softaworks/agent-toolkit

这个仓库里有 43 个技能，GitHub 星标 ★ 2,475。

• agent-md-refactorRefactor bloated AGENTS.md, CLAUDE.md, or similar agent instruction files to fol
• backend-to-frontend-handoff-docsCreate API handoff documentation for frontend developers. Use when backend work
• c4-architectureGenerate architecture documentation using C4 model Mermaid diagrams. Use when as
• codexUse when the user asks to run Codex CLI (codex exec, codex resume) or references
• command-creatorThis skill should be used when creating a Claude Code slash command. Use when us
• commit-workCreate high-quality git commits: review/stage intended changes, split into logic
• crafting-effective-readmesUse when writing or improving README files. Not all READMEs are the same — provi
• daily-meeting-updateInteractive daily standup/meeting update generator. Use when user says 'daily',
• database-schema-designerDesign robust, scalable database schemas for SQL and NoSQL databases. Provides n
• datadog-cliDatadog CLI for searching logs, querying metrics, tracing requests, and managing
• dependency-updaterSmart dependency management for any language. Auto-detects project type, applies
• design-system-starterCreate and evolve design systems with design tokens, component architecture, acc
• difficult-workplace-conversationsStructured approach to workplace conflicts, performance discussions, and challen
• domain-name-brainstormerGenerates creative domain name ideas for your project and checks availability ac
• draw-iodraw.io diagram creation, editing, and review. Use for .drawio XML editing, PNG
• excalidrawUse when working with *.excalidraw or *.excalidraw.json files, user mentions dia
• feedback-masteryNavigate difficult conversations and deliver constructive feedback using structu
• frontend-to-backend-requirementsDocument frontend data needs for backend developers. Use when frontend needs to
• game-changing-featuresFind 10x product opportunities and high-leverage improvements. Use when user wan
• geminiUse when the user asks to run Gemini CLI for code review, plan review, or big co
• gepettoCreates detailed, sectionized implementation plans through research, stakeholder
• humanizer|
• jiraUse when the user mentions Jira issues (e.g., "PROJ-123"), asks about tickets, w
• lesson-learnedAnalyze recent code changes via git history and extract software engineering les
• marp-slideCreate professional Marp presentation slides with 7 beautiful themes (default, m
• meme-factoryGenerate memes using the memegen.link API. Use when users request memes, want to
• mermaid-diagramsComprehensive guide for creating software diagrams using Mermaid syntax. Use whe
• muiMaterial-UI v7 component library patterns including sx prop styling, theme integ
• naming-analyzerSuggest better variable, function, and class names based on context and conventi
• openapi-to-typescriptConverts OpenAPI 3.0 JSON/YAML to TypeScript interfaces and type guards. This sk
• perplexityWeb search and research using Perplexity AI. Use when user says "search", "find"
• plugin-forgeCreate and manage Claude Code plugins with proper structure, manifests, and mark
• professional-communicationGuide technical communication for software developers. Covers email structure, t
• qa-test-plannerGenerate comprehensive test plans, manual test cases, regression test suites, an
• react-devThis skill should be used when building React components with TypeScript, typing
• react-useeffectReact useEffect best practices from official docs. Use when writing/reviewing us
• reducing-entropyManual-only skill for minimizing total codebase size. Only activate when explici
• requirements-clarityClarify ambiguous requirements through focused dialogue before implementation. U
• session-handoffCreates comprehensive handoff documents for seamless AI agent session transfers.
• ship-learn-nextTransform learning content (like YouTube transcripts, articles, tutorials) into
• skill-judgeEvaluate Agent Skill design quality against official specifications and best pra
• web-to-markdownUse ONLY when the user explicitly says: 'use the skill web-to-markdown ...' (or
• writing-clearly-and-conciselyUse when writing prose humans will read—documentation, commit messages, error me