customer-bug-to-failing-test
Skill1 starsChanged 3 months agoMITView on GitHub
Turn a customer bug report into a failing automated test before fixing. Use on tickets or Chinese "先写失败测试", "bug 转测试", "红灯测试". Red-first discipline for AI coders.
In this repository9 other files it gives its agents.
- AGENTS.mdAGENTS.md
- agent-diff-ship-checkSkill
- dead-code-safe-deleteSkill
- env-drift-checkSkill
- feature-flag-lifecycleSkill
- flake-vs-bug-triageSkill
- minimal-repro-packSkill
- secret-redact-before-aiSkill
- using-ship-guard-skillsSkill
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 18
Write test that fails on current main for the right reason.
- Distinctive: line 20
Only then implement fix; prove green.
- Distinctive: line 33
Test that passes before fix (useless)
≈ “Common” is an estimate: at least 1 in 5 of the 364,980 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
Customer Bug to Failing Test
Overview
AI often “fixes” without locking behavior. Force red test first, then fix to green.
Steps
- Extract: actor, action, data, expected, actual from the ticket.
- Choose layer: unit / integration / e2e (prefer lowest reliable layer).
- Write test that fails on current main for the right reason.
- Show failure output.
- Only then implement fix; prove green.
- Note residual gaps (e.g. only unit, not e2e).
Exit criteria
- Bug framed as observable behavior
- Failing test added and run (red)
- Failure reason matches bug
- Fix deferred until red is proven (or explicitly skipped by user)
Anti-patterns
- Fix first, test later “if time”
- Test that passes before fix (useless)
Output template
## Bug → test
### Behavior
### Test location
### Red proof
### Next: implement fixDoes 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.

