ship-test
Skill1 starsChanged 7 months agoMITView on GitHub
Comprehensive QA verification pass. Runs verification-before-completion against PRD acceptance criteria, writes missing tests, runs security scan. Produces REVIEW.md.
In this repository43 other files it gives its agents.
- accessibilitySkill
- agent-evalSkill
- agentic-engineeringSkill
- ai-regression-testingSkill
- api-designSkill
- atomic-planningSkill
- backend-patternsSkill
- coding-standards-eccSkill
- context-engineeringSkill
- frontend-patternsSkill
- git-worktreesSkill
- langchain-dependenciesSkill
- langchain-fundamentalsSkill
- langchain-middlewareSkill
- langchain-ragSkill
- langgraph-fundamentalsSkill
- langgraph-persistenceSkill
- minimalist-skillSkill
- output-skillSkill
- redesign-skillSkill
- security-scanSkill
- ship-architectSkill
- ship-autoSkill
- ship-bugfixSkill
- ship-deploySkill
- ship-discoverSkill
- ship-executeSkill
- ship-finish-branchSkill
- ship-newSkill
- ship-planSkill
- ship-researchSkill
- ship-resumeSkill
- ship-reviewSkill
- ship-settingsSkill
- ship-specSkill
- ship-statusSkill
- ship-worktreeSkill
- soft-skillSkill
- systematic-debuggingSkill
- taste-skillSkill
- test-driven-developmentSkill
- two-stage-reviewSkill
- verification-before-completionSkill
The file
We split this skill into the rules it gives an agent
3 rules. About 0 are common, 3 are distinctive, and 0 are very specific to this project.
≈0
Common · estimate
Many files like this have a rule of this kind.
≈3
Distinctive · estimate
This author's own choices. Worth a look.
0
Very specific
Tied to their project's names, files or tools. Probably skip.
- Common
- Distinctive
- Very specific
- Distinctive: line 10
Read PRD acceptance criteria for completed phases.
- Distinctive: line 15
If a criterion says "filter persists in URL params," actually navigate and check
- Distinctive: line 16
If any criterion cannot be verified, flag it — do not assume passing
≈ “Common” is an estimate: at least 1 in 5 of the 350,495 skill files we read have a rule of the same kind, not the same words. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.
Files
Test — Quality assurance verification
Process
- Read PRD acceptance criteria for completed phases.
- Verification-before-completion: Dispatch a verifier subagent that:
- Runs the full test suite and reports ACTUAL results (not summaries)
- Checks EVERY acceptance criterion against observable behavior
- If a criterion says "filter persists in URL params," actually navigate and check
- If any criterion cannot be verified, flag it — do not assume passing
- Missing test coverage: Dispatch a tester subagent that:
- Identifies untested code paths
- Writes additional tests (unit, integration, e2e)
- Targets minimum 80% coverage
- Runs typecheck and linting
- Security scan: Dispatch a security reviewer subagent that:
- Checks against OWASP top 10
- Scans for hardcoded secrets, SQL injection, XSS
- Validates auth/authz patterns
- Checks M-Pesa callback validation (if applicable)
- Save results to
.claude/state/REVIEW.mdorganized by severity (critical → warning → note). - Report summary to user.
- Output: "Run
/bayes-ship:ship-finish-branchto complete the feature branch."
Does it work?
Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.
No reviews yet
People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.
- It worked
- Partly
- It didn't
Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.
Your trail
Files you open will collect here, so you can find them again.
Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.
Now do this for your own.
Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.