsline 169
[Credential-related source omitted] - Network accessline 171
[Credential-related source omitted] - Network accessline 172
[Credential-related source omitted] - Access to secretsline 172
[Credential-related source omitted] - Network accessline 173
self.base_url = "https://api.payment-provider.com/v1" - Access to secretsline 250
[Credential-related source omitted] - Network accessline 254
response = requests.request( - Access to secretsline 709
[Credential-related source omitted] - Access to secretsline 712
[Credential-related source omitted] - Access to secretsline 716
[Credential-related source omitted] - Access to secretsline 726
[Credential-related source omitted] - Access to secretsline 730
[Credential-related source omitted] - Access to secretsline 733
[Credential-related source omitted]
skills/code-comment-generator/references/style_guides.md
- Network accessline 398
* @see UserValidator#validate(String) * @see #processInternal(User) * @see <a href="https://docs.example.com/api">API Documentation</a> - Network accessline 399
* @see #processInternal(User) * @see <a href="https://docs.example.com/api">API Documentation</a> */ - Network accessline 400
* @see <a href="https://docs.example.com/api">API Documentation</a>
skills/code-pattern-extractor/SKILL.md
skills/code-search-assistant/SKILL.md
- Network accessline 63
// Input snippet calls: fetch(), JSON.parse(), setState() - Network accessline 64
// High match: Code that calls fetch() → JSON.parse() → setState() - Network accessline 65
// Medium match: Code that calls fetch() and setState() in different order - Network accessline 66
// Low match: Code that only calls fetch() - Network accessline 201
async function fetchUserData(userId) { try { const response = await fetch(`/api/users/${userId}`); - Network accessline 202
try { const response = await fetch(`/api/users/${userId}`); const data = await response.json(); - Network accessline 203
const response = await fetch(`/api/users/${userId}`); - Network accessline 213
**Search process**: 1. Call chain: Search for `fetch()`, `response.json()`, `console.error()` - Network accessline 214
1. Call chain: Search for `fetch()`, `response.json()`, `console.error()`
skills/code-smell-detector/SKILL.md
skills/code-smell-detector/scripts/detect_smells.py
- Executable scriptline 1
#!/usr/bin/env python3
skills/code-translation/SKILL.md
- Network accessline 89
async function fetchUserData(userId) { try { const response = await fetch(`/api/users/${userId}`); - Network accessline 90
try { const response = await fetch(`/api/users/${userId}`); if (!response.ok) { - Network accessline 91
const response = await fetch(`/api/users/${userId}`); - Network accessline 109
"""Fetch user data from API.""" try: async with aiohttp.ClientSession() as session: - Network accessline 110
try: async with aiohttp.ClientSession() as session: async with session.get(f'/api/users/{user_id}') as response: - Network accessline 111
async with aiohttp.ClientSession() as session: - Network accessline 239
# Python async def fetch_all(urls): tasks = [fetch(url) for url in urls] - Network accessline 240
async def fetch_all(urls): tasks = [fetch(url) for url in urls] return await asyncio.gather(*tasks) - Network accessline 241
tasks = [fetch(url) for url in urls] - Network accessline 245
// JavaScript async function fetchAll(urls) { const promises = urls.map(url => fetch(url)); - Network accessline 246
async function fetchAll(urls) { const promises = urls.map(url => fetch(url)); return await Promise.all(promises); - Network accessline 247
const promises = urls.map(url => fetch(url)); - Network accessline 378
# Python using requests import requests response = requests.get(url) - Network accessline 379
import requests response = requests.get(url) data = response.json() - Network accessline 380
response = requests.get(url) - Network accessline 384
// JavaScript using fetch const response = await fetch(url); - Network accessline 385
const response = await fetch(url);
skills/code-translation/references/idiomatic_guide.md
- Network accessline 171
// Idiomatic: fetch API const data = await fetch(url).then(res => res.json()); - Network accessline 172
const data = await fetch(url).then(res => res.json()); - Network accessline 276
async function fetchUserData(id) { try { const user = await fetch(`/api/users/${id}`).then(r => r.json()); - Network accessline 277
try { const user = await fetch(`/api/users/${id}`).then(r => r.json()); return user; - Network accessline 278
const user = await fetch(`/api/users/${id}`).then(r => r.json()); - Network accessline 286
// Not idiomatic function fetchUserData(id, callback) { fetch(`/api/users/${id}`) - Network accessline 287
function fetchUserData(id, callback) { fetch(`/api/users/${id}`) .then(r => r.json()) - Network accessline 288
fetch(`/api/users/${id}`)
skills/code-translation/references/project_migration.md
- Access to secretsline 354
[Credential-related source omitted] - Access to secretsline 356
[Credential-related source omitted] - Access to secretsline 369
[Credential-related source omitted] - Access to secretsline 383
[Credential-related source omitted] - Network accessline 502
# Python async def fetch_all(urls): tasks = [fetch(url) for url in urls] - Network accessline 503
async def fetch_all(urls): tasks = [fetch(url) for url in urls] return await asyncio.gather(*tasks) - Network accessline 504
tasks = [fetch(url) for url in urls] - Network accessline 516
go func(idx int, u string) { defer wg.Done() results[idx] = fetch(u) - Network accessline 517
defer wg.Done() results[idx] = fetch(u) }(i, url) - Network accessline 518
results[idx] = fetch(u)
skills/component-boundary-identifier/scripts/analyze_boundaries.py
- Executable scriptline 1
#!/usr/bin/env python3
skills/config-consistency-checker/SKILL.md
- Access to secretsline 110
[Credential-related source omitted]
skills/configuration-generator/SKILL.md
- Access to secretsline 297
[Credential-related source omitted] - Access to secretsline 322
[Credential-related source omitted] - Network accessline 435
web: healthcheck: test: ["CMD", "curl", "-f", "http://localhost:8000/health"] - Network accessline 436
healthcheck: test: ["CMD", "curl", "-f", "http://localhost:8000/health"] interval: 30s - Network accessline 437
test: ["CMD", "curl", "-f", "http://localhost:8000/health"]
skills/configuration-generator/assets/docker-compose.yml
- Access to secretsline 14
[Credential-related source omitted]
skills/configuration-generator/references/app_configs.md
- Network accessline 79
[[source]] url = "https://pypi.org/simple" - Network accessline 80
url = "https://pypi.org/simple" - Network accessline 221
proxy: { '/api': { target: 'http://localhost:8000', - Network accessline 222
'/api': { target: 'http://localhost:8000', changeOrigin: true, - Network accessline 223
target: 'http://localhost:8000', - Network accessline 436
# Security CORS_ORIGINS=http://localhost:3000,http://localhost:8080 - Network accessline 437
CORS_ORIGINS=http://localhost:3000,http://localhost:8080 - Access to secretsline 486
[Credential-related source omitted]
skills/configuration-generator/references/infra_configs.md
- Access to secretsline 101
[Credential-related source omitted] - Network accessline 480
script: - apk add --no-cache curl - curl -LO "https://dl.k8s.io/release/$(curl -L -s https://dl.k8s.io/release/stable.txt)/bin/linux/amd64/kubectl" - Network accessline 481
- apk add --no-cache curl - curl -LO "https://dl.k8s.io/release/$(curl -L -s https://dl.k8s.io/release/stable.txt)/bin/linux/amd64/kubectl" - chmod +x kubectl - Network accessline 482
- curl -LO "https://dl.k8s.io/release/$(curl -L -s https://dl.k8s.io/release/stable.txt)/bin/linux/amd64/kubectl" - Network accessline 485
environment: name: production url: https://myapp.example.com - Network accessline 487
url: https://myapp.example.com - Network accessline 614
# Redirect HTTP to HTTPS return 301 https://$server_name$request_uri; - Network accessline 615
return 301 https://$server_name$request_uri; - Network accessline 632
location / { proxy_pass http://backend; - Network accessline 633
proxy_pass http://backend; - Network accessline 640
location /api/ { limit_req zone=api_limit burst=20 nodelay; proxy_pass http://backend; - Network accessline 641
limit_req zone=api_limit burst=20 nodelay; proxy_pass http://backend; proxy_set_header Host $host; - Network accessline 642
proxy_pass http://backend; - Network accessline 659
<VirtualHost *:80> ServerName myapp.example.com Redirect permanent / https://myapp.example.com/ - Network accessline 660
ServerName myapp.example.com Redirect permanent / https://myapp.example.com/ </VirtualHost> - Network accessline 661
Redirect permanent / https://myapp.example.com/ - Network accessline 676
# Proxy to backend ProxyPass / http://localhost:8000/ - Network accessline 677
ProxyPass / http://localhost:8000/ - Network accessline 678
ProxyPassReverse / http://localhost:8000/
skills/containerization-assistant/SKILL.md
skills/containerization-assistant/assets/.env.example
- Access to secretsline 17
[Credential-related source omitted]
skills/containerization-assistant/assets/Dockerfile.go
- Executable scriptline 1
Executable file
skills/containerization-assistant/assets/Dockerfile.python
- Dangerous shell operationline 11
&& rm -rf /var/lib/apt/lists/*
skills/containerization-assistant/references/dockerfile_best_practices.md
- Access to secretsline 78
[Credential-related source omitted] - Dangerous shell operationline 96
RUN apt-get update && apt-get install -y package && apt-get clean && rm -rf /var/lib/apt/lists/* - Dangerous shell operationline 99
rm -rf /var/lib/apt/lists/* - Network accessline 111
HEALTHCHECK --interval=30s --timeout=3s --start-period=40s --retries=3 \ CMD curl -f http://localhost:3000/health || exit 1 - Network accessline 112
CMD curl -f http://localhost:3000/health || exit 1
skills/containerization-assistant/references/kubernetes_patterns.md
skills/counterexample-to-test-generator/assets/test_templates/python_pytest_template.py
- Executable scriptline 1
Executable file
skills/critical-interval-security-checker/references/vulnerability_patterns.md
- Possible obfuscationline 188
const decoded = JSON.parse(atob(token.split('.')[1]));
skills/critical-interval-security-checker/scripts/check_intervals.py
skills/cve-reachability-analyzer/SKILL.md
- Dangerous shell operationline 112
- Search for `eval()`, `exec()`, `Function()` constructor
skills/cve-reachability-analyzer/references/language_guide.md
- Access to secretsline 31
[Credential-related source omitted] - Dangerous shell operationline 66
- Check for `eval()`, `Function()` constructor - Dangerous shell operationline 172
- Check for `send()`, `public_send()`, `method()`, `eval()` - Dangerous shell operationline 238
- Look for `eval()`, `create_function()`
skills/cve-reachability-analyzer/references/reachability_patterns.md
- Access to secretsline 88
[Credential-related source omitted]
skills/cve-watchlist-action-recommendation-generator/SKILL.md
skills/cve-watchlist-action-recommendation-generator/scripts/calculate_risk_score.py
- Executable scriptline 1
#!/usr/bin/env python3
skills/cve-watchlist-action-recommendation-generator/scripts/parse_scan_results.py
- Executable scriptline 1
#!/usr/bin/env python3
skills/dead-code-eliminator/scripts/find_unused_functions.py
- Executable scriptline 1
#!/usr/bin/env python3
skills/dead-code-eliminator/scripts/find_unused_imports.py
- Executable scriptline 1
#!/usr/bin/env python3
skills/dead-code-removal/SKILL.md
- Network accessline 195
**Inspired by:** [oh-my-opencode](https://github.com/code-yeongyu/oh-my-opencode) remove-deadcode command
skills/dependency-resolver/SKILL.md
- Network accessline 241
