#528 by GitHub stars
xu-xiang/everything-claude-code-zh
everything-claude-code 中文翻译项目:完整的 Claude Code 配置集合(agents, skills, hooks, commands, rules, MCPs)。源自 Anthropic 黑客松获胜者的实战配置,助力中文工程师高效理解与使用 Claude Code。
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
docs/ja-JP/skills/backend-patterns/SKILL.md
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Network or broad shell
First observation → dfbf9467b90d
No earlier version was observed for comparison.
docs/ja-JP/skills/clickhouse-io/SKILL.md
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Local scripts
First observation → dfbf9467b90d
No earlier version was observed for comparison.
docs/ja-JP/skills/coding-standards/SKILL.md
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Network or broad shell
First observation → dfbf9467b90d
No earlier version was observed for comparison.
docs/ja-JP/skills/configure-ecc/SKILL.md
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Network or broad shell
First observation → dfbf9467b90d
No earlier version was observed for comparison.
docs/ja-JP/skills/continuous-learning/SKILL.md
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Local scripts
First observation → dfbf9467b90d
No earlier version was observed for comparison.
docs/ja-JP/skills/continuous-learning-v2/SKILL.md
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Local scripts
First observation → dfbf9467b90d
No earlier version was observed for comparison.
docs/ja-JP/skills/cpp-testing/SKILL.md
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Local scripts
First observation → dfbf9467b90d
No earlier version was observed for comparison.
docs/ja-JP/skills/django-patterns/SKILL.md
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Local scripts
First observation → dfbf9467b90d
No earlier version was observed for comparison.
docs/ja-JP/skills/django-security/SKILL.md
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Network or broad shell
First observation → dfbf9467b90d
No earlier version was observed for comparison.
docs/ja-JP/skills/django-tdd/SKILL.md
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Local scripts
First observation → dfbf9467b90d
No earlier version was observed for comparison.
docs/ja-JP/skills/django-verification/SKILL.md
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Local scripts
First observation → dfbf9467b90d
No earlier version was observed for comparison.
docs/ja-JP/skills/eval-harness/SKILL.md
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Local scripts
First observation → dfbf9467b90d
No earlier version was observed for comparison.
docs/ja-JP/skills/frontend-patterns/SKILL.md
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Network or broad shell
First observation → dfbf9467b90d
No earlier version was observed for comparison.
docs/ja-JP/skills/golang-patterns/SKILL.md
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Network or broad shell
First observation → dfbf9467b90d
No earlier version was observed for comparison.
docs/ja-JP/skills/golang-testing/SKILL.md
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Local scripts
First observation → dfbf9467b90d
No earlier version was observed for comparison.
docs/ja-JP/skills/iterative-retrieval/SKILL.md
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Local scripts
First observation → dfbf9467b90d
No earlier version was observed for comparison.
docs/ja-JP/skills/java-coding-standards/SKILL.md
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Local scripts
First observation → dfbf9467b90d
No earlier version was observed for comparison.
docs/ja-JP/skills/jpa-patterns/SKILL.md
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Local scripts
First observation → dfbf9467b90d
No earlier version was observed for comparison.
docs/ja-JP/skills/nutrient-document-processing/SKILL.md
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Network or broad shell
First observation → dfbf9467b90d
No earlier version was observed for comparison.
docs/ja-JP/skills/postgres-patterns/SKILL.md
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Local scripts
First observation → dfbf9467b90d
No earlier version was observed for comparison.
docs/ja-JP/skills/project-guidelines-example/SKILL.md
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Network or broad shell
First observation → dfbf9467b90d
No earlier version was observed for comparison.
docs/ja-JP/skills/python-patterns/SKILL.md
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Network or broad shell
First observation → dfbf9467b90d
No earlier version was observed for comparison.
docs/ja-JP/skills/python-testing/SKILL.md
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Network or broad shell
First observation → dfbf9467b90d
No earlier version was observed for comparison.
docs/ja-JP/skills/security-review/SKILL.md
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Network or broad shell
First observation → dfbf9467b90d
No earlier version was observed for comparison.
docs/ja-JP/skills/security-scan/SKILL.md
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Local scripts
First observation → dfbf9467b90d
No earlier version was observed for comparison.
docs/ja-JP/skills/springboot-patterns/SKILL.md
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Local scripts
First observation → dfbf9467b90d
No earlier version was observed for comparison.
docs/ja-JP/skills/springboot-security/SKILL.md
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Local scripts
First observation → dfbf9467b90d
No earlier version was observed for comparison.
docs/ja-JP/skills/springboot-tdd/SKILL.md
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Local scripts
First observation → dfbf9467b90d
No earlier version was observed for comparison.
docs/ja-JP/skills/springboot-verification/SKILL.md
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Local scripts
First observation → dfbf9467b90d
No earlier version was observed for comparison.
docs/ja-JP/skills/strategic-compact/SKILL.md
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Local scripts
First observation → dfbf9467b90d
No earlier version was observed for comparison.
docs/ja-JP/skills/tdd-workflow/SKILL.md
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Network or broad shell
First observation → dfbf9467b90d
No earlier version was observed for comparison.
docs/ja-JP/skills/verification-loop/SKILL.md
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Local scripts
First observation → dfbf9467b90d
No earlier version was observed for comparison.
docs/zh-CN/skills/api-design/SKILL.md
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Local scripts
First observation → dfbf9467b90d
No earlier version was observed for comparison.
docs/zh-CN/skills/article-writing/SKILL.md
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Local scripts
First observation → dfbf9467b90d
No earlier version was observed for comparison.
docs/zh-CN/skills/backend-patterns/SKILL.md
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Network or broad shell
First observation → dfbf9467b90d
No earlier version was observed for comparison.
docs/zh-CN/skills/clickhouse-io/SKILL.md
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Local scripts
First observation → dfbf9467b90d
No earlier version was observed for comparison.
docs/zh-CN/skills/coding-standards/SKILL.md
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Network or broad shell
First observation → dfbf9467b90d
No earlier version was observed for comparison.
docs/zh-CN/skills/configure-ecc/SKILL.md
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Network or broad shell
First observation → dfbf9467b90d
No earlier version was observed for comparison.
docs/zh-CN/skills/content-engine/SKILL.md
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Local scripts
First observation → dfbf9467b90d
No earlier version was observed for comparison.
docs/zh-CN/skills/content-hash-cache-pattern/SKILL.md
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Local scripts
First observation → dfbf9467b90d
No earlier version was observed for comparison.
docs/zh-CN/skills/continuous-learning/SKILL.md
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Local scripts
First observation → dfbf9467b90d
No earlier version was observed for comparison.
docs/zh-CN/skills/continuous-learning-v2/SKILL.md
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Local scripts
First observation → dfbf9467b90d
No earlier version was observed for comparison.
docs/zh-CN/skills/cost-aware-llm-pipeline/SKILL.md
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Local scripts
First observation → dfbf9467b90d
No earlier version was observed for comparison.
docs/zh-CN/skills/cpp-coding-standards/SKILL.md
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Local scripts
First observation → dfbf9467b90d
No earlier version was observed for comparison.
docs/zh-CN/skills/cpp-testing/SKILL.md
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Local scripts
First observation → dfbf9467b90d
No earlier version was observed for comparison.
docs/zh-CN/skills/database-migrations/SKILL.md
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Local scripts
First observation → dfbf9467b90d
No earlier version was observed for comparison.
docs/zh-CN/skills/deployment-patterns/SKILL.md
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Network or broad shell
First observation → dfbf9467b90d
No earlier version was observed for comparison.
docs/zh-CN/skills/django-patterns/SKILL.md
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Local scripts
First observation → dfbf9467b90d
No earlier version was observed for comparison.
docs/zh-CN/skills/django-security/SKILL.md
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Network or broad shell
First observation → dfbf9467b90d
No earlier version was observed for comparison.
docs/zh-CN/skills/django-tdd/SKILL.md
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Local scripts
First observation → dfbf9467b90d
No earlier version was observed for comparison.
docs/zh-CN/skills/django-verification/SKILL.md
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Local scripts
First observation → dfbf9467b90d
No earlier version was observed for comparison.
docs/zh-CN/skills/docker-patterns/SKILL.md
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Network or broad shell
First observation → dfbf9467b90d
No earlier version was observed for comparison.
docs/zh-CN/skills/e2e-testing/SKILL.md
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Network or broad shell
First observation → dfbf9467b90d
No earlier version was observed for comparison.
docs/zh-CN/skills/eval-harness/SKILL.md
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Local scripts
First observation → dfbf9467b90d
No earlier version was observed for comparison.
docs/zh-CN/skills/foundation-models-on-device/SKILL.md
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Local scripts
First observation → dfbf9467b90d
No earlier version was observed for comparison.
docs/zh-CN/skills/frontend-patterns/SKILL.md
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Network or broad shell
First observation → dfbf9467b90d
No earlier version was observed for comparison.
docs/zh-CN/skills/frontend-slides/SKILL.md
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Local scripts
First observation → dfbf9467b90d
No earlier version was observed for comparison.
docs/zh-CN/skills/golang-patterns/SKILL.md
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Network or broad shell
First observation → dfbf9467b90d
No earlier version was observed for comparison.
docs/zh-CN/skills/golang-testing/SKILL.md
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Local scripts
First observation → dfbf9467b90d
No earlier version was observed for comparison.
docs/zh-CN/skills/investor-materials/SKILL.md
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Local scripts
First observation → dfbf9467b90d
No earlier version was observed for comparison.
docs/zh-CN/skills/investor-outreach/SKILL.md
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Local scripts
First observation → dfbf9467b90d
No earlier version was observed for comparison.
docs/zh-CN/skills/iterative-retrieval/SKILL.md
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Local scripts
First observation → dfbf9467b90d
No earlier version was observed for comparison.
docs/zh-CN/skills/java-coding-standards/SKILL.md
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Local scripts
First observation → dfbf9467b90d
No earlier version was observed for comparison.
docs/zh-CN/skills/jpa-patterns/SKILL.md
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Local scripts
First observation → dfbf9467b90d
No earlier version was observed for comparison.
docs/zh-CN/skills/liquid-glass-design/SKILL.md
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Local scripts
First observation → dfbf9467b90d
No earlier version was observed for comparison.
docs/zh-CN/skills/market-research/SKILL.md
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Local scripts
First observation → dfbf9467b90d
No earlier version was observed for comparison.
docs/zh-CN/skills/nutrient-document-processing/SKILL.md
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Network or broad shell
First observation → dfbf9467b90d
No earlier version was observed for comparison.
docs/zh-CN/skills/postgres-patterns/SKILL.md
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Local scripts
First observation → dfbf9467b90d
No earlier version was observed for comparison.
docs/zh-CN/skills/project-guidelines-example/SKILL.md
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Network or broad shell
First observation → dfbf9467b90d
No earlier version was observed for comparison.
docs/zh-CN/skills/python-patterns/SKILL.md
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Network or broad shell
First observation → dfbf9467b90d
No earlier version was observed for comparison.
docs/zh-CN/skills/python-testing/SKILL.md
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Network or broad shell
First observation → dfbf9467b90d
No earlier version was observed for comparison.
docs/zh-CN/skills/regex-vs-llm-structured-text/SKILL.md
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Local scripts
First observation → dfbf9467b90d
No earlier version was observed for comparison.
docs/zh-CN/skills/search-first/SKILL.md
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Local scripts
First observation → dfbf9467b90d
No earlier version was observed for comparison.
docs/zh-CN/skills/security-review/SKILL.md
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Network or broad shell
First observation → dfbf9467b90d
No earlier version was observed for comparison.
docs/zh-CN/skills/security-scan/SKILL.md
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Local scripts
First observation → dfbf9467b90d
No earlier version was observed for comparison.
docs/zh-CN/skills/skill-stocktake/SKILL.md
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Local scripts
First observation → dfbf9467b90d
No earlier version was observed for comparison.
docs/zh-CN/skills/springboot-patterns/SKILL.md
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Local scripts
First observation → dfbf9467b90d
No earlier version was observed for comparison.
docs/zh-CN/skills/springboot-security/SKILL.md
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Local scripts
First observation → dfbf9467b90d
No earlier version was observed for comparison.
docs/zh-CN/skills/springboot-tdd/SKILL.md
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Local scripts
First observation → dfbf9467b90d
No earlier version was observed for comparison.
docs/zh-CN/skills/springboot-verification/SKILL.md
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Local scripts
First observation → dfbf9467b90d
No earlier version was observed for comparison.
docs/zh-CN/skills/strategic-compact/SKILL.md
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Local scripts
First observation → dfbf9467b90d
No earlier version was observed for comparison.
docs/zh-CN/skills/swift-actor-persistence/SKILL.md
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Local scripts
First observation → dfbf9467b90d
No earlier version was observed for comparison.
docs/zh-CN/skills/swift-concurrency-6-2/SKILL.md
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Local scripts
First observation → dfbf9467b90d
No earlier version was observed for comparison.
docs/zh-CN/skills/swift-protocol-di-testing/SKILL.md
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Local scripts
First observation → dfbf9467b90d
No earlier version was observed for comparison.
docs/zh-CN/skills/swiftui-patterns/SKILL.md
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Local scripts
First observation → dfbf9467b90d
No earlier version was observed for comparison.
docs/zh-CN/skills/tdd-workflow/SKILL.md
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Network or broad shell
First observation → dfbf9467b90d
No earlier version was observed for comparison.
docs/zh-CN/skills/verification-loop/SKILL.md
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Local scripts
First observation → dfbf9467b90d
No earlier version was observed for comparison.
docs/zh-CN/skills/visa-doc-translate/SKILL.md
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Local scripts
First observation → dfbf9467b90d
No earlier version was observed for comparison.
docs/zh-TW/skills/backend-patterns/SKILL.md
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Network or broad shell
First observation → dfbf9467b90d
No earlier version was observed for comparison.
docs/zh-TW/skills/clickhouse-io/SKILL.md
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Local scripts
First observation → dfbf9467b90d
No earlier version was observed for comparison.
docs/zh-TW/skills/coding-standards/SKILL.md
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Network or broad shell
First observation → dfbf9467b90d
No earlier version was observed for comparison.
docs/zh-TW/skills/continuous-learning/SKILL.md
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Local scripts
First observation → dfbf9467b90d
No earlier version was observed for comparison.
docs/zh-TW/skills/continuous-learning-v2/SKILL.md
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Local scripts
First observation → dfbf9467b90d
No earlier version was observed for comparison.
docs/zh-TW/skills/eval-harness/SKILL.md
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Local scripts
First observation → dfbf9467b90d
No earlier version was observed for comparison.
docs/zh-TW/skills/frontend-patterns/SKILL.md
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Network or broad shell
First observation → dfbf9467b90d
No earlier version was observed for comparison.
docs/zh-TW/skills/golang-patterns/SKILL.md
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Network or broad shell
First observation → dfbf9467b90d
No earlier version was observed for comparison.
docs/zh-TW/skills/golang-testing/SKILL.md
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Local scripts
First observation → dfbf9467b90d
No earlier version was observed for comparison.
docs/zh-TW/skills/iterative-retrieval/SKILL.md
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Local scripts
First observation → dfbf9467b90d
No earlier version was observed for comparison.
docs/zh-TW/skills/postgres-patterns/SKILL.md
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Local scripts
First observation → dfbf9467b90d
No earlier version was observed for comparison.
docs/zh-TW/skills/project-guidelines-example/SKILL.md
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Network or broad shell
First observation → dfbf9467b90d
No earlier version was observed for comparison.
docs/zh-TW/skills/security-review/SKILL.md
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Network or broad shell
First observation → dfbf9467b90d
No earlier version was observed for comparison.
docs/zh-TW/skills/strategic-compact/SKILL.md
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Local scripts
First observation → dfbf9467b90d
No earlier version was observed for comparison.
docs/zh-TW/skills/tdd-workflow/SKILL.md
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Network or broad shell
First observation → dfbf9467b90d
No earlier version was observed for comparison.
docs/zh-TW/skills/verification-loop/SKILL.md
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Local scripts
First observation → dfbf9467b90d
No earlier version was observed for comparison.
skills/api-design/SKILL.md
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Local scripts
First observation → dfbf9467b90d
No earlier version was observed for comparison.
skills/article-writing/SKILL.md
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Local scripts
First observation → dfbf9467b90d
No earlier version was observed for comparison.
skills/autonomous-loops/SKILL.md
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Network or broad shell
First observation → dfbf9467b90d
No earlier version was observed for comparison.
skills/backend-patterns/SKILL.md
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Network or broad shell
First observation → dfbf9467b90d
No earlier version was observed for comparison.
skills/clickhouse-io/SKILL.md
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Local scripts
First observation → dfbf9467b90d
No earlier version was observed for comparison.
skills/coding-standards/SKILL.md
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Network or broad shell
First observation → dfbf9467b90d
No earlier version was observed for comparison.
skills/configure-ecc/SKILL.md
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Network or broad shell
First observation → dfbf9467b90d
No earlier version was observed for comparison.
skills/content-engine/SKILL.md
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Local scripts
First observation → dfbf9467b90d
No earlier version was observed for comparison.
skills/content-hash-cache-pattern/SKILL.md
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Local scripts
First observation → dfbf9467b90d
No earlier version was observed for comparison.
skills/continuous-learning/SKILL.md
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Local scripts
First observation → dfbf9467b90d
No earlier version was observed for comparison.
skills/continuous-learning-v2/SKILL.md
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Network or broad shell
First observation → dfbf9467b90d
No earlier version was observed for comparison.
skills/cost-aware-llm-pipeline/SKILL.md
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Local scripts
First observation → dfbf9467b90d
No earlier version was observed for comparison.
skills/cpp-coding-standards/SKILL.md
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Local scripts
First observation → dfbf9467b90d
No earlier version was observed for comparison.
skills/cpp-testing/SKILL.md
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Local scripts
First observation → dfbf9467b90d
No earlier version was observed for comparison.
skills/database-migrations/SKILL.md
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Local scripts
First observation → dfbf9467b90d
No earlier version was observed for comparison.
skills/deployment-patterns/SKILL.md
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Network or broad shell
First observation → dfbf9467b90d
No earlier version was observed for comparison.
skills/django-patterns/SKILL.md
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Local scripts
First observation → dfbf9467b90d
No earlier version was observed for comparison.
skills/django-security/SKILL.md
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Network or broad shell
First observation → dfbf9467b90d
No earlier version was observed for comparison.
skills/django-tdd/SKILL.md
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Local scripts
First observation → dfbf9467b90d
No earlier version was observed for comparison.
skills/django-verification/SKILL.md
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Local scripts
First observation → dfbf9467b90d
No earlier version was observed for comparison.
skills/docker-patterns/SKILL.md
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Network or broad shell
First observation → dfbf9467b90d
No earlier version was observed for comparison.
skills/e2e-testing/SKILL.md
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Network or broad shell
First observation → dfbf9467b90d
No earlier version was observed for comparison.
skills/eval-harness/SKILL.md
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Local scripts
First observation → dfbf9467b90d
No earlier version was observed for comparison.
skills/foundation-models-on-device/SKILL.md
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Local scripts
First observation → dfbf9467b90d
No earlier version was observed for comparison.
skills/frontend-patterns/SKILL.md
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Network or broad shell
First observation → dfbf9467b90d
No earlier version was observed for comparison.
skills/frontend-slides/SKILL.md
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Local scripts
First observation → dfbf9467b90d
No earlier version was observed for comparison.
skills/golang-patterns/SKILL.md
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Network or broad shell
First observation → dfbf9467b90d
No earlier version was observed for comparison.
skills/golang-testing/SKILL.md
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Local scripts
First observation → dfbf9467b90d
No earlier version was observed for comparison.
skills/investor-materials/SKILL.md
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Local scripts
First observation → dfbf9467b90d
No earlier version was observed for comparison.
skills/investor-outreach/SKILL.md
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Local scripts
First observation → dfbf9467b90d
No earlier version was observed for comparison.
skills/iterative-retrieval/SKILL.md
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Local scripts
First observation → dfbf9467b90d
No earlier version was observed for comparison.
skills/java-coding-standards/SKILL.md
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Local scripts
First observation → dfbf9467b90d
No earlier version was observed for comparison.
skills/jpa-patterns/SKILL.md
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Local scripts
First observation → dfbf9467b90d
No earlier version was observed for comparison.
skills/liquid-glass-design/SKILL.md
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Local scripts
First observation → dfbf9467b90d
No earlier version was observed for comparison.
skills/market-research/SKILL.md
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Local scripts
First observation → dfbf9467b90d
No earlier version was observed for comparison.
skills/nutrient-document-processing/SKILL.md
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Network or broad shell
First observation → dfbf9467b90d
No earlier version was observed for comparison.
skills/plankton-code-quality/SKILL.md
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Network or broad shell
First observation → dfbf9467b90d
No earlier version was observed for comparison.
skills/postgres-patterns/SKILL.md
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Local scripts
First observation → dfbf9467b90d
No earlier version was observed for comparison.
skills/project-guidelines-example/SKILL.md
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Network or broad shell
First observation → dfbf9467b90d
No earlier version was observed for comparison.
skills/python-patterns/SKILL.md
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Network or broad shell
First observation → dfbf9467b90d
No earlier version was observed for comparison.
skills/python-testing/SKILL.md
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Network or broad shell
First observation → dfbf9467b90d
No earlier version was observed for comparison.
skills/regex-vs-llm-structured-text/SKILL.md
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Local scripts
First observation → dfbf9467b90d
No earlier version was observed for comparison.
skills/search-first/SKILL.md
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Local scripts
First observation → dfbf9467b90d
No earlier version was observed for comparison.
skills/security-review/SKILL.md
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Network or broad shell
First observation → dfbf9467b90d
No earlier version was observed for comparison.
skills/security-scan/SKILL.md
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Local scripts
First observation → dfbf9467b90d
No earlier version was observed for comparison.
skills/skill-stocktake/SKILL.md
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Network or broad shell
First observation → dfbf9467b90d
No earlier version was observed for comparison.
skills/springboot-patterns/SKILL.md
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Local scripts
First observation → dfbf9467b90d
No earlier version was observed for comparison.
skills/springboot-security/SKILL.md
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Local scripts
First observation → dfbf9467b90d
No earlier version was observed for comparison.
skills/springboot-tdd/SKILL.md
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Local scripts
First observation → dfbf9467b90d
No earlier version was observed for comparison.
skills/springboot-verification/SKILL.md
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Local scripts
First observation → dfbf9467b90d
No earlier version was observed for comparison.
skills/strategic-compact/SKILL.md
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Local scripts
First observation → dfbf9467b90d
No earlier version was observed for comparison.
skills/swift-actor-persistence/SKILL.md
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Local scripts
First observation → dfbf9467b90d
No earlier version was observed for comparison.
skills/swift-concurrency-6-2/SKILL.md
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Local scripts
First observation → dfbf9467b90d
No earlier version was observed for comparison.
skills/swift-protocol-di-testing/SKILL.md
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Local scripts
First observation → dfbf9467b90d
No earlier version was observed for comparison.
skills/swiftui-patterns/SKILL.md
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Local scripts
First observation → dfbf9467b90d
No earlier version was observed for comparison.
skills/tdd-workflow/SKILL.md
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Network or broad shell
First observation → dfbf9467b90d
No earlier version was observed for comparison.
skills/verification-loop/SKILL.md
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Local scripts
First observation → dfbf9467b90d
No earlier version was observed for comparison.
skills/visa-doc-translate/SKILL.md
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Local scripts
First observation → dfbf9467b90d
No earlier version was observed for comparison.
Verified commit dfbf9467b90dfd29bffa842c4e0a6977112900e2
git clone --filter=blob:none --no-checkout https://github.com/xu-xiang/everything-claude-code-zh.git .hotskills/xu-xiang-everything-claude-code-zh && git -C .hotskills/xu-xiang-everything-claude-code-zh checkout --detach dfbf9467b90dfd29bffa842c4e0a6977112900e2
# Copy each selected skill directory from .hotskills/xu-xiang-everything-claude-code-zh into .claude/skills/<skill-name>/git clone --filter=blob:none --no-checkout https://github.com/xu-xiang/everything-claude-code-zh.git .hotskills/xu-xiang-everything-claude-code-zh && git -C .hotskills/xu-xiang-everything-claude-code-zh checkout --detach dfbf9467b90dfd29bffa842c4e0a6977112900e2
# Copy each selected skill directory from .hotskills/xu-xiang-everything-claude-code-zh into .agents/skills/<skill-name>/git clone --filter=blob:none --no-checkout https://github.com/xu-xiang/everything-claude-code-zh.git .hotskills/xu-xiang-everything-claude-code-zh && git -C .hotskills/xu-xiang-everything-claude-code-zh checkout --detach dfbf9467b90dfd29bffa842c4e0a6977112900e2
# Copy each selected skill directory from .hotskills/xu-xiang-everything-claude-code-zh into .cursor/skills/<skill-name>/git clone --filter=blob:none --no-checkout https://github.com/xu-xiang/everything-claude-code-zh.git .hotskills/xu-xiang-everything-claude-code-zh && git -C .hotskills/xu-xiang-everything-claude-code-zh checkout --detach dfbf9467b90dfd29bffa842c4e0a6977112900e2
# Copy each selected skill directory from .hotskills/xu-xiang-everything-claude-code-zh into .opencode/skills/<skill-name>/Heat
4.9- Star growth, last 7 daysAhead of 77% of tracked repositories
- Star growth, last 24 hoursAhead of 69% of tracked repositories
- Rank movement, last 7 daysAhead of 39% of tracked repositories
- Commits, last 30 daysAhead of 0% of tracked repositories
- Accounts asking about it through MCP, last 7 daysNot available
- Hot votes this weekAhead of 0% of tracked repositories
Heat never changes the order by stars, and sponsorship never touches it. How heat works
Stars over time
Individual skills in this repository
- backend-patterns
docs/ja-JP/skills/backend-patterns - clickhouse-io
docs/ja-JP/skills/clickhouse-io - coding-standards
docs/ja-JP/skills/coding-standards - configure-ecc
docs/ja-JP/skills/configure-ecc - continuous-learning
docs/ja-JP/skills/continuous-learning - continuous-learning-v2
docs/ja-JP/skills/continuous-learning-v2 - cpp-testing
docs/ja-JP/skills/cpp-testing - django-patterns
docs/ja-JP/skills/django-patterns - django-security
docs/ja-JP/skills/django-security - django-tdd
docs/ja-JP/skills/django-tdd - django-verification
docs/ja-JP/skills/django-verification - eval-harness
docs/ja-JP/skills/eval-harness - frontend-patterns
docs/ja-JP/skills/frontend-patterns - golang-patterns
docs/ja-JP/skills/golang-patterns - golang-testing
docs/ja-JP/skills/golang-testing - iterative-retrieval
docs/ja-JP/skills/iterative-retrieval - java-coding-standards
docs/ja-JP/skills/java-coding-standards - jpa-patterns
docs/ja-JP/skills/jpa-patterns - nutrient-document-processing
docs/ja-JP/skills/nutrient-document-processing - postgres-patterns
docs/ja-JP/skills/postgres-patterns - project-guidelines-example
docs/ja-JP/skills/project-guidelines-example - python-patterns
docs/ja-JP/skills/python-patterns - python-testing
docs/ja-JP/skills/python-testing - security-review
docs/ja-JP/skills/security-review - security-scan
docs/ja-JP/skills/security-scan - springboot-patterns
docs/ja-JP/skills/springboot-patterns - springboot-security
docs/ja-JP/skills/springboot-security - springboot-tdd
docs/ja-JP/skills/springboot-tdd - springboot-verification
docs/ja-JP/skills/springboot-verification - strategic-compact
docs/ja-JP/skills/strategic-compact - tdd-workflow
docs/ja-JP/skills/tdd-workflow - verification-loop
docs/ja-JP/skills/verification-loop - api-design
docs/zh-CN/skills/api-design - article-writing
docs/zh-CN/skills/article-writing - backend-patterns
docs/zh-CN/skills/backend-patterns - clickhouse-io
docs/zh-CN/skills/clickhouse-io - coding-standards
docs/zh-CN/skills/coding-standards - configure-ecc
docs/zh-CN/skills/configure-ecc - content-engine
docs/zh-CN/skills/content-engine - content-hash-cache-pattern
docs/zh-CN/skills/content-hash-cache-pattern - continuous-learning
docs/zh-CN/skills/continuous-learning - continuous-learning-v2
docs/zh-CN/skills/continuous-learning-v2 - cost-aware-llm-pipeline
docs/zh-CN/skills/cost-aware-llm-pipeline - cpp-coding-standards
docs/zh-CN/skills/cpp-coding-standards - cpp-testing
docs/zh-CN/skills/cpp-testing - database-migrations
docs/zh-CN/skills/database-migrations - deployment-patterns
docs/zh-CN/skills/deployment-patterns - django-patterns
docs/zh-CN/skills/django-patterns - django-security
docs/zh-CN/skills/django-security - django-tdd
docs/zh-CN/skills/django-tdd - django-verification
docs/zh-CN/skills/django-verification - docker-patterns
docs/zh-CN/skills/docker-patterns - e2e-testing
docs/zh-CN/skills/e2e-testing - eval-harness
docs/zh-CN/skills/eval-harness - foundation-models-on-device
docs/zh-CN/skills/foundation-models-on-device - frontend-patterns
docs/zh-CN/skills/frontend-patterns - frontend-slides
docs/zh-CN/skills/frontend-slides - golang-patterns
docs/zh-CN/skills/golang-patterns - golang-testing
docs/zh-CN/skills/golang-testing - investor-materials
docs/zh-CN/skills/investor-materials - investor-outreach
docs/zh-CN/skills/investor-outreach - iterative-retrieval
docs/zh-CN/skills/iterative-retrieval - java-coding-standards
docs/zh-CN/skills/java-coding-standards - jpa-patterns
docs/zh-CN/skills/jpa-patterns - liquid-glass-design
docs/zh-CN/skills/liquid-glass-design - market-research
docs/zh-CN/skills/market-research - nutrient-document-processing
docs/zh-CN/skills/nutrient-document-processing - postgres-patterns
docs/zh-CN/skills/postgres-patterns - project-guidelines-example
docs/zh-CN/skills/project-guidelines-example - python-patterns
docs/zh-CN/skills/python-patterns - python-testing
docs/zh-CN/skills/python-testing - regex-vs-llm-structured-text
docs/zh-CN/skills/regex-vs-llm-structured-text - search-first
docs/zh-CN/skills/search-first - security-review
docs/zh-CN/skills/security-review - security-scan
docs/zh-CN/skills/security-scan - skill-stocktake
docs/zh-CN/skills/skill-stocktake - springboot-patterns
docs/zh-CN/skills/springboot-patterns - springboot-security
docs/zh-CN/skills/springboot-security - springboot-tdd
docs/zh-CN/skills/springboot-tdd - springboot-verification
docs/zh-CN/skills/springboot-verification - strategic-compact
docs/zh-CN/skills/strategic-compact - swift-actor-persistence
docs/zh-CN/skills/swift-actor-persistence - swift-concurrency-6-2
docs/zh-CN/skills/swift-concurrency-6-2 - swift-protocol-di-testing
docs/zh-CN/skills/swift-protocol-di-testing - swiftui-patterns
docs/zh-CN/skills/swiftui-patterns - tdd-workflow
docs/zh-CN/skills/tdd-workflow - verification-loop
docs/zh-CN/skills/verification-loop - visa-doc-translate
docs/zh-CN/skills/visa-doc-translate - backend-patterns
docs/zh-TW/skills/backend-patterns - clickhouse-io
docs/zh-TW/skills/clickhouse-io - coding-standards
docs/zh-TW/skills/coding-standards - continuous-learning
docs/zh-TW/skills/continuous-learning - continuous-learning-v2
docs/zh-TW/skills/continuous-learning-v2 - eval-harness
docs/zh-TW/skills/eval-harness - frontend-patterns
docs/zh-TW/skills/frontend-patterns - golang-patterns
docs/zh-TW/skills/golang-patterns - golang-testing
docs/zh-TW/skills/golang-testing - iterative-retrieval
docs/zh-TW/skills/iterative-retrieval - postgres-patterns
docs/zh-TW/skills/postgres-patterns - project-guidelines-example
docs/zh-TW/skills/project-guidelines-example - security-review
docs/zh-TW/skills/security-review - strategic-compact
docs/zh-TW/skills/strategic-compact - tdd-workflow
docs/zh-TW/skills/tdd-workflow - verification-loop
docs/zh-TW/skills/verification-loop - api-design
skills/api-design - article-writing
skills/article-writing - autonomous-loops
skills/autonomous-loops - backend-patterns
skills/backend-patterns - clickhouse-io
skills/clickhouse-io - coding-standards
skills/coding-standards - configure-ecc
skills/configure-ecc - content-engine
skills/content-engine - content-hash-cache-pattern
skills/content-hash-cache-pattern - continuous-learning
skills/continuous-learning - continuous-learning-v2
skills/continuous-learning-v2 - cost-aware-llm-pipeline
skills/cost-aware-llm-pipeline - cpp-coding-standards
skills/cpp-coding-standards - cpp-testing
skills/cpp-testing - database-migrations
skills/database-migrations - deployment-patterns
skills/deployment-patterns - django-patterns
skills/django-patterns - django-security
skills/django-security - django-tdd
skills/django-tdd - django-verification
skills/django-verification - docker-patterns
skills/docker-patterns - e2e-testing
skills/e2e-testing - eval-harness
skills/eval-harness - foundation-models-on-device
skills/foundation-models-on-device - frontend-patterns
skills/frontend-patterns - frontend-slides
skills/frontend-slides - golang-patterns
skills/golang-patterns - golang-testing
skills/golang-testing - investor-materials
skills/investor-materials - investor-outreach
skills/investor-outreach - iterative-retrieval
skills/iterative-retrieval - java-coding-standards
skills/java-coding-standards - jpa-patterns
skills/jpa-patterns - liquid-glass-design
skills/liquid-glass-design - market-research
skills/market-research - nutrient-document-processing
skills/nutrient-document-processing - plankton-code-quality
skills/plankton-code-quality - postgres-patterns
skills/postgres-patterns - project-guidelines-example
skills/project-guidelines-example - python-patterns
skills/python-patterns - python-testing
skills/python-testing - regex-vs-llm-structured-text
skills/regex-vs-llm-structured-text - search-first
skills/search-first - security-review
skills/security-review - security-scan
skills/security-scan - skill-stocktake
skills/skill-stocktake - springboot-patterns
skills/springboot-patterns - springboot-security
skills/springboot-security - springboot-tdd
skills/springboot-tdd - springboot-verification
skills/springboot-verification - strategic-compact
skills/strategic-compact - swift-actor-persistence
skills/swift-actor-persistence - swift-concurrency-6-2
skills/swift-concurrency-6-2 - swift-protocol-di-testing
skills/swift-protocol-di-testing - swiftui-patterns
skills/swiftui-patterns - tdd-workflow
skills/tdd-workflow - verification-loop
skills/verification-loop - visa-doc-translate
skills/visa-doc-translate
How it works
backend-patterns
When your agent uses it
后端架构模式、API 设计、数据库优化以及 Node.js、Express 和 Next.js API 路由的服务端最佳实践。
What it loads into context
Frontmatter
38 tokensAlways available to the agent
SKILL.md
3,438 tokensWhen the skill is activated
Reference documents
47,264 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- API 设计模式
- 数据库模式
- 缓存策略
- 错误处理模式
- 身份验证与授权 (Authentication & Authorization)
- 速率限制 (Rate Limiting)
- 后台任务与队列 (Background Jobs & Queues)
- 日志与监控 (Logging & Monitoring)
Scripts executed separately
../../../../.cursor/hooks/after-file-edit.js../../../../.cursor/hooks/after-file-edit.js../../../../.cursor/hooks/after-mcp-execution.js../../../../.cursor/hooks/after-mcp-execution.js../../../../.cursor/hooks/after-shell-execution.js../../../../.cursor/hooks/after-shell-execution.js../../../../.cursor/hooks/after-tab-file-edit.js../../../../.cursor/hooks/after-tab-file-edit.js../../../../.cursor/hooks/before-mcp-execution.js../../../../.cursor/hooks/before-mcp-execution.js../../../../.cursor/hooks/before-read-file.js../../../../.cursor/hooks/before-read-file.js../../../../.cursor/hooks/before-shell-execution.js../../../../.cursor/hooks/before-shell-execution.js../../../../.cursor/hooks/before-submit-prompt.js../../../../.cursor/hooks/before-submit-prompt.js../../../../.cursor/hooks/before-tab-file-read.js../../../../.cursor/hooks/before-tab-file-read.js../../../../.cursor/hooks/pre-compact.js../../../../.cursor/hooks/pre-compact.js../../../../.cursor/hooks/session-end.js../../../../.cursor/hooks/session-end.js../../../../.cursor/hooks/session-start.js../../../../.cursor/hooks/session-start.js../../../../.cursor/hooks/stop.js../../../../.cursor/hooks/stop.js../../../../.cursor/hooks/subagent-start.js../../../../.cursor/hooks/subagent-start.js../../../../.cursor/hooks/subagent-stop.js../../../../.cursor/hooks/subagent-stop.js../../../../skills/continuous-learning-v2/hooks/observe.sh
Files
../../../../.claude-plugin/PLUGIN_SCHEMA_NOTES.mddoc5,746 bytes../../../../.claude-plugin/README.mddoc761 bytes../../../../.claude-plugin/marketplace.jsonasset1,514 bytes../../../../.claude-plugin/plugin.jsonasset698 bytes../../../../.cursor/hooks.jsonasset3,163 bytes../../../../.cursor/hooks/after-file-edit.jsruns660 bytes../../../../.cursor/hooks/after-file-edit.jsruns660 bytes../../../../.cursor/hooks/after-mcp-execution.jsruns456 bytes../../../../.cursor/hooks/after-mcp-execution.jsruns456 bytes../../../../.cursor/hooks/after-shell-execution.jsruns903 bytes../../../../.cursor/hooks/after-shell-execution.jsruns903 bytes../../../../.cursor/hooks/after-tab-file-edit.jsruns440 bytes../../../../.cursor/hooks/after-tab-file-edit.jsruns440 bytes../../../../.cursor/hooks/before-mcp-execution.jsruns396 bytes../../../../.cursor/hooks/before-mcp-execution.jsruns396 bytes../../../../.cursor/hooks/before-read-file.jsruns488 bytes../../../../.cursor/hooks/before-read-file.jsruns488 bytes../../../../.cursor/hooks/before-shell-execution.jsruns1,101 bytes../../../../.cursor/hooks/before-shell-execution.jsruns1,101 bytes../../../../.cursor/hooks/before-submit-prompt.jsruns894 bytes../../../../.cursor/hooks/before-submit-prompt.jsruns894 bytes../../../../.cursor/hooks/before-tab-file-read.jsruns446 bytes../../../../.cursor/hooks/before-tab-file-read.jsruns446 bytes../../../../.cursor/hooks/pre-compact.jsruns304 bytes../../../../.cursor/hooks/pre-compact.jsruns304 bytes../../../../.cursor/hooks/session-end.jsruns374 bytes../../../../.cursor/hooks/session-end.jsruns374 bytes../../../../.cursor/hooks/session-start.jsruns321 bytes../../../../.cursor/hooks/session-start.jsruns321 bytes../../../../.cursor/hooks/stop.jsruns310 bytes../../../../.cursor/hooks/stop.jsruns310 bytes../../../../.cursor/hooks/subagent-start.jsruns324 bytes../../../../.cursor/hooks/subagent-start.jsruns324 bytes../../../../.cursor/hooks/subagent-stop.jsruns326 bytes../../../../.cursor/hooks/subagent-stop.jsruns326 bytes../../../../commands/build-fix.mddoc2,724 bytes../../../../commands/checkpoint.mddoc1,722 bytes../../../../commands/claw.mddoc1,945 bytes../../../../commands/code-review.mddoc1,179 bytes../../../../commands/e2e.mddoc11,057 bytes../../../../commands/eval.mddoc2,724 bytes../../../../commands/evolve.mddoc4,666 bytes../../../../commands/go-build.mddoc4,000 bytes../../../../commands/go-review.mddoc3,739 bytes../../../../commands/go-test.mddoc6,093 bytes../../../../commands/instinct-export.mddoc1,817 bytes../../../../commands/instinct-import.mddoc3,105 bytes../../../../commands/instinct-status.mddoc1,708 bytes../../../../commands/learn-eval.mddoc3,732 bytes../../../../commands/learn.mddoc1,774 bytes../../../../commands/multi-backend.mddoc5,249 bytes../../../../commands/multi-execute.mddoc10,760 bytes../../../../commands/multi-frontend.mddoc5,404 bytes../../../../commands/multi-plan.mddoc8,637 bytes../../../../commands/multi-workflow.mddoc7,708 bytes../../../../commands/orchestrate.mddoc3,598 bytes../../../../commands/plan.mddoc3,518 bytes../../../../commands/pm2.mddoc7,317 bytes../../../../commands/projects.mddoc1,091 bytes../../../../commands/promote.mddoc1,375 bytes../../../../commands/python-review.mddoc7,145 bytes../../../../commands/refactor-clean.mddoc3,068 bytes../../../../commands/sessions.mddoc9,546 bytes../../../../commands/setup-pm.mddoc1,785 bytes../../../../commands/skill-create.mddoc4,853 bytes../../../../commands/tdd.mddoc8,816 bytes../../../../commands/test-coverage.mddoc2,900 bytes../../../../commands/update-codemaps.mddoc2,646 bytes../../../../commands/update-docs.mddoc3,177 bytes../../../../commands/verify.mddoc1,444 bytesSKILL.mdcore13,611 bytes../../../../hooks/README.mddoc7,718 bytes../../../../hooks/hooks.jsonasset7,332 bytes../../../../hooks/hooks.jsonasset7,332 bytes../../../../hooks/hooks.jsonasset7,332 bytes../../../../hooks/hooks.jsonasset7,332 bytes../../../../hooks/hooks.jsonasset7,332 bytes../../../../hooks/hooks.jsonasset7,332 bytes../../../../hooks/hooks.jsonasset7,332 bytes../../../../hooks/hooks.jsonasset7,332 bytes../../../../hooks/hooks.jsonasset7,332 bytes../../../../hooks/hooks.jsonasset7,332 bytes../../../../hooks/hooks.jsonasset7,332 bytes../../../../skills/continuous-learning-v2/hooks/observe.shruns6,732 bytes
Read SKILL.md
# 后端开发模式
适用于可扩展服务端应用程序的后端架构模式与最佳实践。
## API 设计模式
### RESTful API 结构
```typescript
// ✅ 基于资源的 URL
GET /api/markets # 资源列表
GET /api/markets/:id # 获取单个资源
POST /api/markets # 创建资源
PUT /api/markets/:id # 替换资源View the complete source on GitHubclickhouse-io
When your agent uses it
ClickHouse 数据库模式、查询优化、分析以及高性能分析工作负载的数据工程最佳实践。
What it loads into context
Frontmatter
31 tokensAlways available to the agent
SKILL.md
2,660 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
- 概览
- 表设计模式
- 查询优化模式
- 数据插入模式
- 物化视图 (Materialized Views)
- 性能监控
- 常见分析查询
- 数据流水线模式 (Data Pipeline Patterns)
- 最佳实践
Files
SKILL.mdcore9,949 bytes
Read SKILL.md
# ClickHouse 分析模式
针对高性能分析和数据工程的 ClickHouse 特定模式。
## 概览
ClickHouse 是一个用于联机分析处理(OLAP)的列式数据库管理系统(DBMS)。它针对大规模数据集上的快速分析查询进行了优化。
**主要功能:**
- 列式存储
- 数据压缩
- 并行查询执行
- 分布式查询
- 实时分析View the complete source on GitHubcoding-standards
When your agent uses it
TypeScript、JavaScript、React、Node.js 开发的通用编码标准、最佳实践和模式。
What it loads into context
Frontmatter
32 tokensAlways available to the agent
SKILL.md
3,205 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
- 代码质量原则
- TypeScript/JavaScript 标准
- React 最佳实践
- API 设计标准
- 文件结构
- 注释与文档
- 性能最佳实践
- 测试标准
- 代码异味 (Code Smells) 检测
Files
SKILL.mdcore11,662 bytes
Read SKILL.md
# 编码标准与最佳实践
适用于所有项目的通用编码标准。
## 代码质量原则
### 1. 可读性优先 (Readability First)
* 代码被阅读的次数远多于编写的次数
* 明确的变量名和函数名
* 优先考虑自描述代码而非注释
* 保持格式一致
### 2. KISS (Keep It Simple, Stupid)View the complete source on GitHubconfigure-ecc
When your agent uses it
Everything Claude Code 的交互式安装程序 —— 引导用户将技能(Skills)和规则(Rules)安装到用户级或项目级目录,验证路径,并在需要时优化已安装的文件。
What it loads into context
Frontmatter
52 tokensAlways available to the agent
SKILL.md
3,312 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
- 触发时机
- 前提条件
- 步骤 0: 克隆 ECC 仓库
- 步骤 1: 选择安装级别
- 步骤 2: 选择并安装技能
- 步骤 3: 选择并安装规则
- 步骤 4: 安装后验证
- 步骤 5: 优化已安装的文件(可选)
- 步骤 6: 安装摘要
- 故障排除
Files
SKILL.mdcore11,716 bytesSKILL.mdcore11,716 bytesSKILL.mdcore11,716 bytesSKILL.mdcore11,716 bytesSKILL.mdcore11,716 bytesSKILL.mdcore11,716 bytesSKILL.mdcore11,716 bytesSKILL.mdcore11,716 bytes
Read SKILL.md
# 配置 Everything Claude Code (ECC)
这是 Everything Claude Code 项目的交互式分步安装向导。使用 `AskUserQuestion` 引导用户选择性安装技能(Skills)和规则(Rules),验证其准确性并提供优化建议。
## 触发时机
- 当用户输入 "configure ecc"、"install ecc"、"setup everything claude code" 等指令时
- 当用户希望从此项目中选择性地安装技能或规则时
- 当用户希望验证或修复现有的 ECC 安装时
- 当用户希望为项目优化已安装的技能或规则时
## 前提条件
此技能(Skill)在启动前必须可供 Claude Code 访问。引导启动有两种方式:View the complete source on GitHubcontinuous-learning
When your agent uses it
自动从 Claude Code 会话(Session)中提取可重用的模式(Pattern),并将其作为已学习的技能(Skill)保存以备将来使用。
What it loads into context
Frontmatter
45 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
- 工作原理(How it Works)
- 配置(Configuration)
- 模式类型(Pattern Types)
- 钩子配置(Hook Configuration)
- 为什么使用 Stop 钩子
- 相关项目
- 对比笔记(调查:2025年1月)
Files
SKILL.mdcore3,549 bytes
Read SKILL.md
# 持续学习技能(Continuous Learning Skill)
Claude Code 会话结束时自动进行评估,提取可作为已学习技能保存的可重用模式(Pattern)。
## 工作原理(How it Works)
此技能在每个会话结束时作为 **Stop 钩子(Hook)** 执行:
1. **会话评估**:检查会话是否有足够的消息(默认:10 条以上)
2. **模式检测**:识别可从会话中提取的模式
3. **技能提取**:将有用的模式保存到 `~/.claude/skills/learned/`
## 配置(Configuration)
View the complete source on GitHubcontinuous-learning-v2
When your agent uses it
一种基于本能(Instinct)的训练系统,通过钩子(Hooks)观察会话,创建带有置信度评分的原子化本能,并将其进化为技能(Skills)、命令(Commands)或智能体(Agents)。
What it loads into context
Frontmatter
74 tokensAlways available to the agent
SKILL.md
2,421 tokensWhen the skill is activated
Reference documents
1,323 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- v2 新特性
- 本能模型(Instinct Model)
- 工作原理
- 快速入门
- 命令(Commands)
- 配置(Configuration)
- 文件结构
- 与 Skill Creator 的集成
- 置信度评分(Confidence Scoring)
- 为什么在观察中使用钩子(Hooks)而不是技能(Skills)?
