Loading...
Loading...
Found 696 Skills
A comprehensive Git agent skill combining strategic workflows, strict conventional commit standards, and safe execution protocols. Acts as a senior engineer to guide users through atomic, verifiable, and standardized git operations.
Create or update a pull request for the current branch with a summary of all changes.
Lance une réunion autonome rapide avec des personas sélectionnés automatiquement, implémente la décision, crée une MR/PR, commite, pousse et publie un résumé en français — le tout sans intervention de l'utilisateur.
Generate exactly one high-quality Conventional Commit message from the current Git diff. Use when Codex needs to inspect staged changes, summarize the dominant intent, and return only the final commit message with no analysis or extra text.
Ship a change via a feature branch and pull request — never directly to the default branch. Use after any code change, fix, refactor, or docs update that needs to land on main. Branches are named `<card-number>` from the FluentBoards card. Commits go through the husky pre-commit hook (lint-staged); pushes go to the feature branch only; the PR body links back to the card. Hard refuses any push to main / master / trunk.
This skill should be used when the user asks to "commit changes", "craft a commit message", "stage and commit", "commit only session edits", or run a commit workflow with flags like --all, --deep, or --push. Creates atomic git commits with heuristic analysis, conventional-commit formatting, staging rules, optional deep analysis, and optional push.
Autonomous iterative experimentation loop for any programming task. Guides the user through defining goals, measurable metrics, and scope constraints, then runs an autonomous loop of code changes, testing, measuring, and keeping/discarding results. Inspired by Karpathy's autoresearch. USE FOR: autonomous improvement, iterative optimization, experiment loop, auto research, performance tuning, automated experimentation, hill climbing, try things automatically, optimize code, run experiments, autonomous coding loop. DO NOT USE FOR: one-shot tasks, simple bug fixes, code review, or tasks without a measurable metric.
GitHub PR의 미해결 리뷰 스레드를 조회해 코멘트별로 타당성을 검증한 뒤, 적절한 지적만 골라 수정·커밋한다. 모든 리뷰어(봇·사람)의 코멘트를 처리한다. "코드 리뷰 반영해줘", "리뷰 코멘트 처리해줘", "PR 리뷰 적용해줘", "apply PR review comments", "handle review feedback", "autofix", "/autofix" 같은 요청에 활성화한다. 리뷰 코멘트를 그대로 적용하지 않고, 검증에서 적절로 판정된 것만 사용자 승인(기본) 또는 자동(`--auto`)으로 반영한다.
Resolve git merge, rebase, or cherry-pick conflicts via a structural-merge cascade — mergiraf (AST-aware auto-resolve) → git rerere (replay remembered fixes) → kdiff3 (manual fallback). Use when conflicts exist and the user wants them resolved — phrases like "melt the conflicts", "fix the merge conflicts", "resolve the rebase conflicts", "what's conflicting after the merge", "/melt", "fix the cherry-pick", or any prompt that surfaces `<<<<<<<` markers, `CONFLICT (...)` git output, or a half-finished merge state. Use even when only one file is conflicting if the user wants the structural pass attempted before manual editing. Do NOT use for general git operations without conflicts. After `/cook` or `/cure` if a merge step blocked them; before retrying the gate that surfaced the conflict.
Standardized git commits following Conventional Commits. Supports mapping to GitHub and GitLab.
작업을 마무리하는 스킬. 테스트 확인, 커밋/PR, worktree 정리와 함께 5개의 전문 에이전트로 세션 인사이트를 추출합니다.
Create a well-formed git commit from current changes using session history for rationale and summary; use when asked to commit, prepare a commit message, or finalize staged work.