Dependency of: express Path: express > lodash More info: https://npmjs.com/advisories/1065 - Network accessline 243
More info: https://npmjs.com/advisories/1065 - Dangerous shell operationline 705
rm -rf node_modules - Dangerous shell operationline 735
rm package-lock.json - Network accessline 755
# Try different registry npm config set registry https://registry.npmjs.org/ - Network accessline 756
npm config set registry https://registry.npmjs.org/ - Dangerous shell operationline 779
sudo apt-get install build-essential python3
skills/deprecated-api-updater/SKILL.md
- Dangerous shell operationline 184
find . -name "*.bak" -delete
skills/deprecated-api-updater/references/javascript_deprecations.md
- Network accessline 23
// ❌ Deprecated const url = require('url'); const parsed = url.parse('https://example.com/path?query=1'); - Network accessline 25
const parsed = url.parse('https://example.com/path?query=1'); - Network accessline 27
// ✅ Modern const parsed = new URL('https://example.com/path?query=1'); - Network accessline 28
const parsed = new URL('https://example.com/path?query=1'); - Network accessline 370
document.querySelector('.element').classList.add('active'); document.querySelector('.element').addEventListener('click', handler); fetch('/api/data'); - Network accessline 372
fetch('/api/data');
skills/deprecated-api-updater/references/python_deprecations.md
- Network accessline 272
# ❌ Old style import requests s = requests.Session() - Network accessline 273
import requests s = requests.Session() try: - Network accessline 274
s = requests.Session() - Network accessline 275
try: response = s.get('https://api.example.com') finally: - Network accessline 276
response = s.get('https://api.example.com') - Network accessline 280
# ✅ Modern with requests.Session() as s: - Network accessline 281
with requests.Session() as s: - Network accessline 282
response = s.get('https://api.example.com')
skills/deprecated-api-updater/scripts/detect_deprecated_apis.py
- Executable scriptline 1
#!/usr/bin/env python3
skills/deprecated-api-updater/scripts/replace_deprecated_apis.py
- Executable scriptline 1
#!/usr/bin/env python3
skills/design-smell-detector/scripts/detect_smells.py
- Executable scriptline 1
#!/usr/bin/env python3
skills/directed-test-input-generator/references/llm_patterns.md
- Dangerous shell operationline 474
return eval(code)
skills/directed-test-input-generator/scripts/input_generator.py
- Executable scriptline 1
#!/usr/bin/env python3
skills/directed-test-input-generator/scripts/path_analyzer.py
- Executable scriptline 1
#!/usr/bin/env python3
skills/edge-case-generator/references/python_edge_cases.md
skills/environment-setup-assistant/SKILL.md
- Network accessline 50
# Install Homebrew /bin/bash -c "$(curl -fsSL https://raw.githubusercontent.com/Homebrew/install/HEAD/install.sh)" - Dangerous shell operationline 51
/bin/bash -c "$(curl -fsSL https://raw.githubusercontent.com/Homebrew/install/HEAD/install.sh)" - Network accessline 51
/bin/bash -c "$(curl -fsSL https://raw.githubusercontent.com/Homebrew/install/HEAD/install.sh)" - Network accessline 61
# Install Node.js via nvm curl -o- https://raw.githubusercontent.com/nvm-sh/nvm/v0.39.0/install.sh | bash - Dangerous shell operationline 62
curl -o- https://raw.githubusercontent.com/nvm-sh/nvm/v0.39.0/install.sh | bash - Network accessline 62
curl -o- https://raw.githubusercontent.com/nvm-sh/nvm/v0.39.0/install.sh | bash - Network accessline 65
# Install Docker Desktop echo "Please download Docker Desktop from https://www.docker.com/products/docker-desktop" - Network accessline 66
echo "Please download Docker Desktop from https://www.docker.com/products/docker-desktop" - Dangerous shell operationline 98
# Linux: sudo apt-get install python3.11 - Dangerous shell operationline 287
rm -rf venv - Network accessline 347
# Install Node.js via nvm (Node Version Manager) # This allows managing multiple Node.js versions curl -o- https://raw.githubusercontent.com/nvm-sh/nvm/v0.39.0/install.sh | bash - Dangerous shell operationline 349
curl -o- https://raw.githubusercontent.com/nvm-sh/nvm/v0.39.0/install.sh | bash - Network accessline 349
curl -o- https://raw.githubusercontent.com/nvm-sh/nvm/v0.39.0/install.sh | bash - Dangerous shell operationline 397
# macOS/Linux: Use sudo for system installations - Dangerous shell operationline 398
sudo apt-get install package - Dangerous shell operationline 400
# Avoid sudo for user-level tools - Network accessline 439
if ! command -v brew &> /dev/null; then echo "📦 Installing Homebrew..." /bin/bash -c "$(curl -fsSL https://raw.githubusercontent.com/Homebrew/install/HEAD/install.sh)" - Network accessline 440
echo "📦 Installing Homebrew..." /bin/bash -c "$(curl -fsSL https://raw.githubusercontent.com/Homebrew/install/HEAD/install.sh)" fi - Dangerous shell operationline 441
/bin/bash -c "$(curl -fsSL https://raw.githubusercontent.com/Homebrew/install/HEAD/install.sh)" - Network accessline 441
/bin/bash -c "$(curl -fsSL https://raw.githubusercontent.com/Homebrew/install/HEAD/install.sh)" - Network accessline 448
# Install Node.js via nvm echo "📦 Installing Node.js..." curl -o- https://raw.githubusercontent.com/nvm-sh/nvm/v0.39.0/install.sh | bash - Network accessline 449
echo "📦 Installing Node.js..." curl -o- https://raw.githubusercontent.com/nvm-sh/nvm/v0.39.0/install.sh | bash export NVM_DIR="$HOME/.nvm" - Dangerous shell operationline 450
curl -o- https://raw.githubusercontent.com/nvm-sh/nvm/v0.39.0/install.sh | bash - Network accessline 450
curl -o- https://raw.githubusercontent.com/nvm-sh/nvm/v0.39.0/install.sh | bash - Network accessline 470
# Install Docker Desktop echo "📦 Docker Desktop..." echo "Please download from https://www.docker.com/products/docker-desktop" - Network accessline 472
echo "Please download from https://www.docker.com/products/docker-desktop"
skills/environment-setup-assistant/references/platform_instructions.md
- Dangerous shell operationline 21
/bin/bash -c "$(curl -fsSL https://raw.githubusercontent.com/Homebrew/install/HEAD/install.sh)" - Network accessline 21
/bin/bash -c "$(curl -fsSL https://raw.githubusercontent.com/Homebrew/install/HEAD/install.sh)" - Dangerous shell operationline 27
eval "$(/opt/homebrew/bin/brew shellenv)" - Network accessline 61
# Install nvm curl -o- https://raw.githubusercontent.com/nvm-sh/nvm/v0.39.0/install.sh | bash - Dangerous shell operationline 62
curl -o- https://raw.githubusercontent.com/nvm-sh/nvm/v0.39.0/install.sh | bash - Network accessline 62
curl -o- https://raw.githubusercontent.com/nvm-sh/nvm/v0.39.0/install.sh | bash - Network accessline 73
#### Docker Desktop 1. Download from https://www.docker.com/products/docker-desktop - Network accessline 74
1. Download from https://www.docker.com/products/docker-desktop - Dangerous shell operationline 92
eval "$(/opt/homebrew/bin/brew shellenv)" - Dangerous shell operationline 114
sudo apt-get update - Dangerous shell operationline 115
sudo apt-get upgrade -y - Dangerous shell operationline 120
sudo apt-get install -y build-essential curl git wget - Network accessline 120
sudo apt-get install -y build-essential curl git wget - Dangerous shell operationline 127
sudo apt-get install -y git - Dangerous shell operationline 137
sudo apt-get install -y python3.11 python3.11-venv python3-pip - Dangerous shell operationline 140
sudo update-alternatives --install /usr/bin/python python /usr/bin/python3.11 1 - Dangerous shell operationline 141
sudo update-alternatives --install /usr/bin/pip pip /usr/bin/pip3 1 - Network accessline 146
# Install nvm curl -o- https://raw.githubusercontent.com/nvm-sh/nvm/v0.39.0/install.sh | bash - Dangerous shell operationline 147
curl -o- https://raw.githubusercontent.com/nvm-sh/nvm/v0.39.0/install.sh | bash - Network accessline 147
curl -o- https://raw.githubusercontent.com/nvm-sh/nvm/v0.39.0/install.sh | bash - Network accessline 160
# Install dependencies sudo apt-get install -y ca-certificates curl gnupg lsb-release - Dangerous shell operationline 161
sudo apt-get install -y ca-certificates curl gnupg lsb-release - Network accessline 161
sudo apt-get install -y ca-certificates curl gnupg lsb-release - Network accessline 163
# Add Docker's GPG key sudo mkdir -p /etc/apt/keyrings curl -fsSL https://download.docker.com/linux/ubuntu/gpg | \ - Dangerous shell operationline 164
sudo mkdir -p /etc/apt/keyrings - Network accessline 164
sudo mkdir -p /etc/apt/keyrings curl -fsSL https://download.docker.com/linux/ubuntu/gpg | \ sudo gpg --dearmor -o /etc/apt/keyrings/docker.gpg - Dangerous shell operationline 165
curl -fsSL https://download.docker.com/linux/ubuntu/gpg | sudo gpg --dearmor -o /etc/apt/keyrings/docker.gpg - Network accessline 165
curl -fsSL https://download.docker.com/linux/ubuntu/gpg | \ - Dangerous shell operationline 166
sudo gpg --dearmor -o /etc/apt/keyrings/docker.gpg - Dangerous shell operationline 169
echo "deb [arch=$(dpkg --print-architecture) signed-by=/etc/apt/keyrings/docker.gpg] https://download.docker.com/linux/ubuntu $(lsb_release -cs) stable" | sudo tee /etc/apt/sources.list.d/docker.list > /dev/null - Network accessline 169
echo \ "deb [arch=$(dpkg --print-architecture) signed-by=/etc/apt/keyrings/docker.gpg] \ https://download.docker.com/linux/ubuntu \ - Network accessline 170
"deb [arch=$(dpkg --print-architecture) signed-by=/etc/apt/keyrings/docker.gpg] \ https://download.docker.com/linux/ubuntu \ $(lsb_release -cs) stable" | \ - Network accessline 171
https://download.docker.com/linux/ubuntu \ - Dangerous shell operationline 173
sudo tee /etc/apt/sources.list.d/docker.list > /dev/null - Dangerous shell operationline 176
sudo apt-get update - Dangerous shell operationline 177
sudo apt-get install -y docker-ce docker-ce-cli containerd.io docker-compose-plugin - Dangerous shell operationline 180
sudo usermod -aG docker $USER - Network accessline 187
# Download and install wget -O code.deb 'https://code.visualstudio.com/sha/download?build=stable&os=linux-deb-x64' - Network accessline 188
wget -O code.deb 'https://code.visualstudio.com/sha/download?build=stable&os=linux-deb-x64' - Dangerous shell operationline 189
sudo apt install ./code.deb - Dangerous shell operationline 190
rm code.deb - Dangerous shell operationline 229
sudo apt-get update - Dangerous shell operationline 230
sudo apt-get upgrade -y - Network accessline 233
#### 3. Install Windows Terminal (Optional but Recommended) Install from Microsoft Store: https://aka.ms/terminal - Network accessline 234
Install from Microsoft Store: https://aka.ms/terminal - Network accessline 242
#### Git for Windows 1. Download from https://git-scm.com/download/win - Network accessline 243
1. Download from https://git-scm.com/download/win - Network accessline 251
#### Python 1. Download from https://www.python.org/downloads/ - Network accessline 252
1. Download from https://www.python.org/downloads/ - Network accessline 260
#### Node.js 1. Download from https://nodejs.org/ - Network accessline 261
1. Download from https://nodejs.org/ - Network accessline 269
#### Docker Desktop for Windows 1. Download from https://www.docker.com/products/docker-desktop - Network accessline 270
1. Download from https://www.docker.com/products/docker-desktop - Network accessline 275
#### VS Code 1. Download from https://code.visualstudio.com/ - Network accessline 276
1. Download from https://code.visualstudio.com/ - Access to secretsline 324
[Credential-related source omitted] - Access to secretsline 330
[Credential-related source omitted]
skills/environment-setup-assistant/references/tool_guides.md
- Dangerous shell operationline 22
curl https://pyenv.run | bash - Network accessline 22
curl https://pyenv.run | bash - Dangerous shell operationline 29
eval "$(pyenv init -)" - Dangerous shell operationline 53