- 向后兼容性
- 隐私(Privacy)
- 相关链接
Scripts executed separately
../../../../skills/continuous-learning-v2/hooks/observe.sh
Files
SKILL.mdcore9,353 bytesSKILL.mdcore9,353 bytesSKILL.mdcore9,353 bytesSKILL.mdcore9,353 bytesSKILL.mdcore9,353 bytesSKILL.mdcore9,353 bytesSKILL.mdcore9,353 bytesagents/observer.mddoc4,572 bytes../../../../skills/continuous-learning-v2/hooks/observe.shruns6,732 bytes
Read SKILL.md
# 持续学习(Continuous Learning)v2 - 基于本能(Instinct)的架构
这是一款先进的学习系统,能够通过带有置信度评分的小型已学习行为——“本能(Instinct)”,将 Claude Code 会话转化为可重用的知识。
## v2 新特性
| 特性 | v1 | v2 |
|---------|----|----|
| 观察(Observation) | Stop 钩子(会话结束时) | PreToolUse/PostToolUse(100% 可靠性) |
| 分析 | 主上下文(Main Context) | 后台智能体(Background Agent, Haiku) |
| 粒度 | 完整的技能(Skill) | 原子化“本能(Instinct)” |
| 置信度 | 无 | 0.3-0.9 加权 |
| 进化 | 直接转化为技能 | 本能 → 聚类 → 技能/命令/智能体 |
| 共享 | 无 | 本能导出/导入 |View the complete source on GitHubcpp-testing
When your agent uses it
仅在创建/更新/修复 C++ 测试、配置 GoogleTest/CTest、诊断失败或不稳定的测试、以及添加覆盖率或消毒器时使用。
What it loads into context
Frontmatter
48 tokensAlways available to the agent
SKILL.md
2,683 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
- 使用场景
- 核心概念
- TDD 工作流
- 代码示例
- 运行测试
- 调试失败
- 覆盖率 (Coverage)
- 消毒器 (Sanitizers)
- 不稳定测试 (Flaky Test) 的防护栏
- 最佳实践
- 可选附录:模糊测试与属性测试
- GoogleTest 的替代方案
Files
SKILL.mdcore9,669 bytesSKILL.mdcore9,669 bytesSKILL.mdcore9,669 bytesSKILL.mdcore9,669 bytesSKILL.mdcore9,669 bytesSKILL.mdcore9,669 bytes
Read SKILL.md
# C++ Testing(智能体技能)
这是一个基于 CMake/CTest 和 GoogleTest/GoogleMock 的、面向智能体(Agent)的现代 C++(C++17/20)测试工作流(Workflow)。
## 使用场景
- 创建新的 C++ 测试或修改现有测试
- 为 C++ 组件设计单元测试/集成测试覆盖率
- 添加测试覆盖率、CI 门禁和回归保护
- 配置 CMake/CTest 工作流以实现一致的执行
- 调查测试失败或不稳定(Flaky)的行为
- 启用消毒器(Sanitizers)进行内存/竞态诊断
### 不建议使用的场景View the complete source on GitHubdjango-patterns
When your agent uses it
Django 架构模式、使用 DRF 的 REST API 设计、ORM 最佳实践、缓存、信号(Signals)、中间件(Middleware)以及生产级 Django 应用。
What it loads into context
Frontmatter
48 tokensAlways available to the agent
SKILL.md
4,723 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
- 何时启用
- 项目结构
- 模型设计模式
- Django REST Framework 模式
- 服务层(Service Layer)模式
- 缓存策略
- 信号(Signals)
- 中间件(Middleware)
- 性能优化
- 快速参考
Files
SKILL.mdcore21,072 bytesSKILL.mdcore21,072 bytesSKILL.mdcore21,072 bytesSKILL.mdcore21,072 bytesSKILL.mdcore21,072 bytesSKILL.mdcore21,072 bytesSKILL.mdcore21,072 bytesSKILL.mdcore21,072 bytesSKILL.mdcore21,072 bytesSKILL.mdcore21,072 bytesSKILL.mdcore21,072 bytesSKILL.mdcore21,072 bytesSKILL.mdcore21,072 bytesSKILL.mdcore21,072 bytesSKILL.mdcore21,072 bytesSKILL.mdcore21,072 bytesSKILL.mdcore21,072 bytes
Read SKILL.md
# Django 开发模式
适用于构建可扩展且易于维护的应用程序的生产级 Django 架构模式。
## 何时启用
- 构建 Django Web 应用程序时
- 设计 Django REST Framework API 时
- 处理 Django ORM 和模型时
- 配置 Django 项目结构时
- 实现缓存、信号(Signals)、中间件(Middleware)时
## 项目结构
View the complete source on GitHubdjango-security
When your agent uses it
Django 安全最佳实践、身份验证(Authentication)、授权(Authorization)、CSRF 防护、SQL 注入防御、XSS 防御以及安全部署配置。
What it loads into context
Frontmatter
42 tokensAlways available to the agent
SKILL.md
3,977 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
- 何时激活
- 核心安全设置
- 身份验证(Authentication)
- 授权(Authorization)
- 防止 SQL 注入(SQL Injection)
- 防止跨站脚本攻击(XSS)
- CSRF 防护
- 文件上传安全
- API 安全
- 安全响应头
- 环境变量
- 安全事件日志记录
- 快速安全检查清单
Files
SKILL.mdcore16,319 bytesSKILL.mdcore16,319 bytesSKILL.mdcore16,319 bytesSKILL.mdcore16,319 bytesSKILL.mdcore16,319 bytesSKILL.mdcore16,319 bytesSKILL.mdcore16,319 bytesSKILL.mdcore16,319 bytesSKILL.mdcore16,319 bytesSKILL.mdcore16,319 bytesSKILL.mdcore16,319 bytesSKILL.mdcore16,319 bytesSKILL.mdcore16,319 bytesSKILL.mdcore16,319 bytesSKILL.mdcore16,319 bytesSKILL.mdcore16,319 bytesSKILL.mdcore16,319 bytesSKILL.mdcore16,319 bytesSKILL.mdcore16,319 bytesSKILL.mdcore16,319 bytesSKILL.mdcore16,319 bytes
Read SKILL.md
# Django 安全最佳实践
针对 Django 应用程序的全面安全指南,旨在防范常见脆弱性。
## 何时激活
- 配置 Django 身份验证(Authentication)与授权(Authorization)时
- 实现用户权限与角色(Role)时
- 配置生产环境安全设置时
- 审计 Django 应用程序的安全问题时
- 将 Django 应用程序部署到生产环境时
## 核心安全设置
View the complete source on GitHubdjango-tdd
When your agent uses it
Django testing strategies with pytest-django, TDD methodology, factory_boy, mocking, coverage, and testing Django REST Framework APIs.
What it loads into context
Frontmatter
35 tokensAlways available to the agent
SKILL.md
4,820 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
- 何时启用
- Django 的 TDD 工作流
- 设置
- Factory Boy
- 模型测试
- 视图测试
- DRF API 测试
- Mocking 与 Patching
- 集成测试
- 测试最佳实践
- 覆盖率
- 快速参考
Files
SKILL.mdcore21,012 bytesSKILL.mdcore21,012 bytesSKILL.mdcore21,012 bytesSKILL.mdcore21,012 bytesSKILL.mdcore21,012 bytesSKILL.mdcore21,012 bytesSKILL.mdcore21,012 bytesSKILL.mdcore21,012 bytesSKILL.mdcore21,012 bytesSKILL.mdcore21,012 bytesSKILL.mdcore21,012 bytesSKILL.mdcore21,012 bytesSKILL.mdcore21,012 bytesSKILL.mdcore21,012 bytes
Read SKILL.md
# Django 测试驱动开发 (TDD)
使用 pytest、factory_boy 和 Django REST Framework 进行 Django 应用程序的测试驱动开发。
## 何时启用
- 编写新的 Django 应用程序时
- 实现 Django REST Framework API 时
- 测试 Django 模型(Models)、视图(Views)、序列化器(Serializers)时
- 配置 Django 项目的测试基础设施时
## Django 的 TDD 工作流
### 红-绿-重构(Red-Green-Refactor)循环View the complete source on GitHubdjango-verification
When your agent uses it
Verification loop for Django projects: migrations, linting, tests with coverage, security scans, and deployment readiness checks before release or PR.
What it loads into context
Frontmatter
35 tokensAlways available to the agent
SKILL.md
3,236 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
- 阶段 1:环境检查
- 阶段 2:代码质量与格式化
- 阶段 3:数据库迁移(Migrations)
- 阶段 4:测试 + 覆盖率(Coverage)
- 阶段 5:安全扫描
- 阶段 6:Django 管理命令
- 阶段 7:性能检查
- 阶段 8:静态资源(Static Assets)
- 阶段 9:配置审查(Configuration Review)
- 阶段 10:日志设置
- 阶段 11:API 文档(针对 DRF)
- 阶段 12:差异审查(Diff Review)
- 输出模板
- 部署前检查清单(Deployment Checklist)
- 持续集成(CI)
- 快速参考
Files
SKILL.mdcore11,319 bytesSKILL.mdcore11,319 bytesSKILL.mdcore11,319 bytesSKILL.mdcore11,319 bytesSKILL.mdcore11,319 bytesSKILL.mdcore11,319 bytesSKILL.mdcore11,319 bytesSKILL.mdcore11,319 bytesSKILL.mdcore11,319 bytesSKILL.mdcore11,319 bytesSKILL.mdcore11,319 bytesSKILL.mdcore11,319 bytesSKILL.mdcore11,319 bytesSKILL.mdcore11,319 bytesSKILL.mdcore11,319 bytesSKILL.mdcore11,319 bytesSKILL.mdcore11,319 bytesSKILL.mdcore11,319 bytesSKILL.mdcore11,319 bytesSKILL.mdcore11,319 bytesSKILL.mdcore11,319 bytesSKILL.mdcore11,319 bytesSKILL.mdcore11,319 bytesSKILL.mdcore11,319 bytesSKILL.mdcore11,319 bytesSKILL.mdcore11,319 bytesSKILL.mdcore11,319 bytesSKILL.mdcore11,319 bytesSKILL.mdcore11,319 bytesSKILL.mdcore11,319 bytesSKILL.mdcore11,319 bytesSKILL.mdcore11,319 bytesSKILL.mdcore11,319 bytesSKILL.mdcore11,319 bytes
Read SKILL.md
# Django 验证循环(Verification Loop)
在提交 PR 前、发生重大更改后或部署前运行此循环,以确保 Django 应用的质量与安全性。
## 阶段 1:环境检查
```bash
# 检查 Python 版本
python --version # 应与项目要求一致
# 检查虚拟环境
which python
pip list --outdated
View the complete source on GitHubeval-harness
When your agent uses it
Claude Code 会话的正式评测框架,实现了评测驱动开发(EDD)原则
What it loads into context
Frontmatter
44 tokensAlways available to the agent
SKILL.md
1,653 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
- 哲学
- 评测类型
- 评测者类型
- 指标
- 评测工作流
- 集成模式
- 评测存储
- 最佳实践
- 示例:添加身份验证
Files
SKILL.mdcore5,487 bytesSKILL.mdcore5,487 bytesSKILL.mdcore5,487 bytes
Read SKILL.md
# 评测工具集(Eval Harness)技能
Claude Code 会话的正式评测框架,实现了评测驱动开发(Evaluation-Driven Development, EDD)原则。
## 哲学
评测驱动开发将评测视为“AI 开发的单元测试”:
- 在实现前定义预期行为
- 开发过程中持续运行评测
- 追踪每次变更的回归情况
- 使用 pass@k 指标衡量可靠性
## 评测类型
View the complete source on GitHubfrontend-patterns
When your agent uses it
适用于 React、Next.js、状态管理、性能优化和 UI 最佳实践的前端开发模式。
What it loads into context
Frontmatter
32 tokensAlways available to the agent
SKILL.md
3,682 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
- 组件模式
- 自定义 Hook 模式
- 状态管理模式
- 性能优化
- 表单处理模式
- 错误边界模式 (Error Boundary Pattern)
- 动画模式
- 无障碍性 (Accessibility) 模式
Files
SKILL.mdcore14,286 bytes
Read SKILL.md
# 前端开发模式
适用于 React、Next.js 和高性能用户界面的现代前端模式。
## 组件模式
### 组合优于继承 (Composition over Inheritance)
```typescript
// ✅ GOOD: 组件组合
interface CardProps {
children: React.ReactNode
variant?: 'default' | 'outlined'
}View the complete source on GitHubgolang-patterns
When your agent uses it
构建健壮、高效且可维护 Go 应用程序的惯用法(Idiomatic Go)、最佳实践与规范。
What it loads into context
Frontmatter
37 tokensAlways available to the agent
SKILL.md
3,860 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
- 何时启用
- 核心原则
- 错误处理模式(Error Handling Patterns)
- 并发处理模式(Concurrency Patterns)
- 接口设计(Interface Design)
- 包(Package)结构
- 结构体设计
- 内存与性能
- Go 工具链集成
- 快速参考:Go 惯用法
- 应避免的反模式(Anti-patterns)
Files
SKILL.mdcore14,280 bytesSKILL.mdcore14,280 bytes
Read SKILL.md
# Go 开发模式(Go Development Patterns)
用于构建健壮、高效且可维护应用程序的惯用法与最佳实践。
## 何时启用
- 编写新的 Go 代码时
- 评审 Go 代码时
- 重构现有 Go 代码时
- 设计 Go 软件包(Package)/ 模块(Module)时
## 核心原则
### 1. 简单与清晰View the complete source on GitHubgolang-testing
When your agent uses it
保证测试驱动开发与 Go 代码高质量的全面测试策略。
What it loads into context
Frontmatter
25 tokensAlways available to the agent
SKILL.md
5,517 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
- 何时激活
- 核心原则
- 测试组织
- 断言(Assertions)与辅助函数(Helpers)
- 模拟(Mocking)与桩(Stubs)
- 测试 HTTP 处理程序(Handlers)
- 数据库测试
- 基准测试(Benchmarks)
- 模糊测试(Fuzzing Tests)
- 测试覆盖率(Test Coverage)
- 集成测试(Integration Tests)
- 测试并行化(Parallelizing Tests)
- Go 工具集成
- 最佳实践
- 应避免的反模式(Anti-patterns)
- 快速参考
Files
SKILL.mdcore20,181 bytesSKILL.mdcore20,181 bytesSKILL.mdcore20,181 bytesSKILL.mdcore20,181 bytesSKILL.mdcore20,181 bytes
Read SKILL.md
# Go 测试 (Go Testing)
保证测试驱动开发(TDD)与 Go 代码高质量的全面测试策略。
## 何时激活
- 编写新的 Go 代码时
- 审查(Review)Go 代码时
- 改进现有测试时
- 提高测试覆盖率(Test Coverage)时
- 调试与修复 Bug 时
## 核心原则
View the complete source on GitHubiterative-retrieval
When your agent uses it
为了解决子智能体(Sub-agent)的上下文问题,逐步优化上下文获取的模式
What it loads into context
Frontmatter
31 tokensAlways available to the agent
SKILL.md
1,717 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
- 问题
- 解决方案:反复检索
- 实践案例
- 与智能体集成
- 最佳实践
- 相关项目
Files
SKILL.mdcore6,539 bytes
Read SKILL.md
# 反复检索模式 (Iterative Retrieval Pattern)
解决多智能体工作流(Multi-agent Workflow)中的“上下文问题”。子智能体在开始工作之前,通常不知道需要哪些上下文。
## 问题
子智能体(Sub-agent)在启动时上下文有限。它们通常不知道:
- 哪些文件包含相关的代码
- 代码库中存在哪些模式(Patterns)
- 项目使用什么术语
标准方法往往会失败:
- **发送全部**:超出上下文限制(Context Limit)
- **什么都不发**:智能体缺乏关键信息View the complete source on GitHubjava-coding-standards
When your agent uses it
适用于 Spring Boot 服务的 Java 编码规范:命名、不可变性、Optional 使用、流(Stream)、异常、泛型及项目布局。
What it loads into context
Frontmatter
45 tokensAlways available to the agent
SKILL.md
1,045 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
- 核心原则
- 命名
- 不可变性
- Optional 的使用
- 流(Stream)最佳实践
- 异常
- 泛型与类型安全
- 项目结构 (Maven/Gradle)
- 格式与样式
- 应避免的代码异味 (Code Smells)
- 日志记录
- Null 处理
- 测试预期
Files
SKILL.mdcore3,945 bytes
Read SKILL.md
# Java 编码规范
适用于 Spring Boot 服务中易读且可维护的 Java (17+) 代码标准。
## 核心原则
- 清晰度优先于巧妙性
- 默认不可变;最小化共享的可变状态
- 抛出有意义的异常以实现早期失败(Fail fast)
- 一致的命名与包结构
## 命名
```javaView the complete source on GitHubjpa-patterns
When your agent uses it
Spring Boot 中用于实体设计、关联关系、查询优化、事务、审计、索引、分页和连接池的 JPA/Hibernate 模式。
What it loads into context
Frontmatter
42 tokensAlways available to the agent
SKILL.md
1,140 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
- 实体设计 (Entity Design)
- 关联关系与 N+1 问题预防
- 存储库模式 (Repository Pattern)
- 事务 (Transactions)
- 分页 (Pagination)
- 索引创建与性能优化
- 连接池 (Connection Pooling - HikariCP)
- 缓存 (Caching)
- 数据库迁移 (Migration)
- 数据访问测试
Files
SKILL.mdcore4,623 bytes
Read SKILL.md
# JPA/Hibernate 模式
用于 Spring Boot 中的数据建模、存储库(Repository)和性能调优。
## 实体设计 (Entity Design)
```java
@Entity
@Table(name = "markets", indexes = {
@Index(name = "idx_markets_slug", columnList = "slug", unique = true)
})
@EntityListeners(AuditingEntityListener.class)
public class MarketEntity {
@Id @GeneratedValue(strategy = GenerationType.IDENTITY)View the complete source on GitHubnutrient-document-processing
When your agent uses it
使用 Nutrient DWS API 进行文档处理、转换、OCR、提取、脱敏、签名以及表单填充。支持 PDF、DOCX、XLSX、PPTX、HTML 和图像格式。
What it loads into context
Frontmatter
58 tokensAlways available to the agent
SKILL.md
1,891 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
- 设置 (Setup)
- 操作 (Operations)
- MCP 服务端 (代替方案)
- 使用场景
- 相关链接
Files
SKILL.mdcore6,180 bytesSKILL.mdcore6,180 bytesSKILL.mdcore6,180 bytesSKILL.mdcore6,180 bytesSKILL.mdcore6,180 bytesSKILL.mdcore6,180 bytesSKILL.mdcore6,180 bytesSKILL.mdcore6,180 bytesSKILL.mdcore6,180 bytes
Read SKILL.md
# Nutrient 文档处理 (Document Processing)
使用 [Nutrient DWS 处理程序 API (Processor API)](https://www.nutrient.io/api/) 处理文档。它可以进行格式转换、文本与表格提取、扫描文档的光学字符识别 (OCR)、个人身份信息 (PII) 脱敏、添加水印、数字签名以及 PDF 表单填充。
## 设置 (Setup)
请在 **[nutrient.io](https://dashboard.nutrient.io/sign_up/?product=processor)** 获取免费的 API 密钥。
```bash
[Credential-related source omitted]
```
所有请求都以多部分 POST (multipart POST) 的形式发送到 `https://api.nutrient.io/build`,其中包含 `instructions` JSON 字段。
View the complete source on GitHubpostgres-patterns
When your agent uses it
PostgreSQL 数据库模式,涵盖查询优化、架构设计、索引和安全。基于 Supabase 最佳实践。
What it loads into context
Frontmatter
36 tokensAlways available to the agent
SKILL.md
1,167 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
- 触发时机
- 快速参考
- 相关
Files
SKILL.mdcore3,982 bytes
Read SKILL.md
# PostgreSQL 模式 (Patterns)
PostgreSQL 最佳实践快速参考。如需详细指导,请使用 `database-reviewer` 智能体 (Agent)。
## 触发时机
- 创建 SQL 查询或迁移 (Migration) 时
- 设计数据库架构 (Schema) 时
- 排查低速查询时
- 实现行级安全 (Row Level Security) 时
- 配置连接池 (Connection Pooling) 时
## 快速参考
View the complete source on GitHubWhen your agent uses it
What it loads into context
Frontmatter
0 tokensAlways available to the agent
SKILL.md
2,328 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
- 使用场景
- 架构概览
- 文件结构
- 代码模式
- 测试要求
- 部署工作流
- 重要规则
- 相关技能
Files
SKILL.mdcore9,659 bytesSKILL.mdcore9,659 bytesSKILL.mdcore9,659 bytesSKILL.mdcore9,659 bytesSKILL.mdcore9,659 bytesSKILL.mdcore9,659 bytesSKILL.mdcore9,659 bytesSKILL.mdcore9,659 bytesSKILL.mdcore9,659 bytesSKILL.mdcore9,659 bytes
Read SKILL.md
# 项目指南技能(示例)
这是一个项目专用技能(Skill)的示例。请将其用作你自己项目的模板。
基于实际的生产环境应用程序:[Zenith](https://zenith.chat) - AI 驱动的客户发现平台。
---
## 使用场景
在处理为此技能设计的特定项目时请参考此文档。项目技能(Project Skills)包括:
- 架构概览
- 文件结构
- 代码模式
- 测试要求View the complete source on GitHubpython-patterns
When your agent uses it
Pythonic 惯用法、PEP 8 标准、类型提示,以及构建稳健、高效且可维护 Python 应用的最佳实践。
What it loads into context
Frontmatter
41 tokensAlways available to the agent
SKILL.md
4,598 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
- 何时启用
- 核心原则
- 类型提示(Type Hints)
- 错误处理模式
- 上下文管理器(Context Managers)
- 推导式与生成器
- 数据类(Data Classes)与具名元组(Named Tuples)
- 装饰器(Decorators)
- 并发模式
- 包结构
- 内存与性能
- Python 工具集成
- 快速参考:Python 惯用法
- 应避免的反模式
Files
SKILL.mdcore16,743 bytesSKILL.mdcore16,743 bytesSKILL.mdcore16,743 bytesSKILL.mdcore16,743 bytesSKILL.mdcore16,743 bytesSKILL.mdcore16,743 bytesSKILL.mdcore16,743 bytesSKILL.mdcore16,743 bytesSKILL.mdcore16,743 bytesSKILL.mdcore16,743 bytesSKILL.mdcore16,743 bytesSKILL.mdcore16,743 bytesSKILL.mdcore16,743 bytesSKILL.mdcore16,743 bytesSKILL.mdcore16,743 bytesSKILL.mdcore16,743 bytesSKILL.mdcore16,743 bytesSKILL.mdcore16,743 bytesSKILL.mdcore16,743 bytesSKILL.mdcore16,743 bytesSKILL.mdcore16,743 bytesSKILL.mdcore16,743 bytesSKILL.mdcore16,743 bytesSKILL.mdcore16,743 bytesSKILL.mdcore16,743 bytesSKILL.mdcore16,743 bytesSKILL.mdcore16,743 bytesSKILL.mdcore16,743 bytesSKILL.mdcore16,743 bytesSKILL.mdcore16,743 bytesSKILL.mdcore16,743 bytesSKILL.mdcore16,743 bytesSKILL.mdcore16,743 bytesSKILL.mdcore16,743 bytes
Read SKILL.md
# Python 开发模式
用于构建稳健、高效且可维护应用的惯用 Python 模式与最佳实践。
## 何时启用
- 编写新的 Python 代码时
- 审查 Python 代码时
- 重构现有 Python 代码时
- 设计 Python 包/模块时
## 核心原则
### 1. 可读性至关重要View the complete source on GitHubpython-testing
When your agent uses it
使用 pytest、TDD 方法论、固件(Fixtures)、模拟(Mocking)、参数化及覆盖率要求的 Python 测试策略。
What it loads into context
Frontmatter
38 tokensAlways available to the agent
SKILL.md
4,935 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
- 何时启用
- 核心测试哲学
- pytest 基础
- 固件 (Fixtures)
- 参数化 (Parameterization)
- 标记 (Markers) 与测试选择
- 模拟 (Mocking) 与补丁 (Patching)
- 测试异步代码
- 测试异常
- 测试副作用
- 测试组织
- 最佳实践
- 常用模式
- pytest 配置
- 运行测试
- 快速参考
Files
SKILL.mdcore19,079 bytesSKILL.mdcore19,079 bytesSKILL.mdcore19,079 bytesSKILL.mdcore19,079 bytesSKILL.mdcore19,079 bytesSKILL.mdcore19,079 bytesSKILL.mdcore19,079 bytesSKILL.mdcore19,079 bytesSKILL.mdcore19,079 bytesSKILL.mdcore19,079 bytesSKILL.mdcore19,079 bytesSKILL.mdcore19,079 bytesSKILL.mdcore19,079 bytesSKILL.mdcore19,079 bytesSKILL.mdcore19,079 bytesSKILL.mdcore19,079 bytesSKILL.mdcore19,079 bytesSKILL.mdcore19,079 bytesSKILL.mdcore19,079 bytesSKILL.mdcore19,079 bytesSKILL.mdcore19,079 bytesSKILL.mdcore19,079 bytesSKILL.mdcore19,079 bytesSKILL.mdcore19,079 bytesSKILL.mdcore19,079 bytesSKILL.mdcore19,079 bytesSKILL.mdcore19,079 bytesSKILL.mdcore19,079 bytesSKILL.mdcore19,079 bytesSKILL.mdcore19,079 bytesSKILL.mdcore19,079 bytesSKILL.mdcore19,079 bytesSKILL.mdcore19,079 bytesSKILL.mdcore19,079 bytesSKILL.mdcore19,079 bytesSKILL.mdcore19,079 bytesSKILL.mdcore19,079 bytesSKILL.mdcore19,079 bytes
Read SKILL.md
# Python 测试模式
使用 pytest、TDD 方法论和最佳实践的 Python 应用程序全面测试策略。
## 何时启用
- 编写新的 Python 代码时(遵循 TDD:红、绿、重构)
- 设计 Python 项目的测试套件时
- 审查 Python 测试覆盖率时
- 搭建测试基础设施时
## 核心测试哲学
### 测试驱动开发 (TDD)View the complete source on GitHubsecurity-review
When your agent uses it
在添加身份验证、处理用户输入、操作机密信息(Secrets)、创建 API 端点以及实现支付/敏感功能时使用此技能。提供全面的安全检查清单和模式。
What it loads into context
Frontmatter
50 tokensAlways available to the agent
SKILL.md
3,491 tokensWhen the skill is activated
Reference documents
2,957 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- 激活时机
- 安全检查清单
- 安全测试
- 部署前安全检查清单
- 资源
Files
SKILL.mdcore12,412 bytesSKILL.mdcore12,412 bytesSKILL.mdcore12,412 bytescloud-infrastructure-security.mddoc10,423 bytes
Read SKILL.md
# 安全审查技能 (Security Review Skill)
此技能旨在确保所有代码遵循安全最佳实践,并识别潜在漏洞。
## 激活时机
- 实现身份验证 (Authentication) 或授权 (Authorization) 时
- 处理用户输入或文件上传时
- 创建新的 API 端点时
- 操作机密信息 (Secrets) 或凭据时
- 实现支付功能时
- 存储或传输敏感数据时
- 集成第三方 API 时
View the complete source on GitHubsecurity-scan
When your agent uses it
使用 AgentShield 扫描 Claude Code 配置(.claude/ 目录)中的安全漏洞、配置错误和注入风险。检查 CLAUDE.md、settings.json、MCP 服务端、钩子(Hooks)和智能体(Agents)定义。
What it loads into context
Frontmatter
65 tokensAlways available to the agent
SKILL.md
1,385 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
- 启动时机
- 扫描对象
- 前提条件
- 使用方法
- 严重程度分级 (Severity Levels)
- 结果解读
- 链接
Files
SKILL.mdcore4,574 bytesSKILL.mdcore4,574 bytesSKILL.mdcore4,574 bytesSKILL.mdcore4,574 bytesSKILL.mdcore4,574 bytesSKILL.mdcore4,574 bytesSKILL.mdcore4,574 bytes
Read SKILL.md
# 安全扫描技能 (Security Scan Skill)
使用 [AgentShield](https://github.com/affaan-m/agentshield) 审计 Claude Code 配置的安全问题。
## 启动时机
- 设置新的 Claude Code 项目时
- 修改 `.claude/settings.json`、`CLAUDE.md` 或 MCP 配置后
- 提交配置变更前
- 接入具有现有 Claude Code 配置的新仓库时
- 定期进行安全健康检查
## 扫描对象
View the complete source on GitHubspringboot-patterns
When your agent uses it
Spring Boot 架构模式、REST API 设计、分层服务、数据访问、缓存、异步处理与日志。适用于 Java Spring Boot 后端开发。
What it loads into context
Frontmatter
45 tokensAlways available to the agent
SKILL.md
2,332 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
- REST API 结构
- 仓库模式(Repository Pattern, Spring Data JPA)
- 带事务的服务层
- DTO 与校验(Validation)
- 异常处理(Exception Handling)
- 缓存(Caching)
- 异步处理
- 日志(Logging, SLF4J)
- 中间件 / 过滤器(Middleware / Filter)
- 分页与排序
- 具备容错能力的外部调用(Resilient External Calls)
- 限流(Rate Limiting, Filter + Bucket4j)
- 后台任务
- 可观测性(Observability)
- 生产环境默认实践
Files
SKILL.mdcore9,740 bytes
Read SKILL.md
# Spring Boot 开发模式
为构建可扩展的生产级服务提供的 Spring Boot 架构与 API 模式。
## REST API 结构
```java
@RestController
@RequestMapping("/api/markets")
@Validated
class MarketController {
private final MarketService marketService;
MarketController(MarketService marketService) {View the complete source on GitHubspringboot-security
When your agent uses it
Spring Boot 服务的 Spring Security 身份验证/授权、验证、CSRF、密钥、响应头、速率限制和依赖项安全最佳实践。
What it loads into context
Frontmatter
42 tokensAlways available to the agent
SKILL.md
1,075 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
- 身份验证(Authentication)
- 授权(Authorization)
- 输入验证(Input Validation)
- SQL 注入防护
- CSRF 防护
- 密钥管理(Secrets Management)
- 安全响应头(Security Headers)
- 速率限制(Rate Limiting)
- 依赖项安全(Dependency Security)
- 日志与 PII(个人识别信息)
- 文件上传
- 发布前检查清单
Files
SKILL.mdcore4,146 bytes
Read SKILL.md
# Spring Boot 安全审查
在添加身份验证、处理输入、创建端点或处理敏感密钥时使用。
## 身份验证(Authentication)
- 优先使用无状态 JWT 或带有吊销列表的不透明令牌(Opaque Token)
- 对于会话,使用 `httpOnly`、`Secure`、`SameSite=Strict` 的 Cookie
- 在 `OncePerRequestFilter` 或资源服务器中验证令牌
```java
@Component
public class JwtAuthFilter extends OncePerRequestFilter {
private final JwtService jwtService;View the complete source on GitHubspringboot-tdd
When your agent uses it
使用 JUnit 5, Mockito, MockMvc, Testcontainers 和 JaCoCo 进行 Spring Boot 的测试驱动开发(TDD)。适用于添加新功能、修复 bug 或重构场景。
What it loads into context
Frontmatter
54 tokensAlways available to the agent
SKILL.md
1,092 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
- 何时使用
- 工作流 (Workflow)
- 单元测试 (Unit Testing - JUnit 5 + Mockito)
- Web 层测试 (Web Layer Testing - MockMvc)
- 集成测试 (Integration Testing - SpringBootTest)
- 持久化测试 (Persistence Testing - DataJpaTest)
- Testcontainers
- 覆盖率 (Coverage - JaCoCo)
- 断言 (Assertions)
- 测试数据生成器 (Test Data Builder)
- CI 命令 (CI Commands)
Files
SKILL.mdcore4,147 bytes
Read SKILL.md
# Spring Boot TDD 工作流 (Spring Boot TDD Workflow)
为 Spring Boot 服务提供测试驱动开发(TDD)指南,要求覆盖率达到 80% 以上(单元测试 + 集成测试)。
## 何时使用
- 新功能或新端点(Endpoint)
- Bug 修复或重构
- 添加数据访问逻辑或安全规则
## 工作流 (Workflow)
1) 先写测试(且测试应当失败)
2) 实现能让测试通过的最小化代码View the complete source on GitHubspringboot-verification
When your agent uses it
Spring Boot 项目的验证循环:构建、静态分析、带有覆盖率的测试、安全扫描以及发布或 PR 前的差异审查。
What it loads into context
Frontmatter
42 tokensAlways available to the agent
SKILL.md
696 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
- 阶段 1:构建
- 阶段 2:静态分析
- 阶段 3:测试 + 覆盖率
- 阶段 4:安全扫描
- 阶段 5:Lint/格式化(可选门禁)
- 阶段 6:差异审查 (Diff Review)
- 输出模板
- 持续模式
Files
SKILL.mdcore2,297 bytesSKILL.mdcore2,297 bytesSKILL.mdcore2,297 bytesSKILL.mdcore2,297 bytesSKILL.mdcore2,297 bytesSKILL.mdcore2,297 bytesSKILL.mdcore2,297 bytesSKILL.mdcore2,297 bytes
Read SKILL.md
# Spring Boot 验证循环
在提交 PR、发生重大变更后或部署前执行。
## 阶段 1:构建
```bash
mvn -T 4 clean verify -DskipTests
# 或者
./gradlew clean assemble -x test
```
如果构建失败,请停止并修复问题。
View the complete source on GitHubstrategic-compact
When your agent uses it
建议在逻辑间隔处进行手动压缩(Manual Compaction),以在整个任务阶段保持上下文(Context),而非随意的自动压缩。
What it loads into context
Frontmatter
46 tokensAlways available to the agent
SKILL.md
605 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
- 为什么需要策略性压缩?
