test-driven-change
Skill0 starsChanged 13 days agoMITView on GitHub
Implement a behavior change with tests that demonstrate the requirement and protect regressions. Use for bug fixes, new features, and changes with observable inputs and outputs.
1 other project uses a version of this.
Adopted by
Most recently taken up by
- wannanbigpig/ai-engineering-collaborationtheir own version, first seen Nov 6, 2026
Other versions1 project uses a version of this.
Word for word · 0
None found.
Edited · 0
None found.
Wrote their own version · 1
- wannanbigpig/ai-engineering-collaboration★ 2same name
How matches are found. Word for word: the exact same text. Edited: shares passages with this file (“99% same” means 99% of its five-word phrases also appear here; 10% or more counts). Their own version: similar meaning, or, weakest, the same name. We can’t tell which project had it first. Projects are counted among the 200 most-starred candidates, and mentions are links to the repository we found, up to 50 per site, so both counts are a floor.
In this repository25 other files it gives its agents.
- AGENTS.mdAGENTS.md
- agent-skill-auditSkill
- api-contract-checkSkill
- build-rescueSkill
- change-narrativeSkill
- context-handoffSkill
- data-quality-gateSkill
- dataset-workshopSkill
- dependency-careSkill
- docs-syncSkill
- experiment-ledgerSkill
- failure-forensicsSkill
- model-diff-reviewSkill
- model-eval-designSkill
- multi-agent-crosscheckSkill
- parallel-task-designSkill
- performance-proofSkill
- release-readinessSkill
- repo-scoutSkill
- research-evidence-mapSkill
- review-lensSkill
- safe-migrationSkill
- security-surfaceSkill
- spec-firstSkill
- sql-integrity-checkSkill
The file
We split this skill into the rules it gives an agent
7 rules. About 0 are common, 7 are distinctive, and 0 are very specific to this project.
≈0
Common · estimate
Many files like this have a rule of this kind.
≈7
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 14
Write or adapt the smallest test that captures the desired behavior.
- Distinctive: line 15
Run the targeted test and record the initial result.
- Distinctive: line 17
Add edge cases around boundaries, invalid input, empty states, errors, and backwards compatibility where relevant.
- Distinctive: line 18
Run targeted tests, then the appropriate broader suite, formatter, linter, and type checker when available.
- Distinctive: line 25
Do not weaken assertions, skip failing tests, or mock away the behavior under test just to obtain a green result.
- Distinctive: line 26
Do not claim a test passed if it was not executed.
- Distinctive: line 27
If the repository has no test infrastructure, propose the smallest useful check and disclose the limitation.
≈ “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-Driven Change
Operating rule
A test is evidence only if it can fail for the defect or missing behavior being addressed. Do not add tests that merely repeat the implementation.
Procedure
- Find the project's existing test framework and nearest representative tests. Preserve local conventions.
- Write or adapt the smallest test that captures the desired behavior. For a reported bug, make sure it fails before the fix when practical.
- Run the targeted test and record the initial result. If it does not fail, explain why and improve the test.
- Implement the smallest production change that makes the test pass. Avoid unrelated refactors in the same diff.
- Add edge cases around boundaries, invalid input, empty states, errors, and backwards compatibility where relevant.
- Run targeted tests, then the appropriate broader suite, formatter, linter, and type checker when available.
- Inspect the final diff for changed behavior not covered by tests.
Evidence to report
State which tests were run, their actual results, and any checks not run. Include commands when useful.
Boundaries
- Do not weaken assertions, skip failing tests, or mock away the behavior under test just to obtain a green result.
- Do not claim a test passed if it was not executed.
- If the repository has no test infrastructure, propose the smallest useful check and disclose the limitation.
Does it work?
Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.
Reviews can't be read right now.
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.