curl -o- https://raw.githubusercontent.com/nvm-sh/nvm/v0.39.0/install.sh | bash - Network accessline 53
curl -o- https://raw.githubusercontent.com/nvm-sh/nvm/v0.39.0/install.sh | bash - Network accessline 93
git clone https://github.com/rbenv/rbenv.git ~/.rbenv - Network accessline 94
git clone https://github.com/rbenv/ruby-build.git ~/.rbenv/plugins/ruby-build - Network accessline 124
wget -O code.deb 'https://code.visualstudio.com/sha/download?build=stable&os=linux-deb-x64' - Dangerous shell operationline 125
sudo apt install ./code.deb - Network accessline 128
Windows: Download from https://code.visualstudio.com/ - Network accessline 165
**PyCharm (Python)**: - Download: https://www.jetbrains.com/pycharm/download/ - Network accessline 166
- Download: https://www.jetbrains.com/pycharm/download/ - Network accessline 169
**WebStorm (JavaScript/TypeScript)**: - Download: https://www.jetbrains.com/webstorm/download/ - Network accessline 170
- Download: https://www.jetbrains.com/webstorm/download/ - Network accessline 173
**IntelliJ IDEA (Java/Kotlin)**: - Download: https://www.jetbrains.com/idea/download/ - Network accessline 174
- Download: https://www.jetbrains.com/idea/download/ - Dangerous shell operationline 193
sudo apt-get install -y postgresql postgresql-contrib - Dangerous shell operationline 194
sudo systemctl start postgresql - Dangerous shell operationline 195
sudo systemctl enable postgresql - Dangerous shell operationline 213
sudo apt-get install pgadmin4 - Dangerous shell operationline 228
sudo apt-get install -y mysql-server - Dangerous shell operationline 229
sudo systemctl start mysql - Dangerous shell operationline 230
sudo systemctl enable mysql - Dangerous shell operationline 235
sudo mysql_secure_installation - Dangerous shell operationline 244
sudo apt-get install mysql-workbench - Dangerous shell operationline 260
wget -qO - https://www.mongodb.org/static/pgp/server-6.0.asc | sudo apt-key add - - Network accessline 260
wget -qO - https://www.mongodb.org/static/pgp/server-6.0.asc | sudo apt-key add - - Dangerous shell operationline 261
echo "deb [ arch=amd64,arm64 ] https://repo.mongodb.org/apt/ubuntu focal/mongodb-org/6.0 multiverse" | sudo tee /etc/apt/sources.list.d/mongodb-org-6.0.list - Network accessline 261
echo "deb [ arch=amd64,arm64 ] https://repo.mongodb.org/apt/ubuntu focal/mongodb-org/6.0 multiverse" | sudo tee /etc/apt/sources.list.d/mongodb-org-6.0.list - Dangerous shell operationline 262
sudo apt-get update - Dangerous shell operationline 263
sudo apt-get install -y mongodb-org - Dangerous shell operationline 264
sudo systemctl start mongod - Network accessline 267
**GUI Client - MongoDB Compass**: Download from https://www.mongodb.com/products/compass - Network accessline 268
Download from https://www.mongodb.com/products/compass - Dangerous shell operationline 282
sudo apt-get install -y redis-server - Dangerous shell operationline 283
sudo systemctl start redis-server - Network accessline 353
curl -LO https://storage.googleapis.com/minikube/releases/latest/minikube-linux-amd64 - Dangerous shell operationline 354
sudo install minikube-linux-amd64 /usr/local/bin/minikube - Network accessline 367
curl -LO "https://dl.k8s.io/release/$(curl -L -s https://dl.k8s.io/release/stable.txt)/bin/linux/amd64/kubectl" - Dangerous shell operationline 368
sudo install -o root -g root -m 0755 kubectl /usr/local/bin/kubectl - Network accessline 406
Access at http://localhost:8080 - Dangerous shell operationline 419
curl -L "https://packages.gitlab.com/install/repositories/runner/gitlab-runner/script.deb.sh" | sudo bash - Network accessline 419
curl -L "https://packages.gitlab.com/install/repositories/runner/gitlab-runner/script.deb.sh" | sudo bash - Dangerous shell operationline 420
sudo apt-get install gitlab-runner - Dangerous shell operationline 425
sudo gitlab-runner register - Network accessline 439
Download: https://www.postman.com/downloads/ - Network accessline 448
Download: https://insomnia.rest/download - Dangerous shell operationline 457
sudo apt-get install httpie - Network accessline 459
# Usage http GET https://api.github.com/users/github - Network accessline 460
http GET https://api.github.com/users/github - Dangerous shell operationline 470
sudo apt-get install jq - Network accessline 472
# Usage curl -s https://api.github.com/users/github | jq '.name' - Network accessline 473
curl -s https://api.github.com/users/github | jq '.name' - Dangerous shell operationline 483
sudo apt-get install tmux - Dangerous shell operationline 497
sudo apt-get install htop - Dangerous shell operationline 520
sudo apt-get install terminator - Dangerous shell operationline 525
sudo apt-get install tilix - Network accessline 539
Set-ExecutionPolicy Bypass -Scope Process -Force [System.Net.ServicePointManager]::SecurityProtocol = [System.Net.ServicePointManager]::SecurityProtocol -bor 3072 iex ((New-Object System.Net.WebClient).DownloadString('https://community.choc - Network accessline 541
iex ((New-Object System.Net.WebClient).DownloadString('https://community.chocolatey.org/install.ps1'))
skills/environment-setup-assistant/scripts/setup_docker.sh
- Executable scriptline 1
#!/usr/bin/env bash - Network accessline 29
echo "📦 Installing Docker Desktop for macOS..." echo "Please download Docker Desktop from:" echo "https://www.docker.com/products/docker-desktop" - Network accessline 30
echo "Please download Docker Desktop from:" echo "https://www.docker.com/products/docker-desktop" echo "" - Network accessline 31
echo "https://www.docker.com/products/docker-desktop" - Dangerous shell operationline 40
sudo apt-get remove -y docker docker-engine docker.io containerd runc || true - Dangerous shell operationline 43
sudo apt-get update - Dangerous shell operationline 44
sudo apt-get install -y \ - Network accessline 44
sudo apt-get install -y \ ca-certificates \ curl \ - Network accessline 45
ca-certificates \ curl \ gnupg \ - Network accessline 46
curl \ - Dangerous shell operationline 51
sudo mkdir -p /etc/apt/keyrings - Network accessline 51
sudo mkdir -p /etc/apt/keyrings curl -fsSL https://download.docker.com/linux/ubuntu/gpg | sudo gpg --dearmor -o /etc/apt/keyrings/docker.gpg - Dangerous shell operationline 52
curl -fsSL https://download.docker.com/linux/ubuntu/gpg | sudo gpg --dearmor -o /etc/apt/keyrings/docker.gpg - Network accessline 52
curl -fsSL https://download.docker.com/linux/ubuntu/gpg | sudo gpg --dearmor -o /etc/apt/keyrings/docker.gpg - Dangerous shell operationline 55
echo "deb [arch=$(dpkg --print-architecture) signed-by=/etc/apt/keyrings/docker.gpg] https://download.docker.com/linux/ubuntu $(lsb_release -cs) stable" | sudo tee /etc/apt/sources.list.d/docker.list > /dev/null - Network accessline 55
echo \ "deb [arch=$(dpkg --print-architecture) signed-by=/etc/apt/keyrings/docker.gpg] https://download.docker.com/linux/ubuntu \ - Network accessline 56
"deb [arch=$(dpkg --print-architecture) signed-by=/etc/apt/keyrings/docker.gpg] https://download.docker.com/linux/ubuntu \ - Dangerous shell operationline 57
$(lsb_release -cs) stable" | sudo tee /etc/apt/sources.list.d/docker.list > /dev/null - Dangerous shell operationline 60
sudo apt-get update - Dangerous shell operationline 61
sudo apt-get install -y docker-ce docker-ce-cli containerd.io docker-compose-plugin - Dangerous shell operationline 64
sudo usermod -aG docker $USER - Network accessline 93
if ! command -v docker-compose &> /dev/null && [[ "$OS" == "linux" ]]; then echo "📦 Installing Docker Compose..." sudo curl -L "https://github.com/docker/compose/releases/latest/download/docker-compose-$(uname -s)-$(uname -m)" -o /u - Network accessline 94
echo "📦 Installing Docker Compose..." sudo curl -L "https://github.com/docker/compose/releases/latest/download/docker-compose-$(uname -s)-$(uname -m)" -o /usr/local/bin/docker-compose sudo chmod +x /usr/local/bin/docker-compose - Dangerous shell operationline 95
sudo curl -L "https://github.com/docker/compose/releases/latest/download/docker-compose-$(uname -s)-$(uname -m)" -o /usr/local/bin/docker-compose - Network accessline 95
sudo curl -L "https://github.com/docker/compose/releases/latest/download/docker-compose-$(uname -s)-$(uname -m)" -o /usr/local/bin/docker-compose - Dangerous shell operationline 96
sudo chmod +x /usr/local/bin/docker-compose
skills/environment-setup-assistant/scripts/setup_nodejs.sh
- Executable scriptline 1
#!/usr/bin/env bash - Network accessline 33
if [ ! -d "$HOME/.nvm" ]; then echo "Installing nvm..." curl -o- https://raw.githubusercontent.com/nvm-sh/nvm/v0.39.0/install.sh | bash - Dangerous shell operationline 35
curl -o- https://raw.githubusercontent.com/nvm-sh/nvm/v0.39.0/install.sh | bash - Network accessline 35
curl -o- https://raw.githubusercontent.com/nvm-sh/nvm/v0.39.0/install.sh | bash
skills/environment-setup-assistant/scripts/setup_python.sh
- Executable scriptline 1
#!/usr/bin/env bash - Network accessline 33
if ! command -v brew &> /dev/null; then echo "Installing Homebrew..." /bin/bash -c "$(curl -fsSL https://raw.githubusercontent.com/Homebrew/install/HEAD/install.sh)" - Network accessline 34
echo "Installing Homebrew..." /bin/bash -c "$(curl -fsSL https://raw.githubusercontent.com/Homebrew/install/HEAD/install.sh)" fi - Dangerous shell operationline 35
/bin/bash -c "$(curl -fsSL https://raw.githubusercontent.com/Homebrew/install/HEAD/install.sh)" - Network accessline 35
/bin/bash -c "$(curl -fsSL https://raw.githubusercontent.com/Homebrew/install/HEAD/install.sh)" - Dangerous shell operationline 40
sudo apt-get update - Dangerous shell operationline 41
sudo apt-get install -y python3.11 python3.11-venv python3-pip - Network accessline 43
elif [[ "$OS" == "windows" ]]; then echo "Please install Python from https://www.python.org/downloads/" - Network accessline 44
echo "Please install Python from https://www.python.org/downloads/" - Dangerous shell operationline 75
sudo apt-get install -y git build-essential
skills/error-explanation-generator/references/debugging_strategies.md
- Network accessline 419
# Bad - depends on external service def test(): response = requests.get("https://api.example.com") - Network accessline 420
def test(): response = requests.get("https://api.example.com") assert response.status_code == 200 - Network accessline 421
response = requests.get("https://api.example.com") - Network accessline 429
response = requests.get("https://api.example.com") - Network accessline 537
response = requests.get(url) - Network accessline 550
# Configure test to use proxy export HTTP_PROXY=http://localhost:8080 - Network accessline 551
export HTTP_PROXY=http://localhost:8080 - Network accessline 552
export HTTPS_PROXY=http://localhost:8080
skills/exploitability-analyzer/SKILL.md
skills/exploitability-analyzer/references/assessment_criteria.md
- Dangerous shell operationline 184
**Exploit**: `; rm -rf /` executes arbitrary commands
skills/flaky-test-detector/SKILL.md
- Network accessline 62
**External dependencies:** - `requests.get()`, `http.client` - Real network calls - Network accessline 63
- `requests.get()`, `http.client` - Real network calls - Network accessline 211
MEDIUM PRIORITY: - test_api_call (flakiness: 0.62) - Line 23: requests.get() - unmocked network call - Network accessline 213
- Line 23: requests.get() - unmocked network call
skills/flaky-test-detector/references/flaky-patterns.md
- Network accessline 109
# Flaky - depends on network and external service def test_api(): response = requests.get('https://api.example.com/data') - Network accessline 110
def test_api(): response = requests.get('https://api.example.com/data') assert response.status_code == 200 - Network accessline 111
response = requests.get('https://api.example.com/data') - Network accessline 115