- 工作原理
- 钩子(Hook)配置
- 配置
- 最佳实践
- 相关资源
Files
SKILL.mdcore2,092 bytes
Read SKILL.md
# 策略性压缩(Strategic Compact)技能
建议在工作流的战略点手动执行 `/compact` 命令,而不是依赖随意的自动压缩。
## 为什么需要策略性压缩?
自动压缩会在任意点触发:
- 通常发生在任务中途,导致丢失关键上下文
- 无法识别任务的逻辑边界
- 可能会中断复杂的跨步骤操作
在逻辑边界处进行策略性压缩:
- **探索后、执行前** - 压缩研究上下文,保留实现计划
- **里程碑完成后** - 为下一阶段开启全新开始View the complete source on GitHubtdd-workflow
When your agent uses it
在创建新功能、修复 Bug 或重构代码时使用此技能。强制执行测试驱动开发(TDD),要求包括单元测试、集成测试和 E2E 测试在内的测试覆盖率达到 80% 以上。
What it loads into context
Frontmatter
66 tokensAlways available to the agent
SKILL.md
2,820 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
- 何时启用
- 核心原则
- TDD 工作流步骤
- 测试模式
- 测试文件结构
- 外部服务 Mock
- 测试覆盖率验证
- 应避免的常见测试错误
- 持续测试
- 最佳实践
- 成功指标
Files
SKILL.mdcore10,033 bytesSKILL.mdcore10,033 bytesSKILL.mdcore10,033 bytesSKILL.mdcore10,033 bytesSKILL.mdcore10,033 bytesSKILL.mdcore10,033 bytesSKILL.mdcore10,033 bytes
Read SKILL.md
# 测试驱动开发(TDD)工作流
此技能(Skill)旨在确保所有代码开发都遵循具有全面测试覆盖率的测试驱动开发(TDD)原则。
## 何时启用
- 创建新功能或特性
- 修复 Bug 或问题
- 重构现有代码
- 添加 API 接口(Endpoints)
- 创建新组件
## 核心原则
View the complete source on GitHubWhen your agent uses it
What it loads into context
Frontmatter
0 tokensAlways available to the agent
SKILL.md
822 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
- 使用场景
- 验证阶段
- 输出格式
- 持续模式
- 与钩子(Hooks)集成
Files
SKILL.mdcore2,634 bytesSKILL.mdcore2,634 bytesSKILL.mdcore2,634 bytesSKILL.mdcore2,634 bytesSKILL.mdcore2,634 bytesSKILL.mdcore2,634 bytesSKILL.mdcore2,634 bytes
Read SKILL.md
# 验证循环(Verification Loop)技能
针对 Claude Code 会话的全面验证系统。
## 使用场景
在以下情况调用此技能:
- 完成功能或重大代码变更后
- 创建拉取请求(PR)之前
- 需要确认质量门禁(Quality Gates)是否通过时
- 重构代码之后
## 验证阶段
### 阶段 1:构建验证(Build Verification)View the complete source on GitHubapi-design
When your agent uses it
REST API设计模式,包括资源命名、状态码、分页、过滤、错误响应、版本控制和生产API的速率限制。
What it loads into context
Frontmatter
39 tokensAlways available to the agent
SKILL.md
3,571 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
- 何时启用
- 资源设计
- HTTP 方法和状态码
- 响应格式
- 分页
- 过滤、排序和搜索
- 认证和授权
- 速率限制
- 版本控制
- 实现模式
- API 设计清单
Files
SKILL.mdcore12,991 bytesSKILL.mdcore12,991 bytes
Read SKILL.md
# API 设计模式
用于设计一致、对开发者友好的 REST API 的约定和最佳实践。
## 何时启用
* 设计新的 API 端点时
* 审查现有的 API 契约时
* 添加分页、过滤或排序功能时
* 为 API 实现错误处理时
* 规划 API 版本策略时
* 构建面向公众或合作伙伴的 API 时
## 资源设计View the complete source on GitHubarticle-writing
When your agent uses it
根据提供的示例或品牌指导,以独特的语气撰写文章、指南、博客帖子、教程、新闻简报等长篇内容。当用户需要超过一段的精致书面内容时使用,尤其是当语气一致性、结构和可信度至关重要时。
What it loads into context
Frontmatter
75 tokensAlways available to the agent
SKILL.md
848 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
- 何时使用
- 核心规则
- 声音捕捉工作流
- 禁止模式
- 写作流程
- 结构指导
- 质量检查
Files
SKILL.mdcore2,936 bytes
Read SKILL.md
# 文章写作
撰写听起来像真人或真实品牌的长篇内容,而非通用的 AI 输出。
## 何时使用
* 起草博客文章、散文、发布帖、指南、教程或新闻简报时
* 将笔记、转录稿或研究转化为精炼文章时
* 根据示例匹配现有的创始人、运营者或品牌声音时
* 强化已有长篇文稿的结构、节奏和论据时
## 核心规则
1. **以具体事物开头**:示例、输出、轶事、数据、截图描述或代码块。View the complete source on GitHubbackend-patterns
When your agent uses it
后端架构模式、API设计、数据库优化以及适用于Node.js、Express和Next.js API路由的服务器端最佳实践。
What it loads into context
Frontmatter
41 tokensAlways available to the agent
SKILL.md
3,413 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
- 何时激活
- API 设计模式
- 数据库模式
- 缓存策略
- 错误处理模式
- 认证与授权
- 速率限制
- 后台作业与队列
- 日志记录与监控
Files
SKILL.mdcore13,676 bytes
Read SKILL.md
# 后端开发模式
用于可扩展服务器端应用程序的后端架构模式和最佳实践。
## 何时激活
* 设计 REST 或 GraphQL API 端点时
* 实现仓储层、服务层或控制器层时
* 优化数据库查询(N+1问题、索引、连接池)时
* 添加缓存(Redis、内存缓存、HTTP 缓存头)时
* 设置后台作业或异步处理时
* 为 API 构建错误处理和验证结构时
* 构建中间件(认证、日志记录、速率限制)时
View the complete source on GitHubclickhouse-io
When your agent uses it
ClickHouse数据库模式、查询优化、分析以及高性能分析工作负载的数据工程最佳实践。
What it loads into context
Frontmatter
33 tokensAlways available to the agent
SKILL.md
2,659 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
- 何时激活
- 概述
- 表设计模式
- 查询优化模式
- 数据插入模式
- 物化视图
- 性能监控
- 常见分析查询
- 数据流水线模式
- 最佳实践
Files
SKILL.mdcore10,048 bytesSKILL.mdcore10,048 bytes
Read SKILL.md
# ClickHouse 分析模式
用于高性能分析和数据工程的 ClickHouse 特定模式。
## 何时激活
* 设计 ClickHouse 表架构(MergeTree 引擎选择)
* 编写分析查询(聚合、窗口函数、连接)
* 优化查询性能(分区裁剪、投影、物化视图)
* 摄取大量数据(批量插入、Kafka 集成)
* 为分析目的从 PostgreSQL/MySQL 迁移到 ClickHouse
* 实现实时仪表板或时间序列分析
## 概述View the complete source on GitHubcoding-standards
When your agent uses it
适用于TypeScript、JavaScript、React和Node.js开发的通用编码标准、最佳实践和模式。
What it loads into context
Frontmatter
37 tokensAlways available to the agent
SKILL.md
3,033 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
- 何时激活
- 代码质量原则
- TypeScript/JavaScript 标准
- React 最佳实践
- API 设计标准
- 文件组织
- 注释与文档
- 性能最佳实践
- 测试标准
- 代码异味检测
Files
SKILL.mdcore11,519 bytes
Read SKILL.md
# 编码标准与最佳实践
适用于所有项目的通用编码标准。
## 何时激活
* 开始新项目或新模块时
* 审查代码质量和可维护性时
* 重构现有代码以遵循约定时
* 强制执行命名、格式或结构一致性时
* 设置代码检查、格式化或类型检查规则时
* 引导新贡献者熟悉编码规范时
## 代码质量原则View the complete source on GitHubconfigure-ecc
When your agent uses it
Everything Claude Code 的交互式安装程序 — 引导用户选择并安装技能和规则到用户级或项目级目录,验证路径,并可选择优化已安装文件。
What it loads into context
Frontmatter
48 tokensAlways available to the agent
SKILL.md
3,379 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
- 何时激活
- 先决条件
- 步骤 0:克隆 ECC 仓库
- 步骤 1:选择安装级别
- 步骤 2:选择并安装技能
- 步骤 3:选择并安装规则
- 步骤 4:安装后验证
- 步骤 5:优化已安装文件(可选)
- 步骤 6:安装摘要
- 故障排除
Files
SKILL.mdcore12,348 bytesSKILL.mdcore12,348 bytesSKILL.mdcore12,348 bytesSKILL.mdcore12,348 bytesSKILL.mdcore12,348 bytesSKILL.mdcore12,348 bytesSKILL.mdcore12,348 bytesSKILL.mdcore12,348 bytes
Read SKILL.md
# 配置 Everything Claude Code (ECC)
一个交互式、分步安装向导,用于 Everything Claude Code 项目。使用 `AskUserQuestion` 引导用户选择性安装技能和规则,然后验证正确性并提供优化。
## 何时激活
* 用户说 "configure ecc"、"install ecc"、"setup everything claude code" 或类似表述
* 用户想要从此项目中选择性安装技能或规则
* 用户想要验证或修复现有的 ECC 安装
* 用户想要为其项目优化已安装的技能或规则
## 先决条件
此技能必须在激活前对 Claude Code 可访问。有两种引导方式:View the complete source on GitHubcontent-engine
When your agent uses it
为X、LinkedIn、TikTok、YouTube、新闻通讯和跨平台重新利用的多平台活动创建平台原生内容系统。适用于当用户需要社交媒体帖子、帖子串、脚本、内容日历,或一个源资产在多个平台上清晰适配时。
What it loads into context
Frontmatter
74 tokensAlways available to the agent
SKILL.md
808 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
- 何时激活
- 首要问题
- 核心规则
- 平台指南
- 内容再利用流程
- 交付物
- 质量门槛
Files
SKILL.mdcore2,718 bytes
Read SKILL.md
# 内容引擎
将一个想法转化为强大的、平台原生的内容,而不是到处发布相同的东西。
## 何时激活
* 撰写 X 帖子或主题串时
* 起草 LinkedIn 帖子或发布更新时
* 编写短视频或 YouTube 解说稿时
* 将文章、播客、演示或文档改写成社交内容时
* 围绕发布、里程碑或主题制定轻量级内容计划时
## 首要问题
View the complete source on GitHubcontent-hash-cache-pattern
When your agent uses it
使用SHA-256内容哈希缓存昂贵的文件处理结果——路径无关、自动失效、服务层分离。
What it loads into context
Frontmatter
41 tokensAlways available to the agent
SKILL.md
1,464 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
- 何时激活
- 核心模式
- 关键设计决策
- 最佳实践
- 应避免的反模式
- 适用场景
- 不适用场景
Files
SKILL.mdcore5,621 bytesSKILL.mdcore5,621 bytesSKILL.mdcore5,621 bytesSKILL.mdcore5,621 bytesSKILL.mdcore5,621 bytesSKILL.mdcore5,621 bytes
Read SKILL.md
# 内容哈希文件缓存模式
使用 SHA-256 内容哈希作为缓存键,缓存昂贵的文件处理结果(PDF 解析、文本提取、图像分析)。与基于路径的缓存不同,此方法在文件移动/重命名后仍然有效,并在内容更改时自动失效。
## 何时激活
* 构建文件处理管道时(PDF、图像、文本提取)
* 处理成本高且同一文件被重复处理时
* 需要一个 `--cache/--no-cache` CLI 选项时
* 希望在不修改现有纯函数的情况下为其添加缓存时
## 核心模式
### 1. 基于内容哈希的缓存键View the complete source on GitHubcontinuous-learning
When your agent uses it
自动从Claude Code会话中提取可重复使用的模式,并将其保存为学习到的技能以供将来使用。
What it loads into context
Frontmatter
39 tokensAlways available to the agent
SKILL.md
1,067 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
- 何时激活
- 工作原理
- 配置
- 模式类型
- 钩子设置
- 为什么使用停止钩子?
- 相关
- 对比说明(研究:2025年1月)
Files
SKILL.mdcore3,574 bytes
Read SKILL.md
# 持续学习技能
自动评估 Claude Code 会话的结尾,以提取可重用的模式,这些模式可以保存为学习到的技能。
## 何时激活
* 设置从 Claude Code 会话中自动提取模式
* 为会话评估配置停止钩子
* 在 `~/.claude/skills/learned/` 中审查或整理已学习的技能
* 调整提取阈值或模式类别
* 比较 v1(本方法)与 v2(基于本能的方法)
## 工作原理
View the complete source on GitHubcontinuous-learning-v2
When your agent uses it
基于本能的学习系统,通过钩子观察会话,创建具有置信度评分的原子本能,并将其进化为技能/命令/代理。
What it loads into context
Frontmatter
60 tokensAlways available to the agent
SKILL.md
2,348 tokensWhen the skill is activated
Reference documents
1,236 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- 何时激活
- v2 的新特性
- 本能模型
- 工作原理
- 快速开始
- 命令
- 配置
- 文件结构
- 与技能创建器的集成
- 置信度评分
- 为什么用钩子而非技能进行观察?
- 向后兼容性
- 隐私
- 相关链接
Scripts executed separately
../../../../skills/continuous-learning-v2/hooks/observe.sh
Files
SKILL.mdcore9,123 bytesSKILL.mdcore9,123 bytesSKILL.mdcore9,123 bytesSKILL.mdcore9,123 bytesSKILL.mdcore9,123 bytesSKILL.mdcore9,123 bytesSKILL.mdcore9,123 bytesagents/observer.mddoc4,134 bytes../../../../skills/continuous-learning-v2/hooks/observe.shruns6,732 bytes
Read SKILL.md
# 持续学习 v2 - 基于本能的架构
一个高级学习系统,通过原子化的“本能”——带有置信度评分的小型习得行为——将你的 Claude Code 会话转化为可重用的知识。
部分灵感来源于 humanplane (credit: @humanplane) 的 Homunculus 项目。
## 何时激活
* 设置从 Claude Code 会话中自动学习时
* 通过钩子配置基于本能的行为提取时
* 调整学习行为的置信度阈值时
* 审查、导出或导入本能库时
* 将本能进化为完整技能、命令或代理时
View the complete source on GitHubcost-aware-llm-pipeline
When your agent uses it
LLM API 使用成本优化模式 —— 基于任务复杂度的模型路由、预算跟踪、重试逻辑和提示缓存。
What it loads into context
Frontmatter
45 tokensAlways available to the agent
SKILL.md
1,491 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
- 何时激活
- 核心概念
- 组合
- 价格参考(2025-2026)
- 最佳实践
- 应避免的反模式
- 适用场景
Files
SKILL.mdcore5,703 bytesSKILL.mdcore5,703 bytesSKILL.mdcore5,703 bytesSKILL.mdcore5,703 bytesSKILL.mdcore5,703 bytesSKILL.mdcore5,703 bytes
Read SKILL.md
# 成本感知型 LLM 流水线
在保持质量的同时控制 LLM API 成本的模式。将模型路由、预算跟踪、重试逻辑和提示词缓存组合成一个可组合的流水线。
## 何时激活
* 构建调用 LLM API(Claude、GPT 等)的应用程序时
* 处理具有不同复杂度的批量项目时
* 需要将 API 支出控制在预算范围内时
* 需要在复杂任务上优化成本而不牺牲质量时
## 核心概念
### 1. 根据任务复杂度进行模型路由View the complete source on GitHubcpp-coding-standards
When your agent uses it
基于C++核心指南(isocpp.github.io)的C++编码标准。在编写、审查或重构C++代码时使用,以强制实施现代、安全和惯用的实践。
What it loads into context
Frontmatter
57 tokensAlways available to the agent
SKILL.md
6,652 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
- 何时使用
- 贯穿性原则
- 哲学与接口 (P.\*, I.\*)
- 函数 (F.\*)
- 类与类层次结构 (C.\*)
- 资源管理 (R.\*)
- 表达式与语句 (ES.\*)
- 错误处理 (E.\*)
- 常量与不可变性 (Con.\*)
- 并发与并行 (CP.\*)
- 模板与泛型编程 (T.\*)
- 标准库 (SL.\*)
- 枚举 (Enum.\*)
- 源文件与命名 (SF.*, NL.*)
- 性能 (Per.\*)
- 快速参考检查清单
Files
SKILL.mdcore21,628 bytes
Read SKILL.md
# C++ 编码标准(C++ 核心准则)
源自 [C++ 核心准则](https://isocpp.github.io/CppCoreGuidelines/CppCoreGuidelines) 的现代 C++(C++17/20/23)综合编码标准。强制执行类型安全、资源安全、不变性和清晰性。
## 何时使用
* 编写新的 C++ 代码(类、函数、模板)
* 审查或重构现有的 C++ 代码
* 在 C++ 项目中做出架构决策
* 在 C++ 代码库中强制执行一致的风格
* 在语言特性之间做出选择(例如,`enum` 对比 `enum class`,原始指针对比智能指针)
### 何时不应使用
View the complete source on GitHubcpp-testing
When your agent uses it
仅用于编写/更新/修复C++测试、配置GoogleTest/CTest、诊断失败或不稳定的测试,或添加覆盖率/消毒器时使用。
What it loads into context
Frontmatter
50 tokensAlways available to the agent
SKILL.md
2,536 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
- 使用时机
- 核心概念
- TDD 工作流
- 代码示例
- 运行测试
- 调试失败
- 覆盖率
- 消毒剂
- 偶发性测试防护
- 最佳实践
- 可选附录:模糊测试 / 属性测试
- GoogleTest 的替代方案
Files
SKILL.mdcore9,167 bytesSKILL.mdcore9,167 bytesSKILL.mdcore9,167 bytesSKILL.mdcore9,167 bytesSKILL.mdcore9,167 bytesSKILL.mdcore9,167 bytes
Read SKILL.md
# C++ 测试(代理技能)
针对现代 C++(C++17/20)的代理导向测试工作流,使用 GoogleTest/GoogleMock 和 CMake/CTest。
## 使用时机
* 编写新的 C++ 测试或修复现有测试
* 为 C++ 组件设计单元/集成测试覆盖
* 添加测试覆盖、CI 门控或回归保护
* 配置 CMake/CTest 工作流以实现一致的执行
* 调查测试失败或偶发性行为
* 启用用于内存/竞态诊断的消毒剂
### 不适用时机View the complete source on GitHubdatabase-migrations
When your agent uses it
数据库迁移最佳实践,涵盖模式变更、数据迁移、回滚以及零停机部署,适用于PostgreSQL、MySQL及常用ORM(Prisma、Drizzle、Django、TypeORM、golang-migrate)。
What it loads into context
Frontmatter
66 tokensAlways available to the agent
SKILL.md
2,327 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
- 何时激活
- 核心原则
- 迁移安全检查清单
- PostgreSQL 模式
- Prisma (TypeScript/Node.js)
- Drizzle (TypeScript/Node.js)
- Django (Python)
- golang-migrate (Go)
- 零停机迁移策略
- 反模式
Files
SKILL.mdcore9,282 bytesSKILL.mdcore9,282 bytesSKILL.mdcore9,282 bytesSKILL.mdcore9,282 bytesSKILL.mdcore9,282 bytesSKILL.mdcore9,282 bytesSKILL.mdcore9,282 bytesSKILL.mdcore9,282 bytesSKILL.mdcore9,282 bytesSKILL.mdcore9,282 bytesSKILL.mdcore9,282 bytesSKILL.mdcore9,282 bytes
Read SKILL.md
# 数据库迁移模式
为生产系统提供安全、可逆的数据库模式变更。
## 何时激活
* 创建或修改数据库表
* 添加/删除列或索引
* 运行数据迁移(回填、转换)
* 计划零停机模式变更
* 为新项目设置迁移工具
## 核心原则
View the complete source on GitHubdeployment-patterns
When your agent uses it
部署工作流、CI/CD流水线模式、Docker容器化、健康检查、回滚策略以及Web应用程序的生产就绪检查清单。
What it loads into context
Frontmatter
45 tokensAlways available to the agent
SKILL.md
3,108 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
- 何时启用
- 部署策略
- Docker
- CI/CD 流水线
- 健康检查
- 环境配置
- 回滚策略
- 生产就绪检查清单
Files
SKILL.mdcore10,731 bytesSKILL.mdcore10,731 bytesSKILL.mdcore10,731 bytes
Read SKILL.md
# 部署模式
生产环境部署工作流和 CI/CD 最佳实践。
## 何时启用
* 设置 CI/CD 流水线时
* 将应用容器化(Docker)时
* 规划部署策略(蓝绿、金丝雀、滚动)时
* 实现健康检查和就绪探针时
* 准备生产发布时
* 配置环境特定设置时
## 部署策略View the complete source on GitHubdjango-patterns
When your agent uses it
Django架构模式,使用DRF设计REST API,ORM最佳实践,缓存,信号,中间件,以及生产级Django应用程序。
What it loads into context
Frontmatter
42 tokensAlways available to the agent
SKILL.md
4,526 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
- 何时激活
- 项目结构
- 模型设计模式
- Django REST Framework 模式
- 服务层模式
- 缓存策略
- 信号
- 中间件
- 性能优化
- 快速参考
Files
SKILL.mdcore20,828 bytesSKILL.mdcore20,828 bytesSKILL.mdcore20,828 bytesSKILL.mdcore20,828 bytesSKILL.mdcore20,828 bytesSKILL.mdcore20,828 bytesSKILL.mdcore20,828 bytesSKILL.mdcore20,828 bytesSKILL.mdcore20,828 bytesSKILL.mdcore20,828 bytesSKILL.mdcore20,828 bytesSKILL.mdcore20,828 bytesSKILL.mdcore20,828 bytesSKILL.mdcore20,828 bytesSKILL.mdcore20,828 bytesSKILL.mdcore20,828 bytesSKILL.mdcore20,828 bytes
Read SKILL.md
# Django 开发模式
适用于可扩展、可维护应用程序的生产级 Django 架构模式。
## 何时激活
* 构建 Django Web 应用程序时
* 设计 Django REST Framework API 时
* 使用 Django ORM 和模型时
* 设置 Django 项目结构时
* 实现缓存、信号、中间件时
## 项目结构
View the complete source on GitHubdjango-security
When your agent uses it
Django 安全最佳实践、认证、授权、CSRF 防护、SQL 注入预防、XSS 预防和安全部署配置。
What it loads into context
Frontmatter
41 tokensAlways available to the agent
SKILL.md
3,736 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
- 何时启用
- 核心安全设置
- 认证
- 授权
- SQL 注入防护
- XSS 防护
- CSRF 防护
- 文件上传安全
- API 安全
- 安全头部
- 环境变量
- 记录安全事件
- 快速安全检查清单
Files
SKILL.mdcore15,572 bytesSKILL.mdcore15,572 bytesSKILL.mdcore15,572 bytesSKILL.mdcore15,572 bytesSKILL.mdcore15,572 bytesSKILL.mdcore15,572 bytesSKILL.mdcore15,572 bytesSKILL.mdcore15,572 bytesSKILL.mdcore15,572 bytesSKILL.mdcore15,572 bytesSKILL.mdcore15,572 bytesSKILL.mdcore15,572 bytesSKILL.mdcore15,572 bytesSKILL.mdcore15,572 bytesSKILL.mdcore15,572 bytesSKILL.mdcore15,572 bytesSKILL.mdcore15,572 bytesSKILL.mdcore15,572 bytesSKILL.mdcore15,572 bytesSKILL.mdcore15,572 bytesSKILL.mdcore15,572 bytes
Read SKILL.md
# Django 安全最佳实践
保护 Django 应用程序免受常见漏洞侵害的全面安全指南。
## 何时启用
* 设置 Django 认证和授权时
* 实现用户权限和角色时
* 配置生产环境安全设置时
* 审查 Django 应用程序的安全问题时
* 将 Django 应用程序部署到生产环境时
## 核心安全设置
View the complete source on GitHubdjango-tdd
When your agent uses it
Django 测试策略,包括 pytest-django、TDD 方法、factory_boy、模拟、覆盖率以及测试 Django REST Framework API。
What it loads into context
Frontmatter
40 tokensAlways available to the agent
SKILL.md
4,639 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
- 何时激活
- Django 的 TDD 工作流
- 设置
- Factory Boy
- 模型测试
- 视图测试
- DRF API 测试
- 模拟与打补丁
- 集成测试
- 测试最佳实践
- 覆盖率
- 快速参考
Files
SKILL.mdcore20,847 bytesSKILL.mdcore20,847 bytesSKILL.mdcore20,847 bytesSKILL.mdcore20,847 bytesSKILL.mdcore20,847 bytesSKILL.mdcore20,847 bytesSKILL.mdcore20,847 bytesSKILL.mdcore20,847 bytesSKILL.mdcore20,847 bytesSKILL.mdcore20,847 bytesSKILL.mdcore20,847 bytesSKILL.mdcore20,847 bytesSKILL.mdcore20,847 bytesSKILL.mdcore20,847 bytes
Read SKILL.md
# 使用 TDD 进行 Django 测试
使用 pytest、factory\_boy 和 Django REST Framework 进行 Django 应用程序的测试驱动开发。
## 何时激活
* 编写新的 Django 应用程序时
* 实现 Django REST Framework API 时
* 测试 Django 模型、视图和序列化器时
* 为 Django 项目设置测试基础设施时
## Django 的 TDD 工作流
### 红-绿-重构循环View the complete source on GitHubdjango-verification
When your agent uses it
Django项目的验证循环:迁移、代码检查、带覆盖率的测试、安全扫描,以及在发布或PR前的部署就绪检查。
What it loads into context
Frontmatter
45 tokensAlways available to the agent
SKILL.md
3,057 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
- 何时激活
- 阶段 1: 环境检查
- 阶段 2: 代码质量与格式化
- 阶段 3: 数据库迁移
- 阶段 4: 测试与覆盖率
- 阶段 5: 安全扫描
- 阶段 6: Django 管理命令
- 阶段 7: 性能检查
- 阶段 8: 静态资源
- 阶段 9: 配置审查
- 阶段 10: 日志配置
- 阶段 11: API 文档(如果使用 DRF)
- 阶段 12: 差异审查
- 输出模板
- 预部署检查清单
- 持续集成
- 快速参考
Files
SKILL.mdcore11,321 bytesSKILL.mdcore11,321 bytesSKILL.mdcore11,321 bytesSKILL.mdcore11,321 bytesSKILL.mdcore11,321 bytesSKILL.mdcore11,321 bytesSKILL.mdcore11,321 bytesSKILL.mdcore11,321 bytesSKILL.mdcore11,321 bytesSKILL.mdcore11,321 bytesSKILL.mdcore11,321 bytesSKILL.mdcore11,321 bytesSKILL.mdcore11,321 bytesSKILL.mdcore11,321 bytesSKILL.mdcore11,321 bytesSKILL.mdcore11,321 bytesSKILL.mdcore11,321 bytesSKILL.mdcore11,321 bytesSKILL.mdcore11,321 bytesSKILL.mdcore11,321 bytesSKILL.mdcore11,321 bytesSKILL.mdcore11,321 bytesSKILL.mdcore11,321 bytesSKILL.mdcore11,321 bytesSKILL.mdcore11,321 bytesSKILL.mdcore11,321 bytesSKILL.mdcore11,321 bytesSKILL.mdcore11,321 bytesSKILL.mdcore11,321 bytesSKILL.mdcore11,321 bytesSKILL.mdcore11,321 bytesSKILL.mdcore11,321 bytesSKILL.mdcore11,321 bytesSKILL.mdcore11,321 bytes
Read SKILL.md
# Django 验证循环
在发起 PR 之前、进行重大更改之后以及部署之前运行,以确保 Django 应用程序的质量和安全性。
## 何时激活
* 在为一个 Django 项目开启拉取请求之前
* 在重大模型变更、迁移更新或依赖升级之后
* 用于暂存或生产环境的预部署验证
* 运行完整的环境 → 代码检查 → 测试 → 安全 → 部署就绪流水线时
* 验证迁移安全性和测试覆盖率时
## 阶段 1: 环境检查
View the complete source on GitHubdocker-patterns
When your agent uses it
用于本地开发的Docker和Docker Compose模式,包括容器安全、网络、卷策略和多服务编排。
What it loads into context
Frontmatter
37 tokensAlways available to the agent
SKILL.md
2,093 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
- 何时启用
- 用于本地开发的 Docker Compose
- 网络
- 卷策略
- 容器安全
- .dockerignore
- 调试
- 反模式
Files
SKILL.mdcore8,079 bytesSKILL.mdcore8,079 bytesSKILL.mdcore8,079 bytesSKILL.mdcore8,079 bytesSKILL.mdcore8,079 bytes
Read SKILL.md
# Docker 模式
适用于容器化开发的 Docker 和 Docker Compose 最佳实践。
## 何时启用
* 为本地开发设置 Docker Compose
* 设计多容器架构
* 排查容器网络或卷问题
* 审查 Dockerfile 的安全性和大小
* 从本地开发迁移到容器化工作流
## 用于本地开发的 Docker Compose
View the complete source on GitHube2e-testing
When your agent uses it
Playwright E2E 测试模式、页面对象模型、配置、CI/CD 集成、工件管理和不稳定测试策略。
What it loads into context
Frontmatter
42 tokensAlways available to the agent
SKILL.md
2,163 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
- 测试文件组织
- 页面对象模型 (POM)
- 测试结构
- Playwright 配置
- 不稳定测试模式
- 产物管理
- CI/CD 集成
- 测试报告模板
- 钱包 / Web3 测试
- 金融 / 关键流程测试
Files
SKILL.mdcore8,020 bytesSKILL.mdcore8,020 bytes
Read SKILL.md
# E2E 测试模式
用于构建稳定、快速且可维护的 E2E 测试套件的全面 Playwright 模式。
## 测试文件组织
```
tests/
├── e2e/
│ ├── auth/
│ │ ├── login.spec.ts
│ │ ├── logout.spec.ts
│ │ └── register.spec.ts
│ ├── features/View the complete source on GitHubeval-harness
When your agent uses it
克劳德代码会话的正式评估框架,实施评估驱动开发(EDD)原则
What it loads into context
Frontmatter
50 tokensAlways available to the agent
SKILL.md
1,640 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
- 何时激活
- 理念
- 评估类型
- 评分器类型
- 指标
- 评估工作流程
- 集成模式
- 评估存储
- 最佳实践
- 示例:添加身份验证
Files
SKILL.mdcore5,439 bytesSKILL.mdcore5,439 bytesSKILL.mdcore5,439 bytes
Read SKILL.md
# Eval Harness 技能
一个用于 Claude Code 会话的正式评估框架,实现了评估驱动开发 (EDD) 原则。
## 何时激活
* 为 AI 辅助工作流程设置评估驱动开发 (EDD)
* 定义 Claude Code 任务完成的标准(通过/失败)
* 使用 pass@k 指标衡量代理可靠性
* 为提示或代理变更创建回归测试套件
* 跨模型版本对代理性能进行基准测试
## 理念
View the complete source on GitHubfoundation-models-on-device
When your agent uses it
苹果FoundationModels框架用于设备上的LLM——文本生成、使用@Generable进行引导生成、工具调用,以及在iOS 26+中的快照流。
What it loads into context
Frontmatter
47 tokensAlways available to the agent
SKILL.md
1,967 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
- 何时启用
- 核心模式 — 可用性检查
- 核心模式 — 基础会话
- 核心模式 — 使用 @Generable 进行引导式生成
- 核心模式 — 工具调用
- 核心模式 — 快照流式传输
- 关键设计决策
- 最佳实践
- 应避免的反模式
- 何时使用
Files
SKILL.mdcore8,033 bytes
Read SKILL.md
# FoundationModels:设备端 LLM(iOS 26)
使用 FoundationModels 框架将苹果的设备端语言模型集成到应用中的模式。涵盖文本生成、使用 `@Generable` 的结构化输出、自定义工具调用以及快照流式传输——全部在设备端运行,以保护隐私并支持离线使用。
## 何时启用
* 使用 Apple Intelligence 在设备端构建 AI 功能
* 无需依赖云端即可生成或总结文本
* 从自然语言输入中提取结构化数据
* 为特定领域的 AI 操作实现自定义工具调用
* 流式传输结构化响应以实现实时 UI 更新
* 需要保护隐私的 AI(数据不离开设备)
## 核心模式 — 可用性检查View the complete source on GitHubfrontend-patterns
When your agent uses it
React、Next.js、状态管理、性能优化和UI最佳实践的前端开发模式。
What it loads into context
Frontmatter
31 tokensAlways available to the agent
SKILL.md
3,719 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
- 何时激活
- 组件模式
- 自定义 Hooks 模式
- 状态管理模式
- 性能优化
- 表单处理模式
- 错误边界模式
- 动画模式
- 无障碍模式
Files
SKILL.mdcore14,534 bytes
Read SKILL.md
# 前端开发模式
适用于 React、Next.js 和高性能用户界面的现代前端模式。
## 何时激活
* 构建 React 组件(组合、属性、渲染)
* 管理状态(useState、useReducer、Zustand、Context)
* 实现数据获取(SWR、React Query、服务器组件)
* 优化性能(记忆化、虚拟化、代码分割)
* 处理表单(验证、受控输入、Zod 模式)
* 处理客户端路由和导航
* 构建可访问、响应式的 UI 模式
View the complete source on GitHubfrontend-slides
When your agent uses it
从零开始或通过转换PowerPoint文件创建令人惊艳、动画丰富的HTML演示文稿。当用户想要构建演示文稿、将PPT/PPTX转换为网页格式,或为演讲/推介创建幻灯片时使用。帮助非设计师通过视觉探索而非抽象选择发现他们的美学。
What it loads into context
Frontmatter
87 tokensAlways available to the agent
SKILL.md
1,935 tokensWhen the skill is activated
Reference documents
3,142 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- 何时启用
- 不可妥协的原则
- 工作流程
- PPT / PPTX 转换
- 实现要求
- 内容密度限制
- 反模式
- 相关 ECC 技能
- 交付清单
Files
SKILL.mdcore6,506 bytesSTYLE_PRESETS.mddoc9,401 bytes
Read SKILL.md
# 前端幻灯片
创建零依赖、动画丰富的 HTML 演示文稿,完全在浏览器中运行。
灵感来源于 [zarazhangrui](https://github.com/zarazhangrui) 的作品中展示的视觉探索方法。
## 何时启用
* 创建演讲文稿、推介文稿、研讨会文稿或内部演示文稿时
* 将 `.ppt` 或 `.pptx` 幻灯片转换为 HTML 演示文稿时
* 改进现有 HTML 演示文稿的布局、动效或排版时
* 与尚不清楚其设计偏好的用户一起探索演示文稿风格时
## 不可妥协的原则View the complete source on GitHubgolang-patterns
When your agent uses it
用于构建健壮、高效且可维护的Go应用程序的惯用Go模式、最佳实践和约定。
What it loads into context
Frontmatter
39 tokensAlways available to the agent
SKILL.md
3,580 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
- 何时激活
- 核心原则
- 错误处理模式
- 并发模式
- 接口设计
- 包组织
- 结构体设计
- 内存与性能
- Go 工具集成
- 快速参考:Go 惯用法
- 应避免的反模式
Files
SKILL.mdcore13,744 bytesSKILL.mdcore13,744 bytes
Read SKILL.md
# Go 开发模式
用于构建健壮、高效和可维护应用程序的惯用 Go 模式与最佳实践。
## 何时激活
* 编写新的 Go 代码时
* 审查 Go 代码时
* 重构现有 Go 代码时
* 设计 Go 包/模块时
## 核心原则
### 1. 简洁与清晰View the complete source on GitHubgolang-testing
When your agent uses it
Go测试模式包括表格驱动测试、子测试、基准测试、模糊测试和测试覆盖率。遵循TDD方法论,采用地道的Go实践。
What it loads into context
Frontmatter
51 tokensAlways available to the agent
SKILL.md
4,407 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
- 何时激活
- Go 的 TDD 工作流
- 表驱动测试
- 子测试和子基准测试
- 测试辅助函数
- 黄金文件
- 使用接口进行模拟
- 基准测试
- 模糊测试 (Go 1.18+)
- 测试覆盖率
- HTTP 处理器测试
- 命令测试
- 最佳实践
- 与 CI/CD 集成
Files
SKILL.mdcore16,535 bytesSKILL.mdcore16,535 bytesSKILL.mdcore16,535 bytes
Read SKILL.md
# Go 测试模式
遵循 TDD 方法论,用于编写可靠、可维护测试的全面 Go 测试模式。
## 何时激活
* 编写新的 Go 函数或方法时
* 为现有代码添加测试覆盖率时
* 为性能关键代码创建基准测试时
* 为输入验证实现模糊测试时
* 在 Go 项目中遵循 TDD 工作流时
## Go 的 TDD 工作流
View the complete source on GitHubinvestor-materials
When your agent uses it
创建和更新宣传文稿、一页简介、投资者备忘录、加速器申请、财务模型和融资材料。当用户需要面向投资者的文件、预测、资金用途表、里程碑计划或必须在多个融资资产中保持内部一致性的材料时使用。
What it loads into context
Frontmatter
73 tokensAlways available to the agent
SKILL.md
765 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
- 何时启用
- 黄金法则
- 核心工作流程
- 资产指南
- 需避免的危险信号
- 质量关卡
Files
SKILL.mdcore2,508 bytes
Read SKILL.md
# 投资者材料
构建面向投资者的材料,要求一致、可信且易于辩护。
## 何时启用
* 创建或修订融资演讲稿
* 撰写投资者备忘录或一页摘要
* 构建财务模型、里程碑计划或资金使用表
* 回答加速器或孵化器申请问题
* 围绕单一事实来源统一多个融资文件
## 黄金法则
View the complete source on GitHubinvestor-outreach
When your agent uses it
草拟冷邮件、热情介绍简介、跟进邮件、更新邮件和投资者沟通以筹集资金。当用户需要向天使投资人、风险投资公司、战略投资者或加速器进行推广,并需要简洁、个性化的面向投资者的消息时使用。
What it loads into context
Frontmatter
76 tokensAlways available to the agent
SKILL.md
625 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
- 何时激活
- 核心规则
- 冷邮件结构
- 个性化来源
- 跟进节奏
- 熟人介绍请求
- 会后更新
- 质量关卡
Files
SKILL.mdcore2,154 bytes
Read SKILL.md
# 投资者接洽
撰写简短、个性化且易于采取行动的投资者沟通内容。
## 何时激活
* 向投资者发送冷邮件时
* 起草熟人介绍请求时
* 在会议后或无回复时发送跟进邮件时
* 在融资过程中撰写投资者更新时
* 根据基金投资主题或合伙人契合度定制接洽内容时
## 核心规则
View the complete source on GitHubiterative-retrieval
When your agent uses it
逐步优化上下文检索以解决子代理上下文问题的模式
What it loads into context
Frontmatter
30 tokensAlways available to the agent
SKILL.md
1,672 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
- 何时激活
- 问题
- 解决方案:迭代检索
- 实际示例
- 与智能体集成
- 最佳实践
- 相关
Files
SKILL.mdcore6,505 bytes
Read SKILL.md
# 迭代检索模式
解决多智能体工作流中的“上下文问题”,即子智能体在开始工作前不知道需要哪些上下文。
## 何时激活
* 当需要生成需要代码库上下文但无法预先预测的子代理时
* 构建需要逐步完善上下文的多代理工作流时
* 在代理任务中遇到"上下文过大"或"缺少上下文"的失败时
* 为代码探索设计类似 RAG 的检索管道时
* 在代理编排中优化令牌使用时
## 问题
View the complete source on GitHubjava-coding-standards
When your agent uses it
Spring Boot服务的Java编码标准:命名、不可变性、Optional用法、流、异常、泛型和项目布局。
What it loads into context
Frontmatter
45 tokensAlways available to the agent
SKILL.md
1,025 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
- 何时激活
- 核心原则
- 命名
- 不可变性
- Optional 使用
- Streams 最佳实践
- 异常
- 泛型和类型安全
- 项目结构 (Maven/Gradle)
- 格式化和风格
- 需要避免的代码坏味道
- 日志记录
- Null 处理
- 测试期望
Files
SKILL.mdcore3,801 bytes
Read SKILL.md
# Java 编码规范
适用于 Spring Boot 服务中可读、可维护的 Java (17+) 代码的规范。
## 何时激活
* 在 Spring Boot 项目中编写或审查 Java 代码时
* 强制执行命名、不可变性或异常处理约定时
* 使用记录类、密封类或模式匹配(Java 17+)时
* 审查 Optional、流或泛型的使用时
* 构建包和项目布局时
## 核心原则
View the complete source on GitHubjpa-patterns
When your agent uses it
Spring Boot中的JPA/Hibernate模式,用于实体设计、关系处理、查询优化、事务管理、审计、索引、分页和连接池。
What it loads into context
Frontmatter
45 tokensAlways available to the agent
SKILL.md
1,145 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
- 何时激活
- 实体设计
- 关联关系和 N+1 预防
- 存储库模式
- 事务
- 分页
- 索引和性能
- 连接池 (HikariCP)
- 缓存
- 迁移
- 测试数据访问
Files
SKILL.mdcore4,412 bytes
Read SKILL.md
# JPA/Hibernate 模式
用于 Spring Boot 中的数据建模、存储库和性能调优。
## 何时激活
* 设计 JPA 实体和表映射时
* 定义关系时 (@OneToMany, @ManyToOne, @ManyToMany)
* 优化查询时 (N+1 问题预防、获取策略、投影)
* 配置事务、审计或软删除时
* 设置分页、排序或自定义存储库方法时
* 调整连接池 (HikariCP) 或二级缓存时
## 实体设计View the complete source on GitHubliquid-glass-design
When your agent uses it
iOS 26 液态玻璃设计系统 — 适用于 SwiftUI、UIKit 和 WidgetKit 的动态玻璃材质,具有模糊、反射和交互式变形效果。
What it loads into context
Frontmatter
53 tokensAlways available to the agent
SKILL.md
2,307 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
- 何时启用
- 核心模式 — SwiftUI
- 核心模式 — UIKit
- 核心模式 — WidgetKit
- 关键设计决策
- 最佳实践
- 应避免的反模式
- 使用场景
Files
SKILL.mdcore8,814 bytes
Read SKILL.md
# Liquid Glass 设计系统 (iOS 26)
实现苹果 Liquid Glass 的模式指南——这是一种动态材质,会模糊其后的内容,反射周围内容的颜色和光线,并对触摸和指针交互做出反应。涵盖 SwiftUI、UIKit 和 WidgetKit 集成。
## 何时启用
* 为 iOS 26+ 构建或更新采用新设计语言的应用程序时
* 实现玻璃风格的按钮、卡片、工具栏或容器时
* 在玻璃元素之间创建变形过渡时
* 将 Liquid Glass 效果应用于小组件时
* 将现有的模糊/材质效果迁移到新的 Liquid Glass API 时
## 核心模式 — SwiftUI
View the complete source on GitHubmarket-research
When your agent uses it
进行市场研究、竞争分析、投资者尽职调查和行业情报,附带来源归属和决策导向的摘要。适用于用户需要市场规模、竞争对手比较、基金研究、技术扫描或为商业决策提供信息的研究时。
What it loads into context
Frontmatter
70 tokensAlways available to the agent
SKILL.md
592 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
- 何时激活
- 研究标准
- 常见研究模式
- 输出格式
- 质量门
Files
SKILL.mdcore2,034 bytes
Read SKILL.md
# 市场研究
产出支持决策的研究,而非研究表演。
## 何时激活
* 研究市场、品类、公司、投资者或技术趋势时
* 构建 TAM/SAM/SOM 估算时
* 比较竞争对手或相邻产品时
* 在接触前准备投资者档案时
* 在构建、投资或进入市场前对论点进行压力测试时
