test-triage
Skill105 starsChanged 31 days agoMITView on GitHub
Classify failing tests as flaky vs. real regressions and propose a next step for each. Invoke when the user pastes failing test output, asks to triage CI failures, or asks "are these tests flaky".
6 other projects use a version of this.
Adopted by
Most recently taken up by
- MMACABRE/SKILLStheir own version, first seen Nov 8, 2026
- Hoerire/Azurtheir own version, first seen Nov 8, 2026
- niki914/zafirotheir own version, first seen Oct 13, 2026
- openai/pluginstheir own version, first seen Oct 13, 2026
- Thalisu/SKILLStheir own version, first seen Oct 1, 2026
- soumatheusgomes/agentvilletheir own version, first seen Aug 13, 2026
Other versions6 projects use a version of this.
Word for word · 0
None found.
Edited · 0
None found.
Wrote their own version · 6
- openai/plugins★ 7.8ksame name
- niki914/zafiro★ 346same name
- soumatheusgomes/agentville★ 9same name
- Hoerire/Azur★ 2same name
- MMACABRE/SKILLS★ 1same name
- Thalisu/SKILLS★ 1same 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 repository4 other files it gives its agents.
- CLAUDE.mdCLAUDE.md
- changelogSkill
- lint-docsSkill
- pr-describeSkill
The file
We split this skill into the rules it gives an agent
5 rules. 0 are common, 4 are distinctive, and 1 is very specific to this project.
0
Common
Most of the 4 edited versions we read keep these.
4
Distinctive
This author's own choices. Worth a look.
1
Very specific
Tied to their project's names, files or tools. Probably skip.
- Common
- Distinctive
- Very specific
- Distinctive: line 13
Prefer in this order:
- Distinctive: line 14
Test output the user pasted.
- Distinctive: line 20
Read the test file and the code under test.
- Distinctive: line 40
Do not modify code or tests during triage.
- Very specific: line 41
If you can't classify a test in under ~90 seconds of investigation, mark it unknown and say what you'd need.
“Common” is measured: kept by at least 6 in 10 of the 4 edited versions of this file we could read. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.
Files
Test Triage
Given a batch of failing tests, classify each and propose one concrete action per test.
Input sources
Prefer in this order:
- Test output the user pasted.
- A CI log file the user points at (Read it).
- Running the test suite locally — only if the user asks.
For each failing test
- Read the test file and the code under test.
git log -5 --follow <test-file>and the same for the implementation. Look for changes in the last ~24h or the last PR.- Classify:
- Real regression — behavior under test changed in a recent commit, or the assertion is logically correct and the implementation is wrong.
- Flaky — test depends on wall-clock time, ordering, network, randomness, shared global state, or external services without a stub.
- Environmental — passes locally, fails in CI (or vice versa) due to missing env, OS differences, or toolchain versions.
- Stale test — intended behavior changed; the test wasn't updated.
- Propose one action: fix the code, update the test, stub the dependency, add a retry with rationale, delete the test, reproduce locally with
<command>.
Output format
A table, one row per failing test:
| Test | Classification | Likely cause | Proposed action |
Then, below the table, list the tests ranked by fix-first priority (real regressions > stale tests > environmental > flaky-with-high-frequency > low-frequency flakes).
Rules
- Do not modify code or tests during triage. This skill only diagnoses.
- If you can't classify a test in under ~90 seconds of investigation, mark it
unknownand say what you'd need. - Flag any test that looks security-sensitive (auth, crypto, input validation) so the user doesn't wave it through as "flaky."
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.