def test_api(mocker): mocker.patch('requests.get', return_value=Mock(status_code=200)) response = requests.get('https://api.example.com/data') - Network accessline 116
mocker.patch('requests.get', return_value=Mock(status_code=200)) response = requests.get('https://api.example.com/data') assert response.status_code == 200 - Network accessline 117
response = requests.get('https://api.example.com/data') - Access to secretsline 265
[Credential-related source omitted] - Access to secretsline 269
[Credential-related source omitted] - Access to secretsline 270
[Credential-related source omitted]
skills/flaky-test-detector/references/remediation-strategies.md
- Network accessline 195
# Before def test_fetch_data(): response = requests.get("https://api.example.com/data") - Network accessline 196
def test_fetch_data(): response = requests.get("https://api.example.com/data") assert response.status_code == 200 - Network accessline 197
response = requests.get("https://api.example.com/data") - Network accessline 207
response = requests.get("https://api.example.com/data") - Network accessline 214
@Test public void testFetchData() { Response response = httpClient.get("https://api.example.com/data"); - Network accessline 215
public void testFetchData() { Response response = httpClient.get("https://api.example.com/data"); assertEquals(200, response.getStatusCode()); - Network accessline 216
Response response = httpClient.get("https://api.example.com/data"); - Network accessline 227
Response response = httpClient.get("https://api.example.com/data");
skills/flaky-test-detector/scripts/analyze_test_results.py
- Executable scriptline 1
#!/usr/bin/env python3
skills/framework-migration-assistant/assets/example_fastapi_app.py
- Executable scriptline 1
Executable file
skills/framework-migration-assistant/assets/example_flask_app.py
- Executable scriptline 1
Executable file
skills/framework-migration-assistant/scripts/migrate.py
- Executable scriptline 1
#!/usr/bin/env python3
skills/framework-migration-assistant/scripts/migrate_config.py
skills/framework-migration-assistant/scripts/migrate_dependencies.py
- Executable scriptline 1
#!/usr/bin/env python3
skills/framework-migration-assistant/scripts/migrate_routes.py
- Executable scriptline 1
#!/usr/bin/env python3
skills/framework-migration-assistant/scripts/migrate_tests.py
- Executable scriptline 1
#!/usr/bin/env python3
skills/frontend-ui-ux/SKILL.md
- Network accessline 65
**Inspired by:** [oh-my-opencode](https://github.com/code-yeongyu/oh-my-opencode) frontend-ui-ux skill
skills/fuzzing-input-generator/references/fuzzing-patterns.md
skills/git-bisect-assistant/scripts/git_bisect_runner.py
- Executable scriptline 1
#!/usr/bin/env python3
skills/git-master/SKILL.md
- Network accessline 1013
**Inspired by:** [oh-my-opencode](https://github.com/code-yeongyu/oh-my-opencode) git-master skill
skills/github-triage/SKILL.md
- Network accessline 347
**Inspired by:** [oh-my-opencode](https://github.com/code-yeongyu/oh-my-opencode) github-triage skill
skills/imperative-to-coq-model-extractor/SKILL.md
- Network accessline 417
- **Extraction patterns:** See [extraction_patterns.md](references/extraction_patterns.md) for comprehensive pattern catalog - **Coq documentation:** https://coq.inria.fr/documentation - Network accessline 418
- **Coq documentation:** https://coq.inria.fr/documentation - Network accessline 419
- **Software Foundations:** https://softwarefoundations.cis.upenn.edu/ - Network accessline 420
- **Coq standard library:** https://coq.inria.fr/library/
skills/incremental-python-programmer/scripts/analyze_repo_structure.py
- Executable scriptline 1
#!/usr/bin/env python3
skills/init-deep/SKILL.md
- Network accessline 109
**Inspired by:** [oh-my-opencode](https://github.com/code-yeongyu/oh-my-opencode) /init-deep command
skills/integration-test-generator/SKILL.md
skills/integration-test-generator/references/patterns.md
- Network accessline 15
@pytest.fixture def base_url(self): return "http://localhost:8000" - Network accessline 17
return "http://localhost:8000" - Network accessline 22
# Setup user_data = {"username": "testuser", "email": "test@example.com"} response = requests.post(f"{base_url}/users", json=user_data) - Network accessline 23
user_data = {"username": "testuser", "email": "test@example.com"} response = requests.post(f"{base_url}/users", json=user_data) user_id = response.json()["id"] - Network accessline 24
response = requests.post(f"{base_url}/users", json=user_data) - Network accessline 29
# Cleanup requests.delete(f"{base_url}/users/{user_id}") - Network accessline 30
requests.delete(f"{base_url}/users/{user_id}") - Network accessline 41
# Act response = requests.post(f"{base_url}/orders", json=order_data) - Network accessline 42
response = requests.post(f"{base_url}/orders", json=order_data) - Network accessline 50
# Assert - verify user's order list updated user_response = requests.get(f"{base_url}/users/{test_user}/orders") - Network accessline 51
user_response = requests.get(f"{base_url}/users/{test_user}/orders") - Network accessline 67
@pytest.fixture def gql_client(self): transport = RequestsHTTPTransport(url="http://localhost:4000/graphql") - Network accessline 68
def gql_client(self): transport = RequestsHTTPTransport(url="http://localhost:4000/graphql") return Client(transport=transport, fetch_schema_from_transport=True) - Network accessline 69
transport = RequestsHTTPTransport(url="http://localhost:4000/graphql") - Network accessline 344
responses.add( responses.POST, "https://api.payment-gateway.com/charge", - Network accessline 345
responses.POST, "https://api.payment-gateway.com/charge", json={"transaction_id": "txn_123", "status": "success"}, - Network accessline 346
"https://api.payment-gateway.com/charge", - Network accessline 352
responses.add( responses.POST, "https://api.email-service.com/send", - Network accessline 353
responses.POST, "https://api.email-service.com/send", json={"message_id": "msg_456"}, - Network accessline 354
"https://api.email-service.com/send",
skills/interface-contract-verifier/scripts/contract_extractor.py
- Executable scriptline 1
#!/usr/bin/env python3
skills/interface-contract-verifier/scripts/contract_verifier.py
- Executable scriptline 1
#!/usr/bin/env python3
skills/interface-specification-generator/assets/openapi-template.yaml
- Network accessline 8
email: support@example.com servers: - url: https://api.example.com/v1 - Network accessline 9
servers: - url: https://api.example.com/v1 description: Production server - Network accessline 10
- url: https://api.example.com/v1 - Network accessline 11
description: Production server - url: https://staging-api.example.com/v1 description: Staging server - Network accessline 12
- url: https://staging-api.example.com/v1
skills/interface-specification-generator/references/openapi-patterns.md
- Network accessline 380
flows: authorizationCode: authorizationUrl: https://example.com/oauth/authorize - Network accessline 381
authorizationCode: authorizationUrl: https://example.com/oauth/authorize tokenUrl: https://example.com/oauth/token - Network accessline 382
authorizationUrl: https://example.com/oauth/authorize - Network accessline 383
tokenUrl: https://example.com/oauth/token - Network accessline 564
servers: - url: https://api.example.com/v1 - Network accessline 565
- url: https://api.example.com/v1 - Network accessline 566
- url: https://api.example.com/v2
skills/interface-specification-generator/scripts/example.py
- Executable scriptline 1
#!/usr/bin/env python3
skills/interface-specification-generator/scripts/validate_openapi.py
- Executable scriptline 1
#!/usr/bin/env python3
skills/interval-difference-analyzer/references/abstract_interpretation.md
- Dangerous shell operationline 230
abstract_state[x] = eval(e, abstract_state)
skills/interval-difference-analyzer/scripts/compare_intervals.py
- Executable scriptline 1
#!/usr/bin/env python3
skills/interval-difference-analyzer/scripts/interval_analyzer.py
- Executable scriptline 1
#!/usr/bin/env python3
skills/interval-profiling-performance-analyzer/SKILL.md
- Dangerous shell operationline 176
sudo apt-get install linux-tools-generic
skills/interval-profiling-performance-analyzer/references/profiling-tools.md
skills/interval-profiling-performance-analyzer/scripts/generate_visualization.py
- Executable scriptline 1
#!/usr/bin/env python3
skills/interval-profiling-performance-analyzer/scripts/profile_cpp.py
skills/interval-profiling-performance-analyzer/scripts/profile_java.py
- Executable scriptline 1
#!/usr/bin/env python3
skills/interval-profiling-performance-analyzer/scripts/profile_python.py
- Executable scriptline 1
#!/usr/bin/env python3 - Dangerous shell operationline 35
exec(code, script_globals) - Network accessline 64
'total_time': tt, 'cumulative_time': ct, 'time_per_call': tt / nc if nc > 0 else 0, - Network accessline 65
'cumulative_time': ct, 'time_per_call': tt / nc if nc > 0 else 0, }) - Network accessline 66
'time_per_call': tt / nc if nc > 0 else 0,
skills/issue-report-generator/SKILL.md
- Network accessline 375
## Steps to Reproduce 1. Run test: `pytest tests/test_api.py::ApiTest::test_get_user_endpoint` 2. Or make request: `GET http://localhost:8000/api/users` - Network accessline 376
1. Run test: `pytest tests/test_api.py::ApiTest::test_get_user_endpoint 2. Or make request: `GET http://localhost:8000/api/users - Network accessline 377
2. Or make request: `GET http://localhost:8000/api/users` - Network accessline 490
- **Report patterns:** See [report_patterns.md](references/report_patterns.md) for comprehensive templates and examples - **GitHub Issues:** https://docs.github.com/en/issues - Network accessline 491
- **GitHub Issues:** https://docs.github.com/en/issues
skills/java-api-consistency-validator/scripts/validate.py
- Executable scriptline 1
#!/usr/bin/env python3
skills/legacy-code-summarizer/references/architecture_patterns.md
skills/legacy-code-summarizer/references/code_quality_checklist.md
skills/legacy-code-summarizer/references/dependency_analysis.md
- Dangerous shell operationline 453
sudo apt-get install graphviz - Network accessline 490
<html> <head> <script src="https://cdnjs.cloudflare.com/ajax/libs/cytoscape/3.21.0/cytoscape.min.js"></script> - Network accessline 491
<head> <script src="https://cdnjs.cloudflare.com/ajax/libs/cytoscape/3.21.0/cytoscape.min.js"></script> </head> - Network accessline 492
<script src="https://cdnjs.cloudflare.com/ajax/libs/cytoscape/3.21.0/cytoscape.min.js"></script>
skills/linkedin/SKILL.md
- Network accessline 22
1. Go to [app.linkedapi.io](https://app.linkedapi.io) and sign up or log in - Network accessline 97
# Basic profile linkedin person fetch https://www.linkedin.com/in/username --json -q - Network accessline 98
linkedin person fetch https://www.linkedin.com/in/username --json -q - Network accessline 100
# With experience and education linkedin person fetch https://www.linkedin.com/in/username --experience --education --json -q - Network accessline 101
linkedin person fetch https://www.linkedin.com/in/username --experience --education --json -q - Network accessline 103
# With last 5 posts linkedin person fetch https://www.linkedin.com/in/username --posts --posts-limit 5 --json -q - Network accessline 104
linkedin person fetch https://www.linkedin.com/in/username --posts --posts-limit 5 --json -q - Network accessline 161
# Basic company info linkedin company fetch https://www.linkedin.com/company/name --json -q - Network accessline 162
linkedin company fetch https://www.linkedin.com/company/name --json -q - Network accessline 164
# With employees filtered by position linkedin company fetch https://www.linkedin.com/company/name --employees --employees-position "Engineer" --json -q - Network accessline 165
linkedin company fetch https://www.linkedin.com/company/name --employees --employees-position "Engineer" --json -q - Network accessline 167