## 研究标准
View the complete source on GitHubnutrient-document-processing
When your agent uses it
使用Nutrient DWS API处理、转换、OCR识别、提取、编辑、签名和填写文档。支持PDF、DOCX、XLSX、PPTX、HTML和图像格式。
What it loads into context
Frontmatter
58 tokensAlways available to the agent
SKILL.md
1,757 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
- 设置
- 操作
- MCP 服务器(替代方案)
- 使用场景
- 链接
Files
SKILL.mdcore5,777 bytesSKILL.mdcore5,777 bytesSKILL.mdcore5,777 bytesSKILL.mdcore5,777 bytesSKILL.mdcore5,777 bytesSKILL.mdcore5,777 bytesSKILL.mdcore5,777 bytesSKILL.mdcore5,777 bytesSKILL.mdcore5,777 bytes
Read SKILL.md
# 文档处理
使用 [Nutrient DWS Processor API](https://www.nutrient.io/api/) 处理文档。转换格式、提取文本和表格、对扫描文档进行 OCR、编辑 PII、添加水印、数字签名以及填写 PDF 表单。
## 设置
在 **[nutrient.io](https://dashboard.nutrient.io/sign_up/?product=processor)** 获取一个免费的 API 密钥
```bash
[Credential-related source omitted]
```
所有请求都以 multipart POST 形式发送到 `https://api.nutrient.io/build`,并附带一个 `instructions` JSON 字段。
View the complete source on GitHubpostgres-patterns
When your agent uses it
用于查询优化、模式设计、索引和安全性的PostgreSQL数据库模式。基于Supabase最佳实践。
What it loads into context
Frontmatter
37 tokensAlways available to the agent
SKILL.md
1,088 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
- 何时激活
- 快速参考
- 相关
Files
SKILL.mdcore3,794 bytes
Read SKILL.md
# PostgreSQL 模式
PostgreSQL 最佳实践快速参考。如需详细指导,请使用 `database-reviewer` 智能体。
## 何时激活
* 编写 SQL 查询或迁移时
* 设计数据库模式时
* 排查慢查询时
* 实施行级安全性时
* 设置连接池时
## 快速参考
View the complete source on GitHubproject-guidelines-example
When your agent uses it
基于真实生产应用的示例项目特定技能模板。
What it loads into context
Frontmatter
28 tokensAlways available to the agent
SKILL.md
2,281 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
- 何时使用
- 架构概述
- 文件结构
- 代码模式
- 测试要求
- 部署工作流
- 关键规则
- 相关技能
Files
SKILL.mdcore9,692 bytesSKILL.mdcore9,692 bytesSKILL.mdcore9,692 bytesSKILL.mdcore9,692 bytesSKILL.mdcore9,692 bytesSKILL.mdcore9,692 bytesSKILL.mdcore9,692 bytesSKILL.mdcore9,692 bytesSKILL.mdcore9,692 bytesSKILL.mdcore9,692 bytes
Read SKILL.md
# 项目指南技能(示例)
这是一个项目特定技能的示例。将其用作您自己项目的模板。
基于一个真实的生产应用程序:[Zenith](https://zenith.chat) - 由 AI 驱动的客户发现平台。
## 何时使用
在为其设计的特定项目上工作时,请参考此技能。项目技能包含:
* 架构概述
* 文件结构
* 代码模式
* 测试要求View the complete source on GitHubpython-patterns
When your agent uses it
Pythonic 惯用法、PEP 8 标准、类型提示以及构建稳健、高效且可维护的 Python 应用程序的最佳实践。
What it loads into context
Frontmatter
46 tokensAlways available to the agent
SKILL.md
4,350 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
- 何时激活
- 核心原则
- 类型提示
- 错误处理模式
- 上下文管理器
- 推导式和生成器
- 数据类和命名元组
- 装饰器
- 并发模式
- 包组织
- 内存和性能
- Python 工具集成
- 快速参考:Python 惯用法
- 要避免的反模式
Files
SKILL.mdcore16,526 bytesSKILL.mdcore16,526 bytesSKILL.mdcore16,526 bytesSKILL.mdcore16,526 bytesSKILL.mdcore16,526 bytesSKILL.mdcore16,526 bytesSKILL.mdcore16,526 bytesSKILL.mdcore16,526 bytesSKILL.mdcore16,526 bytesSKILL.mdcore16,526 bytesSKILL.mdcore16,526 bytesSKILL.mdcore16,526 bytesSKILL.mdcore16,526 bytesSKILL.mdcore16,526 bytesSKILL.mdcore16,526 bytesSKILL.mdcore16,526 bytesSKILL.mdcore16,526 bytesSKILL.mdcore16,526 bytesSKILL.mdcore16,526 bytesSKILL.mdcore16,526 bytesSKILL.mdcore16,526 bytesSKILL.mdcore16,526 bytesSKILL.mdcore16,526 bytesSKILL.mdcore16,526 bytesSKILL.mdcore16,526 bytesSKILL.mdcore16,526 bytesSKILL.mdcore16,526 bytesSKILL.mdcore16,526 bytesSKILL.mdcore16,526 bytesSKILL.mdcore16,526 bytesSKILL.mdcore16,526 bytesSKILL.mdcore16,526 bytesSKILL.mdcore16,526 bytesSKILL.mdcore16,526 bytes
Read SKILL.md
# Python 开发模式
用于构建健壮、高效和可维护应用程序的惯用 Python 模式与最佳实践。
## 何时激活
* 编写新的 Python 代码
* 审查 Python 代码
* 重构现有的 Python 代码
* 设计 Python 包/模块
## 核心原则
### 1. 可读性很重要View the complete source on GitHubpython-testing
When your agent uses it
使用pytest的Python测试策略,包括TDD方法、夹具、模拟、参数化和覆盖率要求。
What it loads into context
Frontmatter
33 tokensAlways available to the agent
SKILL.md
4,611 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
- 何时激活
- 核心测试理念
- pytest 基础
- 夹具
- 参数化
- 标记器和测试选择
- 模拟和补丁
- 测试异步代码
- 测试异常
- 测试副作用
- 测试组织
- 最佳实践
- 常见模式
- pytest 配置
- 运行测试
- 快速参考
Files
SKILL.mdcore18,633 bytesSKILL.mdcore18,633 bytesSKILL.mdcore18,633 bytesSKILL.mdcore18,633 bytesSKILL.mdcore18,633 bytesSKILL.mdcore18,633 bytesSKILL.mdcore18,633 bytesSKILL.mdcore18,633 bytesSKILL.mdcore18,633 bytesSKILL.mdcore18,633 bytesSKILL.mdcore18,633 bytesSKILL.mdcore18,633 bytesSKILL.mdcore18,633 bytesSKILL.mdcore18,633 bytesSKILL.mdcore18,633 bytesSKILL.mdcore18,633 bytesSKILL.mdcore18,633 bytesSKILL.mdcore18,633 bytesSKILL.mdcore18,633 bytesSKILL.mdcore18,633 bytesSKILL.mdcore18,633 bytesSKILL.mdcore18,633 bytesSKILL.mdcore18,633 bytesSKILL.mdcore18,633 bytesSKILL.mdcore18,633 bytesSKILL.mdcore18,633 bytesSKILL.mdcore18,633 bytesSKILL.mdcore18,633 bytesSKILL.mdcore18,633 bytesSKILL.mdcore18,633 bytesSKILL.mdcore18,633 bytesSKILL.mdcore18,633 bytesSKILL.mdcore18,633 bytesSKILL.mdcore18,633 bytesSKILL.mdcore18,633 bytesSKILL.mdcore18,633 bytesSKILL.mdcore18,633 bytesSKILL.mdcore18,633 bytes
Read SKILL.md
# Python 测试模式
使用 pytest、TDD 方法论和最佳实践的 Python 应用程序全面测试策略。
## 何时激活
* 编写新的 Python 代码(遵循 TDD:红、绿、重构)
* 为 Python 项目设计测试套件
* 审查 Python 测试覆盖率
* 设置测试基础设施
## 核心测试理念
### 测试驱动开发 (TDD)View the complete source on GitHubregex-vs-llm-structured-text
When your agent uses it
选择在解析结构化文本时使用正则表达式还是大型语言模型的决策框架——从正则表达式开始,仅在低置信度的边缘情况下添加大型语言模型。
What it loads into context
Frontmatter
61 tokensAlways available to the agent
SKILL.md
1,784 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
- 何时使用
- 决策框架
- 架构模式
- 实现
- 实际指标
- 最佳实践
- 应避免的反模式
- 适用场景
Files
SKILL.mdcore6,599 bytesSKILL.mdcore6,599 bytesSKILL.mdcore6,599 bytesSKILL.mdcore6,599 bytesSKILL.mdcore6,599 bytes
Read SKILL.md
# 正则表达式 vs LLM 用于结构化文本解析
一个用于解析结构化文本(测验、表单、发票、文档)的实用决策框架。核心见解是:正则表达式能以低成本、确定性的方式处理 95-98% 的情况。将昂贵的 LLM 调用留给剩余的边缘情况。
## 何时使用
* 解析具有重复模式的结构化文本(问题、表单、表格)
* 决定在文本提取时使用正则表达式还是 LLM
* 构建结合两种方法的混合管道
* 在文本处理中优化成本/准确性权衡
## 决策框架
```View the complete source on GitHubsearch-first
When your agent uses it
研究优先于编码的工作流程。在编写自定义代码之前,搜索现有的工具、库和模式。调用研究员代理。
What it loads into context
Frontmatter
42 tokensAlways available to the agent
SKILL.md
1,552 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
- 触发时机
- 工作流程
- 决策矩阵
- 使用方法
- 按类别搜索快捷方式
- 集成点
- 示例
- 反模式
Files
SKILL.mdcore6,383 bytes
Read SKILL.md
# /search-first — 编码前先研究
系统化“在实现之前先寻找现有解决方案”的工作流程。
## 触发时机
在以下情况使用此技能:
* 开始一项很可能已有解决方案的新功能
* 添加依赖项或集成
* 用户要求“添加 X 功能”而你准备开始编写代码
* 在创建新的实用程序、助手或抽象之前
## 工作流程View the complete source on GitHubsecurity-review
When your agent uses it
在添加身份验证、处理用户输入、处理机密信息、创建API端点或实现支付/敏感功能时使用此技能。提供全面的安全检查清单和模式。
What it loads into context
Frontmatter
50 tokensAlways available to the agent
SKILL.md
3,370 tokensWhen the skill is activated
Reference documents
2,763 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- 何时激活
- 安全检查清单
- 安全测试
- 部署前安全检查清单
- 资源
Files
SKILL.mdcore12,052 bytesSKILL.mdcore12,052 bytesSKILL.mdcore12,052 bytesSKILL.mdcore12,052 bytescloud-infrastructure-security.mddoc9,692 bytes
Read SKILL.md
# 安全审查技能
此技能确保所有代码遵循安全最佳实践,并识别潜在漏洞。
## 何时激活
* 实现身份验证或授权时
* 处理用户输入或文件上传时
* 创建新的 API 端点时
* 处理密钥或凭据时
* 实现支付功能时
* 存储或传输敏感数据时
* 集成第三方 API 时
View the complete source on GitHubsecurity-scan
When your agent uses it
使用AgentShield扫描您的Claude代码配置(.claude/目录),以发现安全漏洞、配置错误和注入风险。检查CLAUDE.md、settings.json、MCP服务器、钩子和代理定义。
What it loads into context
Frontmatter
58 tokensAlways available to the agent
SKILL.md
1,305 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
- 何时激活
- 扫描内容
- 先决条件
- 使用方法
- 严重性等级
- 结果解读
- 链接
Files
SKILL.mdcore4,420 bytesSKILL.mdcore4,420 bytesSKILL.mdcore4,420 bytesSKILL.mdcore4,420 bytesSKILL.mdcore4,420 bytesSKILL.mdcore4,420 bytesSKILL.mdcore4,420 bytes
Read SKILL.md
# 安全扫描技能
使用 [AgentShield](https://github.com/affaan-m/agentshield) 审计您的 Claude Code 配置中的安全问题。
## 何时激活
* 设置新的 Claude Code 项目时
* 修改 `.claude/settings.json`、`CLAUDE.md` 或 MCP 配置后
* 提交配置更改前
* 加入具有现有 Claude Code 配置的新代码库时
* 定期进行安全卫生检查时
## 扫描内容
View the complete source on GitHubWhen your agent uses it
用于审计Claude技能和命令的质量。支持快速扫描(仅变更技能)和全面盘点模式,采用顺序子代理批量评估。
What it loads into context
Frontmatter
43 tokensAlways available to the agent
SKILL.md
2,082 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
- 范围
- 模式
- 快速扫描流程
- 全面盘点流程
- 结果文件模式
- 注意事项
Files
SKILL.mdcore7,360 bytesSKILL.mdcore7,360 bytesSKILL.mdcore7,360 bytesSKILL.mdcore7,360 bytesSKILL.mdcore7,360 bytes
Read SKILL.md
# skill-stocktake
斜杠命令 (`/skill-stocktake`),用于使用质量检查清单 + AI 整体判断来审核所有 Claude 技能和命令。支持两种模式:用于最近更改技能的快速扫描,以及用于完整审查的全面盘点。
## 范围
该命令针对以下**相对于调用命令所在目录**的路径:
| 路径 | 描述 |
|------|-------------|
| `~/.claude/skills/` | 全局技能(所有项目) |
| `{cwd}/.claude/skills/` | 项目级技能(如果目录存在) |
**在第 1 阶段开始时,该命令会明确列出找到并扫描了哪些路径。**View the complete source on GitHubspringboot-patterns
When your agent uses it
Spring Boot架构模式、REST API设计、分层服务、数据访问、缓存、异步处理和日志记录。用于Java Spring Boot后端工作。
What it loads into context
Frontmatter
46 tokensAlways available to the agent
SKILL.md
2,337 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
- 何时激活
- REST API 结构
- 仓库模式 (Spring Data JPA)
- 带事务的服务层
- DTO 和验证
- 异常处理
- 缓存
- 异步处理
- 日志记录 (SLF4J)
- 中间件 / 过滤器
- 分页和排序
- 容错的外部调用
- 速率限制 (过滤器 + Bucket4j)
- 后台作业
- 可观测性
- 生产环境默认设置
Files
SKILL.mdcore9,772 bytes
Read SKILL.md
# Spring Boot 开发模式
用于可扩展、生产级服务的 Spring Boot 架构和 API 模式。
## 何时激活
* 使用 Spring MVC 或 WebFlux 构建 REST API
* 构建控制器 → 服务 → 仓库层结构
* 配置 Spring Data JPA、缓存或异步处理
* 添加验证、异常处理或分页
* 为开发/预发布/生产环境设置配置文件
* 使用 Spring Events 或 Kafka 实现事件驱动模式
## REST API 结构View the complete source on GitHubspringboot-security
When your agent uses it
Java Spring Boot 服务中认证/授权、验证、CSRF、密钥、标头、速率限制和依赖安全性的 Spring Security 最佳实践。
What it loads into context
Frontmatter
45 tokensAlways available to the agent
SKILL.md
2,023 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
- 何时激活
- 身份验证
- 授权
- 输入验证
- SQL 注入预防
- 密码编码
- CSRF 保护
- 密钥管理
- 安全头
- CORS 配置
- 速率限制
- 依赖项安全
- 日志记录和 PII
- 文件上传
- 发布前检查清单
Files
SKILL.mdcore7,980 bytesSKILL.mdcore7,980 bytes
Read SKILL.md
# Spring Boot 安全审查
在添加身份验证、处理输入、创建端点或处理密钥时使用。
## 何时激活
* 添加身份验证(JWT、OAuth2、基于会话)
* 实现授权(@PreAuthorize、基于角色的访问控制)
* 验证用户输入(Bean Validation、自定义验证器)
* 配置 CORS、CSRF 或安全标头
* 管理密钥(Vault、环境变量)
* 添加速率限制或暴力破解防护
* 扫描依赖项以查找 CVE
View the complete source on GitHubspringboot-tdd
When your agent uses it
使用JUnit 5、Mockito、MockMvc、Testcontainers和JaCoCo进行Spring Boot的测试驱动开发。适用于添加功能、修复错误或重构时。
What it loads into context
Frontmatter
50 tokensAlways available to the agent
SKILL.md
1,014 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
- 何时使用
- 工作流程
- 单元测试 (JUnit 5 + Mockito)
- Web 层测试 (MockMvc)
- 集成测试 (SpringBootTest)
- 持久层测试 (DataJpaTest)
- Testcontainers
- 覆盖率 (JaCoCo)
- 断言
- 测试数据构建器
- CI 命令
Files
SKILL.mdcore3,777 bytes
Read SKILL.md
# Spring Boot TDD 工作流程
适用于 Spring Boot 服务、覆盖率 80%+(单元 + 集成)的 TDD 指南。
## 何时使用
* 新功能或端点
* 错误修复或重构
* 添加数据访问逻辑或安全规则
## 工作流程
1. 先写测试(它们应该失败)
2. 实现最小代码以通过测试View the complete source on GitHubspringboot-verification
When your agent uses it
Spring Boot项目验证循环:构建、静态分析、测试覆盖、安全扫描,以及发布或PR前的差异审查。
What it loads into context
Frontmatter
42 tokensAlways available to the agent
SKILL.md
1,533 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
- 何时激活
- 阶段 1:构建
- 阶段 2:静态分析
- 阶段 3:测试 + 覆盖率
- 阶段 4:安全扫描
- 阶段 5:代码检查/格式化(可选关卡)
- 阶段 6:差异审查
- 输出模板
- 持续模式
Files
SKILL.mdcore5,853 bytesSKILL.mdcore5,853 bytesSKILL.mdcore5,853 bytesSKILL.mdcore5,853 bytesSKILL.mdcore5,853 bytesSKILL.mdcore5,853 bytesSKILL.mdcore5,853 bytesSKILL.mdcore5,853 bytesSKILL.mdcore5,853 bytes
Read SKILL.md
# Spring Boot 验证循环
在提交 PR 前、重大变更后以及部署前运行。
## 何时激活
* 为 Spring Boot 服务开启拉取请求之前
* 在重大重构或依赖项升级之后
* 用于暂存或生产环境的部署前验证
* 运行完整的构建 → 代码检查 → 测试 → 安全扫描流水线
* 验证测试覆盖率是否满足阈值
## 阶段 1:构建
View the complete source on GitHubstrategic-compact
When your agent uses it
建议在逻辑间隔处手动压缩上下文,以在任务阶段中保留上下文,而非任意的自动压缩。
What it loads into context
Frontmatter
43 tokensAlways available to the agent
SKILL.md
1,136 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
- 何时激活
- 为何采用战略精简?
- 工作原理
- 钩子设置
- 配置
- 压缩决策指南
- 压缩后保留的内容
- 最佳实践
- 相关
Files
SKILL.mdcore4,628 bytesSKILL.mdcore4,628 bytesSKILL.mdcore4,628 bytes
Read SKILL.md
# 战略精简技能
建议在你的工作流程中的战略节点手动执行 `/compact`,而不是依赖任意的自动精简。
## 何时激活
* 运行长时间会话,接近上下文限制时(200K+ tokens)
* 处理多阶段任务时(研究 → 规划 → 实施 → 测试)
* 在同一会话中切换不相关的任务时
* 完成一个主要里程碑并开始新工作时
* 当响应变慢或连贯性下降时(上下文压力)
## 为何采用战略精简?
View the complete source on GitHubswift-actor-persistence
When your agent uses it
在 Swift 中使用 actor 实现线程安全的数据持久化——基于内存缓存与文件支持的存储,通过设计消除数据竞争。
What it loads into context
Frontmatter
45 tokensAlways available to the agent
SKILL.md
1,209 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
- 何时激活
- 核心模式
- 关键设计决策
- 最佳实践
- 应避免的反模式
- 何时使用
Files
SKILL.mdcore4,747 bytes
Read SKILL.md
# 用于线程安全持久化的 Swift Actor
使用 Swift actor 构建线程安全数据持久化层的模式。结合内存缓存与文件支持的存储,利用 actor 模型在编译时消除数据竞争。
## 何时激活
* 在 Swift 5.5+ 中构建数据持久化层
* 需要对共享可变状态进行线程安全访问
* 希望消除手动同步(锁、DispatchQueue)
* 构建具有本地存储的离线优先应用
## 核心模式
### 基于 Actor 的存储库View the complete source on GitHubswift-concurrency-6-2
When your agent uses it
Swift 6.2 可接近的并发性 — 默认单线程,@concurrent 用于显式后台卸载,隔离一致性用于主 actor 类型。
What it loads into context
Frontmatter
49 tokensAlways available to the agent
SKILL.md
2,070 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
- 何时启用
- 核心问题:隐式的后台卸载
- 核心模式 — 隔离的一致性
- 核心模式 — 全局和静态变量
- 核心模式 — 使用 @concurrent 进行后台工作
- 关键设计决策
- 迁移步骤
- 最佳实践
- 应避免的反模式
- 何时使用
Files
SKILL.mdcore7,862 bytes
Read SKILL.md
# Swift 6.2 可接近的并发
采用 Swift 6.2 并发模型的模式,其中代码默认在单线程上运行,并发是显式引入的。在无需牺牲性能的情况下消除常见的数据竞争错误。
## 何时启用
* 将 Swift 5.x 或 6.0/6.1 项目迁移到 Swift 6.2
* 解决数据竞争安全编译器错误
* 设计基于 MainActor 的应用架构
* 将 CPU 密集型工作卸载到后台线程
* 在 MainActor 隔离的类型上实现协议一致性
* 在 Xcode 26 中启用“可接近的并发”构建设置
## 核心问题:隐式的后台卸载View the complete source on GitHubswift-protocol-di-testing
When your agent uses it
基于协议的依赖注入,用于可测试的Swift代码——使用聚焦协议和Swift Testing模拟文件系统、网络和外部API。
What it loads into context
Frontmatter
46 tokensAlways available to the agent
SKILL.md
1,401 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
- 何时激活
- 核心模式
- 最佳实践
- 需要避免的反模式
- 何时使用
Files
SKILL.mdcore5,818 bytes
Read SKILL.md
# 基于协议的 Swift 依赖注入测试
通过将外部依赖(文件系统、网络、iCloud)抽象为小型、专注的协议,使 Swift 代码可测试的模式。支持无需 I/O 的确定性测试。
## 何时激活
* 编写访问文件系统、网络或外部 API 的 Swift 代码时
* 需要在未触发真实故障的情况下测试错误处理路径时
* 构建需要在不同环境(应用、测试、SwiftUI 预览)中工作的模块时
* 设计支持 Swift 并发(actor、Sendable)的可测试架构时
## 核心模式
### 1. 定义小型、专注的协议View the complete source on GitHubswiftui-patterns
When your agent uses it
SwiftUI 架构模式,使用 @Observable 进行状态管理,视图组合,导航,性能优化,以及现代 iOS/macOS UI 最佳实践。
What it loads into context
Frontmatter
43 tokensAlways available to the agent
SKILL.md
1,782 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
- 何时激活
- 状态管理
- 视图组合
- 导航
- 性能
- 预览
- 应避免的反模式
- 参考
Files
SKILL.mdcore6,940 bytes
Read SKILL.md
# SwiftUI 模式
适用于 Apple 平台的现代 SwiftUI 模式,用于构建声明式、高性能的用户界面。涵盖 Observation 框架、视图组合、类型安全导航和性能优化。
## 何时激活
* 构建 SwiftUI 视图和管理状态时(`@State`、`@Observable`、`@Binding`)
* 使用 `NavigationStack` 设计导航流程时
* 构建视图模型和数据流时
* 优化列表和复杂布局的渲染性能时
* 在 SwiftUI 中使用环境值和依赖注入时
## 状态管理
View the complete source on GitHubtdd-workflow
When your agent uses it
在编写新功能、修复错误或重构代码时使用此技能。强制执行测试驱动开发,确保单元测试、集成测试和端到端测试的覆盖率超过80%。
What it loads into context
Frontmatter
58 tokensAlways available to the agent
SKILL.md
2,637 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
- 何时激活
- 核心原则
- TDD 工作流步骤
- 测试模式
- 测试文件组织
- 模拟外部服务
- 测试覆盖率验证
- 应避免的常见测试错误
- 持续测试
- 最佳实践
- 成功指标
Files
SKILL.mdcore9,668 bytesSKILL.mdcore9,668 bytesSKILL.mdcore9,668 bytesSKILL.mdcore9,668 bytesSKILL.mdcore9,668 bytesSKILL.mdcore9,668 bytesSKILL.mdcore9,668 bytes
Read SKILL.md
# 测试驱动开发工作流
此技能确保所有代码开发遵循TDD原则,并具备全面的测试覆盖率。
## 何时激活
* 编写新功能或功能
* 修复错误或问题
* 重构现有代码
* 添加API端点
* 创建新组件
## 核心原则
View the complete source on GitHubverification-loop
When your agent uses it
Claude Code 会话的全面验证系统。
What it loads into context
Frontmatter
21 tokensAlways available to the agent
SKILL.md
755 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
- 何时使用
- 验证阶段
- 输出格式
- 持续模式
- 与钩子的集成
Files
SKILL.mdcore2,450 bytesSKILL.mdcore2,450 bytesSKILL.mdcore2,450 bytesSKILL.mdcore2,450 bytesSKILL.mdcore2,450 bytesSKILL.mdcore2,450 bytesSKILL.mdcore2,450 bytes
Read SKILL.md
# 验证循环技能
一个全面的 Claude Code 会话验证系统。
## 何时使用
在以下情况下调用此技能:
* 完成功能或重大代码变更后
* 创建 PR 之前
* 当您希望确保质量门通过时
* 重构之后
## 验证阶段View the complete source on GitHubvisa-doc-translate
When your agent uses it
将签证申请文件(图片)翻译成英文,并创建包含原文和译文的双语PDF
What it loads into context
Frontmatter
33 tokensAlways available to the agent
SKILL.md
991 tokensWhen the skill is activated
Reference documents
517 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- 说明
- 支持的文档
- 技术实现
- 重要指南
- 使用示例
- 输出示例
Files
README.mddoc1,752 bytesSKILL.mdcore3,483 bytesSKILL.mdcore3,483 bytesSKILL.mdcore3,483 bytesSKILL.mdcore3,483 bytesSKILL.mdcore3,483 bytesSKILL.mdcore3,483 bytesSKILL.mdcore3,483 bytes
Read SKILL.md
您正在协助翻译用于签证申请的签证申请文件。
## 说明
当用户提供图像文件路径时,**自动**执行以下步骤,**无需**请求确认:
1. **图像转换**:如果文件是 HEIC 格式,使用 `sips -s format png <input> --out <output>` 将其转换为 PNG
2. **图像旋转**:
* 检查 EXIF 方向数据
* 根据 EXIF 数据自动旋转图像
* 如果 EXIF 方向是 6,则逆时针旋转 90 度
* 根据需要应用额外旋转(如果文档看起来上下颠倒,则测试 180 度)
View the complete source on GitHubbackend-patterns
When your agent uses it
Backend architecture patterns, API design, database optimization, and server-side best practices for Node.js, Express, and Next.js API routes.
What it loads into context
Frontmatter
35 tokensAlways available to the agent
SKILL.md
3,495 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
- API 設計模式
- 資料庫模式
- 快取策略
- 錯誤處理模式
- 認證與授權
- 速率限制
- 背景任務與佇列
- 日誌與監控
Files
SKILL.mdcore13,295 bytes
Read SKILL.md
# 後端開發模式
用於可擴展伺服器端應用程式的後端架構模式和最佳實務。
## API 設計模式
### RESTful API 結構
```typescript
// ✅ 基於資源的 URL
GET /api/markets # 列出資源
GET /api/markets/:id # 取得單一資源
POST /api/markets # 建立資源
PUT /api/markets/:id # 替換資源View the complete source on GitHubclickhouse-io
When your agent uses it
ClickHouse database patterns, query optimization, analytics, and data engineering best practices for high-performance analytical workloads.
What it loads into context
Frontmatter
30 tokensAlways available to the agent
SKILL.md
2,710 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
- 概述
- 表格設計模式
- 查詢優化模式
- 資料插入模式
- 物化視圖
- 效能監控
- 常見分析查詢
- 資料管線模式
- 最佳實務
Files
SKILL.mdcore9,641 bytes
Read SKILL.md
# ClickHouse 分析模式
用於高效能分析和資料工程的 ClickHouse 特定模式。
## 概述
ClickHouse 是一個列式資料庫管理系統(DBMS),用於線上分析處理(OLAP)。它針對大型資料集的快速分析查詢進行了優化。
**關鍵特性:**
- 列式儲存
- 資料壓縮
- 平行查詢執行
- 分散式查詢
- 即時分析View the complete source on GitHubcoding-standards
When your agent uses it
Universal coding standards, best practices, and patterns for TypeScript, JavaScript, React, and Node.js development.
What it loads into context
Frontmatter
32 tokensAlways available to the agent
SKILL.md
3,341 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
- 程式碼品質原則
- TypeScript/JavaScript 標準
- React 最佳實務
- API 設計標準
- 檔案組織
- 註解與文件
- 效能最佳實務
- 測試標準
- 程式碼異味偵測
Files
SKILL.mdcore11,337 bytes
Read SKILL.md
# 程式碼標準與最佳實務
適用於所有專案的通用程式碼標準。
## 程式碼品質原則
### 1. 可讀性優先
- 程式碼被閱讀的次數遠多於被撰寫的次數
- 使用清晰的變數和函式名稱
- 優先使用自文件化的程式碼而非註解
- 保持一致的格式化
### 2. KISS(保持簡單)
- 使用最簡單的解決方案View the complete source on GitHubcontinuous-learning
When your agent uses it
Automatically extract reusable patterns from Claude Code sessions and save them as learned skills for future use.
What it loads into context
Frontmatter
25 tokensAlways available to the agent
SKILL.md
1,012 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
- 運作方式
- 設定
- 模式類型
- Hook 設定
- 為什麼用 Stop Hook?
- 相關
- 比較筆記(研究:2025 年 1 月)
Files
SKILL.mdcore3,194 bytes
Read SKILL.md
# 持續學習技能
自動評估 Claude Code 工作階段結束時的內容,提取可重用模式並儲存為學習技能。
## 運作方式
此技能作為 **Stop hook** 在每個工作階段結束時執行:
1. **工作階段評估**:檢查工作階段是否有足夠訊息(預設:10+ 則)
2. **模式偵測**:從工作階段識別可提取的模式
3. **技能提取**:將有用模式儲存到 `~/.claude/skills/learned/`
## 設定
View the complete source on GitHubcontinuous-learning-v2
When your agent uses it
Instinct-based learning system that observes sessions via hooks, creates atomic instincts with confidence scoring, and evolves them into skills/commands/agents.
What it loads into context
Frontmatter
45 tokensAlways available to the agent
SKILL.md
2,177 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
- v2 的新功能
- 本能模型
- 運作方式
- 快速開始
- 指令
- 設定
- 檔案結構
- 與 Skill Creator 整合
- 信心評分
- 為何 Hooks vs Skills 用於觀察?
- 向後相容性
- 隱私
- 相關
Files
SKILL.mdcore7,840 bytesSKILL.mdcore7,840 bytesSKILL.mdcore7,840 bytesSKILL.mdcore7,840 bytesSKILL.mdcore7,840 bytes
Read SKILL.md
# 持續學習 v2 - 基於本能的架構
進階學習系統,透過原子「本能」(帶信心評分的小型學習行為)將你的 Claude Code 工作階段轉化為可重用知識。
## v2 的新功能
| 功能 | v1 | v2 |
|------|----|----|
| 觀察 | Stop hook(工作階段結束) | PreToolUse/PostToolUse(100% 可靠) |
| 分析 | 主要上下文 | 背景 agent(Haiku) |
| 粒度 | 完整技能 | 原子「本能」 |
| 信心 | 無 | 0.3-0.9 加權 |
| 演化 | 直接到技能 | 本能 → 聚類 → 技能/指令/agent |
| 分享 | 無 | 匯出/匯入本能 |View the complete source on GitHubeval-harness
When your agent uses it
Formal evaluation framework for Claude Code sessions implementing eval-driven development (EDD) principles
What it loads into context
Frontmatter
38 tokensAlways available to the agent
SKILL.md
1,718 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
- 理念
- Eval 類型
- 評分器類型
- 指標
- Eval 工作流程
- 整合模式
- Eval 儲存
- 最佳實務
- 範例:新增認證
Files
SKILL.mdcore5,000 bytesSKILL.mdcore5,000 bytesSKILL.mdcore5,000 bytes
Read SKILL.md
# Eval Harness 技能
Claude Code 工作階段的正式評估框架,實作 eval 驅動開發(EDD)原則。
## 理念
Eval 驅動開發將 evals 視為「AI 開發的單元測試」:
- 在實作前定義預期行為
- 開發期間持續執行 evals
- 每次變更追蹤回歸
- 使用 pass@k 指標進行可靠性測量
## Eval 類型
View the complete source on GitHubfrontend-patterns
When your agent uses it
Frontend development patterns for React, Next.js, state management, performance optimization, and UI best practices.
What it loads into context
Frontmatter
29 tokensAlways available to the agent
SKILL.md
3,707 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
- 元件模式
- 自訂 Hooks 模式
- 狀態管理模式
- 效能優化
- 表單處理模式
- Error Boundary 模式
- 動畫模式
- 無障礙模式
Files
SKILL.mdcore14,162 bytes
Read SKILL.md
# 前端開發模式
用於 React、Next.js 和高效能使用者介面的現代前端模式。
## 元件模式
### 組合優於繼承
```typescript
// ✅ 良好:元件組合
interface CardProps {
children: React.ReactNode
variant?: 'default' | 'outlined'
}View the complete source on GitHubgolang-patterns
When your agent uses it
Idiomatic Go patterns, best practices, and conventions for building robust, efficient, and maintainable Go applications.
What it loads into context
Frontmatter
31 tokensAlways available to the agent
SKILL.md
3,923 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
- 何時啟用
- 核心原則
- 錯誤處理模式
- 並行模式
- 介面設計
- 套件組織
- 結構設計
- 記憶體與效能
- Go 工具整合
- 快速參考:Go 慣用語
- 要避免的反模式
Files
SKILL.mdcore13,575 bytesSKILL.mdcore13,575 bytes
Read SKILL.md
# Go 開發模式
用於建構穩健、高效且可維護應用程式的慣用 Go 模式和最佳實務。
## 何時啟用
- 撰寫新的 Go 程式碼
- 審查 Go 程式碼
- 重構現有 Go 程式碼
- 設計 Go 套件/模組
## 核心原則
### 1. 簡單與清晰View the complete source on GitHubgolang-testing
When your agent uses it
Go testing patterns including table-driven tests, subtests, benchmarks, fuzzing, and test coverage. Follows TDD methodology with idiomatic Go practices.
What it loads into context
Frontmatter
39 tokensAlways available to the agent
SKILL.md
4,735 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
- 何時啟用
- Go 的 TDD 工作流程
- 表格驅動測試
- 子測試
- 測試輔助函式
- Golden 檔案
- 使用介面 Mock
- 基準測試
- 模糊測試(Go 1.18+)
- 測試覆蓋率
- HTTP Handler 測試
- 測試指令
- 最佳實務
- CI/CD 整合
Files
SKILL.mdcore16,305 bytesSKILL.mdcore16,305 bytesSKILL.mdcore16,305 bytes
Read SKILL.md
# Go 測試模式
用於撰寫可靠、可維護測試的完整 Go 測試模式,遵循 TDD 方法論。
## 何時啟用
- 撰寫新的 Go 函式或方法
- 為現有程式碼增加測試覆蓋率
- 為效能關鍵程式碼建立基準測試
- 實作輸入驗證的模糊測試
- 在 Go 專案中遵循 TDD 工作流程
## Go 的 TDD 工作流程
View the complete source on GitHubiterative-retrieval
When your agent uses it
Pattern for progressively refining context retrieval to solve the subagent context problem
What it loads into context
Frontmatter
22 tokensAlways available to the agent
SKILL.md
1,736 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
- 問題
- 解決方案:迭代檢索
- 實際範例
- 與 Agents 整合
- 最佳實務
- 相關
Files
SKILL.mdcore6,184 bytes
Read SKILL.md
# 迭代檢索模式
解決多 agent 工作流程中的「上下文問題」,其中子 agents 在開始工作之前不知道需要什麼上下文。
## 問題
子 agents 以有限上下文產生。它們不知道:
- 哪些檔案包含相關程式碼
- 程式碼庫中存在什麼模式
- 專案使用什麼術語
標準方法失敗:
- **傳送所有內容**:超過上下文限制
- **不傳送內容**:Agent 缺乏關鍵資訊View the complete source on GitHubpostgres-patterns
When your agent uses it
PostgreSQL database patterns for query optimization, schema design, indexing, and security. Based on Supabase best practices.
What it loads into context
Frontmatter
31 tokensAlways available to the agent
SKILL.md
1,150 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
- 何時啟用
- 快速參考
- 相關
Files
SKILL.mdcore3,716 bytes
Read SKILL.md
# PostgreSQL 模式
PostgreSQL 最佳實務快速參考。詳細指南請使用 `database-reviewer` agent。
## 何時啟用
- 撰寫 SQL 查詢或 migrations
- 設計資料庫 schema
- 疑難排解慢查詢
- 實作 Row Level Security
- 設定連線池
## 快速參考
View the complete source on GitHubWhen your agent uses it
What it loads into context
Frontmatter
0 tokensAlways available to the agent
SKILL.md
2,402 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
- 何時使用
- 架構概覽
- 檔案結構
- 程式碼模式
- 測試要求
- 部署工作流程
- 關鍵規則
- 相關技能
Files
SKILL.mdcore9,540 bytesSKILL.mdcore9,540 bytesSKILL.mdcore9,540 bytesSKILL.mdcore9,540 bytesSKILL.mdcore9,540 bytesSKILL.mdcore9,540 bytesSKILL.mdcore9,540 bytesSKILL.mdcore9,540 bytesSKILL.mdcore9,540 bytesSKILL.mdcore9,540 bytes
Read SKILL.md
# 專案指南技能(範例)
這是專案特定技能的範例。使用此作為你自己專案的範本。
基於真實生產應用程式:[Zenith](https://zenith.chat) - AI 驅動的客戶探索平台。
---
## 何時使用
在處理專案特定設計時參考此技能。專案技能包含:
- 架構概覽
- 檔案結構
- 程式碼模式
- 測試要求View the complete source on GitHubsecurity-review
When your agent uses it
Use this skill when adding authentication, handling user input, working with secrets, creating API endpoints, or implementing payment/sensitive features. Provides comprehensive security checklist and patterns.
What it loads into context
Frontmatter
40 tokensAlways available to the agent
SKILL.md
3,591 tokensWhen the skill is activated
Reference documents
2,996 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- 何時啟用
- 安全性檢查清單
- 安全測試
- 部署前安全檢查清單
- 資源
Files
SKILL.mdcore11,668 bytesSKILL.mdcore11,668 bytesSKILL.mdcore11,668 bytescloud-infrastructure-security.mddoc9,420 bytes
Read SKILL.md
# 安全性審查技能
此技能確保所有程式碼遵循安全性最佳實務並識別潛在漏洞。
## 何時啟用
- 實作認證或授權
- 處理使用者輸入或檔案上傳
- 建立新的 API 端點
- 處理密鑰或憑證
- 實作支付功能
- 儲存或傳輸敏感資料
- 整合第三方 API
View the complete source on GitHubstrategic-compact
When your agent uses it
Suggests manual context compaction at logical intervals to preserve context through task phases rather than arbitrary auto-compaction.
What it loads into context
Frontmatter
30 tokensAlways available to the agent
SKILL.md
614 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
- 為什麼需要策略性壓縮?
- 運作方式
- Hook 設定
- 設定
- 最佳實務
- 相關
Files
SKILL.mdcore1,879 bytes
Read SKILL.md
# 策略性壓縮技能
在工作流程的策略點建議手動 `/compact`,而非依賴任意的自動壓縮。
## 為什麼需要策略性壓縮?
自動壓縮在任意點觸發:
- 經常在任務中途,丟失重要上下文
- 不知道邏輯任務邊界
- 可能中斷複雜的多步驟操作
邏輯邊界的策略性壓縮:
- **探索後、執行前** - 壓縮研究上下文,保留實作計畫
- **完成里程碑後** - 為下一階段重新開始View the complete source on GitHubtdd-workflow
When your agent uses it
Use this skill when writing new features, fixing bugs, or refactoring code. Enforces test-driven development with 80%+ coverage including unit, integration, and E2E tests.
