Individual skill
ship-with-confidence
Professional spec-to-delivery workflow for discussing, planning, designing, implementing, debugging, reviewing, securing, cost-optimizing, verifying, and shipping software changes. Use for features, fixes, refactors, migrations, APIs, expensive cloud or AI integrations, UI/UX work, implementation plans, code review, UAT, or requests to implement/validate work. Adapts ceremony to risk, preserves existing product conventions, requires evidence, security, and API unit-economics review, makes atomic local commits, and permits only one final push after all gates pass. Do not use for a one-line explanation, a purely read-only factual lookup, or a whole-codebase audit of existing code (security-audit for security, code-health-audit for quality, performance, and cost).
skills/ship-with-confidence/SKILL.md
Source commit b0f612844e1aa7d1f2817454d1a5fb60457b8a52
What was checked
- Matches the observed repository HEAD
- Yes
- Scanner rules are current
- No
- Repository scan complete
- No
- Skill scan complete
- Yes
- Observed behavior
- Not checked yet
- Last checked
- Nov 6, 2026
These are observations at the recorded commit, not a guarantee of safety. Review the source before running it.
Install this skill
Choose an agent in your Stack or copy a command below. Commands fetch the pinned commit and copy only this skill directory. Existing destinations are refused. Copying a command does not install anything.
An install command is unavailable: current rules, complete repository and skill scans, an eligible behavior level and a permitted license are required.
Repository context
- Repository stars (not skill ratings)
- 3
- Repository last updated
- Nov 1, 2026
- License
- MIT
Observed agent integration: No specific integration evidence. Standard SKILL.md installation does not imply verified compatibility.
- agent-skills Repository topic
- ai-agents Repository topic
- claude-code Repository topic
- codex Repository topic
- developer-tools Repository topic
- llm Repository topic
- design Derived category
- security Derived category
- engineering Derived category
- operations Derived category
- testing Derived category
- design-interface Derived category
Files and excerpt
File metadata and permitted, redacted excerpts come from the recorded scan. Source links are pinned to that commit.
Browse files
SKILL.mdcore · 4,545 bytesagents/openai.yamlasset · 210 bytesevals/evals.jsonasset · 8,785 bytesevals/implementation-scenarios.jsonasset · 1,599 bytesevals/specialist-routing-baseline.jsonasset · 1,190 bytesevals/specialist-routing-spec.jsonasset · 1,119 bytesevals/specialist-routing-treatment.jsonasset · 1,630 bytesreferences/api-cost.mddoc · 6,529 bytesreferences/contracts.mddoc · 1,106 bytesreferences/debug-review.mddoc · 1,670 bytesreferences/evaluation.mddoc · 1,389 bytesreferences/llm-efficiency.mddoc · 3,706 bytesreferences/memory.mddoc · 924 bytesreferences/resilience.mddoc · 1,038 bytesreferences/security.mddoc · 5,946 bytesreferences/sources.mddoc · 4,932 bytesreferences/specialist-routing.mddoc · 2,604 bytesreferences/specify-design.mddoc · 1,806 bytesreferences/supply-chain.mddoc · 1,224 bytesreferences/tasks-execute.mddoc · 2,260 bytesreferences/ui-ux.mddoc · 2,125 bytesreferences/verify-operate.mddoc · 3,120 bytesreferences/workflow.mddoc · 3,871 bytesscripts/audit_context.pyruns · 2,443 bytesscripts/evaluate_skill.pyruns · 4,030 bytesscripts/final-gate.shruns · 1,358 bytesscripts/final-push.shruns · 368 bytesscripts/git-checkpoint.shruns · 1,013 bytesscripts/project_profile.pyruns · 11,742 bytesscripts/secret_guard.pyruns · 2,983 bytesscripts/test_evaluate_skill.pyruns · 1,091 bytesscripts/test_project_profile.pyruns · 7,101 bytesscripts/test_secret_guard.pyruns · 2,567 bytesscripts/test_validate_evidence.pyruns · 3,798 bytesscripts/validate-install.shruns · 2,483 bytesscripts/validate_evidence.pyruns · 3,054 bytesscripts/validate_skill.pyruns · 2,103 bytes
Read excerpt
# Ship With Confidence
Turn intent into verified software through an adaptive, evidence-first workflow. Keep specialist skills separate and invoke them when the stack or task demands them.
## Non-negotiables
1. Inspect repository instructions and current state before proposing changes.
2. Do not implement an ambiguous high-impact choice. Discuss it first and record the decision.
3. Prefer vertical slices, tests close to behavior, small diffs, and explicit verification criteria.
4. Treat security as a release gate, not an optional cleanup pass.
5. Give every paid or resource-heavy API a unit-economics budget and regression evidence.
6. Preserve an existing design system. A catalog may recommend; it may not silently override product conventions.
7. Commit each completed task locally with explicit paths. Never push checkpoints. Push once, only after final verification passes and only when authorized.
8. Claims require current evidence. Failed or missing evidence counts as failure, not partial credit.