# With decision makers and posts linkedin company fetch https://www.linkedin.com/company/name --dms --posts --posts-limit 10 --json -q - Network accessline 168
linkedin company fetch https://www.linkedin.com/company/name --dms --posts --posts-limit 10 --json -q - Network accessline 198
linkedin message send https://www.linkedin.com/in/username 'Hey, loved your latest post!' --json -q - Network accessline 210
linkedin message get https://www.linkedin.com/in/username --json -q - Network accessline 211
linkedin message get https://www.linkedin.com/in/username --since 2024-01-15T10:30:00Z --json -q - Network accessline 291
linkedin post fetch https://www.linkedin.com/posts/username_activity-123 --json -q - Network accessline 293
# With comments sorted by most recent, including replies linkedin post fetch https://www.linkedin.com/posts/username_activity-123 \ - Network accessline 294
linkedin post fetch https://www.linkedin.com/posts/username_activity-123 \ - Network accessline 314
# With a document linkedin post create 'Our Q4 report' \ --attachments "https://example.com/report.pdf:document:Q4 Report" --json -q - Network accessline 315
linkedin post create 'Our Q4 report' --attachments "https://example.com/report.pdf:document:Q4 Report" --json -q - Network accessline 316
--attachments "https://example.com/report.pdf:document:Q4 Report" --json -q - Network accessline 318
# Post as a company linkedin post create 'Company announcement' \ --company-url https://www.linkedin.com/company/name --json -q - Network accessline 319
linkedin post create 'Company announcement' --company-url https://www.linkedin.com/company/name --json -q - Network accessline 320
--company-url https://www.linkedin.com/company/name --json -q - Network accessline 332
linkedin post react https://www.linkedin.com/posts/username_activity-123 --type like --json -q - Network accessline 334
# React on behalf of a company linkedin post react https://www.linkedin.com/posts/username_activity-123 --type celebrate \ - Network accessline 335
linkedin post react https://www.linkedin.com/posts/username_activity-123 --type celebrate \ - Network accessline 336
--company-url https://www.linkedin.com/company/name --json -q - Network accessline 348
linkedin post comment https://www.linkedin.com/posts/username_activity-123 'Great insights!' --json -q - Network accessline 350
# Comment on behalf of a company linkedin post comment https://www.linkedin.com/posts/username_activity-123 'Well said!' \ - Network accessline 351
linkedin post comment https://www.linkedin.com/posts/username_activity-123 'Well said!' \ - Network accessline 352
--company-url https://www.linkedin.com/company/name --json -q - Network accessline 428
linkedin navigator company fetch https://www.linkedin.com/sales/company/97ural --employees --dms --json -q - Network accessline 429
linkedin navigator company fetch https://www.linkedin.com/sales/company/97ural \ - Network accessline 463
linkedin navigator message send https://www.linkedin.com/in/username \ - Network accessline 495
See [Building Workflows](https://linkedapi.io/docs/building-workflows/) for the workflow JSON schema. - Network accessline 512
- **Single quotes for text arguments.** Use single quotes around message text, post text, and comments to avoid shell interpretation issues with special characters. - **Action limits.** Per-account limits are configurable on the platform. A - Network accessline 513
- **Action limits.** Per-account limits are configurable on the platform. A `limitExceeded` error means the limit was reached. - **URL normalization.** All LinkedIn URLs in responses are normalized to `https://www.linkedin.com/...` format w - Network accessline 514
- **URL normalization.** All LinkedIn URLs in responses are normalized to `https://www.linkedin.com/...` format without trailing slashes.
skills/lsp-refactoring/SKILL.md
- Network accessline 117
**Inspired by:** [oh-my-opencode](https://github.com/code-yeongyu/oh-my-opencode) /refactor command
skills/markdown-document-structurer/references/markdown-best-practices.md
skills/markdown-document-structurer/scripts/analyze_structure.py
- Executable scriptline 1
#!/usr/bin/env python3
skills/metamorphic-test-generator/assets/example-program.py
- Executable scriptline 1
#!/usr/bin/env python3
skills/metamorphic-test-generator/scripts/generate.py
- Executable scriptline 1
#!/usr/bin/env python3
skills/mocking-test-generator/references/python_patterns.md
- Network accessline 18
assert result == expected_value mock_get.assert_called_once_with('https://api.example.com/endpoint') - Network accessline 19
mock_get.assert_called_once_with('https://api.example.com/endpoint') - Access to secretsline 52
[Credential-related source omitted] - Access to secretsline 56
[Credential-related source omitted]
skills/modular-code-enforcement/SKILL.md
- Network accessline 114
**Inspired by:** [oh-my-opencode](https://github.com/code-yeongyu/oh-my-opencode) modular-code-enforcement rule
skills/module-component-generator/references/python-patterns.md
skills/module-level-code-translator/assets/test_template_go.go
- Executable scriptline 1
Executable file
skills/module-level-code-translator/assets/test_template_javascript.js
- Executable scriptline 1
Executable file
skills/module-level-code-translator/assets/test_template_python.py
- Executable scriptline 1
Executable file
skills/module-level-code-translator/references/stdlib_mappings.md
- Network accessline 25
### Python → JavaScript - `requests.get(url)` → `fetch(url)` or `axios.get(url)` - Network accessline 26
- `requests.get(url)` → `fetch(url)` or `axios.get(url)` - Network accessline 27
- `requests.post(url, json=data)` → `fetch(url, {method: 'POST', body: JSON.stringify(data)})` - Network accessline 29
### Python → Java - `requests.get(url)` → `HttpClient.newHttpClient().send(request, BodyHandlers.ofString())` - Network accessline 30
- `requests.get(url)` → `HttpClient.newHttpClient().send(request, BodyHandlers.ofString())` - Network accessline 32
### Python → Go - `requests.get(url)` → `http.Get(url)` - Network accessline 33
- `requests.get(url)` → `http.Get(url)` - Network accessline 34
- `requests.post(url, json=data)` → `http.Post(url, "application/json", bytes.NewBuffer(jsonData))`
skills/nl-to-constraints/assets/specification_schema.json
skills/playwright-automation/SKILL.md
skills/proof-failure-explainer/SKILL.md
- Network accessline 406
- **Failure patterns:** See [failure_patterns.md](references/failure_patterns.md) for comprehensive catalog - **Isabelle documentation:** https://isabelle.in.tum.de/documentation.html - Network accessline 407
- **Isabelle documentation:** https://isabelle.in.tum.de/documentation.html - Network accessline 408
- **Coq documentation:** https://coq.inria.fr/documentation - Network accessline 409
- **Isabelle tutorial:** https://isabelle.in.tum.de/dist/Isabelle/doc/tutorial.pdf - Network accessline 410
- **Software Foundations:** https://softwarefoundations.cis.upenn.edu/
skills/proof-refactoring-assistant/SKILL.md
- Network accessline 479
- **Refactoring patterns:** See [refactoring_patterns.md](references/refactoring_patterns.md) for comprehensive catalog - **Isabelle documentation:** https://isabelle.in.tum.de/documentation.html - Network accessline 480
- **Isabelle documentation:** https://isabelle.in.tum.de/documentation.html - Network accessline 481
- **Coq documentation:** https://coq.inria.fr/documentation
skills/pseudocode-to-python-code/assets/template.py
- Executable scriptline 1
#!/usr/bin/env python3
skills/python-api-consistency-validator/scripts/validate.py
- Executable scriptline 1
#!/usr/bin/env python3
skills/python-regression-test-generator/SKILL.md
- Network accessline 356
def fetch_user_data(user_id): response = requests.get(f'https://api.example.com/users/{user_id}') - Network accessline 357
response = requests.get(f'https://api.example.com/users/{user_id}') - Network accessline 372
async def fetch_user_data(user_id, include_posts=False): async with aiohttp.ClientSession() as session: - Network accessline 373
async with aiohttp.ClientSession() as session: - Network accessline 374
url = f'https://api.example.com/users/{user_id}'
skills/python-regression-test-generator/references/test_generation_patterns.md
- Network accessline 374
result = fetch_data('https://api.example.com/data') - Network accessline 376
assert result['data'] == 'value' mock_get.assert_called_once_with('https://api.example.com/data') - Network accessline 377
mock_get.assert_called_once_with('https://api.example.com/data') - Network accessline 753
def fetch_data(url): response = requests.get(url) - Network accessline 754
response = requests.get(url) - Network accessline 761
with patch('requests.get') as mock_get: mock_get.return_value.json.return_value = {'data': 'value'} result = fetch_data('https://api.example.com') - Network accessline 762
mock_get.return_value.json.return_value = {'data': 'value'} result = fetch_data('https://api.example.com') assert result['data'] == 'value' - Network accessline 763
result = fetch_data('https://api.example.com') - Network accessline 769
async def fetch_data(url): async with aiohttp.ClientSession() as session: - Network accessline 770
async with aiohttp.ClientSession() as session: - Network accessline 785
result = await fetch_data('https://api.example.com')
skills/python-repo-quickstart/SKILL.md
skills/python-repo-quickstart/scripts/analyze_repo.py
skills/python-test-updater/SKILL.md
- Network accessline 372
# Old def fetch(): - Network accessline 373
def fetch(): - Network accessline 376
# New async def fetch(): - Network accessline 377
async def fetch(): - Network accessline 383
# Old def test_fetch(): result = fetch() - Network accessline 384
def test_fetch(): result = fetch() assert result is not None - Network accessline 385
result = fetch() - Network accessline 389
@pytest.mark.asyncio async def test_fetch(): result = await fetch() - Network accessline 390
async def test_fetch(): result = await fetch() assert result is not None - Network accessline 391
result = await fetch()
skills/python-test-updater/references/test-update-patterns.md
- Network accessline 335
def fetch_data(url): return requests.get(url).json() - Network accessline 336
return requests.get(url).json() - Network accessline 341
async def fetch_data(url): async with aiohttp.ClientSession() as session: - Network accessline 342
async with aiohttp.ClientSession() as session: - Network accessline 349
def test_fetch_data(): data = fetch_data("http://api.example.com/data") - Network accessline 350
data = fetch_data("http://api.example.com/data") - Network accessline 356
@pytest.mark.asyncio async def test_fetch_data(): data = await fetch_data("http://api.example.com/data") - Network accessline 357
async def test_fetch_data(): data = await fetch_data("http://api.example.com/data") assert "result" in data - Network accessline 358
data = await fetch_data("http://api.example.com/data")
skills/python-test-updater/scripts/analyze_code_diff.py
- Executable scriptline 1
#!/usr/bin/env python3
skills/python-to-dafny-translator/SKILL.md
- Network accessline 517
- **Translation patterns:** See [translation_patterns.md](references/translation_patterns.md) for comprehensive pattern catalog - **Dafny documentation:** https://dafny.org/ - Network accessline 518
- **Dafny documentation:** https://dafny.org/ - Network accessline 519
- **Dafny tutorial:** https://dafny.org/dafny/OnlineTutorial/guide - Network accessline 520
- **Dafny reference:** https://dafny.org/latest/DafnyRef/DafnyRef
skills/python-to-lean4-translator/references/advanced_features.md
skills/readme-generator/SKILL.md
- Network accessline 42
 - Network accessline 43
 - Network accessline 44
