qc
Skill0 starsChanged 2 months agoNo licenceView on GitHub
Before testing anything, gets the project into a known-good running state — runs its test suite and, if it has one, its release build/publish step (commands read from CLAUDE.md, or asked for once and offered back into it), stopping a conflicting running instance first if needed, then launches the built artifact directly (falling back to the run skill only when there's no distinct build output) — hard-stopping and attributing to the relevant issue on any test/build failure. Then guides the user through manually testing a complete feature (issues under issues/<feature-slug>/, all owner:agent/placeholder issues status:done) against SPEC.md, so the user — not the agent — confirms it works. Derives a scenario checklist from the spec and the feature's issues (adding security scenarios when flagged security: true, excluding placeholder details like colors/copy from pass/fail judgment, noting gaps from any open owner:user blocker), drives the already-running app to each scenario, and records verdicts on issues/FEATURES.md. Recommends a full security-review pass once every feature has passed, plus a summary of remaining open issues/placeholders. On any test/build failure or failed scenario, investigates which issue(s) are responsible, writes feedback into them, and reopens them for implement-issue. Use to test/verify a finished feature, or invoke /qc. Requires SPEC.md and a done feature under issues/.
In this repository9 other files it gives its agents.
- doc-to-issuesSkill
- documentationSkill
- implement-backlogSkill
- implement-issueSkill
- interviewSkill
- polishSkill
- reportSkill
- review-issueSkill
- staging-qa-docSkill
The file
Show its rules and text
We split this skill into the rules it gives an agent
21 rules. About 0 are common, 9 are distinctive, and 12 are very specific to this project.
≈0
Common · estimate
Many files like this have a rule of this kind.
≈9
Distinctive · estimate
This author's own choices. Worth a look.
12
Very specific
Tied to their project's names, files or tools. Probably skip.
No licence file, so all rights are reserved — read it at the source. We count its rules but don't quote them. Read them on GitHub.
≈ “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.
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.