Menú
SkillsMP ha recopilado 10 skills de doidor/agentrig. Abre una skill para revisar su origen y sus detalles.
Mostrando 10 de 10 skills recopiladas.
Read PR review feedback, fix or reject each requested change, reply per thread, resolve every thread, and verify zero threads remain.
Idioma del texto original: inglés
Never cast an approving review on a PR your own (shared) agent identity authored — approval must come from an independent reviewer.
Idioma del texto original: inglés
Rebase the PR branch onto the default branch, resolve conflicts keeping both intents, and verify mergeability before pushing.
Idioma del texto original: inglés
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 del texto original: inglés
Admission bar and structure for writing a new skill, so the skill library stays lean and discoverable.
Idioma del texto original: inglés
Turn a reviewer/judge failure into an instruction-surface change that passes a prevention test.
Idioma del texto original: inglés
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 del texto original: inglés
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 del texto original: inglés
General wait → inspect → fix (max 3) → self-park loop for any post-action verification (build, tests, CI, visual, lint).
Idioma del texto original: inglés
Diagnose and fix a failing CI run for the current branch, then re-verify.
Idioma del texto original: inglés