 - Dangerous shell operationline 84
- Install on Ubuntu: `sudo apt-get install [packages]` - Network accessline 105
\`\`\`bash git clone https://github.com/username/project-name.git - Network accessline 106
git clone https://github.com/username/project-name.git - Access to secretsline 129
[Credential-related source omitted] - Access to secretsline 131
[Credential-related source omitted] - Access to secretsline 134
[Credential-related source omitted] - Network accessline 184
The application will be available at `http://localhost:3000` - Network accessline 188
**Create a new resource**: \`\`\`bash curl -X POST http://localhost:3000/api/resources \ - Network accessline 189
\`\`\`bash curl -X POST http://localhost:3000/api/resources \ -H "Content-Type: application/json" \ - Network accessline 190
curl -X POST http://localhost:3000/api/resources \ - Network accessline 195
**List all resources**: \`\`\`bash curl http://localhost:3000/api/resources - Network accessline 196
\`\`\`bash curl http://localhost:3000/api/resources \`\`\` - Network accessline 197
curl http://localhost:3000/api/resources - Access to secretsline 211
[Credential-related source omitted] - Access to secretsline 223
[Credential-related source omitted] - Access to secretsline 324
[Credential-related source omitted] - Access to secretsline 371
[Credential-related source omitted]
skills/reference-searcher/SKILL.md
- Network accessline 39
# Search GitHub for code patterns via grep.app or GitHub search # e.g., https://grep.app/search?q=getServerSession%28&filter[lang][0]=TypeScript - Network accessline 40
# e.g., https://grep.app/search?q=getServerSession%28&filter[lang][0]=TypeScript - Network accessline 119
**Inspired by:** [oh-my-opencode](https://github.com/code-yeongyu/oh-my-opencode) Librarian agent
skills/regression-consistency-checker/scripts/compare_results.py
- Executable scriptline 1
#!/usr/bin/env python3
skills/release-change-analyzer/SKILL.md
- Network accessline 97
**Inspired by:** [oh-my-opencode](https://github.com/code-yeongyu/oh-my-opencode) get-unpublished-changes command
skills/release-notes-writer/SKILL.md
skills/replay-oriented-instrumentation/SKILL.md
skills/replay-oriented-instrumentation/references/replay-tools.md
skills/reproduction-trace-instrumenter/scripts/python_instrumenter.py
- Executable scriptline 1
#!/usr/bin/env python3
skills/reproduction-trace-instrumenter/scripts/replay_generator.py
- Executable scriptline 1
#!/usr/bin/env python3
skills/requirement-comparison-reporter/scripts/analyze_code_impact.py
- Executable scriptline 1
#!/usr/bin/env python3
skills/requirement-enhancer/references/examples.md
- Access to secretsline 104
[Credential-related source omitted]
skills/rollback-strategy-advisor/SKILL.md
- Network accessline 41
# Check system health curl http://localhost:8080/health # Health endpoint - Network accessline 42
curl http://localhost:8080/health # Health endpoint - Network accessline 114
# 5. Validate rollback (see Step 4) curl http://localhost:8080/health - Network accessline 115
curl http://localhost:8080/health - Network accessline 158
# 4. Validate configuration loaded correctly docker exec <service-name> cat /app/config/app.conf curl http://localhost:8080/health - Network accessline 160
curl http://localhost:8080/health - Access to secretsline 167
[Credential-related source omitted] - Access to secretsline 189
[Credential-related source omitted] - Dangerous shell operationline 217
docker network rm <new-network> - Network accessline 303
# 5. Validate curl http://localhost:8080/health - Network accessline 304
curl http://localhost:8080/health - Network accessline 330
# 2. Application health curl http://localhost:8080/health - Network accessline 331
curl http://localhost:8080/health - Network accessline 332
curl -I http://localhost:8080 # HTTP status code - Network accessline 348
# Test critical user flows curl -X POST http://localhost:8080/api/login -d '{"user":"test","pass":"test"}' - Network accessline 349
curl -X POST http://localhost:8080/api/login -d '{"user":"test","pass":"test"}' - Network accessline 350
curl http://localhost:8080/api/users/1 - Network accessline 456
app: healthcheck: test: ["CMD", "curl", "-f", "http://localhost:8080/health"] - Network accessline 457
healthcheck: test: ["CMD", "curl", "-f", "http://localhost:8080/health"] interval: 30s - Network accessline 458
test: ["CMD", "curl", "-f", "http://localhost:8080/health"]
skills/rollback-strategy-advisor/references/platform_guides.md
- Dangerous shell operationline 32
docker rm myapp-container - Network accessline 61
# 2. Validate old version works curl http://localhost:8081/health - Network accessline 62
curl http://localhost:8081/health - Dangerous shell operationline 69
docker rm myapp-container - Dangerous shell operationline 93
docker rm myapp-container - Access to secretsline 164
[Credential-related source omitted] - Access to secretsline 165
[Credential-related source omitted] - Dangerous shell operationline 266
docker run --rm -v myapp-data:/target -v $(pwd)/backups:/backup alpine sh -c "rm -rf /target/* && tar xzf /backup/myapp-data-20260215_120000.tar.gz -C /target" - Dangerous shell operationline 270
sh -c "rm -rf /target/* && tar xzf /backup/myapp-data-20260215_120000.tar.gz -C /target" - Dangerous shell operationline 295
docker volume rm myapp-data - Dangerous shell operationline 354
docker network rm myapp-network - Network accessline 480
image: myapp:v1.2.3 healthcheck: test: ["CMD", "curl", "-f", "http://localhost:8080/health"] - Network accessline 481
healthcheck: test: ["CMD", "curl", "-f", "http://localhost:8080/health"] interval: 10s - Network accessline 482
test: ["CMD", "curl", "-f", "http://localhost:8080/health"] - Network accessline 547
SERVICE_NAME=${1:-app} PREVIOUS_VERSION=${2} HEALTH_ENDPOINT=${3:-http://localhost:8080/health} - Network accessline 549
HEALTH_ENDPOINT=${3:-http://localhost:8080/health} - Network accessline 563
# Health check for i in {1..30}; do if curl -sf "$HEALTH_ENDPOINT" > /dev/null; then - Network accessline 564
for i in {1..30}; do if curl -sf "$HEALTH_ENDPOINT" > /dev/null; then echo "✓ Service healthy" - Network accessline 565
if curl -sf "$HEALTH_ENDPOINT" > /dev/null; then - Access to secretsline 592
[Credential-related source omitted]
skills/rtl-equivalence-checker/scripts/check_equivalence.py
- Executable scriptline 1
#!/usr/bin/env python3
skills/rtl-equivalence-checker/scripts/counterexample_generator.py
- Executable scriptline 1
#!/usr/bin/env python3
skills/rtl-equivalence-checker/scripts/equivalence_analyzer.py
- Executable scriptline 1
#!/usr/bin/env python3
skills/rtl-equivalence-checker/scripts/rtl_parser.py
- Executable scriptline 1
#!/usr/bin/env python3
skills/security-patch-advisor/references/examples.md
skills/security-patch-advisor/references/remediation_strategies.md
skills/security-sensitive-path-instrumenter/scripts/generate_instrumentation.py
- Executable scriptline 1
#!/usr/bin/env python3
skills/semantic-equivalence-verifier/references/language_patterns.md
- Network accessline 277
// Artifact A function fetchData(url) { return fetch(url).then(r => r.json()); - Network accessline 278
function fetchData(url) { return fetch(url).then(r => r.json()); } - Network accessline 279
return fetch(url).then(r => r.json()); - Network accessline 282
// Artifact B async function fetchData(url) { const response = await fetch(url); - Network accessline 283
async function fetchData(url) { const response = await fetch(url); return response.json(); - Network accessline 284
const response = await fetch(url);
skills/semantic-szz-analyzer/references/language_support.md
- Dangerous shell operationline 301
- `eval()` and `exec()`: Cannot be fully analyzed statically - Network accessline 414
- Tree-sitter documentation: https://tree-sitter.github.io/tree-sitter/ - Network accessline 415
- Python AST documentation: https://docs.python.org/3/library/ast.html - Network accessline 416
- Javalang: https://github.com/c2nes/javalang - Network accessline 417
- Esprima: https://esprima.org/
skills/semantic-szz-analyzer/scripts/batch_analyze.py
- Executable scriptline 1
#!/usr/bin/env python3
skills/semantic-szz-analyzer/scripts/semantic_analyzer.py
- Executable scriptline 1
#!/usr/bin/env python3
skills/semantic-szz-analyzer/scripts/semantic_szz.py
- Executable scriptline 1
#!/usr/bin/env python3
skills/session-handoff/SKILL.md
- Network accessline 104
**Inspired by:** [oh-my-opencode](https://github.com/code-yeongyu/oh-my-opencode) /handoff command
skills/skill-creator/LICENSE.txt
skills/skill-creator/scripts/init_skill.py
- Executable scriptline 1
#!/usr/bin/env python3
skills/skill-creator/scripts/package_skill.py
- Executable scriptline 1
#!/usr/bin/env python3
skills/skill-creator/scripts/quick_validate.py
- Executable scriptline 1
#!/usr/bin/env python3
skills/smart-mutation-operator-generator/scripts/generate_operators.py
- Executable scriptline 1
#!/usr/bin/env python3
skills/smv-model-extractor/scripts/cfg_analyzer.py
- Executable scriptline 1
#!/usr/bin/env python3
skills/smv-model-extractor/scripts/extract_model.py
- Executable scriptline 1
#!/usr/bin/env python3
skills/smv-model-extractor/scripts/language_parser.py
- Executable scriptline 1
#!/usr/bin/env python3
skills/smv-model-extractor/scripts/smv_generator.py
- Executable scriptline 1
#!/usr/bin/env python3
skills/specification-to-temporal-logic-generator/scripts/convert_format.py
- Executable scriptline 1
#!/usr/bin/env python3
skills/specification-to-temporal-logic-generator/scripts/validate_formula.py
- Executable scriptline 1
#!/usr/bin/env python3
skills/spring-mvc-to-boot-migrator/SKILL.md
- Network accessline 247
curl http://localhost:8080/users
skills/spring-mvc-to-boot-migrator/references/migration_guide.md
- Network accessline 432
public void addCorsMappings(CorsRegistry registry) { registry.addMapping("/**") .allowedOrigins("http://localhost:3000"); - Network accessline 433
registry.addMapping("/**") .allowedOrigins("http://localhost:3000"); } - Network accessline 434
.allowedOrigins("http://localhost:3000"); - Network accessline 441
spring.web.cors.allowed-origins=http://localhost:3000 - Network accessline 461
curl http://localhost:8080/users - Network accessline 471
curl http://localhost:8080/actuator/health
skills/spring-mvc-to-boot-migrator/scripts/migrate.py
skills/spring-mvc-to-boot-migrator/scripts/migrate_annotations.py
- Executable scriptline 1
#!/usr/bin/env python3
skills/spring-mvc-to-boot-migrator/scripts/migrate_build.py
- Executable scriptline 1
#!/usr/bin/env python3 - Network accessline 36
tree = ET.parse(pom_file) root = tree.getroot() ns = {'m': 'http://maven.apache.org/POM/4.0.0'} - Network accessline 38
ns = {'m': 'http://maven.apache.org/POM/4.0.0'} - Network accessline 41
ET.register_namespace('', 'http://maven.apache.org/POM/4.0.0')
skills/spring-mvc-to-boot-migrator/scripts/migrate_config.py
- Executable scriptline 1
#!/usr/bin/env python3
skills/spring-mvc-to-boot-migrator/scripts/migrate_tests.py
- Executable scriptline 1
#!/usr/bin/env python3
skills/state-snapshot-instrumenter/assets/example_python.py
- Executable scriptline 1
Executable file
skills/state-snapshot-instrumenter/assets/snapshot_schema.json
skills/state-snapshot-instrumenter/scripts/analyze_snapshots.py
- Executable scriptline 1
#!/usr/bin/env python3
skills/state-snapshot-instrumenter/scripts/instrument_c.py
- Executable scriptline 1
#!/usr/bin/env python3
skills/state-snapshot-instrumenter/scripts/instrument_java.py
- Executable scriptline 1
#!/usr/bin/env python3
skills/state-snapshot-instrumenter/scripts/instrument_python.py
- Executable scriptline 1
#!/usr/bin/env python3
skills/state-snapshot-instrumenter/scripts/snapshot_runtime.py
skills/static-reasoning-verifier/scripts/verify_java.py
