Menu
SkillsMP a collecté 10 skills depuis doidor/agentrig. Ouvrez un skill pour examiner sa source et ses détails.
Affichage de 10 skills collectés sur 10.
Read PR review feedback, fix or reject each requested change, reply per thread, resolve every thread, and verify zero threads remain.
Langue du texte source : anglais
Never cast an approving review on a PR your own (shared) agent identity authored — approval must come from an independent reviewer.
Langue du texte source : anglais
Rebase the PR branch onto the default branch, resolve conflicts keeping both intents, and verify mergeability before pushing.
Langue du texte source : anglais
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.
Langue du texte source : anglais
Admission bar and structure for writing a new skill, so the skill library stays lean and discoverable.
Langue du texte source : anglais
Turn a reviewer/judge failure into an instruction-surface change that passes a prevention test.
Langue du texte source : anglais
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.
Langue du texte source : anglais
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".
Langue du texte source : anglais
General wait → inspect → fix (max 3) → self-park loop for any post-action verification (build, tests, CI, visual, lint).
Langue du texte source : anglais
Diagnose and fix a failing CI run for the current branch, then re-verify.
Langue du texte source : anglais