QA
Thoroughly QA a feature against the running platform — bring the stack up, find seeded accounts at every privilege tier, then probe correctness, security, and accessibility, proving each finding before reporting it. Produces a ranked findings list you pick from, fixes what you pick, and hands off to /colormath:ship. Use this whenever the user wants to QA, test, audit, review, or "go through" a feature or area of the platform, asks "what's broken in X" or "is X solid", wants a pre-release or pre-demo check, or mentions a QA round — even when they never say the word "QA".
Works with: Claude Code (native) · Cursor, Codex CLI (manual)
native: this artifact type is that client's own format
Install (Claude Code):
cp -r qa ~/.claude/skills/- tashan score: 42.0
- Adoption: 2 repos
- Upkeep: 64.0
- Freshness: 99.0
- Evidence coverage: 84% of the inputs this score can use — the rest are unknown, and the score is discounted for it
- Health: active
- Contributors: 1
- License: MIT
Security audit
Not scanned yet. We audit npm-published capabilities for known advisories, install-time scripts and permission surface; this one has no npm package we can resolve, or has not reached the queue.
source ↗ · skill:ColorMath/qa
Already running this? npx tashan-cli doctor checks your whole config against the Index — how it works ›
Measured 2026-08-09 · scorer s5 · how · something wrong here?