- Executable scriptline 1
#!/usr/bin/env python3
skills/static-reasoning-verifier/scripts/verify_python.py
- Executable scriptline 1
#!/usr/bin/env python3
skills/static-vulnerability-detector/SKILL.md
skills/static-vulnerability-detector/references/cwe_patterns.md
- Access to secretsline 178
[Credential-related source omitted] - Access to secretsline 186
[Credential-related source omitted] - Access to secretsline 187
[Credential-related source omitted] - Network accessline 289
# Vulnerable: Unencrypted transmission requests.get(f"http://api.example.com/user?ssn={ssn}") # VULNERABLE - Network accessline 290
requests.get(f"http://api.example.com/user?ssn={ssn}") # VULNERABLE - Network accessline 297
# Safe: Use HTTPS requests.get(f"https://api.example.com/user?ssn={ssn}") - Network accessline 298
requests.get(f"https://api.example.com/user?ssn={ssn}") - Network accessline 394
# Vulnerable: Unvalidated URL url = request.args.get('url') response = requests.get(url) # VULNERABLE: can access internal services - Network accessline 396
response = requests.get(url) # VULNERABLE: can access internal services - Network accessline 403
if parsed.netloc not in ALLOWED_DOMAINS: raise ValueError("Domain not allowed") response = requests.get(url) - Network accessline 405
response = requests.get(url)
skills/static-vulnerability-detector/references/examples.md
- Network accessline 46
**References**: - OWASP SQL Injection: https://owasp.org/www-community/attacks/SQL_Injection - Network accessline 47
- OWASP SQL Injection: https://owasp.org/www-community/attacks/SQL_Injection - Network accessline 48
- CWE-89: https://cwe.mitre.org/data/definitions/89.html - Network accessline 103
**References**: - CWE-119: https://cwe.mitre.org/data/definitions/119.html - Network accessline 104
- CWE-119: https://cwe.mitre.org/data/definitions/119.html - Access to secretsline 150
[Credential-related source omitted] - Access to secretsline 151
[Credential-related source omitted] - Access to secretsline 152
[Credential-related source omitted] - Access to secretsline 153
[Credential-related source omitted] - Network accessline 166
**References**: - CWE-798: https://cwe.mitre.org/data/definitions/798.html - Network accessline 167
- CWE-798: https://cwe.mitre.org/data/definitions/798.html - Dangerous shell operationline 208
return (os.system, ('rm -rf /',)) - Network accessline 246
**References**: - CWE-502: https://cwe.mitre.org/data/definitions/502.html - Network accessline 247
- CWE-502: https://cwe.mitre.org/data/definitions/502.html - Network accessline 324
**References**: - CWE-306: https://cwe.mitre.org/data/definitions/306.html - Network accessline 325
- CWE-306: https://cwe.mitre.org/data/definitions/306.html - Network accessline 388
**References**: - CWE-327: https://cwe.mitre.org/data/definitions/327.html - Network accessline 389
- CWE-327: https://cwe.mitre.org/data/definitions/327.html
skills/strategic-planner/SKILL.md
- Network accessline 103
**Inspired by:** [oh-my-opencode](https://github.com/code-yeongyu/oh-my-opencode) Prometheus planning agent
skills/symbolic-execution-assistant/references/tool_integration.md
- Network accessline 24
# Install dependencies sudo apt-get install build-essential curl libcap-dev git cmake \ - Dangerous shell operationline 25
sudo apt-get install build-essential curl libcap-dev git cmake \ - Network accessline 25
sudo apt-get install build-essential curl libcap-dev git cmake \ - Dangerous shell operationline 30
sudo apt-get install llvm-13 llvm-13-dev llvm-13-tools - Network accessline 32
# Build KLEE git clone https://github.com/klee/klee.git - Network accessline 33
git clone https://github.com/klee/klee.git - Dangerous shell operationline 39
sudo make install - Network accessline 292
git clone https://github.com/javapathfinder/jpf-core.git - Network accessline 300
git clone https://github.com/SymbolicPathFinder/jpf-symbc.git
skills/szz-bug-identifier/scripts/szz_analyzer.py
- Executable scriptline 1
#!/usr/bin/env python3
skills/taint-instrumentation-assistant/SKILL.md
- Access to secretsline 291
[Credential-related source omitted]
skills/taint-instrumentation-assistant/scripts/example.py
- Executable scriptline 1
#!/usr/bin/env python3
skills/technical-debt-analyzer/SKILL.md
- Network accessline 614
// Before (deprecated request) const request = require('request'); request('https://api.example.com', (error, response, body) => { - Network accessline 615
const request = require('request'); request('https://api.example.com', (error, response, body) => { console.log(body); - Network accessline 616
request('https://api.example.com', (error, response, body) => { - Network accessline 620
// After (axios) const axios = require('axios'); const response = await axios.get('https://api.example.com'); - Network accessline 621
const axios = require('axios'); const response = await axios.get('https://api.example.com'); console.log(response.data); - Network accessline 622
const response = await axios.get('https://api.example.com');
skills/template-code-generator/assets/react-app/package.json
- Executable scriptline 1
Executable file
skills/template-code-generator/references/template_patterns.md
- Network accessline 105
const fetchData = async () => { try { const response = await fetch(url); - Network accessline 106
try { const response = await fetch(url); if (!response.ok) throw new Error('Network response was not ok'); - Network accessline 107
const response = await fetch(url); - Network accessline 127
const API_BASE_URL = import.meta.env.VITE_API_URL || 'http://localhost:8000'; - Network accessline 131
options?: RequestInit ): Promise<T> { const response = await fetch(`${API_BASE_URL}${endpoint}`, { - Network accessline 132
): Promise<T> { const response = await fetch(`${API_BASE_URL}${endpoint}`, { ...options, - Network accessline 133
const response = await fetch(`${API_BASE_URL}${endpoint}`, { - Network accessline 246
# CORS ALLOWED_ORIGINS: List[str] = ["http://localhost:3000"] - Network accessline 247
ALLOWED_ORIGINS: List[str] = ["http://localhost:3000"] - Access to secretsline 250
[Credential-related source omitted] - Network accessline 647
long_description=open('README.md').read(), long_description_content_type='text/markdown', url='https://github.com/yourusername/my-cli-tool', - Network accessline 648
long_description_content_type='text/markdown', url='https://github.com/yourusername/my-cli-tool', classifiers=[ - Network accessline 649
url='https://github.com/yourusername/my-cli-tool', - Network accessline 716
{ "$schema": "https://turbo.build/schema.json", - Network accessline 717
"$schema": "https://turbo.build/schema.json",
skills/test-case-documentation/scripts/extract_tests.py
- Executable scriptline 1
#!/usr/bin/env python3
skills/test-case-reducer/references/language-specific.md
skills/test-case-reducer/scripts/reduce_test.py
- Executable scriptline 1
#!/usr/bin/env python3
skills/test-deduplicator/scripts/coverage_analyzer.py
- Executable scriptline 1
#!/usr/bin/env python3
skills/test-deduplicator/scripts/deduplicator.py
- Executable scriptline 1
#!/usr/bin/env python3
skills/test-deduplicator/scripts/semantic_analyzer.py
- Executable scriptline 1
#!/usr/bin/env python3
skills/test-guided-debloating/SKILL.md
- Dangerous shell operationline 82
rm path/to/unused_file.py
skills/test-guided-debloating/scripts/analyze_coverage.py
- Executable scriptline 1
#!/usr/bin/env python3
skills/test-guided-migration-assistant/scripts/analyze_test_failures.py
- Executable scriptline 1
#!/usr/bin/env python3
skills/test-suite-prioritizer/references/framework_guides.md
skills/time-aware-dependency-cve-scanner/SKILL.md
skills/time-aware-dependency-cve-scanner/references/dependency_formats.md
- Network accessline 47
"express": { "version": "4.18.2", "resolved": "https://registry.npmjs.org/express/-/express-4.18.2.tgz", - Network accessline 48
"version": "4.18.2", "resolved": "https://registry.npmjs.org/express/-/express-4.18.2.tgz", "requires": { - Network accessline 49
"resolved": "https://registry.npmjs.org/express/-/express-4.18.2.tgz", - Network accessline 234
name = "serde" version = "1.0.144" source = "registry+https://github.com/rust-lang/crates.io-index" - Network accessline 235
version = "1.0.144" source = "registry+https://github.com/rust-lang/crates.io-index" checksum = "..." - Network accessline 236
source = "registry+https://github.com/rust-lang/crates.io-index"
skills/time-aware-dependency-cve-scanner/references/vulnerability_databases.md
- Network accessline 7
**URL**: https://osv.dev - Network accessline 8
**API**: https://api.osv.dev/v1/query - Network accessline 32
**Endpoint**: `POST https://api.osv.dev/v1/query` - Network accessline 99
**URL**: https://nvd.nist.gov - Network accessline 100
**API**: https://services.nvd.nist.gov/rest/json/cves/2.0 - Network accessline 108
**Requires API key** for higher rate limits. Get one at: https://nvd.nist.gov/developers/request-an-api-key - Network accessline 110
**Endpoint**: `GET https://services.nvd.nist.gov/rest/json/cves/2.0` - Network accessline 120
GET https://services.nvd.nist.gov/rest/json/cves/2.0?pubStartDate=2023-01-01T00:00:00.000&pubEndDate=2023-12-31T23:59:59.999 - Network accessline 162
**URL**: https://github.com/advisories - Network accessline 173
**Endpoint**: `POST https://api.github.com/graphql`
skills/time-aware-dependency-cve-scanner/scripts/parse_dependencies.py
skills/time-aware-dependency-cve-scanner/scripts/query_cves.py
- Executable scriptline 1
#!/usr/bin/env python3 - Network accessline 70
url = "https://api.osv.dev/v1/query" - Network accessline 79
try: response = requests.post(url, json=payload, timeout=10) - Network accessline 80
response = requests.post(url, json=payload, timeout=10) - Access to secretsline 100
[Credential-related source omitted] - Network accessline 118
url = "https://api.github.com/graphql" - Network accessline 148
try: response = requests.post(url, json=payload, headers=headers, timeout=10) - Network accessline 149
response = requests.post(url, json=payload, headers=headers, timeout=10)
skills/time-aware-dependency-cve-scanner/scripts/scan_repository.py
- Executable scriptline 1
#!/usr/bin/env python3
skills/tlaplus-guided-code-repair/scripts/parse_tlc_trace.py
- Executable scriptline 1
#!/usr/bin/env python3
skills/tlaplus-guided-code-repair/scripts/run_tlc.py
- Executable scriptline 1
#!/usr/bin/env python3
skills/tlaplus-spec-generator/SKILL.md
- Network accessline 305
- **TLA+ Toolbox**: IDE for writing and checking TLA+ specs (https://lamport.azurewebsites.net/tla/toolbox.html)
skills/tlaplus-spec-generator/references/distributed_patterns.md
skills/tlaplus-spec-generator/scripts/generate_spec.py
- Executable scriptline 1
#!/usr/bin/env python3
skills/tlaplus-spec-generator/scripts/program_analyzer.py
- Executable scriptline 1
#!/usr/bin/env python3
skills/tlaplus-spec-generator/scripts/tlaplus_generator.py
- Executable scriptline 1
#!/usr/bin/env python3
skills/trace-collection-assistant/assets/schema_template.json
skills/trace-collection-assistant/scripts/extract_debug_info.py
- Executable scriptline 1
#!/usr/bin/env python3
skills/trace-collection-assistant/scripts/filter_trace.py
- Executable scriptline 1
#!/usr/bin/env python3
skills/trace-collection-assistant/scripts/parse_ltrace.py
- Executable scriptline 1
#!/usr/bin/env python3
skills/trace-collection-assistant/scripts/parse_strace.py
- Executable scriptline 1
#!/usr/bin/env python3
skills/unit-test-generator/references/test_patterns.md
- Network accessline 540
"""Should fetch data asynchronously.""" # Act result = await fetcher.fetch_data("https://api.example.com") - Network accessline 542
result = await fetcher.fetch_data("https://api.example.com") - Network accessline 551
