Start every bug-testing run by filling a run manifest, fingerprinting the live build, and confirming access, scope, budgets, and prohibited actions. Use before any QA, bug hunt, regression, or release-gate test of a web app, API, workflow, or agent.
72
90%
Does it follow best practices?
Run evals on this skill
Adds up to 20 points to the overall score
Passed
No findings from the security scan
templates/run-manifest.yaml to runs/<run-id>/manifest.yaml.<meta> build tags, hashed JS bundle names, response headers (x-vercel-id, server, etag), workflow version IDs, and DB migration version. Record expected and observed values. If they differ, stop and report a drift warning.PROGRESS.md, ledger.csv, cleanup.csv, and evidence/.itsablabla/qa-bug-agent-skills
9a6f628
If you maintain this skill, you can claim it as your own. Once claimed, you can manage eval scenarios, bundle related skills, attach documentation or rules, and ensure cross-agent compatibility.