github-automation
Automate the bridge between local development and the remote repository.
Découvrez les skills content media automation tools, comparez leurs dépôts et consultez leurs instructions.
Automate the bridge between local development and the remote repository.
Lightweight Haiku sub-agent for cleaning up C# code. Removes commented code, fixes indentation, removes debug Print() statements, and formats code consistently. Auto-triggers on cleanup requests.
Guide for incrementally upgrading Nx library peerDependencies from Angular 15 to support both 15 and 16. Use when upgrading Angular libraries in a monolith, making libs dual-compatible, or preparing for Angular...
Scaffold repo-local Ralph autonomous harness under scripts/ralph/. Use when user runs /flow-next:ralph-init.
Construct git commit messages in the format "(): subject" and assist with running git commit. Use when a user asks to prepare or execute a commit with this formatted message.
Keeps all project documents consistent after code or spec changes. Use after any approved update.
Verify implementation matches change artifacts. Use when the user wants to validate that implementation is complete, correct, and coherent before archiving.
Prepare structured PR reviews using a three-phase framework (Context, Analysis, Validation). Use when reviewing pull requests, when user shares a PR URL, or mentions "review PR", "code review", or "check this P...
Systematically implements incomplete features from CHANGELOG.md [Unreleased] section with testing
코드베이스 탐색 및 분석. 3개 이상 파일 탐색, 아키텍처 파악, 영향 범위 분석 시 자동 호출
Auto-implement improvements with dry-run safety checks and rollback
Build template substitution and conditional logic.
Use when implementing any feature or bugfix, before writing implementation code
Standardize repository layout, module boundaries, naming conventions, and baseline docs for Java backend projects. Use when starting a new project, restructuring an existing repo, or migrating to a mono-repo.
Analyze git diffs and intelligently split mixed changes into clean, logical conventional commits. Use when the user needs to organize uncommitted changes that mix multiple change types (feat, fix, refactor, cho...
Analyzes a .NET 8 codebase and produces analysis findings for upgrading to .NET 10. Uses pm7y-ralph-planner to generate TASKS.md with validation requirements and learnings tracking for autonomous execution. Use...
Acts as a DevOps & MLOps expert for the LB-ASM-X2648 project. Use when the user asks about deployment, branches, pipeline errors, or releasing new features.
Expert at TSDoc comments, Storybook stories, VitePress docs, TypeDoc API generation. Use when documenting code, adding comments, creating stories, or generating API docs.
Build production Next.js websites from Figma designs with headless CMS integration. Use when building websites from Figma, creating CMS-driven sites, or converting designs to code. Handles Figma extraction, CMS...
Phase 2 of Eiffel Spec Kit. Runs progressive AI review chain (Ollama → Claude → Grok → Gemini → Human). Generates approach.md and synopsis.md. BLOCKS until human approves. Use with /eiffel.review command.
Use this skill when the user asks to implement/build/create a feature, or asks about development process, git workflow, or planning. Triggers on: "implement feature", "build feature", "add feature", "create fea...
Set up CI/CD pipelines with GitHub Actions. Use when creating new projects, adding automation, or when manual verification becomes bottleneck. Covers lint, test, build, deploy automation.
Expert in building npm package CLIs with Unix philosophy, automatic project root detection, argument parsing, interactive/non-interactive modes, and CLI library ecosystems. Use PROACTIVELY for CLI tool developm...
Creates or updates a GitHub PR with Jira integration, mermaid diagrams, and AI disclosure. Runs pre-push checks first. Use when ready to submit code for review or update an existing PR. Invoke with /create-pr.
Le classement utilise les étoiles du dépôt GitHub indexé. Plusieurs skills peuvent partager ce nombre : ce n’est ni un nombre d’installations ni une note de qualité.