# Act & Assert with pytest.raises(asyncio.TimeoutError): await fetcher.fetch_data("https://slow-api.example.com", timeout=0.1) - Network accessline 553
await fetcher.fetch_data("https://slow-api.example.com", timeout=0.1) - Network accessline 558
# Arrange urls = [ "https://api1.example.com", - Network accessline 559
urls = [ "https://api1.example.com", "https://api2.example.com", - Network accessline 560
"https://api1.example.com", - Network accessline 561
"https://api2.example.com", - Network accessline 562
"https://api3.example.com" - Network accessline 583
# Act result = await fetcher.fetch_with_retry("https://api.example.com", retries=3) - Network accessline 584
result = await fetcher.fetch_with_retry("https://api.example.com", retries=3) - Network accessline 606
// when CompletableFuture<Data> future = fetcher.fetchData("https://api.example.com"); - Network accessline 607
CompletableFuture<Data> future = fetcher.fetchData("https://api.example.com"); - Network accessline 618
AsyncDataFetcher fetcher = new AsyncDataFetcher(); String[] urls = { "https://api1.example.com", - Network accessline 619
String[] urls = { "https://api1.example.com", "https://api2.example.com", - Network accessline 620
"https://api1.example.com", - Network accessline 621
"https://api2.example.com", - Network accessline 622
"https://api3.example.com" - Network accessline 640
// when CompletableFuture<Data> future = fetcher.fetchData("https://invalid-url"); - Network accessline 641
CompletableFuture<Data> future = fetcher.fetchData("https://invalid-url");
skills/verified-spec-code-mapper/SKILL.md
- Network accessline 487
- **Mapping patterns:** See [mapping_patterns.md](references/mapping_patterns.md) for comprehensive patterns and templates - **Coq documentation:** https://coq.inria.fr/documentation - Network accessline 488
- **Coq documentation:** https://coq.inria.fr/documentation - Network accessline 489
- **Dafny documentation:** https://dafny.org/ - Network accessline 490
- **Isabelle documentation:** https://isabelle.in.tum.de/documentation.html
skills/vulnerability-pattern-matcher/SKILL.md
- Access to secretsline 175
[Credential-related source omitted] - Access to secretsline 177
[Credential-related source omitted] - Network accessline 295
def fetch_url(): url = request.args.get('url') response = requests.get(url) - Network accessline 296
url = request.args.get('url') response = requests.get(url) return response.content - Network accessline 297
response = requests.get(url) - Network accessline 328
if parsed.hostname not in ALLOWED_HOSTS: return "Invalid URL", 400 response = requests.get(url, timeout=5) - Network accessline 329
return "Invalid URL", 400 response = requests.get(url, timeout=5) return response.content - Network accessline 330
response = requests.get(url, timeout=5)
skills/vulnerability-pattern-matcher/references/vulnerability_patterns.md
- Access to secretsline 114
[Credential-related source omitted] - Dangerous shell operationline 232
eval(userInput); - Network accessline 411
import ssl context = ssl._create_unverified_context() urllib.request.urlopen(url, context=context) - Network accessline 413
urllib.request.urlopen(url, context=context) - Network accessline 485
def fetch_url(): url = request.args.get('url') response = requests.get(url) - Network accessline 486
url = request.args.get('url') response = requests.get(url) return response.content - Network accessline 487
response = requests.get(url) - Network accessline 541
// SAFE DocumentBuilderFactory factory = DocumentBuilderFactory.newInstance(); factory.setFeature("http://apache.org/xml/features/disallow-doctype-decl", true); - Network accessline 542
DocumentBuilderFactory factory = DocumentBuilderFactory.newInstance(); factory.setFeature("http://apache.org/xml/features/disallow-doctype-decl", true); factory.setFeature("http://xml.org/sax/features/external-general-entities", false); - Network accessline 543
factory.setFeature("http://apache.org/xml/features/disallow-doctype-decl", true); - Network accessline 544
factory.setFeature("http://xml.org/sax/features/external-general-entities", false); - Network accessline 545
factory.setFeature("http://xml.org/sax/features/external-parameter-entities", false); - Dangerous shell operationline 604
- User input in system(), exec(), shell commands - Dangerous shell operationline 633
- eval(), exec() with user input - Dangerous shell operationline 641
eval(user_code)
skills/vulnerability-root-cause-analyzer/references/analysis_strategies.md
- Dangerous shell operationline 90
- system(), popen(), exec() calls
How the signals fit together
Facts from a static read of the files at the pinned commit. They describe what the code does, not why.
Some files could not be read; the facts below still hold.
Combined signals: 7 facts
- Runs the official installer from raw.githubusercontent.comenvironment-setup-assistant/SKILL.md:51Low confidence
- Passes content downloaded from raw.githubusercontent.com to an interpreterenvironment-setup-assistant/SKILL.md:62High confidence
- Passes content downloaded from raw.githubusercontent.com to an interpreterenvironment-setup-assistant/SKILL.md:349High confidence
- Runs the official installer from raw.githubusercontent.comenvironment-setup-assistant/SKILL.md:441Low confidence
- Passes content downloaded from raw.githubusercontent.com to an interpreterenvironment-setup-assistant/SKILL.md:450High confidence
- Passes content downloaded from raw.githubusercontent.com to an interpreterenvironment-setup-assistant/scripts/setup_nodejs.sh:35High confidence
- Runs the official installer from raw.githubusercontent.comenvironment-setup-assistant/scripts/setup_python.sh:35Low confidence
Signal confidence: 493 facts
- Access to secrets in code of the SKILL.mdagent-browser/SKILL.md:143High confidence
- Access to secrets in code of the SKILL.mdagent-browser/SKILL.md:144High confidence
- Access to secrets in code of the SKILL.mdagent-browser/SKILL.md:145High confidence
- Dangerous shell operation in code of the SKILL.mdagent-browser/SKILL.md:182High confidence
- Network access in code of the SKILL.mdagent-browser/SKILL.md:199High confidence
- Network access in code of the SKILL.mdagent-browser/SKILL.md:213High confidence
- Network access in code of the SKILL.mdagent-browser/SKILL.md:214High confidence
- Network access in code of the SKILL.mdagent-browser/SKILL.md:222High confidence
- Network access in code of the SKILL.mdagent-browser/SKILL.md:224High confidence
- Network access in code of the SKILL.mdagent-browser/SKILL.md:264High confidence
- Network access in code of the SKILL.mdagent-browser/SKILL.md:265High confidence
- Network access in prose of the SKILL.mdagent-browser/SKILL.md:268Low confidence
- Network access in prose of the SKILL.mdagent-browser/SKILL.md:270Low confidence
- Network access in prose of documentationambiguity-detector/references/ambiguity_patterns.md:315Low confidence
- Network access in code of documentationapi-design-assistant/references/openapi-template.md:17Low confidence
- Network access in code of documentationapi-design-assistant/references/openapi-template.md:18Low confidence
- Network access in code of documentationapi-design-assistant/references/openapi-template.md:19Low confidence
- Network access in code of documentationapi-design-assistant/references/openapi-template.md:20Low confidence
- Network access in code of documentationapi-design-assistant/references/openapi-template.md:435Low confidence
- Network access in code of documentationapi-design-assistant/references/openapi-template.md:436Low confidence
- Network access in code of documentationapi-design-assistant/references/openapi-template.md:437Low confidence
- Network access in code of documentationapi-design-assistant/references/openapi-template.md:438Low confidence
- Network access in code of documentationapi-design-assistant/references/openapi-template.md:453Low confidence
- Network access in code of documentationapi-design-assistant/references/openapi-template.md:454Low confidence
- Network access in code of the SKILL.mdapi-documentation-generator/SKILL.md:151High confidence
- Network access in code of the SKILL.mdapi-documentation-generator/SKILL.md:152High confidence
- Network access in code of the SKILL.mdapi-documentation-generator/SKILL.md:250High confidence
- Network access in code of the SKILL.mdapi-documentation-generator/SKILL.md:262High confidence
- Network access in code of the SKILL.mdapi-documentation-generator/SKILL.md:263High confidence
- Network access in code of the SKILL.mdapi-documentation-generator/SKILL.md:350High confidence
- Network access in code of the SKILL.mdapi-documentation-generator/SKILL.md:359High confidence
- Network access in code of the SKILL.mdapi-documentation-generator/SKILL.md:360High confidence
- Network access in code of the SKILL.mdapi-documentation-generator/SKILL.md:361High confidence
- Network access in code of the SKILL.mdapi-documentation-generator/SKILL.md:372High confidence
- Network access in code of the SKILL.mdapi-documentation-generator/SKILL.md:373High confidence
- Network access in code of the SKILL.mdapi-documentation-generator/SKILL.md:374High confidence
- Network access in code of the SKILL.mdapi-documentation-generator/SKILL.md:447High confidence
- Network access in code of the SKILL.mdapi-documentation-generator/SKILL.md:449High confidence
- Network access in code of documentationapi-documentation-generator/assets/api-doc-template.md:10Low confidence
- Network access in code of documentationapi-documentation-generator/assets/api-doc-template.md:71Low confidence
- Network access in code of documentationapi-documentation-generator/assets/api-doc-template.md:142Low confidence
- Network access in code of documentationapi-documentation-generator/assets/api-doc-template.md:381Low confidence
- Network access in code of documentationapi-documentation-generator/assets/api-doc-template.md:404Low confidence
- Network access in code of the SKILL.mdbehavior-preservation-checker/SKILL.md:120High confidence
- Network access in code of the SKILL.mdbehavior-preservation-checker/SKILL.md:121High confidence
- Network access in code of the SKILL.mdbehavior-preservation-checker/SKILL.md:122High confidence
- Network access in code of the SKILL.mdbehavior-preservation-checker/SKILL.md:123High confidence
- Network access in code of documentationbehavior-preservation-checker/references/comparison_techniques.md:176Low confidence
- Network access in code of documentationbehavior-preservation-checker/references/comparison_techniques.md:177Low confidence
- Network access in code of documentationbehavior-preservation-checker/references/comparison_techniques.md:178Low confidence
and 443 more
Only the first 500 facts are listed.
Works with
| Agent | Status | Evidence | Install to |
|---|---|---|---|
| Claude Code | Compatible | Standard SKILL.md skills/abstract-domain-explorer/SKILL.md | .claude/skills/<skill-name>/ |
| Codex | Compatible | Standard SKILL.md skills/abstract-domain-explorer/SKILL.md | .agents/skills/<skill-name>/ |
| Cursor | Compatible | Standard SKILL.md skills/abstract-domain-explorer/SKILL.md | .cursor/skills/<skill-name>/ |
| Gemini CLI | Compatible | Standard SKILL.md skills/abstract-domain-explorer/SKILL.md | .gemini/skills/<skill-name>/ |
| GitHub Copilot | Compatible | Standard SKILL.md skills/abstract-domain-explorer/SKILL.md | .github/skills/<skill-name>/ |
| OpenCode | Compatible | Standard SKILL.md skills/abstract-domain-explorer/SKILL.md | .opencode/skills/<skill-name>/ |
- Native The repository ships a manifest, folder or frontmatter field for this agent.
- Compatible A standard SKILL.md that this agent can read.
- Unknown No evidence either way.
Derived automatically from paths, manifests and frontmatter. Not tested on each agent.