What it loads into context
Frontmatter
47 tokensAlways available to the agent
SKILL.md
2,945 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
- 何時啟用
- 核心原則
- TDD 工作流程步驟
- 測試模式
- 測試檔案組織
- Mock 外部服務
- 測試覆蓋率驗證
- 常見測試錯誤避免
- 持續測試
- 最佳實務
- 成功指標
Files
SKILL.mdcore9,517 bytesSKILL.mdcore9,517 bytesSKILL.mdcore9,517 bytesSKILL.mdcore9,517 bytesSKILL.mdcore9,517 bytesSKILL.mdcore9,517 bytesSKILL.mdcore9,517 bytes
Read SKILL.md
# 測試驅動開發工作流程
此技能確保所有程式碼開發遵循 TDD 原則,並具有完整的測試覆蓋率。
## 何時啟用
- 撰寫新功能或功能性程式碼
- 修復 Bug 或問題
- 重構現有程式碼
- 新增 API 端點
- 建立新元件
## 核心原則
View the complete source on GitHubWhen your agent uses it
What it loads into context
Frontmatter
0 tokensAlways available to the agent
SKILL.md
847 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
- 何時使用
- 驗證階段
- 輸出格式
- 持續模式
- 與 Hooks 整合
Files
SKILL.mdcore2,297 bytesSKILL.mdcore2,297 bytesSKILL.mdcore2,297 bytesSKILL.mdcore2,297 bytesSKILL.mdcore2,297 bytesSKILL.mdcore2,297 bytesSKILL.mdcore2,297 bytes
Read SKILL.md
# 驗證循環技能
Claude Code 工作階段的完整驗證系統。
## 何時使用
在以下情況呼叫此技能:
- 完成功能或重大程式碼變更後
- 建立 PR 前
- 想確保品質門檻通過時
- 重構後
## 驗證階段
### 階段 1:建置驗證View the complete source on GitHubapi-design
When your agent uses it
生产级 API 的 REST API 设计模式,包括资源命名、状态码、分页、过滤、错误响应、版本控制和速率限制。
What it loads into context
Frontmatter
42 tokensAlways available to the agent
SKILL.md
3,875 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
- 何时启用
- 资源设计 (Resource Design)
- HTTP 方法与状态码
- 响应格式 (Response Format)
- 分页 (Pagination)
- 过滤、排序与搜索 (Filtering, Sorting, and Search)
- 身份验证与授权 (Authentication and Authorization)
- 速率限制 (Rate Limiting)
- 版本控制 (Versioning)
- 实现模式 (Implementation Patterns)
- API 设计自检清单 (API Design Checklist)
Files
SKILL.mdcore13,696 bytesSKILL.mdcore13,696 bytes
Read SKILL.md
# API 设计模式 (API Design Patterns)
设计一致且开发者友好的 REST API 的规范与最佳实践。
## 何时启用
- 设计新的 API 端点 (Endpoints)
- 审查现有的 API 合约 (Contracts)
- 添加分页、过滤或排序功能
- 为 API 实现错误处理
- 规划 API 版本控制策略
- 构建公开或面向合作伙伴的 API
## 资源设计 (Resource Design)View the complete source on GitHubarticle-writing
When your agent uses it
编写文章、指南、博客帖子、教程、新闻通讯(newsletter)以及其他长篇内容。这些内容具有从提供的示例或品牌指南中提取出的独特语气。当用户需要比段落更长的精美文案,且对语气一致性、结构和可信度有要求时,请使用此技能(Skill)。
What it loads into context
Frontmatter
86 tokensAlways available to the agent
SKILL.md
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
- 何时激活 (When to Activate)
- 核心规则 (Core Rules)
- 语气捕捉工作流 (Voice Capture Workflow)
- 禁用模式 (Banned Patterns)
- 写作流程 (Writing Process)
- 结构指南 (Structure Guidance)
- 质量把控 (Quality Gate)
Files
SKILL.mdcore3,421 bytes
Read SKILL.md
# 文章撰写 (Article Writing)
撰写听起来像真实人物或品牌、而非通用 AI 生成的长篇内容。
## 何时激活 (When to Activate)
- 起草博客文章、散文、发布说明、指南、教程或新闻通讯(newsletter)
- 将笔记、访谈记录或研究资料转化为精美的文章
- 根据示例模仿现有创始人、运营者或品牌的语气
- 对已撰写的长篇文案进行结构优化、节奏把控及证据补充
## 核心规则 (Core Rules)
1. 以具体事物开头:示例、输出、轶事、数字、截图描述或代码块。View the complete source on GitHubautonomous-loops
When your agent uses it
自主运行 Claude Code 循环的模式与架构 —— 从简单的顺序流水线到 RFC 驱动的多智能体 DAG 系统。
What it loads into context
Frontmatter
46 tokensAlways available to the agent
SKILL.md
6,904 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
- 适用场景
- 循环模式频谱 (Loop Pattern Spectrum)
- 1. 顺序流水线 (Sequential Pipeline, `claude -p`)
- 2. NanoClaw REPL
- 3. 无限智能体循环 (Infinite Agentic Loop)
- 4. 持续 Claude PR 循环 (Continuous Claude PR Loop)
- 5. 去杂质模式 (The De-Sloppify Pattern)
- 6. Ralphinho / RFC 驱动的 DAG 编排 (RFC-Driven DAG Orchestration)
- 选择合适的模式
- 反模式 (Anti-Patterns)
- 参考资料
Scripts executed separately
../../scripts/claw.js../../scripts/claw.js
Files
../../scripts/claw.jsruns7,471 bytes../../scripts/claw.jsruns7,471 bytesSKILL.mdcore25,371 bytesSKILL.mdcore25,371 bytesSKILL.mdcore25,371 bytesSKILL.mdcore25,371 bytesSKILL.mdcore25,371 bytesSKILL.mdcore25,371 bytesSKILL.mdcore25,371 bytesSKILL.mdcore25,371 bytesSKILL.mdcore25,371 bytesSKILL.mdcore25,371 bytesSKILL.mdcore25,371 bytesSKILL.mdcore25,371 bytesSKILL.mdcore25,371 bytesSKILL.mdcore25,371 bytes
Read SKILL.md
# 自主循环技能 (Autonomous Loops Skill)
用于自主运行 Claude Code 循环的模式、架构和参考实现。涵盖了从简单的 `claude -p` 流水线到完整的 RFC 驱动多智能体(multi-agent)DAG 编排的所有内容。
## 适用场景
- 设置无需人工干预即可运行的自主开发工作流(Workflows)
- 为你的问题选择合适的循环架构(简单 vs 复杂)
- 构建 CI/CD 风格的持续开发流水线
- 运行具有合并协调机制的并行智能体(Agents)
- 在循环迭代之间实现上下文(Context)持久化
- 为自主工作流添加质量门禁(Quality gates)和清理环节
## 循环模式频谱 (Loop Pattern Spectrum)View the complete source on GitHubbackend-patterns
When your agent uses it
后端架构模式、API 设计、数据库优化以及针对 Node.js、Express 和 Next.js API 路由的服务端最佳实践。
What it loads into context
Frontmatter
42 tokensAlways available to the agent
SKILL.md
3,576 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
- 何时激活 (When to Activate)
- API 设计模式
- 数据库模式
- 缓存策略
- 错误处理模式
- 身份验证与授权
- 限流 (Rate Limiting)
- 后台任务与队列 (Background Jobs & Queues)
- 日志与监控 (Logging & Monitoring)
Files
SKILL.mdcore14,039 bytes
Read SKILL.md
# 后端开发模式 (Backend Development Patterns)
用于构建可扩展服务端应用的后端架构模式与最佳实践。
## 何时激活 (When to Activate)
- 设计 REST 或 GraphQL API 端点时
- 实现仓储层(Repository)、服务层(Service)或控制层(Controller)时
- 优化数据库查询(N+1 问题、索引、连接池)时
- 添加缓存(Redis、内存缓存、HTTP 缓存头)时
- 设置后台作业(Background jobs)或异步处理时
- 为 API 构建错误处理与数据校验机制时
- 编写中间件(身份验证、日志记录、限流)时
View the complete source on GitHubclickhouse-io
When your agent uses it
ClickHouse 数据库模式、查询优化、分析以及高性能分析负载的数据工程最佳实践。
What it loads into context
Frontmatter
33 tokensAlways available to the agent
SKILL.md
2,815 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
- 何时激活 (When to Activate)
- 概述 (Overview)
- 表设计模式 (Table Design Patterns)
- 查询优化模式 (Query Optimization Patterns)
- 数据插入模式 (Data Insertion Patterns)
- 物化视图 (Materialized Views)
- 性能监控 (Performance Monitoring)
- 常用分析查询 (Common Analytics Queries)
- 数据管道模式 (Data Pipeline Patterns)
- 最佳实践 (Best Practices)
Files
SKILL.mdcore10,594 bytes
Read SKILL.md
# ClickHouse 分析模式 (ClickHouse Analytics Patterns)
针对高性能分析和数据工程的 ClickHouse 特定模式。
## 何时激活 (When to Activate)
- 设计 ClickHouse 表结构(MergeTree 引擎选择)
- 编写分析查询(聚合、窗口函数、连接)
- 优化查询性能(分区剪枝、投影、物化视图)
- 摄取海量数据(批量插入、Kafka 集成)
- 将分析业务从 PostgreSQL/MySQL 迁移到 ClickHouse
- 实现实时仪表盘或时间序列分析
## 概述 (Overview)View the complete source on GitHubcoding-standards
When your agent uses it
适用于 TypeScript、JavaScript、React 和 Node.js 开发的通用编码标准、最佳实践和模式。
What it loads into context
Frontmatter
38 tokensAlways available to the agent
SKILL.md
3,415 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
- 何时启用 (When to Activate)
- 代码质量原则 (Code Quality Principles)
- TypeScript/JavaScript 规范
- React 最佳实践
- API 设计规范 (API Design Standards)
- 文件组织 (File Organization)
- 注释与文档 (Comments & Documentation)
- 性能最佳实践 (Performance Best Practices)
- 测试规范 (Testing Standards)
- 代码异味(Code Smell)检测
Files
SKILL.mdcore12,529 bytes
Read SKILL.md
# 编码标准与最佳实践 (Coding Standards & Best Practices)
适用于所有项目的通用编码标准。
## 何时启用 (When to Activate)
- 启动新项目或模块时
- 为了质量和可维护性进行代码审查(Code Review)时
- 重构现有代码以遵循规范时
- 强制执行命名、格式或结构的一致性时
- 设置 linting、格式化或类型检查规则时
- 引导新贡献者了解编码规范时
## 代码质量原则 (Code Quality Principles)View the complete source on GitHubconfigure-ecc
When your agent uses it
Everything Claude Code 的交互式安装程序 —— 引导用户选择并将技能(Skills)和规则(Rules)安装到用户级或项目级目录,验证路径,并可选地优化已安装的文件。
What it loads into context
Frontmatter
57 tokensAlways available to the agent
SKILL.md
3,861 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
- 何时激活
- 前提条件
- 步骤 0:克隆 ECC 仓库
- 步骤 1:选择安装层级
- 步骤 2:选择并安装技能(Skills)
- 步骤 3:选择并安装规则(Rules)
- 步骤 4:安装后验证
- 步骤 5:优化已安装的文件(可选)
- 步骤 6:安装总结
- 故障排除
Files
SKILL.mdcore13,828 bytesSKILL.mdcore13,828 bytesSKILL.mdcore13,828 bytesSKILL.mdcore13,828 bytesSKILL.mdcore13,828 bytesSKILL.mdcore13,828 bytesSKILL.mdcore13,828 bytesSKILL.mdcore13,828 bytes
Read SKILL.md
# 配置 Everything Claude Code (ECC)
一个针对 Everything Claude Code 项目的交互式分步安装向导。使用 `AskUserQuestion` 引导用户选择性地安装技能(Skills)和规则(Rules),然后验证正确性并提供优化建议。
## 何时激活
- 用户说 "configure ecc"、"install ecc"、"setup everything claude code" 或类似指令时
- 用户想要从本项目中选择性安装技能(Skills)或规则(Rules)时
- 用户想要验证或修复现有的 ECC 安装时
- 用户想要为他们的项目优化已安装的技能(Skills)或规则(Rules)时
## 前提条件
此技能(Skill)在激活前必须可被 Claude Code 访问。有两种引导方式:View the complete source on GitHubcontent-engine
When your agent uses it
为 X、LinkedIn、TikTok、YouTube、时事通讯(Newsletters)以及跨平台重用活动创建平台原生(platform-native)的内容系统。当用户需要社交帖子、推文串(threads)、脚本、内容日历,或将单一资源资产清晰地适配到多个平台时使用。
What it loads into context
Frontmatter
82 tokensAlways available to the agent
SKILL.md
925 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
- 何时激活 (When to Activate)
- 首要问题 (First Questions)
- 核心规则 (Core Rules)
- 平台指南 (Platform Guidance)
- 重用流程 (Repurposing Flow)
- 交付物 (Deliverables)
- 质量关卡 (Quality Gate)
Files
SKILL.mdcore3,242 bytesSKILL.mdcore3,242 bytes
Read SKILL.md
# 内容引擎 (Content Engine)
将一个想法转化为强大的、平台原生(platform-native)的内容,而不是在所有地方发布同样的东西。
## 何时激活 (When to Activate)
- 编写 X 帖子或推文串(threads)
- 起草 LinkedIn 帖子或发布更新
- 编写短视频(short-form video)或 YouTube 讲解视频脚本
- 将文章、播客(podcasts)、演示(demos)或文档重用为社交内容
- 围绕发布、里程碑或主题构建轻量级内容计划
## 首要问题 (First Questions)
View the complete source on GitHubcontent-hash-cache-pattern
When your agent uses it
使用 SHA-256 内容哈希缓存高昂的文件处理结果 —— 与路径无关、自动失效且服务层分离。
What it loads into context
Frontmatter
42 tokensAlways available to the agent
SKILL.md
1,573 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
- 何时激活
- 核心模式
- 关键设计决策
- 最佳实践
- 应避免的反模式 (Anti-Patterns)
- 适用场景
- 不适用场景
Files
SKILL.mdcore5,949 bytesSKILL.mdcore5,949 bytesSKILL.mdcore5,949 bytesSKILL.mdcore5,949 bytesSKILL.mdcore5,949 bytesSKILL.mdcore5,949 bytes
Read SKILL.md
# 内容哈希文件缓存模式 (Content-Hash File Cache Pattern)
使用 SHA-256 内容哈希(而非文件路径)作为缓存键,缓存高昂的文件处理结果(如 PDF 解析、文本提取、图像分析)。与基于路径的缓存不同,这种方法在文件移动/重命名后依然有效,并在内容变化时自动失效。
## 何时激活
- 构建文件处理流水线(Pipeline),如 PDF、图像或文本提取
- 处理成本高昂且需要重复处理相同文件
- 需要提供 `--cache/--no-cache` 命令行选项
- 希望在不修改现有纯函数(Pure Functions)的情况下为其添加缓存功能
## 核心模式
### 1. 基于内容哈希的缓存键View the complete source on GitHubcontinuous-learning
When your agent uses it
Automatically extract reusable patterns from Claude Code sessions and save them as learned skills for future use.
What it loads into context
Frontmatter
28 tokensAlways available to the agent
SKILL.md
1,145 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
- 何时激活
- 工作原理
- 配置
- 模式类型
- 钩子设置(Hook Setup)
- 为什么使用 Stop 钩子?
- 相关内容
- 比较笔记(调研:2025年1月)
Scripts executed separately
evaluate-session.sh
Files
SKILL.mdcore3,923 bytesconfig.jsonasset391 bytesevaluate-session.shruns2,391 bytes
Read SKILL.md
# 持续学习技能(Continuous Learning Skill)
在会话结束时自动评估 Claude Code 会话,提取可保存为已学习技能(Learned Skills)的可复用模式。
## 何时激活
- 设置从 Claude Code 会话中自动提取模式
- 为会话评估配置 `Stop` 钩子(Hook)
- 查看或整理 `~/.claude/skills/learned/` 中的已学习技能
- 调整提取阈值或模式类别
- 比较 v1(当前)与 v2(基于直觉/Instinct)的方法
## 工作原理
View the complete source on GitHubcontinuous-learning-v2
When your agent uses it
基于本能(Instinct)的学习系统,通过钩子(hooks)观察会话,创建带有置信度评分的原子本能,并将其演化为技能(Skills)、命令(Commands)或智能体(Agents)。v2.1 版本增加了项目作用域(project-scoped)的本能,以防止跨项目污染。
What it loads into context
Frontmatter
100 tokensAlways available to the agent
SKILL.md
3,632 tokensWhen the skill is activated
Reference documents
2,262 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- 何时激活
- v2.1 的新特性
- v2 的新特性(对比 v1)
- 本能模型(The Instinct Model)
- 工作原理
- 项目检测(Project Detection)
- 快速开始
- 命令
- 配置
- 文件结构
- 作用域决策指南
- 本能提升 (项目 -> 全局)
- 置信度评分
- 为什么使用钩子(Hooks)而非技能(Skills)进行观察?
- 向后兼容性
- 隐私
- 相关内容
Scripts executed separately
agents/start-observer.shhooks/observe.shscripts/detect-project.shscripts/instinct-cli.pyscripts/test_parse_instinct.py
Files
SKILL.mdcore12,712 bytesSKILL.mdcore12,712 bytesSKILL.mdcore12,712 bytesSKILL.mdcore12,712 bytesSKILL.mdcore12,712 bytesSKILL.mdcore12,712 bytesSKILL.mdcore12,712 bytesagents/observer.mddoc7,531 bytesagents/start-observer.shruns9,400 bytesconfig.jsonasset135 byteshooks/observe.shruns6,732 bytesscripts/detect-project.shruns4,800 bytesscripts/instinct-cli.pyruns45,628 bytesscripts/test_parse_instinct.pyruns32,256 bytes
Read SKILL.md
# 持续学习(Continuous Learning)v2.1 - 基于本能(Instinct)的架构
一个先进的学习系统,通过原子级“本能(Instincts)”——带有置信度评分的小型学习行为,将你的 Claude Code 会话转化为可复用的知识。
**v2.1** 增加了 **项目作用域本能(project-scoped instincts)** —— React 模式保留在你的 React 项目中,Python 约定保留在你的 Python 项目中,而通用模式(如“始终验证输入”)则在全局共享。
## 何时激活
- 设置从 Claude Code 会话中自动学习
- 配置通过钩子(hooks)提取基于本能的行为
- 调整学习行为的置信度阈值
- 查看、导出或导入本能库
- 将本能演化为完整的技能(Skills)、命令(Commands)或智能体(Agents)
- 管理项目作用域与全局本能View the complete source on GitHubcost-aware-llm-pipeline
When your agent uses it
LLM API 使用成本优化模式——基于任务复杂度的模型路由、预算跟踪、重试逻辑和提示词缓存。
What it loads into context
Frontmatter
46 tokensAlways available to the agent
SKILL.md
1,584 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
- 何时启用
- 核心概念
- 组合使用
- 价格参考 (2025-2026)
- 最佳实践
- 应避免的反模式 (Anti-Patterns)
- 使用场景
Files
SKILL.mdcore5,997 bytesSKILL.mdcore5,997 bytesSKILL.mdcore5,997 bytesSKILL.mdcore5,997 bytesSKILL.mdcore5,997 bytesSKILL.mdcore5,997 bytes
Read SKILL.md
# 成本感知型 LLM 流水线 (Cost-Aware LLM Pipeline)
在保持质量的同时控制 LLM API 成本的模式。将模型路由 (Model Routing)、预算跟踪 (Budget Tracking)、重试逻辑 (Retry Logic) 和提示词缓存 (Prompt Caching) 组合成一个可复用的流水线。
## 何时启用
- 构建调用 LLM API(Claude、GPT 等)的应用
- 处理具有不同复杂度的批量项目
- 需要将 API 支出控制在预算范围内
- 在不牺牲复杂任务质量的前提下优化成本
## 核心概念
### 1. 基于任务复杂度的模型路由 (Model Routing)View the complete source on GitHubcpp-coding-standards
When your agent uses it
基于 C++ 核心指南 (isocpp.github.io) 的 C++ 编码规范。在编写、评审或重构 C++ 代码时使用,以强制执行现代、安全且地道的实践。
What it loads into context
Frontmatter
62 tokensAlways available to the agent
SKILL.md
7,063 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
- 何时使用
- 核心原则 (Cross-Cutting Principles)
- 哲学与接口 (P.*, I.*)
- 函数 (F.*)
- 类与类层次结构 (C.*)
- 资源管理 (R.*)
- 表达式与语句 (ES.*)
- 错误处理 (E.*)
- 常量与不变性 (Con.*)
- 并发与并行 (CP.*)
- 模板与泛型编程 (T.*)
- 标准库 (SL.*)
- 枚举 (Enum.*)
- 源文件与命名 (SF.*, NL.*)
- 性能 (Per.*)
- 快速参考自检清单
Files
SKILL.mdcore22,659 bytes
Read SKILL.md
# C++ 编码规范 (C++ Core Guidelines)
源自 [C++ 核心指南 (C++ Core Guidelines)](https://isocpp.github.io/CppCoreGuidelines/CppCoreGuidelines) 的现代 C++ (C++17/20/23) 综合编码规范。强制执行类型安全 (Type safety)、资源安全 (Resource safety)、不变性 (Immutability) 和清晰度。
## 何时使用
- 编写新的 C++ 代码(类、函数、模板)
- 评审或重构现有的 C++ 代码
- 在 C++ 项目中做出架构决策
- 在 C++ 代码库中强制执行一致的风格
- 在语言特性之间进行选择(例如 `enum` vs `enum class`,原始指针 vs 智能指针)
### 何时不使用
View the complete source on GitHubcpp-testing
When your agent uses it
仅在编写/更新/修复 C++ 测试、配置 GoogleTest/CTest、诊断失败或不稳定的测试、或添加覆盖率/检测器(Sanitizers)时使用。
What it loads into context
Frontmatter
56 tokensAlways available to the agent
SKILL.md
2,687 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
- 适用场景
- 核心概念
- TDD 工作流
- 代码示例
- 运行测试
- 调试失败用例
- 覆盖率 (Coverage)
- 检测器 (Sanitizers)
- 不稳定测试(Flaky Tests)防护准则
- 最佳实践
- 可选附录:模糊测试 / 属性测试
- GoogleTest 的替代方案
Files
SKILL.mdcore9,666 bytesSKILL.mdcore9,666 bytesSKILL.mdcore9,666 bytesSKILL.mdcore9,666 bytesSKILL.mdcore9,666 bytesSKILL.mdcore9,666 bytes
Read SKILL.md
# C++ 测试(智能体技能)
针对现代 C++ (C++17/20) 的智能体测试工作流,使用 GoogleTest/GoogleMock 配合 CMake/CTest。
## 适用场景
- 编写新的 C++ 测试或修复现有测试
- 为 C++ 组件设计单元/集成测试覆盖
- 添加测试覆盖、CI 门禁或回归防护
- 配置 CMake/CTest 工作流以实现一致性执行
- 调查测试失败或不稳定(Flaky)行为
- 启用检测器(Sanitizers)进行内存/竞态诊断
### 不适用场景View the complete source on GitHubdatabase-migrations
When your agent uses it
跨 PostgreSQL、MySQL 及常用 ORM(Prisma、Drizzle、Django、TypeORM、golang-migrate)的模式变更(schema changes)、数据迁移、回滚及零停机部署(zero-downtime deployments)的数据库迁移最佳实践。
What it loads into context
Frontmatter
72 tokensAlways available to the agent
SKILL.md
2,570 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
- 激活时机
- 核心原则
- 迁移安全核查表(Migration Safety Checklist)
- PostgreSQL 模式
- Prisma (TypeScript/Node.js)
- Drizzle (TypeScript/Node.js)
- Django (Python)
- golang-migrate (Go)
- 零停机迁移策略(Zero-Downtime Migration Strategy)
- 反模式(Anti-Patterns)
Files
SKILL.mdcore9,760 bytesSKILL.mdcore9,760 bytesSKILL.mdcore9,760 bytesSKILL.mdcore9,760 bytesSKILL.mdcore9,760 bytesSKILL.mdcore9,760 bytesSKILL.mdcore9,760 bytesSKILL.mdcore9,760 bytesSKILL.mdcore9,760 bytesSKILL.mdcore9,760 bytesSKILL.mdcore9,760 bytesSKILL.mdcore9,760 bytes
Read SKILL.md
# 数据库迁移模式(Database Migration Patterns)
面向生产系统的安全、可逆的数据库模式变更(Schema Changes)。
## 激活时机
- 创建或修改数据库表
- 添加/删除列或索引
- 执行数据迁移(数据回填 backfill、转换 transform)
- 规划零停机(zero-downtime)模式变更
- 为新项目设置迁移工具链
## 核心原则
View the complete source on GitHubdeployment-patterns
When your agent uses it
Deployment workflows, CI/CD pipeline patterns, Docker containerization, health checks, rollback strategies, and production readiness checklists for web applications.
What it loads into context
Frontmatter
38 tokensAlways available to the agent
SKILL.md
3,346 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
- 何时激活
- 部署策略 (Deployment Strategies)
- Docker
- CI/CD 流水线 (CI/CD Pipeline)
- 健康检查 (Health Checks)
- 环境配置 (Environment Configuration)
- 回滚策略 (Rollback Strategy)
- 生产就绪自检清单 (Production Readiness Checklist)
Files
SKILL.mdcore11,390 bytesSKILL.mdcore11,390 bytesSKILL.mdcore11,390 bytes
Read SKILL.md
# 部署模式 (Deployment Patterns)
生产部署工作流与 CI/CD 最佳实践。
## 何时激活
- 设置 CI/CD 流水线 (Pipelines)
- 对应用程序进行 Docker 容器化
- 规划部署策略(蓝绿部署、金丝雀部署、滚动更新)
- 实现健康检查 (Health Checks) 与就绪探针 (Readiness Probes)
- 准备生产发布
- 配置环境特定的设置
## 部署策略 (Deployment Strategies)View the complete source on GitHubdjango-patterns
When your agent uses it
Django 架构模式、使用 DRF 的 REST API 设计、ORM 最佳实践、缓存、信号(Signals)、中间件(Middleware)以及生产级 Django 应用。
What it loads into context
Frontmatter
51 tokensAlways available to the agent
SKILL.md
4,850 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
- 何时激活 (When to Activate)
- 项目结构 (Project Structure)
- 模型设计模式 (Model Design Patterns)
- Django REST Framework 模式 (Django REST Framework Patterns)
- 服务层模式 (Service Layer Pattern)
- 缓存策略 (Caching Strategies)
- 信号 (Signals)
- 中间件 (Middleware)
- 性能优化 (Performance Optimization)
- 快速参考 (Quick Reference)
Files
SKILL.mdcore21,686 bytesSKILL.mdcore21,686 bytesSKILL.mdcore21,686 bytesSKILL.mdcore21,686 bytesSKILL.mdcore21,686 bytesSKILL.mdcore21,686 bytesSKILL.mdcore21,686 bytesSKILL.mdcore21,686 bytesSKILL.mdcore21,686 bytesSKILL.mdcore21,686 bytesSKILL.mdcore21,686 bytesSKILL.mdcore21,686 bytesSKILL.mdcore21,686 bytesSKILL.mdcore21,686 bytesSKILL.mdcore21,686 bytesSKILL.mdcore21,686 bytesSKILL.mdcore21,686 bytes
Read SKILL.md
# Django 开发模式 (Django Development Patterns)
适用于可扩展、可维护应用程序的生产级 Django 架构模式。
## 何时激活 (When to Activate)
- 构建 Django Web 应用程序
- 设计 Django REST Framework (DRF) API
- 处理 Django ORM 和模型 (Models)
- 搭建 Django 项目结构
- 实现缓存 (Caching)、信号 (Signals)、中间件 (Middleware)
## 项目结构 (Project Structure)
View the complete source on GitHubdjango-security
When your agent uses it
Django 安全最佳实践,涵盖身份验证、授权、CSRF 防护、SQL 注入预防、XSS 预防以及安全部署配置。
What it loads into context
Frontmatter
44 tokensAlways available to the agent
SKILL.md
3,928 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
- 何时启用
- 核心安全设置
- 身份验证 (Authentication)
- 授权 (Authorization)
- SQL 注入预防
- XSS 预防
- CSRF 防护
- 文件上传安全
- API 安全
- 安全响应头
- 环境变量
- 记录安全事件
- 快速安全检查清单
Files
SKILL.mdcore15,947 bytesSKILL.mdcore15,947 bytesSKILL.mdcore15,947 bytesSKILL.mdcore15,947 bytesSKILL.mdcore15,947 bytesSKILL.mdcore15,947 bytesSKILL.mdcore15,947 bytesSKILL.mdcore15,947 bytesSKILL.mdcore15,947 bytesSKILL.mdcore15,947 bytesSKILL.mdcore15,947 bytesSKILL.mdcore15,947 bytesSKILL.mdcore15,947 bytesSKILL.mdcore15,947 bytesSKILL.mdcore15,947 bytesSKILL.mdcore15,947 bytesSKILL.mdcore15,947 bytesSKILL.mdcore15,947 bytesSKILL.mdcore15,947 bytesSKILL.mdcore15,947 bytesSKILL.mdcore15,947 bytes
Read SKILL.md
# Django 安全最佳实践 (Django Security Best Practices)
针对 Django 应用程序的全面安全指南,旨在防范常见漏洞。
## 何时启用
- 设置 Django 身份验证 (Authentication) 和授权 (Authorization) 时
- 实现用户权限和角色时
- 配置生产环境安全设置时
- 审查 Django 应用程序的安全问题时
- 将 Django 应用程序部署到生产环境时
## 核心安全设置
View the complete source on GitHubdjango-tdd
When your agent uses it
使用 pytest-django 进行 Django 测试的策略、TDD 方法论、factory_boy、Mock 模拟、测试覆盖率以及测试 Django REST Framework API。
What it loads into context
Frontmatter
47 tokensAlways available to the agent
SKILL.md
4,897 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
- 何时激活
- Django 的 TDD 工作流
- 配置
- Factory Boy
- 模型(Model)测试
- 视图(View)测试
- DRF API 测试
- Mock 模拟与打补丁(Patching)
- 集成测试
- 测试最佳实践
- 覆盖率(Coverage)
- 快速参考
Files
SKILL.mdcore21,245 bytesSKILL.mdcore21,245 bytesSKILL.mdcore21,245 bytesSKILL.mdcore21,245 bytesSKILL.mdcore21,245 bytesSKILL.mdcore21,245 bytesSKILL.mdcore21,245 bytesSKILL.mdcore21,245 bytesSKILL.mdcore21,245 bytesSKILL.mdcore21,245 bytesSKILL.mdcore21,245 bytesSKILL.mdcore21,245 bytesSKILL.mdcore21,245 bytesSKILL.mdcore21,245 bytes
Read SKILL.md
# 使用 TDD 进行 Django 测试
使用 pytest、factory_boy 和 Django REST Framework 对 Django 应用程序进行测试驱动开发(TDD)。
## 何时激活
- 编写新的 Django 应用程序时
- 实现 Django REST Framework API 时
- 测试 Django 模型(Models)、视图(Views)和序列化器(Serializers)时
- 为 Django 项目搭建测试基础设施时
## Django 的 TDD 工作流
### 红-绿-重构(Red-Green-Refactor)周期View the complete source on GitHubdjango-verification
When your agent uses it
针对 Django 项目的验证循环:包含数据库迁移、代码检查、带覆盖率的测试、安全扫描,以及在发布或 PR 前的部署就绪检查。
What it loads into context
Frontmatter
47 tokensAlways available to the agent
SKILL.md
3,364 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
- 何时启用
- 阶段 1:环境检查 (Environment Check)
- 阶段 2:代码质量与格式化 (Code Quality & Formatting)
- 阶段 3:数据库迁移 (Migrations)
- 阶段 4:测试 + 覆盖率 (Tests + Coverage)
- 阶段 5:安全扫描 (Security Scan)
- 阶段 6:Django 管理命令 (Django Management Commands)
- 阶段 7:性能检查 (Performance Checks)
- 阶段 8:静态资源 (Static Assets)
- 阶段 9:配置审查 (Configuration Review)
- 阶段 10:日志配置 (Logging Configuration)
- 阶段 11:API 文档 (API Documentation, 如果使用 DRF)
- 阶段 12:差异审查 (Diff Review)
- 输出模板 (Output Template)
- 部署前检查清单 (Pre-Deployment Checklist)
- 持续集成 (Continuous Integration)
- 快速参考 (Quick Reference)
Files
SKILL.mdcore11,868 bytesSKILL.mdcore11,868 bytesSKILL.mdcore11,868 bytesSKILL.mdcore11,868 bytesSKILL.mdcore11,868 bytesSKILL.mdcore11,868 bytesSKILL.mdcore11,868 bytesSKILL.mdcore11,868 bytesSKILL.mdcore11,868 bytesSKILL.mdcore11,868 bytesSKILL.mdcore11,868 bytesSKILL.mdcore11,868 bytesSKILL.mdcore11,868 bytesSKILL.mdcore11,868 bytesSKILL.mdcore11,868 bytesSKILL.mdcore11,868 bytesSKILL.mdcore11,868 bytesSKILL.mdcore11,868 bytesSKILL.mdcore11,868 bytesSKILL.mdcore11,868 bytesSKILL.mdcore11,868 bytesSKILL.mdcore11,868 bytesSKILL.mdcore11,868 bytesSKILL.mdcore11,868 bytesSKILL.mdcore11,868 bytesSKILL.mdcore11,868 bytesSKILL.mdcore11,868 bytesSKILL.mdcore11,868 bytesSKILL.mdcore11,868 bytesSKILL.mdcore11,868 bytesSKILL.mdcore11,868 bytesSKILL.mdcore11,868 bytesSKILL.mdcore11,868 bytesSKILL.mdcore11,868 bytes
Read SKILL.md
# Django 验证循环 (Django Verification Loop)
在提交 PR 前、重大变更后以及部署前运行,以确保 Django 应用的质量与安全性。
## 何时启用
- 在为 Django 项目提交 Pull Request 前
- 在重大模型变更、迁移更新或依赖升级后
- 预发布(Staging)或生产环境部署前的验证
- 运行完整的 环境检查 → 代码检查 → 测试 → 安全扫描 → 部署就绪流水线
- 验证迁移安全性及测试覆盖率
## 阶段 1:环境检查 (Environment Check)
View the complete source on GitHubdocker-patterns
When your agent uses it
用于本地开发、容器安全、网络、卷策略和多服务编排的 Docker 与 Docker Compose 模式。
What it loads into context
Frontmatter
38 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
- 激活时机
- 用于本地开发的 Docker Compose
- 网络(Networking)
- 卷策略(Volume Strategies)
- 容器安全(Container Security)
- .dockerignore
- 调试(Debugging)
- 反模式(Anti-Patterns)
Files
SKILL.mdcore8,665 bytesSKILL.mdcore8,665 bytesSKILL.mdcore8,665 bytesSKILL.mdcore8,665 bytesSKILL.mdcore8,665 bytes
Read SKILL.md
# Docker 模式 (Docker Patterns)
容器化开发的 Docker 和 Docker Compose 最佳实践。
## 激活时机
- 为本地开发设置 Docker Compose
- 设计多容器架构
- 排查容器网络或卷(Volume)问题
- 审查 Dockerfile 的安全性与镜像大小
- 从本地开发迁移到容器化工作流(Workflow)
## 用于本地开发的 Docker Compose
View the complete source on GitHube2e-testing
When your agent uses it
Playwright E2E 测试模式、页面对象模型 (Page Object Model)、配置、CI/CD 集成、产物管理以及不稳定测试 (Flaky Test) 策略。
What it loads into context
Frontmatter
53 tokensAlways available to the agent
SKILL.md
2,363 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
- 测试文件组织 (Test File Organization)
- 页面对象模型 (Page Object Model - POM)
- 测试结构 (Test Structure)
- Playwright 配置 (Playwright Configuration)
- 不稳定测试模式 (Flaky Test Patterns)
- 产物管理 (Artifact Management)
- CI/CD 集成 (CI/CD Integration)
- 测试报告模板 (Test Report Template)
- 钱包 / Web3 测试 (Wallet / Web3 Testing)
- 金融 / 关键流程测试 (Financial / Critical Flow Testing)
Files
SKILL.mdcore8,755 bytesSKILL.mdcore8,755 bytes
Read SKILL.md
# E2E 测试模式 (E2E Testing Patterns)
用于构建稳定、快速且易于维护的 E2E 测试套件的全面 Playwright 模式。
## 测试文件组织 (Test File Organization)
```
tests/
├── e2e/
│ ├── auth/
│ │ ├── login.spec.ts
│ │ ├── logout.spec.ts
│ │ └── register.spec.ts
│ ├── features/View the complete source on GitHubeval-harness
When your agent uses it
为 Claude Code 会话提供的正式评测框架,实现了评测驱动开发(EDD)原则
What it loads into context
Frontmatter
50 tokensAlways available to the agent
SKILL.md
1,785 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
- 何时激活
- 核心理念
- 评测类型
- 评分器(Grader)类型
- 指标
- 评测工作流
- 集成模式
- 评测存储
- 最佳实践
- 示例:添加身份验证(Authentication)
Files
SKILL.mdcore6,006 bytesSKILL.mdcore6,006 bytesSKILL.mdcore6,006 bytes
Read SKILL.md
# 评测工具链(Eval Harness)技能(Skill)
一个用于 Claude Code 会话的正式评测框架,实现了评测驱动开发(Eval-Driven Development, EDD)原则。
## 何时激活
- 为 AI 辅助工作流设置评测驱动开发(EDD)
- 为 Claude Code 任务完成定义通过/失败的标准
- 使用 pass@k 指标衡量智能体(Agent)的可靠性
- 为提示词(Prompt)或智能体(Agent)的变更创建回归测试套件
- 跨模型版本对智能体(Agent)性能进行基准测试
## 核心理念
View the complete source on GitHubfoundation-models-on-device
When your agent uses it
Apple FoundationModels 框架,用于设备端大语言模型(LLM)—— iOS 26+ 中的文本生成、配合 @Generable 的引导式生成、工具调用以及快照流式传输。
What it loads into context
Frontmatter
59 tokensAlways available to the agent
SKILL.md
2,057 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
- 何时激活
- 核心模式 —— 可用性检查
- 核心模式 —— 基础会话
- 核心模式 —— 使用 @Generable 的引导式生成
- 核心模式 —— 工具调用
- 核心模式 —— 快照流式传输
- 关键设计决策
- 最佳实践
- 应避免的反模式
- 何时使用
Files
SKILL.mdcore8,161 bytes
Read SKILL.md
# FoundationModels:设备端大语言模型 (iOS 26)
使用 FoundationModels 框架将 Apple 的设备端语言模型集成到应用中的模式。涵盖文本生成、使用 `@Generable` 的结构化输出、自定义工具调用以及快照流式传输 —— 全部在设备端运行,以支持隐私保护和离线使用。
## 何时激活
- 使用 Apple Intelligence 在设备端构建 AI 驱动的功能
- 在不依赖云端的情况下生成或总结文本
- 从自然语言输入中提取结构化数据
- 为特定领域的 AI 操作实现自定义工具调用
- 流式传输结构化响应以实现实时 UI 更新
- 需要隐私保护的 AI(数据不离开设备)
## 核心模式 —— 可用性检查View the complete source on GitHubfrontend-patterns
When your agent uses it
针对 React、Next.js、状态管理、性能优化及 UI 最佳实践的前端开发模式。
What it loads into context
Frontmatter
35 tokensAlways available to the agent
SKILL.md
3,882 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
- 何时激活
- 组件模式 (Component Patterns)
- 自定义 Hook 模式 (Custom Hooks Patterns)
- 状态管理模式 (State Management Patterns)
- 性能优化 (Performance Optimization)
- 表单处理模式 (Form Handling Patterns)
- 错误边界模式 (Error Boundary Pattern)
- 动画模式 (Animation Patterns)
- 可访问性模式 (Accessibility Patterns)
Files
SKILL.mdcore15,194 bytes
Read SKILL.md
# 前端开发模式 (Frontend Development Patterns)
适用于 React、Next.js 和高性能用户界面的现代前端模式。
## 何时激活
- 构建 React 组件(组合、Props、渲染)
- 管理状态(useState、useReducer、Zustand、Context)
- 实现数据获取(SWR、React Query、服务端组件)
- 优化性能(记忆化、虚拟化、代码分割)
- 处理表单(验证、受控输入、Zod 模式)
- 处理客户端路由与导航
- 构建可访问(Accessible)、响应式的 UI 模式
View the complete source on GitHubfrontend-slides
When your agent uses it
从头开始创建令人惊叹、动画丰富的 HTML 演示文稿,或通过转换 PowerPoint 文件生成。当用户想要构建演示文稿、将 PPT/PPTX 转换为网页版,或为演讲/路演创建幻灯片时使用。帮助非设计师通过视觉探索而非抽象选择来发现他们的审美。
What it loads into context
Frontmatter
91 tokensAlways available to the agent
SKILL.md
2,077 tokensWhen the skill is activated
Reference documents
3,332 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- 激活时机(When to Activate)
- 硬性规定(Non-Negotiables)
- 工作流(Workflow)
- PPT / PPTX 转换
- 实现要求(Implementation Requirements)
- 内容密度限制(Content Density Limits)
- 反面模式(Anti-Patterns)
- 相关的 ECC 技能(Related ECC Skills)
- 交付物检查清单(Deliverable Checklist)
Files
SKILL.mdcore7,212 bytesSTYLE_PRESETS.mddoc10,168 bytes
Read SKILL.md
# 前端幻灯片(Frontend Slides)
创建完全在浏览器中运行、零依赖、动画丰富的 HTML 演示文稿。
受 zarazhangrui 作品中展示的视觉探索方法的启发(致谢:@zarazhangrui)。
## 激活时机(When to Activate)
- 创建演讲幻灯片组(Talk deck)、路演幻灯片组(Pitch deck)、工作坊幻灯片组或内部演示文稿
- 将 `.ppt` 或 `.pptx` 幻灯片转换为 HTML 演示文稿
- 改进现有 HTML 演示文稿的布局、动态(Motion)或排版(Typography)
- 与尚不清楚其设计偏好的用户一起探索演示风格
## 硬性规定(Non-Negotiables)View the complete source on GitHubgolang-patterns
When your agent uses it
编写稳健、高效且易于维护的 Go 应用程序的惯用模式、最佳实践和约定。
What it loads into context
Frontmatter
38 tokensAlways available to the agent
SKILL.md
3,848 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
- 激活时机
- 核心原则
- 错误处理模式 (Error Handling Patterns)
- 并发模式 (Concurrency Patterns)
- 接口设计 (Interface Design)
- 包组织 (Package Organization)
- 结构体设计 (Struct Design)
- 内存与性能 (Memory and Performance)
- Go 工具链集成
- 快速参考:Go 惯用语 (Go Idioms)
- 应避免的反模式 (Anti-Patterns)
Files
SKILL.mdcore14,293 bytesSKILL.mdcore14,293 bytes
Read SKILL.md
# Go 开发模式 (Go Development Patterns)
构建稳健、高效且易于维护的应用程序的惯用 Go 模式和最佳实践。
## 激活时机
- 编写新的 Go 代码时
- 评审 Go 代码时
- 重构现有 Go 代码时
- 设计 Go 包/模块时
## 核心原则
### 1. 简单与清晰View the complete source on GitHubgolang-testing
When your agent uses it
Go 测试模式,包括表格驱动测试、子测试、基准测试、模糊测试和测试覆盖率。遵循具有惯用 Go 实践的 TDD 方法论。
What it loads into context
Frontmatter
53 tokensAlways available to the agent
SKILL.md
4,627 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
- 何时激活
- Go 的 TDD 工作流
- 表格驱动测试 (Table-Driven Tests)
- 子测试与子基准测试 (Subtests and Sub-benchmarks)
- 测试助手 (Test Helpers)
- Golden Files (对比文件测试)
- 使用接口进行 Mock (Mocking with Interfaces)
- 基准测试 (Benchmarks)
- 模糊测试 (Fuzzing) (Go 1.18+)
- 测试覆盖率 (Test Coverage)
- HTTP Handler 测试
- 测试命令
- 最佳实践
- CI/CD 集成
Files
SKILL.mdcore16,945 bytesSKILL.mdcore16,945 bytesSKILL.mdcore16,945 bytes
Read SKILL.md
# Go 测试模式 (Testing Patterns)
遵循测试驱动开发(TDD)方法论,编写可靠且易于维护的 Go 测试的全面模式。
## 何时激活
- 编写新的 Go 函数或方法时
- 为现有代码增加测试覆盖率时
- 为性能关键型代码创建基准测试(Benchmarks)时
- 为输入验证实现模糊测试(Fuzz tests)时
- 在 Go 项目中遵循 TDD 工作流时
## Go 的 TDD 工作流
View the complete source on GitHubinvestor-materials
When your agent uses it
创建并更新路演 PPT(Pitch Decks)、一页纸简介(One-pagers)、投资备忘录(Investor Memos)、加速器申请(Accelerator Applications)、财务模型(Financial Models)以及融资材料。当用户需要面向投资者的文档、预测、资金用途表(Use-of-funds tables)、里程碑计划,或需要在多个融资资产之间保持内部一致性时,请使用此功能。
What it loads into context
Frontmatter
104 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
- 何时激活(When to Activate)
- 黄金法则(Golden Rule)
- 核心工作流(Core Workflow)
- 资产指南(Asset Guidance)
- 需避免的红线(Red Flags to Avoid)
- 质量把关(Quality Gate)
Files
SKILL.mdcore3,239 bytes
Read SKILL.md
# 融资材料(Investor Materials)
构建一致、可靠且易于辩护的面向投资者的材料。
## 何时激活(When to Activate)
- 创建或修改路演 PPT(Pitch Deck)
- 编写投资备忘录(Investor Memo)或一页纸简介(One-pager)
- 构建财务模型、里程碑计划或资金用途表(Use-of-funds table)
- 回答加速器(Accelerator)或孵化器申请问题
- 围绕单一事实来源(Source of Truth)对齐多个融资文档
## 黄金法则(Golden Rule)
View the complete source on GitHubinvestor-outreach
When your agent uses it
Draft cold emails, warm intro blurbs, follow-ups, update emails, and investor communications for fundraising. Use when the user wants outreach to angels, VCs, strategic investors, or accelerators and needs concise, personalized, investor-facing messaging.
