Loading...
Loading...
Found 42 Skills
Modular Code Organization
Code template search and generation tool. Auto-initializes on first use. Use when: 1. search/get - user needs code templates, "检索模板", "search template" 2. generate - user wants to create template from code/file/repo/url, "生成模板" 3. upload - user has prepared template files, "上传模板" Requirements: JDK 17+, Git (for first-time setup)
Storybook MCP server integration for component-aware AI development. Covers 6 tools across 3 toolsets (dev, docs, testing): component discovery via list-all-documentation/get-documentation, story previews via preview-stories, and automated testing via run-story-tests. Use when generating components that should reuse existing Storybook components, running component tests via MCP, or previewing stories in chat.
Navigate the SLDD (Spec Loops Driven Development) process and choose the correct skill for the current stage. Use when starting a new feature or when unsure which step comes next.
Delegate coding tasks to Codex, Claude Code, or Pi agents via background process. Use when: (1) building/creating new features or apps, (2) reviewing PRs (spawn in temp dir), (3) refactoring large codebases, (4) iterative coding that needs file exploration. NOT for: simple one-liner fixes (just edit), reading code (use read tool), thread-bound ACP harness requests in chat (for example spawn/run Codex or Claude Code in a Discord thread; use sessions_spawn with runtime:"acp"), or any work in ~/clawd workspace (never spawn agents here). Claude Code: use --print --permission-mode bypassPermissions (no PTY). Codex/Pi/OpenCode: pty:true required.
Agent harness architecture — structure a project's agent context across layers for effective AI-assisted development. Covers CLAUDE.md, skills, design docs, hooks, and all artifacts that shape how an agent understands and operates in a codebase. Use when setting up or improving a project's agent configuration, when agent context feels bloated or disorganized, when onboarding a new project for AI-assisted development, or when the agent keeps losing architectural awareness mid-task. Trigger on phrases like "set up claude", "improve CLAUDE.md", "agent keeps forgetting", "context is too long", "harness setup", "organize agent context", "how should I structure my prompts". Supports arguments: `/harness audit` to evaluate an existing project's context architecture, `/harness init` to set up harness from scratch.
Comprehensive guide for AI-assisted vibe coding. Use when the user wants to build applications through natural language prompts using tools like Lovable, Cursor, Replit, or Bolt. Includes best practices, pitfall awareness, tool-specific guidance, architectural decision support, and MVP scope definition with a bias toward cutting features aggressively to ship faster.
Claude Code AI-assisted development workflow. Activate when discussing Claude Code usage, AI-assisted coding, prompting strategies, or Claude Code-specific patterns.
Keep AI tooling files (.claude, .codex, .cursor, .windsurf, .augment, .kiro, .cline, .roo, .gemini, etc.) on dev branch but exclude them from main/master. Use when managing branches, creating PRs to main, merging to main, or setting up a repo's branch strategy for AI-assisted development. Triggers on git merge/PR operations targeting main or master.
Enter copilot mode — human drives, Claude assists. Relaxes worktree enforcement, allows main commits.
Methodology for effective AI-assisted software development. Use when helping users build software with AI coding assistants, debugging AI-generated code, planning features for AI implementation, managing version control in AI workflows, or when users mention "vibe coding," Cursor, Windsurf, or similar AI coding tools. Provides strategies for planning, testing, debugging, and iterating on code written with LLM assistance.
Used when you need to perform Discover (reverse engineering) on legacy projects with existing code, consolidate repository facts into `.aisdlc/project/`, and you find that AI or teams frequently guess entry points and boundaries, have duplicate writing of indexes and details, or lack evidence chains leading to repeated rework.