qa
Skill1 starsChanged 7 months agoMITView on GitHub
Systematic QA pass — test the feature, find bugs, report with repro steps
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 13
After implementing a feature
- Distinctive: line 14
Before shipping or creating a PR
- Distinctive: line 15
When you want to verify edge cases were handled
≈ “Common” is an estimate: at least 1 in 5 of the 308,232 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
qa
Invoke this skill to run a structured QA testing pass.
When to use
- After implementing a feature
- Before shipping or creating a PR
- When you want to verify edge cases were handled
What it does
- Identifies what was built (reads recent changes, plan if available)
- Generates a test plan:
- Happy path scenarios
- Edge cases (empty, null, max, concurrent)
- Error/failure paths
- Integration points
- Executes each test case — runs code, reads output, verifies behavior
- For each failure: documents repro steps, expected vs actual
- Reports:
- Health score (0–100)
- Passed / Failed / Skipped counts
- Bug list with repro steps
- Recommendation: SHIP / SHIP WITH NOTES / HOLD
Example
@qa "the new authentication flow"In this repository22 other files it gives its agents.
- analyzeSkill
- autopilotSkill
- cancelSkill
- carefulSkill
- chaosSkill
- checkpointSkill
- decision-reviewSkill
- deep-interviewSkill
- diagnoseSkill
- exploreSkill
- git-masterSkill
- incidentSkill
- noteSkill
- pipelineSkill
- ralphSkill
- ralplanSkill
- resumeSkill
- reviewSkill
- security-reviewSkill
- tddSkill
- teamSkill
- ultraworkSkill
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.