Chargement du README du dépôt…
Affichage de 8 skills collectés sur 8.
Use when asked to run a full repo hygiene pass, full cleanup, or to maintain a repo in one go — and whenever the user invokes /safe-code or any wrapper of it (/skill:safe-code, /skills safe-code, $safe-code, @safe-code, or bare safe-code), including…
Langue du texte source : anglais
Build or update the codegraph code index for the current repository. Use before safe-code audits, refactors, reviews, debugging, or when the index may be stale.
Langue du texte source : anglais
Scan an entire codebase to detect and safely remove dead code such as unused functions, orphaned modules, unreferenced exports, stale configs, dead routes, and leftover workflow artifacts. Use when asked to clean up dead code, remove unused code, prune stale…
Langue du texte source : anglais
Systematically debug a symptom with a red-capable feedback loop, a minimised repro, ranked falsifiable hypotheses, tagged probes, and a regression test at the correct seam. Graph tools accelerate the search when present; they are never required.
Langue du texte source : anglais
Navigate and understand codebase structure using the codegraph index. Use for repo orientation, AGENTS.md authoring, architecture mapping, or finding relevant code.
Langue du texte source : anglais
Review working-tree, branch, or PR changes on two separate axes — Standards (repo conventions + a smell baseline) and Spec (does it do what the active feature spec asked) — with blast-radius and test-coverage checks. Graph tools accelerate when present; never…
Langue du texte source : anglais
Refactor code safely in small verified slices while keeping repo continuity docs in sync. Uses the codegraph index for callers, impact radius, and affected tests when available. Use when an agent is asked to refactor, restructure, clean up, remove or replace…
Langue du texte source : anglais
Senior engineer discipline layer for any coding task. Use when asked to make an AI agent think like a senior/master developer, improve strategy, create task lists, measure twice cut once, keep repositories clean, avoid overengineering, critique strategy…
Langue du texte source : anglais
Copiez ce prompt dans l’assistant IA que vous utilisez.
Follow https://skillsmp.com/skill-install/prompt.md to install Agent Skills from https://github.com/afu-it/safe-code.Le README n’a pas pu être chargé. Vous pouvez toujours consulter les Skills du dépôt ci-dessous.