Menu
O SkillsMP coletou 10 skills de doidor/agentrig. Abra uma skill para revisar a origem e os detalhes.
Mostrando 10 de 10 skills coletadas.
Read PR review feedback, fix or reject each requested change, reply per thread, resolve every thread, and verify zero threads remain.
Idioma do texto original: inglês
Never cast an approving review on a PR your own (shared) agent identity authored — approval must come from an independent reviewer.
Idioma do texto original: inglês
Rebase the PR branch onto the default branch, resolve conflicts keeping both intents, and verify mergeability before pushing.
Idioma do texto original: inglês
Evaluate THIS repository's agent harness — a deterministic structure audit (A1) plus content quality probes (A2), plus an isolated producer/judge dynamic eval (B) with paired sign-test A/B variant comparison.
Idioma do texto original: inglês
Admission bar and structure for writing a new skill, so the skill library stays lean and discoverable.
Idioma do texto original: inglês
Turn a reviewer/judge failure into an instruction-surface change that passes a prevention test.
Idioma do texto original: inglês
Record a newly-discovered gotcha to `.agents/wiki/` BEFORE handoff — the harness's feedback loop. The wiki is how the next agent doesn't repeat your discovery.
Idioma do texto original: inglês
Run the project's own build/test/lint and converge before handing work to a reviewer. Requires explicit baseline → after evidence — the suite must be shown to change state, not just be "green at the end".
Idioma do texto original: inglês
General wait → inspect → fix (max 3) → self-park loop for any post-action verification (build, tests, CI, visual, lint).
Idioma do texto original: inglês
Diagnose and fix a failing CI run for the current branch, then re-verify.
Idioma do texto original: inglês