Test
Document-driven agent pipeline for software R&D: analyze → plan → review → develop → test. Portable skills for Cursor, Claude Code & Codex.
npx -y skills add Colacn/agent-pipeline --skill testAssembled from the repository path, not quoted from the project. Check it against their README if it does not work.
One thing to look at
- 1 stars1 stars. Stars are a popularity signal and not a quality one, but at this level it is likely that nobody has read this closely except its author, and you would be relying on your own review.
What its author says it does
Copied from the file, not written here
Use this skill when validating code changes after develop-stage delivery, including regression focus, release gating, and traceable test evidence. It outputs test reports or ledgers and supports AskQuestion-based issue intake for ambiguous or manual acceptance findings.
SKILL.md
1.5 KB, as published. Nobody here has run it
Test
Instructions
- 完整执行规范见
references/execution-playbook.md。落盘前执行scripts/bootstrap-run.sh<slug>（若尚无 outputs）。 - Inputs：验收 Given/When/Then、
develop改动清单、兼容说明。 - 分层对照：
references/layering-appendix-a.md+ overlay（若有）。 - Evidence：结论须可复现；未测范围必须写明；纪律见
references/test-discipline.md。 - 流水线：
references/workflow-pipeline.md。 - 落盘：每次结束须生成/更新
test.report.md或台账；手动补录见references/manual-intake.md。 - develop 出口后建议
bash scripts/check-run.sh <slug>。
On-demand references
references/test-discipline.md— Prove-It、验证命令纪律references/report-and-ledger-checklist.mdreferences/manual-intake.mdreferences/execution-playbook.md
When not to use
- 无改动说明且无验收线索、无法补材料。