search
Deep search mode - parallel multi-source search across codebase, docs, and web
Découvrez les skills content media automation tools, comparez leurs dépôts et consultez leurs instructions.
Deep search mode - parallel multi-source search across codebase, docs, and web
Analyze code and suggest refactoring opportunities with rationale
This skill should be used when the user asks to "review code", "perform code review", "check code quality", "review PR", "provide code feedback", or needs guidance on code review best practices and standards in...
This skill should be used when the user asks to "check quality gates", "validate against standards", "read AGENTS.md", "enforce project patterns", "follow constitution.md", "validate code quality", or needs gui...
Quick PR creation reference
Analyzes design docs and existing projects to create detailed, actionable implementation plans for Claude Code. Use when the user asks to create an implementation plan, analyze a feature, or break down tasks.
Build frontend pages, reusable components, layouts, and styling. Use for UI development tasks.
Use this skill when working with DocFX documentation pipelines. Covers docfx.json configuration, metadata extraction, toc.yml navigation, cross-references (xref/UID), and GitHub Pages deployment.
Bootstrap development sessions with automated startup rituals - checks recommendations, git status, launches scout + planner agents in parallel.
Enforces conventional commit message and branch naming conventions with specific prefixes (feat, fix, docs, style, refactor, perf, test, chore). Use when creating git commits, suggesting branch names, reviewing...
Use when implementing any feature or bugfix, before writing implementation code
Automates the complete release process for this Obsidian plugin. This skill should be used when the user requests to publish a new version, bump version numbers, sync versions across files, update changelog, bu...
Expert integration for the Serena MCP Server - a powerful coding agent toolkit providing IDE-like semantic code understanding to LLMs. This skill should be used when working with codebases through Serena tools,...
Provides comprehensive Python code review with focus on quality, bugs, security, and best practices. Use when reviewing Python code, functions, or modules for quality assessment.
Generate Conventional Commits git commit messages from the staged diff. Use this when the user asks to craft a commit message or when preparing a commit.
Retrieve code diff from a GitHub Pull Request via GitHub API. Use this as the first step in a code review pipeline when reviewing GitHub PRs.
Deep codebase context analysis like Greptile. Analyzes blast radius of changes, dependency graphs, and architectural consistency. Use when reviewing changes to core utilities, shared libraries, or database mode...
Perform thorough code reviews following Google's 5-step methodology. Use when reviewing pull requests, change lists, or any code changes to ensure quality, correctness, and maintainability.
Review code style, maintainability, and documentation. Checks readability, naming, modularity, abstractions, and documentation accuracy. Use as a final pass on all files.
Proactively use to generate or update a CHANGELOG.md file from Jujutsu commit history. Use when you need to create release notes, document changes between tags, or update the project changelog. Emphasizes break...
This skill should be used when users want to create, configure, or debug Claude Code hooks. Hooks are shell commands that execute at various points in Claude Code's lifecycle (PreToolUse, PostToolUse, Stop, Ses...
Enforce Claude Compass development standards and best practices. This skill should be used when writing or modifying code in the Claude Compass repository, including parsers, database migrations, graph builders...
Development process rules for this project including testing, branching, and commit standards. Use when implementing features, fixing bugs, or making any code changes.
Review Claude Code plugin marketplace configurations against official best practices. Use when analyzing marketplace.json and plugin.json files for structural issues, common errors, path validation, and consist...
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.