What it loads into context
Frontmatter
60 tokensAlways available to the agent
SKILL.md
770 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
- 何时激活(When to Activate)
- 核心规则(Core Rules)
- 冷启动邮件结构(Cold Email Structure)
- 个性化来源(Personalization Sources)
- 跟进节奏(Follow-Up Cadence)
- 引荐请求(Warm Intro Requests)
- 会后更新(Post-Meeting Updates)
- 质量把控(Quality Gate)
Files
SKILL.mdcore2,866 bytes
Read SKILL.md
# 投资者外联(Investor Outreach)
编写简短、个性化且易于跟进的投资者沟通内容。
## 何时激活(When to Activate)
- 向投资者发送冷启动邮件(Cold Email)时
- 撰写请求引荐(Warm Intro)的简述时
- 在会议后或未收到回复时发送跟进(Follow-up)邮件时
- 在融资过程中编写投资者更新(Investor Updates)时
- 根据基金投资理念(Thesis)或合伙人匹配度定制外联内容时
## 核心规则(Core Rules)
View the complete source on GitHubiterative-retrieval
When your agent uses it
逐步优化上下文检索以解决子智能体(subagent)上下文问题的模式。
What it loads into context
Frontmatter
35 tokensAlways available to the agent
SKILL.md
1,905 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
- 何时激活
- 问题背景(The Problem)
- 解决方案:迭代检索(The Solution: Iterative Retrieval)
- 实践案例
- 与智能体(Agents)集成
- 最佳实践
- 相关资源
Files
SKILL.mdcore7,302 bytes
Read SKILL.md
# 迭代检索模式(Iterative Retrieval Pattern)
解决了多智能体工作流(multi-agent workflows)中的“上下文问题”——子智能体(subagent)在开始工作前往往不知道自己需要哪些上下文。
## 何时激活
- 生成需要事先无法完全预测的代码库上下文(codebase context)的子智能体时
- 构建上下文需要逐步优化的多智能体工作流时
- 在智能体任务中遇到“上下文过大”或“缺失上下文”的失败时
- 为代码探索设计类 RAG 的检索流水线时
- 优化智能体编排(agent orchestration)中的 Token 使用时
## 问题背景(The Problem)
View the complete source on GitHubjava-coding-standards
When your agent uses it
Spring Boot 服务的 Java 编码规范:命名、不可变性、Optional 使用、流(streams)、异常、泛型以及项目布局。
What it loads into context
Frontmatter
47 tokensAlways available to the agent
SKILL.md
1,184 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
- 何时激活 (When to Activate)
- 核心原则 (Core Principles)
- 命名 (Naming)
- 不可变性 (Immutability)
- Optional 使用 (Optional Usage)
- 流最佳实践 (Streams Best Practices)
- 异常处理 (Exceptions)
- 泛型与类型安全 (Generics and Type Safety)
- 项目结构 (Project Structure - Maven/Gradle)
- 格式与风格 (Formatting and Style)
- 应避免的代码异味 (Code Smells to Avoid)
- 日志记录 (Logging)
- 空值处理 (Null Handling)
- 测试期望 (Testing Expectations)
Files
SKILL.mdcore4,548 bytes
Read SKILL.md
# Java 编码规范 (Java Coding Standards)
适用于 Spring Boot 服务中可读、可维护的 Java (17+) 代码规范。
## 何时激活 (When to Activate)
- 在 Spring Boot 项目中编写或评审 Java 代码时
- 强制执行命名、不可变性(immutability)或异常处理约定时
- 使用 records、密封类(sealed classes)或模式匹配(pattern matching)(Java 17+)时
- 评审 Optional、流(streams)或泛型(generics)的使用时
- 规划包结构和项目布局时
## 核心原则 (Core Principles)
View the complete source on GitHubjpa-patterns
When your agent uses it
JPA/Hibernate 模式,涵盖 Spring Boot 中的实体设计、关系、查询优化、事务、审计、索引、分页和连接池。
What it loads into context
Frontmatter
46 tokensAlways available to the agent
SKILL.md
1,212 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
- 何时激活
- 实体设计
- 关联关系与防止 N+1 问题
- Repository 模式
- 事务
- 分页
- 索引与性能
- 连接池 (HikariCP)
- 缓存
- 数据库迁移 (Migrations)
- 测试数据访问
Files
SKILL.mdcore4,718 bytes
Read SKILL.md
# JPA/Hibernate 模式
用于 Spring Boot 中的数据建模、仓库层(Repositories)实现和性能调优。
## 何时激活
- 设计 JPA 实体(Entities)和表映射
- 定义关联关系(@OneToMany、@ManyToOne、@ManyToMany)
- 优化查询(防止 N+1 问题、抓取策略、投影)
- 配置事务、审计(Auditing)或逻辑删除
- 设置分页、排序或自定义 Repository 方法
- 调优连接池(HikariCP)或二级缓存(Second-level Caching)
## 实体设计View the complete source on GitHubliquid-glass-design
When your agent uses it
iOS 26 灵动玻璃(Liquid Glass)设计系统 — 适用于 SwiftUI、UIKit 和 WidgetKit 的具有模糊、反射和交互式变形效果的动态玻璃材质。
What it loads into context
Frontmatter
56 tokensAlways available to the agent
SKILL.md
2,379 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
- 何时激活
- 核心模式 — SwiftUI
- 核心模式 — UIKit
- 核心模式 — WidgetKit
- 关键设计决策
- 最佳实践
- 应避免的反模式
- 何时使用
Files
SKILL.mdcore8,989 bytes
Read SKILL.md
# 灵动玻璃(Liquid Glass)设计系统 (iOS 26)
实现 Apple 灵动玻璃(Liquid Glass)的设计模式 — 这是一种动态材质,可以模糊背后的内容,反射周围内容的颜色和光影,并对触摸和指针交互做出反应。涵盖了 SwiftUI、UIKit 和 WidgetKit 的集成。
## 何时激活
- 为 iOS 26+ 构建或更新采用新设计语言的应用
- 实现玻璃风格的按钮、卡片、工具栏或容器
- 在玻璃元素之间创建变形(Morphing)过渡
- 为小组件(Widgets)应用灵动玻璃效果
- 将现有的模糊/材质效果迁移到新的灵动玻璃 API
## 核心模式 — SwiftUI
View the complete source on GitHubmarket-research
When your agent uses it
执行市场研究(market research)、竞争分析、投资者尽职调查和行业情报,提供来源引用及面向决策的摘要。当用户需要市场规模估算、竞品对比、基金研究、技术扫描或为业务决策提供支持的研究时,请使用此技能。
What it loads into context
Frontmatter
76 tokensAlways available to the agent
SKILL.md
709 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
- 何时激活 (When to Activate)
- 研究标准 (Research Standards)
- 常用研究模式 (Common Research Modes)
- 输出格式 (Output Format)
- 质量门禁 (Quality Gate)
Files
SKILL.mdcore2,746 bytes
Read SKILL.md
# 市场研究 (Market Research)
生成支持决策的研究,而非流于形式的研究报告。
## 何时激活 (When to Activate)
- 研究市场、品类、公司、投资者或技术趋势。
- 构建 TAM/SAM/SOM(总目标市场/可服务市场/可获得市场)估算。
- 比较竞争对手或相邻产品。
- 在外联之前准备投资者档案(Dossiers)。
- 在构建、注资或进入市场之前,对假设进行压力测试。
## 研究标准 (Research Standards)
View the complete source on GitHubnutrient-document-processing
When your agent uses it
使用 Nutrient DWS API 处理、转换、OCR、提取、脱敏、签名和填充文档。支持 PDF、DOCX、XLSX、PPTX、HTML 和图像。
What it loads into context
Frontmatter
57 tokensAlways available to the agent
SKILL.md
1,847 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
- 设置(Setup)
- 操作(Operations)
- MCP 服务器(替代方案)
- 何时使用
- 链接(Links)
Files
SKILL.mdcore6,177 bytesSKILL.mdcore6,177 bytesSKILL.mdcore6,177 bytesSKILL.mdcore6,177 bytesSKILL.mdcore6,177 bytesSKILL.mdcore6,177 bytesSKILL.mdcore6,177 bytesSKILL.mdcore6,177 bytesSKILL.mdcore6,177 bytes
Read SKILL.md
# Nutrient 文档处理(Nutrient Document Processing)
使用 [Nutrient DWS Processor API](https://www.nutrient.io/api/) 处理文档。转换格式、提取文本和表格、对扫描文档进行 OCR 光学字符识别、脱敏个人身份信息(PII)、添加水印、进行数字签名以及填充 PDF 表单。
## 设置(Setup)
在 **[nutrient.io](https://dashboard.nutrient.io/sign_up/?product=processor)** 获取免费 API 密钥。
```bash
[Credential-related source omitted]
```
所有请求均以 multipart POST 形式发送至 `https://api.nutrient.io/build`,并包含一个 `instructions` JSON 字段。
View the complete source on GitHubplankton-code-quality
When your agent uses it
使用 Plankton 实现编写时代码质量强制执行 —— 通过钩子在每次文件编辑时进行自动格式化、代码检查,并由 Claude 驱动自动修复。
What it loads into context
Frontmatter
57 tokensAlways available to the agent
SKILL.md
2,281 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
- 适用场景
- 工作原理
- 设置
- 与 ECC 配合使用
- 配置参考
- 环境变量覆盖
- 参考资料
Files
SKILL.mdcore7,595 bytesSKILL.mdcore7,595 bytes
Read SKILL.md
# Plankton 代码质量技能(Plankton Code Quality Skill)
Plankton(感谢 @alxfazio)的集成参考,这是一个针对 Claude Code 的编写时(Write-time)代码质量强制执行系统。Plankton 通过工具调用后钩子(PostToolUse hooks)在每次文件编辑时运行格式化程序和 Linter,然后启动 Claude 子进程(Subprocess)来修复智能体(Agent)未捕捉到的违规项。
## 适用场景
- 你希望在每次文件编辑时(而不只是提交时)自动进行格式化和代码检查。
- 你需要防御智能体通过修改 Linter 配置来绕过检查,而不是真正修复代码。
- 你希望针对修复任务进行分级模型路由(Haiku 用于简单样式,Sonnet 用于逻辑,Opus 用于类型)。
- 你使用多种语言进行开发(Python, TypeScript, Shell, YAML, JSON, TOML, Markdown, Dockerfile)。
## 工作原理
### 三阶段架构View the complete source on GitHubpostgres-patterns
When your agent uses it
PostgreSQL 数据库模式,用于查询优化、架构设计、索引和安全性。基于 Supabase 最佳实践。
What it loads into context
Frontmatter
39 tokensAlways available to the agent
SKILL.md
1,200 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
- 何时激活
- 快速参考
- 相关资源
Files
SKILL.mdcore4,134 bytes
Read SKILL.md
# PostgreSQL 最佳实践模式 (PostgreSQL Patterns)
PostgreSQL 最佳实践快速参考。如需详细指导,请使用 `database-reviewer` 智能体 (Agent)。
## 何时激活
- 编写 SQL 查询或迁移脚本
- 设计数据库架构 (Schema)
- 排查慢查询问题
- 实现行级安全性 (Row Level Security, RLS)
- 设置连接池 (Connection Pooling)
## 快速参考
View the complete source on GitHubproject-guidelines-example
When your agent uses it
基于真实生产应用程序的项目特定技能(Skill)模板示例。
What it loads into context
Frontmatter
32 tokensAlways available to the agent
SKILL.md
2,410 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
- 何时使用
- 架构概览
- 文件结构
- 代码模式
- 测试要求
- 部署工作流
- 关键规则
- 相关技能
Files
SKILL.mdcore9,984 bytesSKILL.mdcore9,984 bytesSKILL.mdcore9,984 bytesSKILL.mdcore9,984 bytesSKILL.mdcore9,984 bytesSKILL.mdcore9,984 bytesSKILL.mdcore9,984 bytesSKILL.mdcore9,984 bytesSKILL.mdcore9,984 bytesSKILL.mdcore9,984 bytes
Read SKILL.md
# 项目指南技能(Skill)示例
这是一个项目特定技能(Skill)的示例。请将其作为你自己项目的模板。
基于真实生产应用程序:[Zenith](https://zenith.chat) - AI 驱动的客户挖掘平台。
## 何时使用
在处理其设计的特定项目时参考此技能。项目技能包含:
- 架构概览
- 文件结构
- 代码模式
- 测试要求
- 部署工作流View the complete source on GitHubpython-patterns
When your agent uses it
构建健壮、高效且易于维护的 Python 应用程序的 Python 惯用法(Pythonic idioms)、PEP 8 标准、类型提示(Type hints)以及最佳实践。
What it loads into context
Frontmatter
56 tokensAlways available to the agent
SKILL.md
4,692 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
- 何时激活
- 核心原则
- 类型提示 (Type Hints)
- 错误处理模式
- 上下文管理器 (Context Managers)
- 推导式 (Comprehensions) 与生成器 (Generators)
- 数据类 (Data Classes) 与具名元组 (Named Tuples)
- 装饰器 (Decorators)
- 并发模式 (Concurrency Patterns)
- 包结构组织 (Package Organization)
- 内存与性能
- Python 工具链集成
- 快速参考:Python 惯用法
- 应避免的反模式 (Anti-Patterns)
Files
SKILL.mdcore17,305 bytesSKILL.mdcore17,305 bytesSKILL.mdcore17,305 bytesSKILL.mdcore17,305 bytesSKILL.mdcore17,305 bytesSKILL.mdcore17,305 bytesSKILL.mdcore17,305 bytesSKILL.mdcore17,305 bytesSKILL.mdcore17,305 bytesSKILL.mdcore17,305 bytesSKILL.mdcore17,305 bytesSKILL.mdcore17,305 bytesSKILL.mdcore17,305 bytesSKILL.mdcore17,305 bytesSKILL.mdcore17,305 bytesSKILL.mdcore17,305 bytesSKILL.mdcore17,305 bytesSKILL.mdcore17,305 bytesSKILL.mdcore17,305 bytesSKILL.mdcore17,305 bytesSKILL.mdcore17,305 bytesSKILL.mdcore17,305 bytesSKILL.mdcore17,305 bytesSKILL.mdcore17,305 bytesSKILL.mdcore17,305 bytesSKILL.mdcore17,305 bytesSKILL.mdcore17,305 bytesSKILL.mdcore17,305 bytesSKILL.mdcore17,305 bytesSKILL.mdcore17,305 bytesSKILL.mdcore17,305 bytesSKILL.mdcore17,305 bytesSKILL.mdcore17,305 bytesSKILL.mdcore17,305 bytes
Read SKILL.md
# Python 开发模式 (Python Development Patterns)
用于构建健壮、高效且易于维护的应用程序的 Python 惯用模式与最佳实践。
## 何时激活
- 编写新的 Python 代码时
- 评审 Python 代码时
- 重构现有的 Python 代码时
- 设计 Python 包(Packages)或模块(Modules)时
## 核心原则
### 1. 可读性至上 (Readability Counts)View the complete source on GitHubpython-testing
When your agent uses it
使用 pytest、TDD 方法论、测试夹具(Fixtures)、模拟(Mocking)、参数化(Parametrization)以及覆盖率要求的 Python 测试策略。
What it loads into context
Frontmatter
47 tokensAlways available to the agent
SKILL.md
4,982 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
- 何时激活
- 核心测试哲学
- pytest 基础
- 测试夹具 (Fixtures)
- 参数化 (Parametrization)
- 标记 (Markers) 与测试选择
- 模拟 (Mocking) 与打补丁 (Patching)
- 测试异步代码
- 测试异常
- 测试副作用
- 测试组织
- 最佳实践
- 常见模式
- pytest 配置
- 运行测试
- 快速参考
Files
SKILL.mdcore19,311 bytesSKILL.mdcore19,311 bytesSKILL.mdcore19,311 bytesSKILL.mdcore19,311 bytesSKILL.mdcore19,311 bytesSKILL.mdcore19,311 bytesSKILL.mdcore19,311 bytesSKILL.mdcore19,311 bytesSKILL.mdcore19,311 bytesSKILL.mdcore19,311 bytesSKILL.mdcore19,311 bytesSKILL.mdcore19,311 bytesSKILL.mdcore19,311 bytesSKILL.mdcore19,311 bytesSKILL.mdcore19,311 bytesSKILL.mdcore19,311 bytesSKILL.mdcore19,311 bytesSKILL.mdcore19,311 bytesSKILL.mdcore19,311 bytesSKILL.mdcore19,311 bytesSKILL.mdcore19,311 bytesSKILL.mdcore19,311 bytesSKILL.mdcore19,311 bytesSKILL.mdcore19,311 bytesSKILL.mdcore19,311 bytesSKILL.mdcore19,311 bytesSKILL.mdcore19,311 bytesSKILL.mdcore19,311 bytesSKILL.mdcore19,311 bytesSKILL.mdcore19,311 bytesSKILL.mdcore19,311 bytesSKILL.mdcore19,311 bytesSKILL.mdcore19,311 bytesSKILL.mdcore19,311 bytesSKILL.mdcore19,311 bytesSKILL.mdcore19,311 bytesSKILL.mdcore19,311 bytesSKILL.mdcore19,311 bytes
Read SKILL.md
# Python 测试模式(Python Testing Patterns)
使用 pytest、测试驱动开发(TDD)方法论和最佳实践的 Python 应用程序综合测试策略。
## 何时激活
- 编写新的 Python 代码时(遵循 TDD:红、绿、重构)
- 为 Python 项目设计测试套件时
- 审查 Python 测试覆盖率时
- 搭建测试基础设施时
## 核心测试哲学
### 测试驱动开发 (TDD)View the complete source on GitHubregex-vs-llm-structured-text
When your agent uses it
在解析结构化文本时,用于在正则表达式(Regex)和大型语言模型(LLM)之间进行选择的决策框架——优先使用正则表达式,仅针对低置信度的边界情况引入 LLM。
What it loads into context
Frontmatter
72 tokensAlways available to the agent
SKILL.md
2,052 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
- 何时激活(When to Activate)
- 决策框架(Decision Framework)
- 架构模式(Architecture Pattern)
- 实现参考(Implementation)
- 真实世界指标 (Real-World Metrics)
- 最佳实践 (Best Practices)
- 应避免的反模式 (Anti-Patterns to Avoid)
- 适用场景 (When to Use)
Files
SKILL.mdcore7,346 bytesSKILL.mdcore7,346 bytesSKILL.mdcore7,346 bytesSKILL.mdcore7,346 bytesSKILL.mdcore7,346 bytes
Read SKILL.md
# 结构化文本解析:正则表达式(Regex)与大语言模型(LLM)的抉择
这是一个用于解析结构化文本(测验、表单、发票、文档)的实用决策框架。核心见解是:正则表达式(Regex)能以极低的成本确定性地处理 95-98% 的情况。应将昂贵的 LLM 调用保留给剩余的边界情况(Edge Cases)。
## 何时激活(When to Activate)
- 解析具有重复模式的结构化文本(问题、表单、表格等)
- 在文本提取任务中权衡使用正则表达式还是 LLM
- 构建结合这两种方法的混合流水线(Hybrid Pipelines)
- 在文本处理中优化成本与准确性的平衡
## 决策框架(Decision Framework)
```View the complete source on GitHubsearch-first
When your agent uses it
Research-before-coding workflow. Search for existing tools, libraries, and patterns before writing custom code. Invokes the researcher agent.
What it loads into context
Frontmatter
36 tokensAlways available to the agent
SKILL.md
1,813 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
- 触发条件(Trigger)
- 工作流(Workflow)
- 决策矩阵(Decision Matrix)
- 如何使用
- 按类别搜索快捷方式
- 集成点(Integration Points)
- 示例
- 反模式(Anti-Patterns)
Files
SKILL.mdcore7,211 bytes
Read SKILL.md
# /search-first — 编码前先调研(Research Before You Code)
将“在实现前搜索现有解决方案”的工作流系统化。
## 触发条件(Trigger)
在以下场景使用此技能(Skill):
- 开始开发一个很可能已有现成解决方案的新功能
- 添加依赖项或集成
- 用户要求“添加 X 功能”且你正准备编写代码
- 在创建新的工具类(Utility)、辅助函数(Helper)或抽象层之前
## 工作流(Workflow)
View the complete source on GitHubsecurity-review
When your agent uses it
在添加身份验证、处理用户输入、操作机密信息、创建 API 接口或实现支付/敏感功能时使用此技能。提供全面的安全自查清单和模式。
What it loads into context
Frontmatter
51 tokensAlways available to the agent
SKILL.md
3,588 tokensWhen the skill is activated
Reference documents
3,039 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- 何时启用
- 安全自查清单
- 安全测试(Security Testing)
- 部署前安全自查清单
- 资源
Files
SKILL.mdcore12,850 bytesSKILL.mdcore12,850 bytesSKILL.mdcore12,850 bytescloud-infrastructure-security.mddoc10,820 bytes
Read SKILL.md
# 安全审查技能(Security Review Skill)
此技能(Skill)旨在确保所有代码遵循安全最佳实践,并识别潜在的漏洞。
## 何时启用
- 实现身份验证(Authentication)或授权(Authorization)时
- 处理用户输入或文件上传时
- 创建新的 API 接口(Endpoints)时
- 操作机密(Secrets)或凭据(Credentials)时
- 实现支付功能时
- 存储或传输敏感数据时
- 集成第三方 API 时
View the complete source on GitHubsecurity-scan
When your agent uses it
使用 AgentShield 扫描您的 Claude Code 配置(.claude/ 目录)是否存在安全漏洞、配置错误和注入风险。检查项包括 CLAUDE.md、settings.json、MCP 服务器、钩子(Hooks)以及智能体(Agent)定义。
What it loads into context
Frontmatter
72 tokensAlways available to the agent
SKILL.md
1,427 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
- 何时激活
- 扫描对象
- 前置条件
- 使用方法
- 严重程度等级 (Severity Levels)
- 结果解读
- 相关链接
Files
SKILL.mdcore4,819 bytesSKILL.mdcore4,819 bytesSKILL.mdcore4,819 bytesSKILL.mdcore4,819 bytesSKILL.mdcore4,819 bytesSKILL.mdcore4,819 bytesSKILL.mdcore4,819 bytes
Read SKILL.md
# 安全扫描技能 (Security Scan Skill)
使用 [AgentShield](https://github.com/affaan-m/agentshield) 审计您的 Claude Code 配置安全问题。
## 何时激活
- 设置新的 Claude Code 项目时
- 修改 `.claude/settings.json`、`CLAUDE.md` 或 MCP 配置后
- 提交配置更改前
- 加入具有现有 Claude Code 配置的新仓库时
- 定期的安全卫生检查
## 扫描对象
View the complete source on GitHubWhen your agent uses it
用于对 Claude 技能(Skills)和命令进行质量审计。支持快速扫描(Quick Scan,仅针对变更的技能)和全面盘点(Full Stocktake)模式,并通过子智能体(subagent)进行顺序批处理评估。
What it loads into context
Frontmatter
63 tokensAlways available to the agent
SKILL.md
2,358 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
- 作用范围(Scope)
- 模式(Modes)
- 快速扫描流程(Quick Scan Flow)
- 全面盘点流程(Full Stocktake Flow)
- 结果文件 Schema
- 注意事项
Scripts executed separately
scripts/quick-diff.shscripts/save-results.shscripts/scan.sh
Files
SKILL.mdcore8,354 bytesSKILL.mdcore8,354 bytesSKILL.mdcore8,354 bytesSKILL.mdcore8,354 bytesSKILL.mdcore8,354 bytesscripts/quick-diff.shruns3,271 bytesscripts/save-results.shruns1,952 bytesscripts/scan.shruns5,677 bytes
Read SKILL.md
# skill-stocktake
斜杠命令(`/skill-stocktake`),使用质量检查清单 + AI 综合判断来审计所有 Claude 技能(Skills)和命令。支持两种模式:针对最近变更技能的快速扫描(Quick Scan),以及用于完整审查的全面盘点(Full Stocktake)。
## 作用范围(Scope)
该命令的目标路径**相对于调用它的目录**:
| 路径 | 描述 |
|------|-------------|
| `~/.claude/skills/` | 全局技能(适用于所有项目) |
| `{cwd}/.claude/skills/` | 项目级技能(如果该目录存在) |
**在阶段 1(Phase 1)开始时,该命令会明确列出已发现并扫描的路径。**View the complete source on GitHubspringboot-patterns
When your agent uses it
Spring Boot 架构模式、REST API 设计、分层服务、数据访问、缓存、异步处理和日志记录。适用于 Java Spring Boot 后端开发。
What it loads into context
Frontmatter
49 tokensAlways available to the agent
SKILL.md
2,398 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
- 何时启用
- REST API 结构
- 存储库模式(Spring Data JPA)
- 带事务的服务层
- DTO 与验证
- 异常处理
- 缓存
- 异步处理
- 日志记录 (SLF4J)
- 中间件 / 过滤器
- 分页和排序
- 具有容错能力的外部调用
- 速率限制(过滤器 + Bucket4j)
- 后台作业
- 可观察性
- 生产环境默认值
Files
SKILL.mdcore9,924 bytes
Read SKILL.md
# Spring Boot 开发模式
适用于可扩展、生产级服务的 Spring Boot 架构和 API 模式。
## 何时启用
- 使用 Spring MVC 或 WebFlux 构建 REST API
- 组织 控制器 (Controller) → 服务 (Service) → 存储库 (Repository) 层
- 配置 Spring Data JPA、缓存或异步处理
- 添加验证、异常处理或分页
- 为开发/测试/生产环境设置配置文件(Profiles)
- 使用 Spring 事件(Spring Events)或 Kafka 实现事件驱动模式
## REST API 结构View the complete source on GitHubspringboot-security
When your agent uses it
Spring Boot 服务的身份验证/授权、校验、CSRF、机密管理、响应头、速率限制及依赖安全的 Spring Security 最佳实践。
What it loads into context
Frontmatter
47 tokensAlways available to the agent
SKILL.md
2,196 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
- 何时激活(When to Activate)
- 身份验证(Authentication)
- 授权(Authorization)
- 输入校验(Input Validation)
- 防止 SQL 注入(SQL Injection Prevention)
- 密码编码(Password Encoding)
- CSRF 防护(CSRF Protection)
- 机密管理(Secrets Management)
- 安全响应头(Security Headers)
- CORS 配置
- 速率限制(Rate Limiting)
- 依赖安全(Dependency Security)
- 日志与 PII(个人身份信息)
- 文件上传(File Uploads)
- 发布前清单(Checklist Before Release)
Files
SKILL.mdcore8,837 bytesSKILL.mdcore8,837 bytes
Read SKILL.md
# Spring Boot 安全审查(Security Review)
在添加身份验证(Auth)、处理输入、创建端点或处理机密信息时使用。
## 何时激活(When to Activate)
- 添加身份验证(JWT、OAuth2、基于 Session 的认证)
- 实现授权(`@PreAuthorize`、基于角色的访问控制)
- 校验用户输入(Bean Validation、自定义校验器)
- 配置 CORS、CSRF 或安全响应头
- 管理机密信息(Vault、环境变量)
- 添加速率限制(Rate Limiting)或暴力破解防护
- 扫描依赖项的 CVE 漏洞
View the complete source on GitHubspringboot-tdd
When your agent uses it
使用 JUnit 5、Mockito、MockMvc、Testcontainers 和 JaCoCo 进行 Spring Boot 的测试驱动开发 (TDD)。在添加功能、修复 Bug 或进行重构时使用。
What it loads into context
Frontmatter
56 tokensAlways available to the agent
SKILL.md
1,054 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
- 适用场景
- 工作流
- 单元测试 (JUnit 5 + Mockito)
- Web 层测试 (MockMvc)
- 集成测试 (SpringBootTest)
- 持久层测试 (DataJpaTest)
- Testcontainers
- 测试覆盖率 (JaCoCo)
- 断言 (Assertions)
- 测试数据生成器 (Test Data Builders)
- CI 命令
Files
SKILL.mdcore3,937 bytes
Read SKILL.md
# Spring Boot TDD 工作流
针对具有 80% 以上覆盖率(单元测试 + 集成测试)的 Spring Boot 服务的 TDD 指南。
## 适用场景
- 新功能或 API 端点开发
- Bug 修复或重构
- 添加数据访问逻辑或安全规则
## 工作流
1) 先写测试(测试应当失败)
2) 实现通过测试的最简代码View the complete source on GitHubspringboot-verification
When your agent uses it
Spring Boot 项目验证循环:包含构建、静态分析、带覆盖率的测试、安全扫描,以及发布或 PR 前的差异审查。
What it loads into context
Frontmatter
47 tokensAlways available to the agent
SKILL.md
1,704 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
- 触发时机
- 第一阶段:构建 (Build)
- 第二阶段:静态分析 (Static Analysis)
- 第三阶段:测试与覆盖率 (Tests + Coverage)
- 第四阶段:安全扫描 (Security Scan)
- 第五阶段:代码检查/格式化 (Lint/Format)(可选关卡)
- 第六阶段:差异审查 (Diff Review)
- 输出模板
- 持续模式 (Continuous Mode)
Files
SKILL.mdcore6,516 bytesSKILL.mdcore6,516 bytesSKILL.mdcore6,516 bytesSKILL.mdcore6,516 bytesSKILL.mdcore6,516 bytesSKILL.mdcore6,516 bytesSKILL.mdcore6,516 bytesSKILL.mdcore6,516 bytes
Read SKILL.md
# Spring Boot 验证循环 (Verification Loop)
在合并请求 (PR) 之前、重大变更之后以及部署前运行。
## 触发时机
- 在为 Spring Boot 服务开启合并请求 (Pull Request) 之前
- 在重大重构 (Refactoring) 或依赖 (Dependency) 升级之后
- 预发布或生产环境部署 (Deployment) 前的验证
- 运行完整的 构建 (Build) → 代码检查 (Lint) → 测试 (Test) → 安全扫描 (Security Scan) 流水线 (Pipeline)
- 验证测试覆盖率 (Test Coverage) 是否达到阈值
## 第一阶段:构建 (Build)
View the complete source on GitHubstrategic-compact
When your agent uses it
Suggests manual context compaction at logical intervals to preserve context through task phases rather than arbitrary auto-compaction.
What it loads into context
Frontmatter
33 tokensAlways available to the agent
SKILL.md
1,173 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
- 何时激活 (When to Activate)
- 为什么需要策略性压缩? (Why Strategic Compaction?)
- 工作原理 (How It Works)
- 钩子设置 (Hook Setup)
- 配置 (Configuration)
- 压缩决策指南 (Compaction Decision Guide)
- 哪些内容在压缩后存留 (What Survives Compaction)
- 最佳实践 (Best Practices)
- 相关资源 (Related)
Scripts executed separately
suggest-compact.sh
Files
SKILL.mdcore4,225 bytesSKILL.mdcore4,225 bytesSKILL.mdcore4,225 bytessuggest-compact.shruns1,788 bytes
Read SKILL.md
# 策略性压缩技能 (Strategic Compact Skill)
建议在工作流的战略点手动执行 `/compact`,而不是依赖随机的自动压缩。
## 何时激活 (When to Activate)
- 运行接近上下文限制(200K+ token)的长会话时
- 处理多阶段任务(研究 → 规划 → 实现 → 测试)时
- 在同一个会话中切换不相关的任务时
- 完成重大里程碑并开始新工作后
- 当响应变慢或连贯性下降(上下文压力)时
## 为什么需要策略性压缩? (Why Strategic Compaction?)
View the complete source on GitHubswift-actor-persistence
When your agent uses it
Swift 中使用 actor 实现的线程安全数据持久化 —— 结合内存缓存与文件存储,从设计上消除数据竞争。
What it loads into context
Frontmatter
44 tokensAlways available to the agent
SKILL.md
1,326 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
- 何时启用
- 核心模式 (Core Pattern)
- 关键设计决策 (Key Design Decisions)
- 最佳实践 (Best Practices)
- 避免的反模式 (Anti-Patterns to Avoid)
- 适用场景 (When to Use)
Files
SKILL.mdcore5,270 bytes
Read SKILL.md
# 使用 Swift Actors 实现线程安全持久化 (Swift Actors for Thread-Safe Persistence)
使用 Swift actor 构建线程安全数据持久化层的模式。该模式结合了内存缓存(In-memory caching)与基于文件的存储,利用 actor 模型(Actor model)在编译时消除数据竞争(Data races)。
## 何时启用
- 在 Swift 5.5+ 中构建数据持久化层
- 需要对共享可变状态(Shared mutable state)进行线程安全访问
- 希望消除手动同步操作(如 locks、DispatchQueues)
- 构建具有本地存储的离线优先(Offline-first)应用
## 核心模式 (Core Pattern)
### 基于 Actor 的仓库模式 (Actor-Based Repository)View the complete source on GitHubswift-concurrency-6-2
When your agent uses it
Swift 6.2 易用的并发(Approachable Concurrency)—— 默认单线程,使用 @concurrent 进行显式后台卸载,针对主执行角色(Main Actor)类型的隔离一致性。
What it loads into context
Frontmatter
60 tokensAlways available to the agent
SKILL.md
2,207 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
- 何时激活
- 核心问题:隐式后台卸载
- 核心模式 —— 隔离一致性 (Isolated Conformances)
- 核心模式 —— 全局和静态变量
- 核心模式 —— 使用 @concurrent 进行后台工作
- 关键设计决策
- 迁移步骤
- 最佳实践
- 应避免的反模式 (Anti-Patterns)
- 何时使用
Files
SKILL.mdcore8,216 bytes
Read SKILL.md
# Swift 6.2 易用的并发 (Approachable Concurrency)
采用 Swift 6.2 并发模型的模式:代码默认在单线程运行,并发需显式引入。在不牺牲性能的情况下消除常见的数据竞争(Data-race)错误。
## 何时激活
- 将 Swift 5.x 或 6.0/6.1 项目迁移到 Swift 6.2
- 解决数据竞争安全的编译器错误
- 设计基于 `MainActor` 的应用架构
- 将 CPU 密集型工作卸载到后台线程
- 在 `MainActor` 隔离的类型上实现协议一致性(Protocol conformances)
- 在 Xcode 26 中启用易用的并发(Approachable Concurrency)构建设置
## 核心问题:隐式后台卸载View the complete source on GitHubswift-protocol-di-testing
When your agent uses it
基于协议的依赖注入(Protocol-based Dependency Injection),通过精简的协议和 Swift 测试框架(Swift Testing)来模拟文件系统、网络和外部 API,编写可测试的 Swift 代码。
What it loads into context
Frontmatter
63 tokensAlways available to the agent
SKILL.md
1,499 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
- 何时激活
- 核心模式
- 最佳实践
- 需避免的反模式(Anti-Patterns)
- 何时使用
Files
SKILL.mdcore6,310 bytes
Read SKILL.md
# 基于 Swift 协议的依赖注入(Testing)
通过将外部依赖(文件系统、网络、iCloud)抽象到精简且功能集中的协议(Protocols)后面,使 Swift 代码变得可测试。这种模式支持无需实际 I/O 即可进行确定性测试(Deterministic Tests)。
## 何时激活
- 编写访问文件系统、网络或外部 API 的 Swift 代码时
- 需要在不触发实际故障的情况下测试错误处理路径时
- 构建需要在不同环境(App、测试、SwiftUI 预览)下运行的模块时
- 使用 Swift 并发(Concurrency,如 Actor、Sendable)设计可测试架构时
## 核心模式
### 1. 定义精简且功能集中的协议View the complete source on GitHubswiftui-patterns
When your agent uses it
SwiftUI 架构模式,使用 @Observable 进行状态管理,视图组合、导航、性能优化以及现代 iOS/macOS UI 最佳实践。
What it loads into context
Frontmatter
43 tokensAlways available to the agent
SKILL.md
1,860 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
- 何时激活
- 状态管理 (State Management)
- 视图组合 (View Composition)
- 导航 (Navigation)
- 性能 (Performance)
- 预览 (Previews)
- 需避免的反模式 (Anti-Patterns)
- 参考资料 (References)
Files
SKILL.mdcore7,306 bytes
Read SKILL.md
# SwiftUI 模式 (SwiftUI Patterns)
在 Apple 平台上构建声明式、高性能用户界面的现代 SwiftUI 模式。涵盖 Observation 框架、视图组合、类型安全导航以及性能优化。
## 何时激活
- 构建 SwiftUI 视图并管理状态(`@State`, `@Observable`, `@Binding`)
- 使用 `NavigationStack` 设计导航流
- 构建视图模型(View Model)和数据流
- 针对列表和复杂布局优化渲染性能
- 在 SwiftUI 中使用环境值(Environment Values)和依赖注入
## 状态管理 (State Management)
View the complete source on GitHubtdd-workflow
When your agent uses it
在编写新功能、修复 Bug 或重构代码时使用此技能。强制执行测试驱动开发(TDD),包括单元测试、集成测试和 E2E 测试,且覆盖率需达到 80% 以上。
What it loads into context
Frontmatter
68 tokensAlways available to the agent
SKILL.md
2,873 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
- 何时启用
- 核心原则
- TDD 工作流步骤
- 测试模式(Testing Patterns)
- 测试文件组织
- 模拟(Mocking)外部服务
- 测试覆盖率验证
- 应避免的常见测试错误
- 持续测试
- 最佳实践
- 成功指标
Files
SKILL.mdcore10,223 bytesSKILL.mdcore10,223 bytesSKILL.mdcore10,223 bytesSKILL.mdcore10,223 bytesSKILL.mdcore10,223 bytesSKILL.mdcore10,223 bytesSKILL.mdcore10,223 bytes
Read SKILL.md
# 测试驱动开发(TDD)工作流(Test-Driven Development Workflow)
此技能(Skill)旨在确保所有代码开发均遵循 TDD 原则,并具备全面的测试覆盖率。
## 何时启用
- 编写新功能或新特性
- 修复 Bug 或问题
- 重构现有代码
- 添加 API 端点(Endpoints)
- 创建新组件(Components)
## 核心原则
View the complete source on GitHubverification-loop
When your agent uses it
Claude Code 会话的全方位验证系统。
What it loads into context
Frontmatter
23 tokensAlways available to the agent
SKILL.md
852 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
- 何时使用
- 验证阶段
- 输出格式
- 持续模式
- 与钩子(Hooks)集成
Files
SKILL.mdcore2,658 bytesSKILL.mdcore2,658 bytesSKILL.mdcore2,658 bytesSKILL.mdcore2,658 bytesSKILL.mdcore2,658 bytesSKILL.mdcore2,658 bytesSKILL.mdcore2,658 bytes
Read SKILL.md
# 验证循环技能(Verification Loop Skill)
Claude Code 会话的全方位验证系统。
## 何时使用
在以下场景调用此技能(Skill):
- 完成功能开发或重大代码变更后
- 在创建拉取请求(PR)之前
- 当你想确保通过质量门禁时
- 重构之后
## 验证阶段
View the complete source on GitHubvisa-doc-translate
When your agent uses it
将签证申请文件(图像)翻译成英文,并创建包含原文和译文的双语 PDF。
What it loads into context
Frontmatter
35 tokensAlways available to the agent
SKILL.md
1,049 tokensWhen the skill is activated
Reference documents
561 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- 指令 (Instructions)
- 支持的文件类型 (Supported Documents)
- 技术实现 (Technical Implementation)
- 重要指南 (Important Guidelines)
- 使用示例 (Example Usage)
- 输出示例 (Output Example)
Files
README.mddoc1,981 bytesSKILL.mdcore3,979 bytesSKILL.mdcore3,979 bytesSKILL.mdcore3,979 bytesSKILL.mdcore3,979 bytesSKILL.mdcore3,979 bytesSKILL.mdcore3,979 bytesSKILL.mdcore3,979 bytes
Read SKILL.md
你正在协助翻译用于签证申请的文件。
## 指令 (Instructions)
当用户提供图像文件路径时,**自动 (AUTOMATICALLY)** 执行以下步骤,**无需 (WITHOUT)** 请求确认:
1. **图像转换 (Image Conversion)**:如果文件是 HEIC 格式,使用 `sips -s format png <input> --out <output>` 将其转换为 PNG。
2. **图像旋转 (Image Rotation)**:
- 检查 EXIF 方向数据。
- 根据 EXIF 数据自动旋转图像。
- 如果 EXIF 方向为 6,则逆时针旋转 90 度。
- 根据需要应用额外的旋转(如果文档看起来是倒置的,尝试旋转 180 度)。
View the complete source on GitHubSkills included
- backend-patterns
- clickhouse-io
- coding-standards
- configure-ecc
- continuous-learning
- continuous-learning-v2
- cpp-testing
- django-patterns
- django-security
- django-tdd
- django-verification
- eval-harness
- frontend-patterns
- golang-patterns
- golang-testing
- iterative-retrieval
- java-coding-standards
- jpa-patterns
- nutrient-document-processing
- postgres-patterns
- python-patterns
- python-testing
- security-review
- security-scan
- springboot-patterns
- springboot-security
- springboot-tdd
- springboot-verification
- strategic-compact
- tdd-workflow
- api-design
- article-writing
- backend-patterns
- clickhouse-io
- coding-standards
- configure-ecc
- content-engine
- content-hash-cache-pattern
- continuous-learning
- continuous-learning-v2
- cost-aware-llm-pipeline
- cpp-coding-standards
- cpp-testing
- database-migrations
- deployment-patterns
- django-patterns
- django-security
- django-tdd
- django-verification
- docker-patterns
- e2e-testing
- eval-harness
- foundation-models-on-device
- frontend-patterns
- frontend-slides
- golang-patterns
- golang-testing
- investor-materials
- investor-outreach
- iterative-retrieval
- java-coding-standards
- jpa-patterns
- liquid-glass-design
- market-research
- nutrient-document-processing
- postgres-patterns
- project-guidelines-example
- python-patterns
- python-testing
- regex-vs-llm-structured-text
- search-first
- security-review
- security-scan
- springboot-patterns
- springboot-security
- springboot-tdd
- springboot-verification
- strategic-compact
- swift-actor-persistence
- swift-concurrency-6-2
- swift-protocol-di-testing
- swiftui-patterns
- tdd-workflow
- verification-loop
- visa-doc-translate
- backend-patterns
- clickhouse-io
- coding-standards
- continuous-learning
- continuous-learning-v2
- eval-harness
- frontend-patterns
- golang-patterns
- golang-testing
- iterative-retrieval
- postgres-patterns
- security-review
- strategic-compact
- tdd-workflow
- api-design
- article-writing
- autonomous-loops
- backend-patterns
- clickhouse-io
- coding-standards
- configure-ecc
- content-engine
- content-hash-cache-pattern
- continuous-learning
- continuous-learning-v2
- cost-aware-llm-pipeline
- cpp-coding-standards
- cpp-testing
- database-migrations
- deployment-patterns
- django-patterns
- django-security
- django-tdd
- django-verification
- docker-patterns
- e2e-testing
- eval-harness
- foundation-models-on-device
- frontend-patterns
- frontend-slides
- golang-patterns
- golang-testing
- investor-materials
- investor-outreach
- iterative-retrieval
- java-coding-standards
- jpa-patterns
- liquid-glass-design
- market-research
- nutrient-document-processing
- plankton-code-quality
- postgres-patterns
- project-guidelines-example
- python-patterns
- python-testing
- regex-vs-llm-structured-text
- search-first
- security-review
- security-scan
- springboot-patterns
- springboot-security
- springboot-tdd
- springboot-verification
- strategic-compact
- swift-actor-persistence
- swift-concurrency-6-2
- swift-protocol-di-testing
- swiftui-patterns
- tdd-workflow
- verification-loop
- visa-doc-translate
Repository facts
- License
- MIT
- Created
- Jan 27, 2026
- Last pushed
- Mar 5, 2026
- Forks
- 332
- Open issues
- 0
- Project activity
- Slowing
Rank over the last 12 weeks
Now #528 · best #393 · down 75 in 30 days
- #519 on Oct 30
- #520 on Oct 31
- #522 on Nov 1
- #525 from Nov 2 to Nov 3
- #527 from Nov 4 to Nov 5
- #528 since Nov 6
68 earlier periods
- #378 on Aug 2
- #382 on Aug 7
- #386 on Aug 8
- #385 on Aug 9
- #396 on Aug 10
- #398 on Aug 11
- #392 on Aug 12
- #395 on Aug 13
- #398 on Aug 14
- #393 on Aug 15
- #398 on Aug 16
- #397 on Aug 17
- #407 on Aug 18
- #405 on Aug 19
- #402 from Aug 20 to Aug 21
- #397 on Aug 22
- #407 on Aug 23
- #404 on Aug 24
- #408 on Aug 25
- #407 on Aug 26
- #414 on Aug 27
- #416 on Aug 28
- #404 on Aug 30
- #418 on Aug 31
- #421 on Sep 1
- #417 on Sep 2
- #418 on Sep 3
- #409 on Sep 4
- #415 on Sep 5
- #413 on Sep 6
- #422 on Sep 7
- #425 on Sep 8
- #422 on Sep 9
- #427 on Sep 10
- #425 on Sep 11
- #425 on Sep 13
- #433 on Sep 14
- #431 on Sep 17
- #442 on Sep 18
- #437 on Sep 20
- #439 on Sep 21
- #436 on Sep 24
- #442 on Sep 27
- #450 on Sep 28
- #457 on Sep 29
- #452 on Sep 30
- #450 on Oct 1
- #447 on Oct 2
- #435 on Oct 3
- #430 on Oct 4
- #448 on Oct 6
- #453 on Oct 7
- #461 on Oct 8
- #463 on Oct 9
- #459 on Oct 10
- #458 on Oct 11
- #468 on Oct 12
- #465 on Oct 13
- #468 on Oct 14
- #471 on Oct 15
- #476 on Oct 16
- #467 on Oct 17
- #485 from Oct 19 to Oct 20
- #491 on Oct 21
- #486 on Oct 22
- #509 on Oct 25
- #515 on Oct 28
- #516 on Oct 29
Before you install
Network or broad shellAutomated signals, not a guarantee
Checked Nov 3, 2026
Not fully analyzed: some files were too long, unreadable or missing. This never lowers the level.
