refactor
Analyze code and suggest refactoring opportunities with blast radius assessment, risk evaluation, and recommended order of operations
Discover databases automation tools skills, compare source repositories and read the instructions for each workflow.
Analyze code and suggest refactoring opportunities with blast radius assessment, risk evaluation, and recommended order of operations
Get Shit Done (GSD) - A comprehensive project management system for solo developers using Claude agents
Transform ideas into detailed implementation specifications. Creates specs with requirements, design, and implementation steps.
Workflow for working with existing codebase
Multi-agent specification review and iteration. Writes specs via spec-writer, reviews with AI personas, and iterates until approved.
Scaffold spec-workflow configuration in your project. Creates config files, philosophy templates, and persona examples.
Explores codebase and writes structured analysis documents. Spawned by map-codebase with a focus area.
Synchronizes documentation (README.md, CHANGELOG.md, API docs) with implementation. Preserves user content outside speckit markers. Updates are non-destructive and clearly delineated. Always run after /speckit....
Create distinctive, production-grade frontend interfaces with high design quality. Use this skill when the user asks to build web components, pages, or applications. Generates creative, polished code that avoid...
Comprehensive Typst copilot for semantic improvements, markdown conversion, compilation with visual debugging, and expert consultation. Use when working with Typst documents for (1) improving or refactoring Typ...
Capture user ideas verbatim in .wrangler/ideas/ directory using the MCP issues_create tool with type='idea'. Preserves exact user wording without interpretation or enhancement.
Detect and track design token drift between Figma design systems and code implementations - report-only skill that identifies inconsistencies and creates wrangler issues for resolution
Set up Git hooks for automated testing and code quality enforcement. Interactive configuration with smart project detection.
Generates standardized pull request descriptions following project conventions for GitHub PRs. Use when asked to create a PR description, or when PR description generation is part of a larger PR creation workfl...
Generates standardized pull request titles following project conventions for GitHub PRs. Use when asked to create a PR title, or when PR title generation is part of a larger PR creation workflow. This skill han...
This skill should be used when the user asks to "execute task", "implement feature", "delegate work", "run workflow", "review code", "code quality check", or needs task orchestration and code review guidance. P...
Generate standardized .agent-os directory structure with product documentation, mission, tech-stack, roadmap, and decision records. Enables AI-native workflows.
Finds WHERE code lives in a codebase - locates files by topic/feature, categorizes by purpose, organizes findings. Super grep/glob/ls tool for navigating unfamiliar codebases.
Static analysis with Semgrep - pattern-based security scanning and custom rule creation.
Comprehensive code review toolkit for evaluating quality across multiple languages. Use for PR analysis, quality checking, and generating review reports. Based on alirezarezvani/claude-skills.
Official coding standards and best practices derived from Xcode's internal AI chat templates.
初始化基于 lint-staged + simple-git-hooks + prettier 的 git 提交前代码格式化流程。用于在任何 Node.js 项目中快速搭建代码格式化和 git 钩子配置。
Scan codebase to identify opportunities to replace custom implementations with well-maintained open source libraries. Creates worktree, implements changes, and submits PR for review. Multi-phase workflow with p...
Validates project wrangler version on session start, detects breaking changes, and recommends updates
The default order uses GitHub repository stars from our indexed data. Stars belong to the source repository and may be shared by multiple skills. They indicate repository interest, not skill installs or an independent quality score.