Show 895 notes
.cursor/hooks/after-file-edit.js:1Analysis incomplete: Referenced executable target unavailable; not analyzed.cursor/hooks/after-mcp-execution.js:1Analysis incomplete: Referenced executable target unavailable; not analyzed.cursor/hooks/after-shell-execution.js:1Analysis incomplete: Referenced executable target unavailable; not analyzed.cursor/hooks/after-tab-file-edit.js:1Analysis incomplete: Referenced executable target unavailable; not analyzed.cursor/hooks/before-mcp-execution.js:1Analysis incomplete: Referenced executable target unavailable; not analyzed.cursor/hooks/before-read-file.js:1Analysis incomplete: Referenced executable target unavailable; not analyzed.cursor/hooks/before-shell-execution.js:1Analysis incomplete: Referenced executable target unavailable; not analyzed.cursor/hooks/before-submit-prompt.js:1Analysis incomplete: Referenced executable target unavailable; not analyzed.cursor/hooks/before-tab-file-read.js:1Analysis incomplete: Referenced executable target unavailable; not analyzed.cursor/hooks/pre-compact.js:1Analysis incomplete: Referenced executable target unavailable; not analyzed.cursor/hooks/session-end.js:1Analysis incomplete: Referenced executable target unavailable; not analyzed.cursor/hooks/session-start.js:1Analysis incomplete: Referenced executable target unavailable; not analyzed.cursor/hooks/stop.js:1Analysis incomplete: Referenced executable target unavailable; not analyzed.cursor/hooks/subagent-start.js:1Analysis incomplete: Referenced executable target unavailable; not analyzed.cursor/hooks/subagent-stop.js:1Analysis incomplete: Referenced executable target unavailable; not analyzedhooks/hooks.json:1Analysis incomplete: Referenced executable target unavailable; not analyzedhooks/hooks.json:1Analysis incomplete: Referenced executable target unavailable; not analyzedhooks/hooks.json:1Analysis incomplete: Referenced executable target unavailable; not analyzedhooks/hooks.json:1Analysis incomplete: Referenced executable target unavailable; not analyzedhooks/hooks.json:1Analysis incomplete: Referenced executable target unavailable; not analyzed
- No broad tool permissions
- 16 dangerous shell commandsin 8 files: continuous-learning-v2/agents/start-observer.sh:84 configure-ecc/SKILL.md:30 configure-ecc/SKILL.md:32 and 5 more
- 575 network referencesin 96 files: nutrient-document-processing/SKILL.md:8 nutrient-document-processing/SKILL.md:9 nutrient-document-processing/SKILL.md:9 and 93 more
- No hidden or obfuscated text
- 6 instruction override signalsin 1 file: continuous-learning-v2/scripts/instinct-cli.py:1100
- 45 executable scriptsin 26 files: skills/continuous-learning-v2/hooks/observe.sh:1 .cursor/hooks/after-file-edit.js:1 .cursor/hooks/after-mcp-execution.js:1 and 23 more
- 174 references to secretsin 51 files: nutrient-document-processing/SKILL.md:15 nutrient-document-processing/SKILL.md:16 nutrient-document-processing/SKILL.md:16 and 48 more
- No requests to vote in Hot
Show all 816 signals by file
.claude-plugin/marketplace.json
- Network accessline 1
{ "$schema": "https://anthropic.com/claude-code/marketplace.schema.json", - Network accessline 2
"$schema": "https://anthropic.com/claude-code/marketplace.schema.json", - Network accessline 20
"email": "me@affaanmustafa.com" }, "homepage": "https://github.com/affaan-m/everything-claude-code", - Network accessline 21
}, "homepage": "https://github.com/affaan-m/everything-claude-code", "repository": "https://github.com/affaan-m/everything-claude-code", - Network accessline 22
"homepage": "https://github.com/affaan-m/everything-claude-code", - Network accessline 23
"repository": "https://github.com/affaan-m/everything-claude-code",
.claude-plugin/plugin.json
- Network accessline 5
"author": { "name": "Affaan Mustafa", "url": "https://x.com/affaanmustafa" - Network accessline 6
"name": "Affaan Mustafa", "url": "https://x.com/affaanmustafa" }, - Network accessline 7
"url": "https://x.com/affaanmustafa" - Network accessline 8
}, "homepage": "https://github.com/affaan-m/everything-claude-code", "repository": "https://github.com/affaan-m/everything-claude-code", - Network accessline 9
"homepage": "https://github.com/affaan-m/everything-claude-code", - Network accessline 10
"repository": "https://github.com/affaan-m/everything-claude-code",
.cursor/hooks/after-file-edit.js
.cursor/hooks/after-mcp-execution.js
.cursor/hooks/after-shell-execution.js
.cursor/hooks/after-tab-file-edit.js
.cursor/hooks/before-mcp-execution.js
.cursor/hooks/before-read-file.js
.cursor/hooks/before-shell-execution.js
.cursor/hooks/before-submit-prompt.js
.cursor/hooks/before-tab-file-read.js
.cursor/hooks/pre-compact.js
.cursor/hooks/session-end.js
.cursor/hooks/session-start.js
.cursor/hooks/stop.js
.cursor/hooks/subagent-start.js
.cursor/hooks/subagent-stop.js
commands/e2e.md
commands/instinct-import.md
commands/pm2.md
- Access to secretsline 29
[Credential-related source omitted]
commands/skill-create.md
- Network accessline 160
对于高级功能(1万+ 提交、团队共享、自动 PR),请使用 [Skill Creator GitHub App](https://github.com/apps/skill-creator): - Network accessline 162
- 安装:[github.com/apps/skill-creator](https://github.com/apps/skill-creator) - Network accessline 174
*属于 [Everything Claude Code](https://github.com/affaan-m/everything-claude-code) 的一部分*
docs/ja-JP/skills/backend-patterns/SKILL.md
- Access to secretsline 350
[Credential-related source omitted] - Network accessline 432
): Promise<boolean> { const now = Date.now() const requests = this.requests.get(identifier) || [] - Network accessline 434
const requests = this.requests.get(identifier) || [] - Network accessline 436
// 删除窗口外的旧请求 const recentRequests = requests.filter(time => now - time < windowMs) - Network accessline 437
const recentRequests = requests.filter(time => now - time < windowMs) - Network accessline 443
// 添加当前请求 recentRequests.push(now) this.requests.set(identifier, recentRequests) - Network accessline 445
this.requests.set(identifier, recentRequests)
docs/ja-JP/skills/coding-standards/SKILL.md
- Network accessline 90
async function fetchData(url: string) { try { const response = await fetch(url) - Network accessline 92
const response = await fetch(url) - Network accessline 105
// ❌ 错误:缺乏错误处理 async function fetchData(url) { const response = await fetch(url) - Network accessline 106
async function fetchData(url) { const response = await fetch(url) return response.json() - Network accessline 107
const response = await fetch(url)
docs/ja-JP/skills/configure-ecc/SKILL.md
- Dangerous shell operationline 30
rm -rf /tmp/everything-claude-code - Network accessline 30
rm -rf /tmp/everything-claude-code git clone https://github.com/affaan-m/everything-claude-code.git /tmp/everything-claude-code - Network accessline 31
git clone https://github.com/affaan-m/everything-claude-code.git /tmp/everything-claude-code - Dangerous shell operationline 255
rm -rf /tmp/everything-claude-code
docs/ja-JP/skills/continuous-learning-v2/SKILL.md
docs/ja-JP/skills/continuous-learning-v2/agents/observer.md
docs/ja-JP/skills/continuous-learning/SKILL.md
- Network accessline 79
- [The Longform Guide](https://x.com/affaanmustafa/status/2014040193557471352) - 关于持续学习的部分
docs/ja-JP/skills/cpp-testing/SKILL.md
- Network accessline 161
FetchContent_Declare( googletest URL https://github.com/google/googletest/archive/refs/tags/${GTEST_VERSION}.zip - Network accessline 162
googletest URL https://github.com/google/googletest/archive/refs/tags/${GTEST_VERSION}.zip ) - Network accessline 163
URL https://github.com/google/googletest/archive/refs/tags/${GTEST_VERSION}.zip
docs/ja-JP/skills/django-patterns/SKILL.md
- Access to secretsline 60
[Credential-related source omitted]
docs/ja-JP/skills/django-security/SKILL.md
- Access to secretsline 28
[Credential-related source omitted] - Access to secretsline 48
[Credential-related source omitted] - Network accessline 339
CSRF_COOKIE_HTTPONLY = True # 防止 JavaScript 访问 CSRF_COOKIE_SAMESITE = 'Lax' # 在某些场景下防止 CSRF CSRF_TRUSTED_ORIGINS = ['https://example.com'] # 受信任的来源 - Network accessline 341
CSRF_TRUSTED_ORIGINS = ['https://example.com'] # 受信任的来源 - Network accessline 366
fetch('/api/endpoint/', { - Network accessline 423
# 在生产环境中为媒体文件使用独立域名 MEDIA_DOMAIN = 'https://media.example.com' - Network accessline 424
MEDIA_DOMAIN = 'https://media.example.com' - Network accessline 491
# settings.py CSP_DEFAULT_SRC = "'self'" CSP_SCRIPT_SRC = "'self' https://cdn.example.com" - Network accessline 492
CSP_DEFAULT_SRC = "'self'" CSP_SCRIPT_SRC = "'self' https://cdn.example.com" CSP_STYLE_SRC = "'self' 'unsafe-inline'" - Network accessline 493
CSP_SCRIPT_SRC = "'self' https://cdn.example.com" - Network accessline 494
CSP_STYLE_SRC = "'self' 'unsafe-inline'" CSP_IMG_SRC = "'self' data: https:" CSP_CONNECT_SRC = "'self' https://api.example.com" - Network accessline 496
CSP_CONNECT_SRC = "'self' https://api.example.com" - Access to secretsline 528
[Credential-related source omitted] - Access to secretsline 531
[Credential-related source omitted] - Access to secretsline 535
[Credential-related source omitted]
docs/ja-JP/skills/django-verification/SKILL.md
docs/ja-JP/skills/frontend-patterns/SKILL.md
- Network accessline 103
useEffect(() => { fetch(url) - Network accessline 104
fetch(url) - Network accessline 188
const { data: markets, loading, error, refetch } = useQuery( 'markets', () => fetch('/api/markets').then(r => r.json()), - Network accessline 189
'markets', () => fetch('/api/markets').then(r => r.json()), { - Network accessline 190
() => fetch('/api/markets').then(r => r.json()),
docs/ja-JP/skills/golang-patterns/SKILL.md
- Network accessline 272
ch := make(chan []byte) go func() { data, _ := fetch(url) - Network accessline 273
go func() { data, _ := fetch(url) ch <- data // 如果没有接收者,将永远阻塞 - Network accessline 274
data, _ := fetch(url) - Network accessline 282
ch := make(chan []byte, 1) // 有缓冲通道 go func() { data, err := fetch(url) - Network accessline 283
go func() { data, err := fetch(url) if err != nil { - Network accessline 284
data, err := fetch(url)
docs/ja-JP/skills/iterative-retrieval/SKILL.md
- Network accessline 200
- [The Longform Guide](https://x.com/affaanmustafa/status/2014040193557471352) - 子智能体编排(Sub-agent Orchestration)章节
docs/ja-JP/skills/nutrient-document-processing/SKILL.md
- Network accessline 8
使用 [Nutrient DWS 处理程序 API (Processor API)](https://www.nutrient.io/api/) 处理文档。它可以进行格式转换、文本与表格提取、扫描文档的光学字符识别 (OCR)、个人身份信息 (PII) 脱敏、添加水印、数字签名以及 PDF 表单填充。 - Network accessline 12
请在 **[nutrient.io](https://dashboard.nutrient.io/sign_up/?product=processor)** 获取免费的 API 密钥。 - Access to secretsline 15
[Credential-related source omitted] - Network accessline 18
所有请求都以多部分 POST (multipart POST) 的形式发送到 `https://api.nutrient.io/build`,其中包含 `instructions` JSON 字段。 - Network accessline 25
# 从 DOCX 转换为 PDF curl -X POST https://api.nutrient.io/build \ - Network accessline 26
[Credential-related source omitted] - Access to secretsline 26
[Credential-related source omitted] - Access to secretsline 27
[Credential-related source omitted] - Network accessline 32
# 从 PDF 转换为 DOCX curl -X POST https://api.nutrient.io/build \ - Network accessline 33
[Credential-related source omitted] - Access to secretsline 33
[Credential-related source omitted] - Access to secretsline 34
[Credential-related source omitted] - Network accessline 39
# 从 HTML 转换为 PDF curl -X POST https://api.nutrient.io/build \ - Network accessline 40
[Credential-related source omitted] - Access to secretsline 40
[Credential-related source omitted] - Access to secretsline 41
[Credential-related source omitted] - Network accessline 52
# 提取纯文本 curl -X POST https://api.nutrient.io/build \ - Network accessline 53
[Credential-related source omitted] - Access to secretsline 53
[Credential-related source omitted] - Access to secretsline 54
[Credential-related source omitted] - Network accessline 59
# 将表格提取为 Excel curl -X POST https://api.nutrient.io/build \ - Network accessline 60
[Credential-related source omitted] - Access to secretsline 60
[Credential-related source omitted] - Access to secretsline 61
[Credential-related source omitted] - Network accessline 70
# 对扫描件进行 OCR 并生成可搜索的 PDF(支持 100 多种语言) curl -X POST https://api.nutrient.io/build \ - Network accessline 71
[Credential-related source omitted] - Access to secretsline 71
[Credential-related source omitted] - Access to secretsline 72
[Credential-related source omitted] - Network accessline 78
语言:通过 ISO 639-2 代码支持 100 多种语言(例如:`eng`、`deu`、`fra`、`spa`、`jpn`、`kor`、`chi_sim`、`chi_tra`、`ara`、`hin`、`rus`)。完整语言名称如 `english` 或 `german` 也可使用。有关所有受支持的代码,请参阅 [完整 OCR 语言列表](https://www.nutrient.io/guides/document-engine/ocr/language-support/) - Network accessline 83
# 基于模式(社会安全号码 SSN、电子邮件) curl -X POST https://api.nutrient.io/build \ - Network accessline 84
[Credential-related source omitted] - Access to secretsline 84
[Credential-related source omitted] - Access to secretsline 85
[Credential-related source omitted] - Network accessline 90
# 基于正则表达式 curl -X POST https://api.nutrient.io/build \ - Network accessline 91
[Credential-related source omitted] - Access to secretsline 91
[Credential-related source omitted] - Access to secretsline 92
[Credential-related source omitted] - Network accessline 103
[Credential-related source omitted] - Access to secretsline 103
[Credential-related source omitted] - Access to secretsline 104
[Credential-related source omitted] - Network accessline 113
# 自签名 CMS 签名 curl -X POST https://api.nutrient.io/build \ - Network accessline 114
[Credential-related source omitted] - Access to secretsline 114
[Credential-related source omitted] - Access to secretsline 115
[Credential-related source omitted] - Network accessline 124
[Credential-related source omitted] - Access to secretsline 124
[Credential-related source omitted] - Access to secretsline 125
[Credential-related source omitted] - Access to secretsline 142
[Credential-related source omitted] - Network accessline 162
- [API 游乐场 (Playground)](https://dashboard.nutrient.io/processor-api/playground/) - Network accessline 163
- [完整 API 文档](https://www.nutrient.io/guides/dws-processor/) - Network accessline 164
- [npm MCP 服务端](https://www.npmjs.com/package/@nutrient-sdk/dws-mcp-server)
docs/ja-JP/skills/project-guidelines-example/SKILL.md
- Network accessline 5
基于实际的生产环境应用程序:[Zenith](https://zenith.chat) - AI 驱动的客户发现平台。 - Network accessline 126
): Promise<ApiResponse<T>> { try { const response = await fetch(`/api${endpoint}`, { - Network accessline 127
try { const response = await fetch(`/api${endpoint}`, { ...options, - Network accessline 128
const response = await fetch(`/api${endpoint}`, { - Network accessline 241
@pytest.fixture async def client(): async with AsyncClient(app=app, base_url="http://test") as ac: - Network accessline 242
async def client(): async with AsyncClient(app=app, base_url="http://test") as ac: yield ac - Network accessline 243
async with AsyncClient(app=app, base_url="http://test") as ac: - Network accessline 313
# 前端 (.env.local) NEXT_PUBLIC_API_URL=https://api.example.com - Network accessline 314
NEXT_PUBLIC_API_URL=https://api.example.com - Network accessline 315
NEXT_PUBLIC_SUPABASE_URL=https://xxx.supabase.co - Network accessline 319
[Credential-related source omitted] - Network accessline 320
[Credential-related source omitted] - Access to secretsline 320
[Credential-related source omitted] - Network accessline 321
SUPABASE_URL=https://xxx.supabase.co
docs/ja-JP/skills/python-patterns/SKILL.md
- Network accessline 448
"""抓取 URL(I/O 密集型操作)。""" import urllib.request with urllib.request.urlopen(url) as response: - Network accessline 449
import urllib.request with urllib.request.urlopen(url) as response: return response.read().decode() - Network accessline 450
with urllib.request.urlopen(url) as response: - Network accessline 487
"""异步抓取 URL。""" import aiohttp async with aiohttp.ClientSession() as session: - Network accessline 488
import aiohttp async with aiohttp.ClientSession() as session: async with session.get(url) as response: - Network accessline 489
async with aiohttp.ClientSession() as session:
docs/ja-JP/skills/python-testing/SKILL.md
- Network accessline 321
@pytest.mark.integration def test_api_integration(): response = requests.get("https://api.example.com") - Network accessline 322
def test_api_integration(): response = requests.get("https://api.example.com") assert response.status_code == 200 - Network accessline 323
response = requests.get("https://api.example.com") - Access to secretsline 456
[Credential-related source omitted] - Access to secretsline 462
[Credential-related source omitted]
docs/ja-JP/skills/security-review/SKILL.md
- Access to secretsline 32
[Credential-related source omitted] - Access to secretsline 37
[Credential-related source omitted] - Network accessline 219
img-src 'self' data: https:; font-src 'self'; connect-src 'self' https://api.example.com; - Network accessline 220
font-src 'self'; connect-src 'self' https://api.example.com; `.replace(/\s{2,}/g, ' ').trim() - Network accessline 221
connect-src 'self' https://api.example.com; - Network accessline 427
// 测试身份验证 test('requires authentication', async () => { const response = await fetch('/api/protected') - Network accessline 428
test('requires authentication', async () => { const response = await fetch('/api/protected') expect(response.status).toBe(401) - Network accessline 429
const response = await fetch('/api/protected') - Network accessline 433
// 测试授权 test('requires admin role', async () => { const response = await fetch('/api/admin', { - Network accessline 434
[Credential-related source omitted] - Network accessline 435
const response = await fetch('/api/admin', { - Network accessline 441
// 测试输入验证 test('rejects invalid input', async () => { const response = await fetch('/api/users', { - Network accessline 442
test('rejects invalid input', async () => { const response = await fetch('/api/users', { method: 'POST', - Network accessline 443
const response = await fetch('/api/users', { - Network accessline 451
test('enforces rate limits', async () => { const requests = Array(101).fill(null).map(() => fetch('/api/endpoint') - Network accessline 452
const requests = Array(101).fill(null).map(() => fetch('/api/endpoint') ) - Network accessline 453
fetch('/api/endpoint') - Network accessline 487
- [OWASP Top 10](https://owasp.org/www-project-top-ten/) - Network accessline 488
- [Next.js 安全指南](https://nextjs.org/docs/security) - Network accessline 489
- [Supabase 安全指南](https://supabase.com/docs/guides/auth) - Network accessline 490
- [Web Security Academy](https://portswigger.net/web-security)
docs/ja-JP/skills/security-review/cloud-infrastructure-security.md
- Access to secretsline 76
[Credential-related source omitted] - Network accessline 240
// ✅ 正确:带有安全标头(Security Headers)的 Cloudflare Workers export default { async fetch(request: Request): Promise<Response> { - Network accessline 241
export default { async fetch(request: Request): Promise<Response> { const response = await fetch(request); - Network accessline 242
async fetch(request: Request): Promise<Response> { - Network accessline 243
const response = await fetch(request); - Network accessline 355
- [AWS Security Best Practices](https://aws.amazon.com/security/best-practices/) - Network accessline 356
- [CIS AWS Foundations Benchmark](https://www.cisecurity.org/benchmark/amazon_web_services) - Network accessline 357
- [Cloudflare Security Documentation](https://developers.cloudflare.com/security/) - Network accessline 358
- [OWASP Cloud Security](https://owasp.org/www-project-cloud-security/) - Network accessline 359
- [Terraform Security Best Practices](https://www.terraform.io/docs/cloud/guides/recommended-practices/)
docs/ja-JP/skills/security-scan/SKILL.md
- Network accessline 8
使用 [AgentShield](https://github.com/affaan-m/agentshield) 审计 Claude Code 配置的安全问题。 - Access to secretsline 94
[Credential-related source omitted] - Access to secretsline 95
[Credential-related source omitted] - Network accessline 163
- **GitHub**: [github.com/affaan-m/agentshield](https://github.com/affaan-m/agentshield) - Network accessline 164
- **npm**: [npmjs.com/package/ecc-agentshield](https://www.npmjs.com/package/ecc-agentshield)
docs/ja-JP/skills/strategic-compact/SKILL.md
- Network accessline 62
- [The Longform Guide](https://x.com/affaanmustafa/status/2014040193557471352) - 令牌(Token)优化章节
docs/ja-JP/skills/tdd-workflow/SKILL.md
- Network accessline 152
describe('GET /api/markets', () => { it('returns markets successfully', async () => { const request = new NextRequest('http://localhost/api/markets') - Network accessline 153
it('returns markets successfully', async () => { const request = new NextRequest('http://localhost/api/markets') const response = await GET(request) - Network accessline 154
const request = new NextRequest('http://localhost/api/markets') - Network accessline 163
it('validates query parameters', async () => { const request = new NextRequest('http://localhost/api/markets?limit=invalid') - Network accessline 164
const request = new NextRequest('http://localhost/api/markets?limit=invalid') - Network accessline 170
it('handles database errors gracefully', async () => { // Mock 数据库故障 const request = new NextRequest('http://localhost/api/markets') - Network accessline 171
// Mock 数据库故障 const request = new NextRequest('http://localhost/api/markets') // 测试错误处理 - Network accessline 172
const request = new NextRequest('http://localhost/api/markets')
docs/ja-JP/skills/verification-loop/SKILL.md
- Access to secretsline 64
[Credential-related source omitted]
docs/zh-CN/skills/backend-patterns/SKILL.md
- Access to secretsline 361
[Credential-related source omitted] - Network accessline 443
): Promise<boolean> { const now = Date.now() const requests = this.requests.get(identifier) || [] - Network accessline 445
const requests = this.requests.get(identifier) || [] - Network accessline 447
// Remove old requests outside window const recentRequests = requests.filter(time => now - time < windowMs) - Network accessline 448
const recentRequests = requests.filter(time => now - time < windowMs) - Network accessline 454
// Add current request recentRequests.push(now) this.requests.set(identifier, recentRequests) - Network accessline 456
this.requests.set(identifier, recentRequests)
docs/zh-CN/skills/coding-standards/SKILL.md
- Network accessline 100
async function fetchData(url: string) { try { const response = await fetch(url) - Network accessline 102
const response = await fetch(url) - Network accessline 115
// ❌ BAD: No error handling async function fetchData(url) { const response = await fetch(url) - Network accessline 116
async function fetchData(url) { const response = await fetch(url) return response.json() - Network accessline 117
const response = await fetch(url)
docs/zh-CN/skills/configure-ecc/SKILL.md
- Dangerous shell operationline 32
rm -rf /tmp/everything-claude-code - Network accessline 32
rm -rf /tmp/everything-claude-code git clone https://github.com/affaan-m/everything-claude-code.git /tmp/everything-claude-code - Network accessline 33
git clone https://github.com/affaan-m/everything-claude-code.git /tmp/everything-claude-code - Dangerous shell operationline 280
rm -rf /tmp/everything-claude-code
docs/zh-CN/skills/continuous-learning-v2/SKILL.md
docs/zh-CN/skills/continuous-learning-v2/agents/observer.md
docs/zh-CN/skills/continuous-learning/SKILL.md
- Network accessline 88
* [长篇指南](https://x.com/affaanmustafa/status/2014040193557471352) - 关于持续学习的章节
docs/zh-CN/skills/cpp-coding-standards/SKILL.md
- Network accessline 9
源自 [C++ 核心准则](https://isocpp.github.io/CppCoreGuidelines/CppCoreGuidelines) 的现代 C++(C++17/20/23)综合编码标准。强制执行类型安全、资源安全、不变性和清晰性。 - Network accessline 371
void run() { try { fetch_data("https://api.example.com"); - Network accessline 372
try { fetch_data("https://api.example.com"); } catch (const NetworkError& e) { - Network accessline 373
fetch_data("https://api.example.com");
docs/zh-CN/skills/cpp-testing/SKILL.md
- Network accessline 162
FetchContent_Declare( googletest URL Google Test framework (official repository) https://github.com/google/googletest/archive/refs/tags/${GTEST_VERSION}.zip - Network accessline 163
googletest URL Google Test framework (official repository) https://github.com/google/googletest/archive/refs/tags/${GTEST_VERSION}.zip ) - Network accessline 164
URL Google Test framework (official repository) https://github.com/google/googletest/archive/refs/tags/${GTEST_VERSION}.zip
docs/zh-CN/skills/deployment-patterns/SKILL.md
- Network accessline 114
HEALTHCHECK --interval=30s --timeout=3s --start-period=5s --retries=3 \ CMD wget --no-verbose --tries=1 --spider http://localhost:3000/health || exit 1 - Network accessline 115
CMD wget --no-verbose --tries=1 --spider http://localhost:3000/health || exit 1 - Network accessline 137
EXPOSE 8080 HEALTHCHECK --interval=30s --timeout=3s CMD wget -qO- http://localhost:8080/health || exit 1 - Network accessline 138
HEALTHCHECK --interval=30s --timeout=3s CMD wget -qO- http://localhost:8080/health || exit 1 - Network accessline 164
HEALTHCHECK --interval=30s --timeout=3s CMD python -c "import urllib.request; urllib.request.urlopen('http://localhost:8000/health/')" || exit 1 - Access to secretsline 339
[Credential-related source omitted]
docs/zh-CN/skills/django-patterns/SKILL.md
- Access to secretsline 61
[Credential-related source omitted]
docs/zh-CN/skills/django-security/SKILL.md
- Access to secretsline 29
[Credential-related source omitted] - Access to secretsline 49
[Credential-related source omitted] - Network accessline 340
CSRF_COOKIE_HTTPONLY = True # Prevent JavaScript access CSRF_COOKIE_SAMESITE = 'Lax' # Prevent CSRF in some cases CSRF_TRUSTED_ORIGINS = ['https://example.com'] # Trusted domains - Network accessline 342
CSRF_TRUSTED_ORIGINS = ['https://example.com'] # Trusted domains - Network accessline 367
fetch('/api/endpoint/', { - Network accessline 424
# Use a separate domain for media in production MEDIA_DOMAIN = 'https://media.example.com' - Network accessline 425
MEDIA_DOMAIN = 'https://media.example.com' - Network accessline 492
# settings.py CSP_DEFAULT_SRC = "'self'" CSP_SCRIPT_SRC = "'self' https://cdn.example.com" - Network accessline 493
CSP_DEFAULT_SRC = "'self'" CSP_SCRIPT_SRC = "'self' https://cdn.example.com" CSP_STYLE_SRC = "'self' 'unsafe-inline'" - Network accessline 494
CSP_SCRIPT_SRC = "'self' https://cdn.example.com" - Network accessline 495
CSP_STYLE_SRC = "'self' 'unsafe-inline'" CSP_IMG_SRC = "'self' data: https:" CSP_CONNECT_SRC = "'self' https://api.example.com" - Network accessline 497
CSP_CONNECT_SRC = "'self' https://api.example.com" - Access to secretsline 529
[Credential-related source omitted] - Access to secretsline 532
[Credential-related source omitted] - Access to secretsline 536
[Credential-related source omitted]
docs/zh-CN/skills/django-verification/SKILL.md
docs/zh-CN/skills/docker-patterns/SKILL.md
- Network accessline 113
ENV NODE_ENV=production EXPOSE 3000 HEALTHCHECK --interval=30s --timeout=3s CMD wget -qO- http://localhost:3000/health || exit 1 - Network accessline 114
EXPOSE 3000 HEALTHCHECK --interval=30s --timeout=3s CMD wget -qO- http://localhost:3000/health || exit 1 CMD ["node", "dist/server.js"] - Network accessline 115
HEALTHCHECK --interval=30s --timeout=3s CMD wget -qO- http://localhost:3000/health || exit 1 - Access to secretsline 267
[Credential-related source omitted] - Access to secretsline 269
[Credential-related source omitted] - Access to secretsline 282
[Credential-related source omitted] - Access to secretsline 290
[Credential-related source omitted] - Network accessline 337
# Check connectivity docker compose exec app wget -qO- http://api:3000/health - Network accessline 338
docker compose exec app wget -qO- http://api:3000/health - Access to secretsline 364
[Credential-related source omitted]
docs/zh-CN/skills/e2e-testing/SKILL.md
- Network accessline 115
], use: { baseURL: process.env.BASE_URL || 'http://localhost:3000', - Network accessline 116
use: { baseURL: process.env.BASE_URL || 'http://localhost:3000', trace: 'on-first-retry', - Network accessline 117
baseURL: process.env.BASE_URL || 'http://localhost:3000', - Network accessline 130
webServer: { command: 'npm run dev', url: 'http://localhost:3000', - Network accessline 131
command: 'npm run dev', url: 'http://localhost:3000', reuseExistingServer: !process.env.CI, - Network accessline 132
url: 'http://localhost:3000',
docs/zh-CN/skills/frontend-patterns/SKILL.md
- Network accessline 114
useEffect(() => { fetch(url) - Network accessline 115
fetch(url) - Network accessline 199
const { data: markets, loading, error, refetch } = useQuery( 'markets', () => fetch('/api/markets').then(r => r.json()), - Network accessline 200
'markets', () => fetch('/api/markets').then(r => r.json()), { - Network accessline 201
() => fetch('/api/markets').then(r => r.json()),
docs/zh-CN/skills/frontend-slides/SKILL.md
- Network accessline 11
灵感来源于 [zarazhangrui](https://github.com/zarazhangrui) 的作品中展示的视觉探索方法。
docs/zh-CN/skills/golang-patterns/SKILL.md
- Network accessline 273
ch := make(chan []byte) go func() { data, _ := fetch(url) - Network accessline 274
go func() { data, _ := fetch(url) ch <- data // Blocks forever if no receiver - Network accessline 275
data, _ := fetch(url) - Network accessline 283
ch := make(chan []byte, 1) // Buffered channel go func() { data, err := fetch(url) - Network accessline 284
go func() { data, err := fetch(url) if err != nil { - Network accessline 285
data, err := fetch(url)
docs/zh-CN/skills/iterative-retrieval/SKILL.md
- Network accessline 213
* [长篇指南](https://x.com/affaanmustafa/status/2014040193557471352) - 子智能体编排部分
docs/zh-CN/skills/nutrient-document-processing/SKILL.md
- Network accessline 9
使用 [Nutrient DWS Processor API](https://www.nutrient.io/api/) 处理文档。转换格式、提取文本和表格、对扫描文档进行 OCR、编辑 PII、添加水印、数字签名以及填写 PDF 表单。 - Network accessline 13
在 **[nutrient.io](https://dashboard.nutrient.io/sign_up/?product=processor)** 获取一个免费的 API 密钥 - Access to secretsline 16
[Credential-related source omitted] - Network accessline 19
所有请求都以 multipart POST 形式发送到 `https://api.nutrient.io/build`,并附带一个 `instructions` JSON 字段。 - Network accessline 26
# DOCX to PDF curl -X POST https://api.nutrient.io/build \ - Network accessline 27
[Credential-related source omitted] - Access to secretsline 27
[Credential-related source omitted] - Access to secretsline 28
[Credential-related source omitted] - Network accessline 33
# PDF to DOCX curl -X POST https://api.nutrient.io/build \ - Network accessline 34
[Credential-related source omitted] - Access to secretsline 34
[Credential-related source omitted] - Access to secretsline 35
[Credential-related source omitted] - Network accessline 40
# HTML to PDF curl -X POST https://api.nutrient.io/build \ - Network accessline 41
[Credential-related source omitted] - Access to secretsline 41
[Credential-related source omitted] - Access to secretsline 42
[Credential-related source omitted] - Network accessline 53
# Extract plain text curl -X POST https://api.nutrient.io/build \ - Network accessline 54
[Credential-related source omitted] - Access to secretsline 54
[Credential-related source omitted] - Access to secretsline 55
[Credential-related source omitted] - Network accessline 60
# Extract tables as Excel curl -X POST https://api.nutrient.io/build \ - Network accessline 61
[Credential-related source omitted] - Access to secretsline 61
[Credential-related source omitted] - Access to secretsline 62
[Credential-related source omitted] - Network accessline 71
# OCR to searchable PDF (supports 100+ languages) curl -X POST https://api.nutrient.io/build \ - Network accessline 72
[Credential-related source omitted] - Access to secretsline 72
[Credential-related source omitted] - Access to secretsline 73
[Credential-related source omitted] - Network accessline 79
支持语言:通过 ISO 639-2 代码支持 100 多种语言(例如,`eng`, `deu`, `fra`, `spa`, `jpn`, `kor`, `chi_sim`, `chi_tra`, `ara`, `hin`, `rus`)。完整的语言名称如 `english` 或 `german` 也适用。查看 [完整的 OCR 语言表](https://www.nutrient.io/guides/document-engine/ocr/language-support/) - Network accessline 84
# Pattern-based (SSN, email) curl -X POST https://api.nutrient.io/build \ - Network accessline 85
[Credential-related source omitted] - Access to secretsline 85
[Credential-related source omitted] - Access to secretsline 86
[Credential-related source omitted] - Network accessline 91
# Regex-based curl -X POST https://api.nutrient.io/build \ - Network accessline 92
[Credential-related source omitted] - Access to secretsline 92
[Credential-related source omitted] - Access to secretsline 93
[Credential-related source omitted] - Network accessline 104
[Credential-related source omitted] - Access to secretsline 104
[Credential-related source omitted] - Access to secretsline 105
[Credential-related source omitted] - Network accessline 114
# Self-signed CMS signature curl -X POST https://api.nutrient.io/build \ - Network accessline 115
[Credential-related source omitted] - Access to secretsline 115
[Credential-related source omitted] - Access to secretsline 116
[Credential-related source omitted] - Network accessline 125
[Credential-related source omitted] - Access to secretsline 125
[Credential-related source omitted] - Access to secretsline 126
[Credential-related source omitted] - Access to secretsline 143
[Credential-related source omitted] - Network accessline 163
* [API 游乐场](https://dashboard.nutrient.io/processor-api/playground/) - Network accessline 164
* [完整 API 文档](https://www.nutrient.io/guides/dws-processor/) - Network accessline 165
* [npm MCP 服务器](https://www.npmjs.com/package/@nutrient-sdk/dws-mcp-server)
docs/zh-CN/skills/project-guidelines-example/SKILL.md
- Network accessline 11
基于一个真实的生产应用程序:[Zenith](https://zenith.chat) - 由 AI 驱动的客户发现平台。 - Network accessline 133
): Promise<ApiResponse<T>> { try { const response = await fetch(`/api${endpoint}`, { - Network accessline 134
try { const response = await fetch(`/api${endpoint}`, { ...options, - Network accessline 135
const response = await fetch(`/api${endpoint}`, { - Network accessline 249
@pytest.fixture async def client(): async with AsyncClient(app=app, base_url="http://test") as ac: - Network accessline 250
async def client(): async with AsyncClient(app=app, base_url="http://test") as ac: yield ac - Network accessline 251
async with AsyncClient(app=app, base_url="http://test") as ac: - Network accessline 322
# Frontend (.env.local) NEXT_PUBLIC_API_URL=https://api.example.com - Network accessline 323
NEXT_PUBLIC_API_URL=https://api.example.com - Network accessline 324
NEXT_PUBLIC_SUPABASE_URL=https://xxx.supabase.co - Network accessline 328
[Credential-related source omitted] - Network accessline 329
[Credential-related source omitted] - Access to secretsline 329
[Credential-related source omitted] - Network accessline 330
SUPABASE_URL=https://xxx.supabase.co
docs/zh-CN/skills/python-patterns/SKILL.md
- Network accessline 449
"""Fetch a URL (I/O-bound operation).""" import urllib.request with urllib.request.urlopen(url) as response: - Network accessline 450
import urllib.request with urllib.request.urlopen(url) as response: return response.read().decode() - Network accessline 451
with urllib.request.urlopen(url) as response: - Network accessline 488
"""Fetch a URL asynchronously.""" import aiohttp async with aiohttp.ClientSession() as session: - Network accessline 489
import aiohttp async with aiohttp.ClientSession() as session: async with session.get(url) as response: - Network accessline 490
async with aiohttp.ClientSession() as session:
docs/zh-CN/skills/python-testing/SKILL.md
- Network accessline 322
@pytest.mark.integration def test_api_integration(): response = requests.get("https://api.example.com") - Network accessline 323
def test_api_integration(): response = requests.get("https://api.example.com") assert response.status_code == 200 - Network accessline 324
response = requests.get("https://api.example.com") - Access to secretsline 457
[Credential-related source omitted] - Access to secretsline 463
[Credential-related source omitted]
docs/zh-CN/skills/security-review/SKILL.md
- Access to secretsline 35
[Credential-related source omitted] - Access to secretsline 40
[Credential-related source omitted] - Network accessline 235
img-src 'self' data: https:; font-src 'self'; connect-src 'self' https://api.example.com; - Network accessline 236
font-src 'self'; connect-src 'self' https://api.example.com; `.replace(/\s{2,}/g, ' ').trim() - Network accessline 237
connect-src 'self' https://api.example.com; - Network accessline 460
// Test authentication test('requires authentication', async () => { const response = await fetch('/api/protected') - Network accessline 461
test('requires authentication', async () => { const response = await fetch('/api/protected') expect(response.status).toBe(401) - Network accessline 462
const response = await fetch('/api/protected') - Network accessline 466
// Test authorization test('requires admin role', async () => { const response = await fetch('/api/admin', { - Network accessline 467
[Credential-related source omitted] - Network accessline 468
const response = await fetch('/api/admin', { - Network accessline 474
// Test input validation test('rejects invalid input', async () => { const response = await fetch('/api/users', { - Network accessline 475
test('rejects invalid input', async () => { const response = await fetch('/api/users', { method: 'POST', - Network accessline 476
const response = await fetch('/api/users', { - Network accessline 484
test('enforces rate limits', async () => { const requests = Array(101).fill(null).map(() => fetch('/api/endpoint') - Network accessline 485
const requests = Array(101).fill(null).map(() => fetch('/api/endpoint') ) - Network accessline 486
fetch('/api/endpoint') - Network accessline 520
* [OWASP Top 10](https://owasp.org/www-project-top-ten/) - Network accessline 521
* [Next.js 安全](https://nextjs.org/docs/security) - Network accessline 522
* [Supabase 安全](https://supabase.com/docs/guides/auth) - Network accessline 523
* [Web 安全学院](https://portswigger.net/web-security)
docs/zh-CN/skills/security-review/cloud-infrastructure-security.md
- Access to secretsline 76
[Credential-related source omitted] - Network accessline 240
// ✅ CORRECT: Cloudflare Workers with security headers export default { async fetch(request: Request): Promise<Response> { - Network accessline 241
export default { async fetch(request: Request): Promise<Response> { const response = await fetch(request); - Network accessline 242
async fetch(request: Request): Promise<Response> { - Network accessline 243
const response = await fetch(request); - Network accessline 355
* [AWS 安全最佳实践](https://aws.amazon.com/security/best-practices/) - Network accessline 356
* [CIS AWS 基础基准](https://www.cisecurity.org/benchmark/amazon_web_services) - Network accessline 357
* [Cloudflare 安全文档](https://developers.cloudflare.com/security/) - Network accessline 358
* [OWASP 云安全](https://owasp.org/www-project-cloud-security/) - Network accessline 359
* [Terraform 安全最佳实践](https://www.terraform.io/docs/cloud/guides/recommended-practices/)
docs/zh-CN/skills/security-scan/SKILL.md
- Network accessline 9
使用 [AgentShield](https://github.com/affaan-m/agentshield) 审计您的 Claude Code 配置中的安全问题。 - Access to secretsline 96
[Credential-related source omitted] - Access to secretsline 97
[Credential-related source omitted] - Network accessline 171
* **GitHub**: [github.com/affaan-m/agentshield](https://github.com/affaan-m/agentshield) - Network accessline 172
* **npm**: [npmjs.com/package/ecc-agentshield](https://www.npmjs.com/package/ecc-agentshield)
docs/zh-CN/skills/springboot-security/SKILL.md
- Network accessline 168
cloud: vault: uri: https://vault.example.com - Network accessline 169
[Credential-related source omitted] - Network accessline 170
uri: https://vault.example.com - Access to secretsline 171
[Credential-related source omitted] - Network accessline 193
public CorsConfigurationSource corsConfigurationSource() { CorsConfiguration config = new CorsConfiguration(); config.setAllowedOrigins(List.of("https://app.example.com")); - Network accessline 194
CorsConfiguration config = new CorsConfiguration(); config.setAllowedOrigins(List.of("https://app.example.com")); config.setAllowedMethods(List.of("GET", "POST", "PUT", "DELETE")); - Network accessline 195
config.setAllowedOrigins(List.of("https://app.example.com"));
docs/zh-CN/skills/springboot-verification/SKILL.md
- Access to secretsline 172
[Credential-related source omitted]
docs/zh-CN/skills/strategic-compact/SKILL.md
- Network accessline 104
* [长篇指南](https://x.com/affaanmustafa/status/2014040193557471352) — Token 优化部分
docs/zh-CN/skills/tdd-workflow/SKILL.md
- Network accessline 168
describe('GET /api/markets', () => { it('returns markets successfully', async () => { const request = new NextRequest('http://localhost/api/markets') - Network accessline 169
it('returns markets successfully', async () => { const request = new NextRequest('http://localhost/api/markets') const response = await GET(request) - Network accessline 170
const request = new NextRequest('http://localhost/api/markets') - Network accessline 179
it('validates query parameters', async () => { const request = new NextRequest('http://localhost/api/markets?limit=invalid') - Network accessline 180
const request = new NextRequest('http://localhost/api/markets?limit=invalid') - Network accessline 186
it('handles database errors gracefully', async () => { // Mock database failure const request = new NextRequest('http://localhost/api/markets') - Network accessline 187
// Mock database failure const request = new NextRequest('http://localhost/api/markets') // Test error handling - Network accessline 188
const request = new NextRequest('http://localhost/api/markets')
docs/zh-CN/skills/verification-loop/SKILL.md
- Access to secretsline 77
[Credential-related source omitted]
docs/zh-TW/skills/backend-patterns/SKILL.md
- Access to secretsline 350
[Credential-related source omitted] - Network accessline 432
): Promise<boolean> { const now = Date.now() const requests = this.requests.get(identifier) || [] - Network accessline 434
const requests = this.requests.get(identifier) || [] - Network accessline 436
// 移除視窗外的舊請求 const recentRequests = requests.filter(time => now - time < windowMs) - Network accessline 437
const recentRequests = requests.filter(time => now - time < windowMs) - Network accessline 443
// 新增當前請求 recentRequests.push(now) this.requests.set(identifier, recentRequests) - Network accessline 445
this.requests.set(identifier, recentRequests)
docs/zh-TW/skills/coding-standards/SKILL.md
- Network accessline 86
async function fetchData(url: string) { try { const response = await fetch(url) - Network accessline 88
const response = await fetch(url) - Network accessline 101
// ❌ 不良:無錯誤處理 async function fetchData(url) { const response = await fetch(url) - Network accessline 102
async function fetchData(url) { const response = await fetch(url) return response.json() - Network accessline 103
const response = await fetch(url)
docs/zh-TW/skills/continuous-learning-v2/SKILL.md
docs/zh-TW/skills/continuous-learning/SKILL.md
- Network accessline 79
- [Longform Guide](https://x.com/affaanmustafa/status/2014040193557471352) - 持續學習章節
docs/zh-TW/skills/frontend-patterns/SKILL.md
- Network accessline 103
useEffect(() => { fetch(url) - Network accessline 104
fetch(url) - Network accessline 188
const { data: markets, loading, error, refetch } = useQuery( 'markets', () => fetch('/api/markets').then(r => r.json()), - Network accessline 189
'markets', () => fetch('/api/markets').then(r => r.json()), { - Network accessline 190
() => fetch('/api/markets').then(r => r.json()),
docs/zh-TW/skills/golang-patterns/SKILL.md
- Network accessline 272
ch := make(chan []byte) go func() { data, _ := fetch(url) - Network accessline 273
go func() { data, _ := fetch(url) ch <- data // 如果無接收者會永遠阻塞 - Network accessline 274
data, _ := fetch(url) - Network accessline 282
ch := make(chan []byte, 1) // 帶緩衝的 channel go func() { data, err := fetch(url) - Network accessline 283
go func() { data, err := fetch(url) if err != nil { - Network accessline 284
data, err := fetch(url)
docs/zh-TW/skills/iterative-retrieval/SKILL.md
- Network accessline 200
- [Longform Guide](https://x.com/affaanmustafa/status/2014040193557471352) - 子 agent 協調章節
docs/zh-TW/skills/project-guidelines-example/SKILL.md
- Network accessline 5
基於真實生產應用程式:[Zenith](https://zenith.chat) - AI 驅動的客戶探索平台。 - Network accessline 126
): Promise<ApiResponse<T>> { try { const response = await fetch(`/api${endpoint}`, { - Network accessline 127
try { const response = await fetch(`/api${endpoint}`, { ...options, - Network accessline 128
const response = await fetch(`/api${endpoint}`, { - Network accessline 241
@pytest.fixture async def client(): async with AsyncClient(app=app, base_url="http://test") as ac: - Network accessline 242
async def client(): async with AsyncClient(app=app, base_url="http://test") as ac: yield ac - Network accessline 243
async with AsyncClient(app=app, base_url="http://test") as ac: - Network accessline 313
# 前端(.env.local) NEXT_PUBLIC_API_URL=https://api.example.com - Network accessline 314
NEXT_PUBLIC_API_URL=https://api.example.com - Network accessline 315
NEXT_PUBLIC_SUPABASE_URL=https://xxx.supabase.co - Network accessline 319
[Credential-related source omitted] - Network accessline 320
[Credential-related source omitted] - Access to secretsline 320
[Credential-related source omitted] - Network accessline 321
SUPABASE_URL=https://xxx.supabase.co
docs/zh-TW/skills/security-review/SKILL.md
- Access to secretsline 32
[Credential-related source omitted] - Access to secretsline 37
[Credential-related source omitted] - Network accessline 219
img-src 'self' data: https:; font-src 'self'; connect-src 'self' https://api.example.com; - Network accessline 220
font-src 'self'; connect-src 'self' https://api.example.com; `.replace(/\s{2,}/g, ' ').trim() - Network accessline 221
connect-src 'self' https://api.example.com; - Network accessline 427
// 測試認證 test('requires authentication', async () => { const response = await fetch('/api/protected') - Network accessline 428
test('requires authentication', async () => { const response = await fetch('/api/protected') expect(response.status).toBe(401) - Network accessline 429
const response = await fetch('/api/protected') - Network accessline 433
// 測試授權 test('requires admin role', async () => { const response = await fetch('/api/admin', { - Network accessline 434
[Credential-related source omitted] - Network accessline 435
const response = await fetch('/api/admin', { - Network accessline 441
// 測試輸入驗證 test('rejects invalid input', async () => { const response = await fetch('/api/users', { - Network accessline 442
test('rejects invalid input', async () => { const response = await fetch('/api/users', { method: 'POST', - Network accessline 443
const response = await fetch('/api/users', { - Network accessline 451
test('enforces rate limits', async () => { const requests = Array(101).fill(null).map(() => fetch('/api/endpoint') - Network accessline 452
const requests = Array(101).fill(null).map(() => fetch('/api/endpoint') ) - Network accessline 453
fetch('/api/endpoint') - Network accessline 487
- [OWASP Top 10](https://owasp.org/www-project-top-ten/) - Network accessline 488
- [Next.js Security](https://nextjs.org/docs/security) - Network accessline 489
- [Supabase Security](https://supabase.com/docs/guides/auth) - Network accessline 490
- [Web Security Academy](https://portswigger.net/web-security)
docs/zh-TW/skills/security-review/cloud-infrastructure-security.md
- Access to secretsline 76
[Credential-related source omitted] - Network accessline 240
// ✅ 正確:帶安全標頭的 Cloudflare Workers export default { async fetch(request: Request): Promise<Response> { - Network accessline 241
export default { async fetch(request: Request): Promise<Response> { const response = await fetch(request); - Network accessline 242
async fetch(request: Request): Promise<Response> { - Network accessline 243
const response = await fetch(request); - Network accessline 355
- [AWS Security Best Practices](https://aws.amazon.com/security/best-practices/) - Network accessline 356
- [CIS AWS Foundations Benchmark](https://www.cisecurity.org/benchmark/amazon_web_services) - Network accessline 357
- [Cloudflare Security Documentation](https://developers.cloudflare.com/security/) - Network accessline 358
- [OWASP Cloud Security](https://owasp.org/www-project-cloud-security/) - Network accessline 359
- [Terraform Security Best Practices](https://www.terraform.io/docs/cloud/guides/recommended-practices/)
docs/zh-TW/skills/strategic-compact/SKILL.md
- Network accessline 62
- [Longform Guide](https://x.com/affaanmustafa/status/2014040193557471352) - Token 優化章節
docs/zh-TW/skills/tdd-workflow/SKILL.md
- Network accessline 152
describe('GET /api/markets', () => { it('returns markets successfully', async () => { const request = new NextRequest('http://localhost/api/markets') - Network accessline 153
it('returns markets successfully', async () => { const request = new NextRequest('http://localhost/api/markets') const response = await GET(request) - Network accessline 154
const request = new NextRequest('http://localhost/api/markets') - Network accessline 163
it('validates query parameters', async () => { const request = new NextRequest('http://localhost/api/markets?limit=invalid') - Network accessline 164
const request = new NextRequest('http://localhost/api/markets?limit=invalid') - Network accessline 170
it('handles database errors gracefully', async () => { // Mock 資料庫失敗 const request = new NextRequest('http://localhost/api/markets') - Network accessline 171
// Mock 資料庫失敗 const request = new NextRequest('http://localhost/api/markets') // 測試錯誤處理 - Network accessline 172
const request = new NextRequest('http://localhost/api/markets')
docs/zh-TW/skills/verification-loop/SKILL.md
- Access to secretsline 64
[Credential-related source omitted]
hooks/hooks.json
scripts/claw.js
skills/autonomous-loops/SKILL.md
- Dangerous shell operationline 90
rm .claude-context.md - Dangerous shell operationline 234
curl -fsSL https://raw.githubusercontent.com/AnandChowdhary/continuous-claude/HEAD/install.sh | bash - Network accessline 234
curl -fsSL https://raw.githubusercontent.com/AnandChowdhary/continuous-claude/HEAD/install.sh | bash
skills/backend-patterns/SKILL.md
- Access to secretsline 361
[Credential-related source omitted] - Network accessline 443
): Promise<boolean> { const now = Date.now() const requests = this.requests.get(identifier) || [] - Network accessline 445
const requests = this.requests.get(identifier) || [] - Network accessline 447
// 移除窗口期之前的旧请求 const recentRequests = requests.filter(time => now - time < windowMs) - Network accessline 448
const recentRequests = requests.filter(time => now - time < windowMs) - Network accessline 454
// 添加当前请求 recentRequests.push(now) this.requests.set(identifier, recentRequests) - Network accessline 456
this.requests.set(identifier, recentRequests)
skills/coding-standards/SKILL.md
- Network accessline 96
async function fetchData(url: string) { try { const response = await fetch(url) - Network accessline 98
const response = await fetch(url) - Network accessline 111
// ❌ 劣:没有错误处理 async function fetchData(url) { const response = await fetch(url) - Network accessline 112
async function fetchData(url) { const response = await fetch(url) return response.json() - Network accessline 113
const response = await fetch(url)
skills/configure-ecc/SKILL.md
- Dangerous shell operationline 31
rm -rf /tmp/everything-claude-code - Network accessline 31
rm -rf /tmp/everything-claude-code git clone https://github.com/affaan-m/everything-claude-code.git /tmp/everything-claude-code - Network accessline 32
git clone https://github.com/affaan-m/everything-claude-code.git /tmp/everything-claude-code - Dangerous shell operationline 283
rm -rf /tmp/everything-claude-code
skills/continuous-learning-v2/SKILL.md
skills/continuous-learning-v2/agents/observer.md
- Network accessline 193
当直觉从技能创建器(存储库分析)导入时,它们具有: - `source: "repo-analysis"` - `source_repo: "https://github.com/..."` - Network accessline 194
- `source: "repo-analysis"` - `source_repo: "https://github.com/..."` - `scope: "project"`(因为它们来自特定存储库) - Network accessline 195
- `source_repo: "https://github.com/..."`
skills/continuous-learning-v2/agents/start-observer.sh
- Executable scriptline 1
#!/bin/bash - Access to secretsline 50
[Credential-related source omitted] - Dangerous shell operationline 84
rm -f "$PID_FILE" - Dangerous shell operationline 88
rm -f "$PID_FILE" - Dangerous shell operationline 109
rm -f "$PID_FILE" - Dangerous shell operationline 133
rm -f "$PID_FILE" - Dangerous shell operationline 162
rm -f "$PID_FILE"
skills/continuous-learning-v2/hooks/observe.sh
- Executable scriptline 1
#!/bin/bash - Executable scriptline 1
#!/bin/bash - Executable scriptline 1
#!/bin/bash - Executable scriptline 1
#!/bin/bash - Access to secretsline 88
[Credential-related source omitted] - Access to secretsline 88
[Credential-related source omitted] - Access to secretsline 88
[Credential-related source omitted] - Access to secretsline 88
[Credential-related source omitted] - Access to secretsline 134
[Credential-related source omitted] - Access to secretsline 134
[Credential-related source omitted] - Access to secretsline 134
[Credential-related source omitted] - Access to secretsline 134
[Credential-related source omitted] - Access to secretsline 161
[Credential-related source omitted] - Access to secretsline 161
[Credential-related source omitted] - Access to secretsline 161
[Credential-related source omitted] - Access to secretsline 161
[Credential-related source omitted] - Access to secretsline 165
[Credential-related source omitted] - Access to secretsline 165
[Credential-related source omitted] - Access to secretsline 165
[Credential-related source omitted] - Access to secretsline 165
[Credential-related source omitted] - Access to secretsline 166
[Credential-related source omitted] - Access to secretsline 166
[Credential-related source omitted] - Access to secretsline 166
[Credential-related source omitted] - Access to secretsline 166
[Credential-related source omitted]
skills/continuous-learning-v2/scripts/detect-project.sh
- Executable scriptline 1
#!/bin/bash - Access to secretsline 105
[Credential-related source omitted] - Access to secretsline 115
[Credential-related source omitted] - Access to secretsline 122
[Credential-related source omitted] - Access to secretsline 123
[Credential-related source omitted] - Access to secretsline 124
[Credential-related source omitted] - Access to secretsline 125
[Credential-related source omitted]
skills/continuous-learning-v2/scripts/instinct-cli.py
- Executable scriptline 1
#!/usr/bin/env python3 - Access to secretsline 111
[Credential-related source omitted] - Network accessline 440
print(f"Fetching from URL: {source}") try: with urllib.request.urlopen(source) as response: - Network accessline 441
try: with urllib.request.urlopen(source) as response: content = response.read().decode('utf-8') - Network accessline 442
with urllib.request.urlopen(source) as response: - Instruction override signalline 1100
import_parser.add_argument('source', help='File path or URL') import_parser.add_argument('--dry-run', action='store_true', help='Preview without importing') import_parser.add_argument('--force', action='store_true', help='Skip confi - Instruction override signalline 1101
import_parser.add_argument('--dry-run', action='store_true', help='Preview without importing') import_parser.add_argument('--force', action='store_true', help='Skip confirmation') import_parser.add_argument('--min-confidence', type= - Instruction override signalline 1102
import_parser.add_argument('--force', action='store_true', help='Skip confirmation') - Instruction override signalline 1120
promote_parser = subparsers.add_parser('promote', help='Promote project instincts to global scope') promote_parser.add_argument('instinct_id', nargs='?', help='Specific instinct ID to promote') promote_parser.add_argument('--force', - Instruction override signalline 1121
promote_parser.add_argument('instinct_id', nargs='?', help='Specific instinct ID to promote') promote_parser.add_argument('--force', action='store_true', help='Skip confirmation') promote_parser.add_argument('--dry-run', action='sto - Instruction override signalline 1122
promote_parser.add_argument('--force', action='store_true', help='Skip confirmation')
skills/continuous-learning-v2/scripts/test_parse_instinct.py
- Executable scriptline 1
Executable file - Network accessline 137
"name": pname, "root": str(tree["root"] / "fake-repo"), "remote": "https://github.com/test/test-project.git", - Network accessline 138
"root": str(tree["root"] / "fake-repo"), "remote": "https://github.com/test/test-project.git", "project_dir": project_dir, - Network accessline 139
"remote": "https://github.com/test/test-project.git", - Network accessline 355
return SimpleNamespace(returncode=0, stdout=str(fake_repo) + "\n", stderr="") if "get-url" in cmd: return SimpleNamespace(returncode=0, stdout="https://github.com/test/my-repo.git\n", stderr="") - Network accessline 356
if "get-url" in cmd: return SimpleNamespace(returncode=0, stdout="https://github.com/test/my-repo.git\n", stderr="") return SimpleNamespace(returncode=1, stdout="", stderr="") - Network accessline 357
return SimpleNamespace(returncode=0, stdout="https://github.com/test/my-repo.git\n", stderr="") - Network accessline 665
"name": "my-app", "root": "/home/user/my-app", "remote": "https://github.com/user/my-app.git", - Network accessline 666
"root": "/home/user/my-app", "remote": "https://github.com/user/my-app.git", "last_seen": "2025-01-15T12:00:00Z", - Network accessline 667
"remote": "https://github.com/user/my-app.git", - Network accessline 950
def test_update_registry_atomic_replaces_file(patch_globals): tree = patch_globals _update_registry("abc123", "demo", "/repo", "https://example.com/repo.git") - Network accessline 951
tree = patch_globals _update_registry("abc123", "demo", "/repo", "https://example.com/repo.git") data = json.loads(tree["registry_file"].read_text()) - Network accessline 952
_update_registry("abc123", "demo", "/repo", "https://example.com/repo.git")
skills/continuous-learning/SKILL.md
- Network accessline 88
- [长篇指南(The Longform Guide)](https://x.com/affaanmustafa/status/2014040193557471352) - 关于持续学习的章节
skills/continuous-learning/evaluate-session.sh
- Executable scriptline 1
#!/bin/bash
skills/cpp-coding-standards/SKILL.md
- Network accessline 9
源自 [C++ 核心指南 (C++ Core Guidelines)](https://isocpp.github.io/CppCoreGuidelines/CppCoreGuidelines) 的现代 C++ (C++17/20/23) 综合编码规范。强制执行类型安全 (Type safety)、资源安全 (Resource safety)、不变性 (Immutability) 和清晰度。 - Network accessline 371
void run() { try { fetch_data("https://api.example.com"); - Network accessline 372
try { fetch_data("https://api.example.com"); } catch (const NetworkError& e) { - Network accessline 373
fetch_data("https://api.example.com");
skills/cpp-testing/SKILL.md
- Network accessline 163
googletest # Google Test 框架 (官方仓库) URL https://github.com/google/googletest/archive/refs/tags/${GTEST_VERSION}.zip - Network accessline 164
# Google Test 框架 (官方仓库) URL https://github.com/google/googletest/archive/refs/tags/${GTEST_VERSION}.zip ) - Network accessline 165
URL https://github.com/google/googletest/archive/refs/tags/${GTEST_VERSION}.zip
skills/deployment-patterns/SKILL.md
- Network accessline 114
HEALTHCHECK --interval=30s --timeout=3s --start-period=5s --retries=3 \ CMD wget --no-verbose --tries=1 --spider http://localhost:3000/health || exit 1 - Network accessline 115
CMD wget --no-verbose --tries=1 --spider http://localhost:3000/health || exit 1 - Network accessline 137
EXPOSE 8080 HEALTHCHECK --interval=30s --timeout=3s CMD wget -qO- http://localhost:8080/health || exit 1 - Network accessline 138
HEALTHCHECK --interval=30s --timeout=3s CMD wget -qO- http://localhost:8080/health || exit 1 - Network accessline 164
HEALTHCHECK --interval=30s --timeout=3s CMD python -c "import urllib.request; urllib.request.urlopen('http://localhost:8000/health/')" || exit 1 - Access to secretsline 339
[Credential-related source omitted]
skills/django-patterns/SKILL.md
- Access to secretsline 61
[Credential-related source omitted]
skills/django-security/SKILL.md
- Access to secretsline 29
[Credential-related source omitted] - Access to secretsline 49
[Credential-related source omitted] - Network accessline 340
CSRF_COOKIE_HTTPONLY = True # 防止 JavaScript 访问 CSRF_COOKIE_SAMESITE = 'Lax' # 在某些情况下防止 CSRF CSRF_TRUSTED_ORIGINS = ['https://example.com'] # 受信任的域名 - Network accessline 342
CSRF_TRUSTED_ORIGINS = ['https://example.com'] # 受信任的域名 - Network accessline 367
fetch('/api/endpoint/', { - Network accessline 424
# 在生产环境中为媒体文件使用独立域名 MEDIA_DOMAIN = 'https://media.example.com' - Network accessline 425
MEDIA_DOMAIN = 'https://media.example.com' - Network accessline 492
# settings.py CSP_DEFAULT_SRC = "'self'" CSP_SCRIPT_SRC = "'self' https://cdn.example.com" - Network accessline 493
CSP_DEFAULT_SRC = "'self'" CSP_SCRIPT_SRC = "'self' https://cdn.example.com" CSP_STYLE_SRC = "'self' 'unsafe-inline'" - Network accessline 494
CSP_SCRIPT_SRC = "'self' https://cdn.example.com" - Network accessline 495
CSP_STYLE_SRC = "'self' 'unsafe-inline'" CSP_IMG_SRC = "'self' data: https:" CSP_CONNECT_SRC = "'self' https://api.example.com" - Network accessline 497
CSP_CONNECT_SRC = "'self' https://api.example.com" - Access to secretsline 529
[Credential-related source omitted] - Access to secretsline 532
[Credential-related source omitted] - Access to secretsline 536
[Credential-related source omitted]
skills/django-verification/SKILL.md
skills/docker-patterns/SKILL.md
- Network accessline 113
ENV NODE_ENV=production EXPOSE 3000 HEALTHCHECK --interval=30s --timeout=3s CMD wget -qO- http://localhost:3000/health || exit 1 - Network accessline 114
EXPOSE 3000 HEALTHCHECK --interval=30s --timeout=3s CMD wget -qO- http://localhost:3000/health || exit 1 CMD ["node", "dist/server.js"] - Network accessline 115
HEALTHCHECK --interval=30s --timeout=3s CMD wget -qO- http://localhost:3000/health || exit 1 - Access to secretsline 266
[Credential-related source omitted] - Access to secretsline 268
[Credential-related source omitted] - Access to secretsline 281
[Credential-related source omitted] - Access to secretsline 289
[Credential-related source omitted] - Network accessline 336
# 检查连通性 docker compose exec app wget -qO- http://api:3000/health - Network accessline 337
docker compose exec app wget -qO- http://api:3000/health - Access to secretsline 363
[Credential-related source omitted]
skills/e2e-testing/SKILL.md
- Network accessline 115
], use: { baseURL: process.env.BASE_URL || 'http://localhost:3000', - Network accessline 116
use: { baseURL: process.env.BASE_URL || 'http://localhost:3000', trace: 'on-first-retry', - Network accessline 117
baseURL: process.env.BASE_URL || 'http://localhost:3000', - Network accessline 130
webServer: { command: 'npm run dev', url: 'http://localhost:3000', - Network accessline 131
command: 'npm run dev', url: 'http://localhost:3000', reuseExistingServer: !process.env.CI, - Network accessline 132
url: 'http://localhost:3000',
skills/frontend-patterns/SKILL.md
- Network accessline 114
useEffect(() => { fetch(url) - Network accessline 115
fetch(url) - Network accessline 199
const { data: markets, loading, error, refetch } = useQuery( 'markets', () => fetch('/api/markets').then(r => r.json()), - Network accessline 200
'markets', () => fetch('/api/markets').then(r => r.json()), { - Network accessline 201
() => fetch('/api/markets').then(r => r.json()),
skills/golang-patterns/SKILL.md
- Network accessline 273
ch := make(chan []byte) go func() { data, _ := fetch(url) - Network accessline 274
go func() { data, _ := fetch(url) ch <- data // 如果没有接收者,将永久阻塞 - Network accessline 275
data, _ := fetch(url) - Network accessline 283
ch := make(chan []byte, 1) // 使用缓冲通道 go func() { data, err := fetch(url) - Network accessline 284
go func() { data, err := fetch(url) if err != nil { - Network accessline 285
data, err := fetch(url)
skills/iterative-retrieval/SKILL.md
- Network accessline 211
- [长篇指南 (The Longform Guide)](https://x.com/affaanmustafa/status/2014040193557471352) —— 子智能体编排部分
skills/nutrient-document-processing/SKILL.md
- Network accessline 9
使用 [Nutrient DWS Processor API](https://www.nutrient.io/api/) 处理文档。转换格式、提取文本和表格、对扫描文档进行 OCR 光学字符识别、脱敏个人身份信息(PII)、添加水印、进行数字签名以及填充 PDF 表单。 - Network accessline 13
在 **[nutrient.io](https://dashboard.nutrient.io/sign_up/?product=processor)** 获取免费 API 密钥。 - Access to secretsline 16
[Credential-related source omitted] - Network accessline 19
所有请求均以 multipart POST 形式发送至 `https://api.nutrient.io/build`,并包含一个 `instructions` JSON 字段。 - Network accessline 26
# DOCX 转 PDF curl -X POST https://api.nutrient.io/build \ - Network accessline 27
[Credential-related source omitted] - Access to secretsline 27
[Credential-related source omitted] - Access to secretsline 28
[Credential-related source omitted] - Network accessline 33
# PDF 转 DOCX curl -X POST https://api.nutrient.io/build \ - Network accessline 34
[Credential-related source omitted] - Access to secretsline 34
[Credential-related source omitted] - Access to secretsline 35
[Credential-related source omitted] - Network accessline 40
# HTML 转 PDF curl -X POST https://api.nutrient.io/build \ - Network accessline 41
[Credential-related source omitted] - Access to secretsline 41
[Credential-related source omitted] - Access to secretsline 42
[Credential-related source omitted] - Network accessline 53
# 提取纯文本 curl -X POST https://api.nutrient.io/build \ - Network accessline 54
[Credential-related source omitted] - Access to secretsline 54
[Credential-related source omitted] - Access to secretsline 55
[Credential-related source omitted] - Network accessline 60
# 将表格提取为 Excel curl -X POST https://api.nutrient.io/build \ - Network accessline 61
[Credential-related source omitted] - Access to secretsline 61
[Credential-related source omitted] - Access to secretsline 62
[Credential-related source omitted] - Network accessline 71
# OCR 转为可搜索的 PDF(支持 100 多种语言) curl -X POST https://api.nutrient.io/build \ - Network accessline 72
[Credential-related source omitted] - Access to secretsline 72
[Credential-related source omitted] - Access to secretsline 73
[Credential-related source omitted] - Network accessline 79
语言:支持 100 多种语言,通过 ISO 639-2 代码指定(例如 `eng`, `deu`, `fra`, `spa`, `jpn`, `kor`, `chi_sim`, `chi_tra`, `ara`, `hin`, `rus`)。也可以使用完整的语言名称,如 `english` 或 `german`。请参阅[完整的 OCR 语言对照表](https://www.nutrient.io/guides/document-engine/ocr/language-supp - Network accessline 84
# 基于模式(SSN, 电子邮件) curl -X POST https://api.nutrient.io/build \ - Network accessline 85
[Credential-related source omitted] - Access to secretsline 85
[Credential-related source omitted] - Access to secretsline 86
[Credential-related source omitted] - Network accessline 91
# 基于正则表达式 curl -X POST https://api.nutrient.io/build \ - Network accessline 92
[Credential-related source omitted] - Access to secretsline 92
[Credential-related source omitted] - Access to secretsline 93
[Credential-related source omitted] - Network accessline 104
[Credential-related source omitted] - Access to secretsline 104
[Credential-related source omitted] - Access to secretsline 105
[Credential-related source omitted] - Network accessline 114
# 自签名 CMS 签名 curl -X POST https://api.nutrient.io/build \ - Network accessline 115
[Credential-related source omitted] - Access to secretsline 115
[Credential-related source omitted] - Access to secretsline 116
[Credential-related source omitted] - Network accessline 125
[Credential-related source omitted] - Access to secretsline 125
[Credential-related source omitted] - Access to secretsline 126
[Credential-related source omitted] - Access to secretsline 143
[Credential-related source omitted] - Network accessline 163
- [API 游乐场 (API Playground)](https://dashboard.nutrient.io/processor-api/playground/) - Network accessline 164
- [完整 API 文档](https://www.nutrient.io/guides/dws-processor/) - Network accessline 165
- [npm MCP 服务器](https://www.npmjs.com/package/@nutrient-sdk/dws-mcp-server)
skills/plankton-code-quality/SKILL.md
- Network accessline 76
# 将 Plankton 克隆到你的项目(或共享位置) # 注: Plankton 由 @alxfazio 开发 git clone https://github.com/alexfazio/plankton.git - Network accessline 77
# 注: Plankton 由 @alxfazio 开发 git clone https://github.com/alexfazio/plankton.git cd plankton - Network accessline 78
git clone https://github.com/alexfazio/plankton.git
skills/project-guidelines-example/SKILL.md
- Network accessline 11
基于真实生产应用程序:[Zenith](https://zenith.chat) - AI 驱动的客户挖掘平台。 - Network accessline 130
): Promise<ApiResponse<T>> { try { const response = await fetch(`/api${endpoint}`, { - Network accessline 131
try { const response = await fetch(`/api${endpoint}`, { ...options, - Network accessline 132
const response = await fetch(`/api${endpoint}`, { - Network accessline 245
@pytest.fixture async def client(): async with AsyncClient(app=app, base_url="http://test") as ac: - Network accessline 246
async def client(): async with AsyncClient(app=app, base_url="http://test") as ac: yield ac - Network accessline 247
async with AsyncClient(app=app, base_url="http://test") as ac: - Network accessline 317
# 前端 (.env.local) NEXT_PUBLIC_API_URL=https://api.example.com - Network accessline 318
NEXT_PUBLIC_API_URL=https://api.example.com - Network accessline 319
NEXT_PUBLIC_SUPABASE_URL=https://xxx.supabase.co - Network accessline 323
[Credential-related source omitted] - Network accessline 324
[Credential-related source omitted] - Access to secretsline 324
[Credential-related source omitted] - Network accessline 325
SUPABASE_URL=https://xxx.supabase.co
skills/python-patterns/SKILL.md
- Network accessline 449
"""抓取 URL(I/O 密集型操作)。""" import urllib.request with urllib.request.urlopen(url) as response: - Network accessline 450
import urllib.request with urllib.request.urlopen(url) as response: return response.read().decode() - Network accessline 451
with urllib.request.urlopen(url) as response: - Network accessline 488
"""异步抓取 URL。""" import aiohttp async with aiohttp.ClientSession() as session: - Network accessline 489
import aiohttp async with aiohttp.ClientSession() as session: async with session.get(url) as response: - Network accessline 490
async with aiohttp.ClientSession() as session:
skills/python-testing/SKILL.md
- Network accessline 322
@pytest.mark.integration def test_api_integration(): response = requests.get("https://api.example.com") - Network accessline 323
def test_api_integration(): response = requests.get("https://api.example.com") assert response.status_code == 200 - Network accessline 324
response = requests.get("https://api.example.com") - Access to secretsline 457
[Credential-related source omitted] - Access to secretsline 463
[Credential-related source omitted]
skills/security-review/SKILL.md
- Access to secretsline 33
[Credential-related source omitted] - Access to secretsline 38
[Credential-related source omitted] - Network accessline 220
img-src 'self' data: https:; font-src 'self'; connect-src 'self' https://api.example.com; - Network accessline 221
font-src 'self'; connect-src 'self' https://api.example.com; `.replace(/\s{2,}/g, ' ').trim() - Network accessline 222
connect-src 'self' https://api.example.com; - Network accessline 428
// 测试身份验证 test('需要身份验证', async () => { const response = await fetch('/api/protected') - Network accessline 429
test('需要身份验证', async () => { const response = await fetch('/api/protected') expect(response.status).toBe(401) - Network accessline 430
const response = await fetch('/api/protected') - Network accessline 434
// 测试授权 test('需要管理员角色', async () => { const response = await fetch('/api/admin', { - Network accessline 435
[Credential-related source omitted] - Network accessline 436
const response = await fetch('/api/admin', { - Network accessline 442
// 测试输入验证 test('拒绝无效输入', async () => { const response = await fetch('/api/users', { - Network accessline 443
test('拒绝无效输入', async () => { const response = await fetch('/api/users', { method: 'POST', - Network accessline 444
const response = await fetch('/api/users', { - Network accessline 452
test('执行速率限制', async () => { const requests = Array(101).fill(null).map(() => fetch('/api/endpoint') - Network accessline 453
const requests = Array(101).fill(null).map(() => fetch('/api/endpoint') ) - Network accessline 454
fetch('/api/endpoint') - Network accessline 488
- [OWASP Top 10](https://owasp.org/www-project-top-ten/) - Network accessline 489
- [Next.js 安全指南](https://nextjs.org/docs/security) - Network accessline 490
- [Supabase 安全指南](https://supabase.com/docs/guides/auth) - Network accessline 491
- [Web Security Academy](https://portswigger.net/web-security)
skills/security-review/cloud-infrastructure-security.md
- Access to secretsline 76
[Credential-related source omitted] - Network accessline 240
// ✅ 正确:带有安全响应头的 Cloudflare Workers export default { async fetch(request: Request): Promise<Response> { - Network accessline 241
export default { async fetch(request: Request): Promise<Response> { const response = await fetch(request); - Network accessline 242
async fetch(request: Request): Promise<Response> { - Network accessline 243
const response = await fetch(request); - Network accessline 355
- [AWS 安全最佳实践](https://aws.amazon.com/security/best-practices/) - Network accessline 356
- [CIS AWS 基础基准](https://www.cisecurity.org/benchmark/amazon_web_services) - Network accessline 357
- [Cloudflare 安全文档](https://developers.cloudflare.com/security/) - Network accessline 358
- [OWASP 云安全](https://owasp.org/www-project-cloud-security/) - Network accessline 359
- [Terraform 安全最佳实践](https://www.terraform.io/docs/cloud/guides/recommended-practices/)
skills/security-scan/SKILL.md
- Network accessline 9
使用 [AgentShield](https://github.com/affaan-m/agentshield) 审计您的 Claude Code 配置安全问题。 - Access to secretsline 95
[Credential-related source omitted] - Access to secretsline 96
[Credential-related source omitted] - Network accessline 164
- **GitHub**: [github.com/affaan-m/agentshield](https://github.com/affaan-m/agentshield) - Network accessline 165
- **npm**: [npmjs.com/package/ecc-agentshield](https://www.npmjs.com/package/ecc-agentshield)
skills/skill-stocktake/scripts/quick-diff.sh
skills/skill-stocktake/scripts/save-results.sh
skills/skill-stocktake/scripts/scan.sh
skills/springboot-security/SKILL.md
- Network accessline 168
cloud: vault: uri: https://vault.example.com - Network accessline 169
[Credential-related source omitted] - Network accessline 170
uri: https://vault.example.com - Access to secretsline 171
[Credential-related source omitted] - Network accessline 193
public CorsConfigurationSource corsConfigurationSource() { CorsConfiguration config = new CorsConfiguration(); config.setAllowedOrigins(List.of("https://app.example.com")); - Network accessline 194
CorsConfiguration config = new CorsConfiguration(); config.setAllowedOrigins(List.of("https://app.example.com")); config.setAllowedMethods(List.of("GET", "POST", "PUT", "DELETE")); - Network accessline 195
config.setAllowedOrigins(List.of("https://app.example.com"));
skills/springboot-verification/SKILL.md
- Access to secretsline 169
[Credential-related source omitted]
skills/strategic-compact/SKILL.md
- Network accessline 101
- [长篇指南 (The Longform Guide)](https://x.com/affaanmustafa/status/2014040193557471352) — Token 优化章节
skills/strategic-compact/suggest-compact.sh
- Executable scriptline 1
#!/bin/bash
skills/tdd-workflow/SKILL.md
- Network accessline 153
describe('GET /api/markets', () => { it('returns markets successfully', async () => { const request = new NextRequest('http://localhost/api/markets') - Network accessline 154
it('returns markets successfully', async () => { const request = new NextRequest('http://localhost/api/markets') const response = await GET(request) - Network accessline 155
const request = new NextRequest('http://localhost/api/markets') - Network accessline 164
it('validates query parameters', async () => { const request = new NextRequest('http://localhost/api/markets?limit=invalid') - Network accessline 165
const request = new NextRequest('http://localhost/api/markets?limit=invalid') - Network accessline 171
it('handles database errors gracefully', async () => { // 模拟数据库故障 const request = new NextRequest('http://localhost/api/markets') - Network accessline 172
// 模拟数据库故障 const request = new NextRequest('http://localhost/api/markets') // 测试错误处理 - Network accessline 173
const request = new NextRequest('http://localhost/api/markets')
skills/verification-loop/SKILL.md
- Access to secretsline 70
[Credential-related source omitted]
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.
Signal confidence: 500 facts
- Executable script in code of a file that runs.cursor/hooks/after-file-edit.js:1High confidence
- Executable script in code of a file that runs.cursor/hooks/after-file-edit.js:1High confidence
- Executable script in code of a file that runs.cursor/hooks/after-mcp-execution.js:1High confidence
- Executable script in code of a file that runs.cursor/hooks/after-mcp-execution.js:1High confidence
- Executable script in code of a file that runs.cursor/hooks/after-shell-execution.js:1High confidence
- Executable script in code of a file that runs.cursor/hooks/after-shell-execution.js:1High confidence
- Executable script in code of a file that runs.cursor/hooks/after-tab-file-edit.js:1High confidence
- Executable script in code of a file that runs.cursor/hooks/after-tab-file-edit.js:1High confidence
- Executable script in code of a file that runs.cursor/hooks/before-mcp-execution.js:1High confidence
- Executable script in code of a file that runs.cursor/hooks/before-mcp-execution.js:1High confidence
- Executable script in code of a file that runs.cursor/hooks/before-read-file.js:1High confidence
- Executable script in code of a file that runs.cursor/hooks/before-read-file.js:1High confidence
- Executable script in code of a file that runs.cursor/hooks/before-shell-execution.js:1High confidence
- Executable script in code of a file that runs.cursor/hooks/before-shell-execution.js:1High confidence
- Executable script in code of a file that runs.cursor/hooks/before-submit-prompt.js:1High confidence
- Executable script in code of a file that runs.cursor/hooks/before-submit-prompt.js:1High confidence
- Executable script in code of a file that runs.cursor/hooks/before-tab-file-read.js:1High confidence
- Executable script in code of a file that runs.cursor/hooks/before-tab-file-read.js:1High confidence
- Executable script in code of a file that runs.cursor/hooks/pre-compact.js:1High confidence
- Executable script in code of a file that runs.cursor/hooks/pre-compact.js:1High confidence
- Executable script in code of a file that runs.cursor/hooks/session-end.js:1High confidence
- Executable script in code of a file that runs.cursor/hooks/session-end.js:1High confidence
- Executable script in code of a file that runs.cursor/hooks/session-start.js:1High confidence
- Executable script in code of a file that runs.cursor/hooks/session-start.js:1High confidence
- Executable script in code of a file that runs.cursor/hooks/stop.js:1High confidence
- Executable script in code of a file that runs.cursor/hooks/stop.js:1High confidence
- Executable script in code of a file that runs.cursor/hooks/subagent-start.js:1High confidence
- Executable script in code of a file that runs.cursor/hooks/subagent-start.js:1High confidence
- Executable script in code of a file that runs.cursor/hooks/subagent-stop.js:1High confidence
- Executable script in code of a file that runs.cursor/hooks/subagent-stop.js:1High confidence
- Network access in code of documentationcommands/e2e.md:358Low confidence
- Network access in code of documentationcommands/e2e.md:359Low confidence
- Network access in code of documentationcommands/instinct-import.md:28Low confidence
- Network access in code of documentationcommands/instinct-import.md:29Low confidence
- Access to secrets in prose of documentationcommands/pm2.md:29Low confidence
- Network access in prose of documentationcommands/skill-create.md:160Low confidence
- Network access in prose of documentationcommands/skill-create.md:162Low confidence
- Network access in prose of documentationcommands/skill-create.md:174Low confidence
- Access to secrets in code of the SKILL.md: a variable, placeholder or call, not a stored valuebackend-patterns/SKILL.md:350Low confidence
- Network access in code of the SKILL.mdbackend-patterns/SKILL.md:432High confidence
- Network access in code of the SKILL.mdbackend-patterns/SKILL.md:434High confidence
- Network access in code of the SKILL.mdbackend-patterns/SKILL.md:436High confidence
- Network access in code of the SKILL.mdbackend-patterns/SKILL.md:437High confidence
- Network access in code of the SKILL.mdbackend-patterns/SKILL.md:443High confidence
- Network access in code of the SKILL.mdbackend-patterns/SKILL.md:445High confidence
- Network access in code of the SKILL.mdcoding-standards/SKILL.md:90High confidence
- Network access in code of the SKILL.mdcoding-standards/SKILL.md:92High confidence
- Network access in code of the SKILL.mdcoding-standards/SKILL.md:105High confidence
- Network access in code of the SKILL.mdcoding-standards/SKILL.md:106High confidence
- Network access in code of the SKILL.mdcoding-standards/SKILL.md:107High confidence
and 450 more
Only the first 500 facts are listed.
Works with
| Agent | Status | Evidence | Install to |
|---|---|---|---|
| Claude Code | Native | Manifest .claude-plugin/marketplace.json | .claude/skills/<skill-name>/ |
| Codex | Native | Manifest .codex/AGENTS.md | .agents/skills/<skill-name>/ |
| Cursor | Native | Path .cursor/hooks.json | .cursor/skills/<skill-name>/ |
| Gemini CLI | Compatible | Standard SKILL.md docs/ja-JP/skills/backend-patterns/SKILL.md | .gemini/skills/<skill-name>/ |
| GitHub Copilot | Compatible | Standard SKILL.md docs/ja-JP/skills/backend-patterns/SKILL.md | .github/skills/<skill-name>/ |
| OpenCode | Native | Path .opencode/MIGRATION.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.
Add this badge to your README
It updates every night and links to this page.
[](https://hotskills.dev/skill/xu-xiang-everything-claude-code-zh/)