发现 tools llm ai 相关 Skills，比较来源仓库和用途，查看适合你工作流的技能说明。
Use buzzllm CLI to perform web searches, execute Python code in Docker, search/analyze local codebases, or generate code change blocks. Trigger when user asks for web search, Python execution, code analysis, or...
Use when starting any conversation - establishes how to find and use skills, requiring Skill tool invocation before ANY response including clarifying questions
Guide for using pagent - a PRD-to-code orchestration tool. Use when users ask how to use pagent, run agents, create PRDs, or transform requirements into code.
Analyzes completed projects to identify generalizable patterns, common workflows, and reusable knowledge worth extracting into skills. Use after completing a project to review LOG.md, skill updates, and project...
Transforms user project requirements into a structured CLAUDE.md context file. Use when starting a new project and need to document project goals, architecture, technical stack, constraints, and conventions. Th...
Manages project progress tracking and maintains a chronological log of completed tasks, decisions, and updates. Use when completing milestones, making architectural decisions, or documenting project evolution....
Use this skill when creating, updating, or maintaining ARCHITECTURE.md files, when users ask about "my architecture documentation" or "architecture", when generating presentations/slides/PowerPoint from archite...
Expert in .faf (Foundational AI-context Format) files for persistent project context. Use when working with .faf files, project DNA, CLAUDE.md bi-sync, faf-cli commands, MCP server configuration, or AI-readines...
Explain what FAF is, why it matters, and how it works when user asks about FAF, project context, AI-readiness, The Reading Order, or persistent context. Use when user says "what is FAF", "explain project.faf",...
Initialize project.faf files when starting new projects, when user asks to set up AI context, create project DNA, or needs persistent context. Automatically detects project type (React, TypeScript, Next.js, Sve...
Expert in debugging and fixing broken n8n workflows. Use when troubleshooting workflow errors, fixing failed executions, resolving expression issues, debugging HTTP requests, handling credential problems, or op...
Calculate AI-readiness score (0-100%) for any project with project.faf file. Shows Podium tier (Trophy/Gold/Silver/Bronze), identifies strengths and gaps, provides improvement roadmap. Use when user asks "what'...
Improve project.faf AI-readiness score through guided enhancements. Identifies missing sections, suggests improvements, helps reach next Podium tier (Bronze→Silver→Gold→Trophy). Use when user asks "improve my s...
Expert in building n8n workflows from scratch. Use when creating new n8n workflows, adding nodes, connecting APIs, setting up webhooks, transforming data, or implementing automation patterns. Focuses on workflo...
Understand where FAF works - Claude Code (CLI + Skills), claude-faf-mcp (Desktop + MCP), vs claude.ai (web - file upload only). Explains faf-cli vs MCP differences, when to use each platform. Use when user asks...
PROTOCOL skill for checkpoint-based context preservation using Serena MCP. Automatically creates checkpoints at wave boundaries and before PreCompact. Enables zero-context-loss multi-session work with structure...
Generates SHANNON_INDEX for 94% token reduction (58K → 3K tokens). Compresses large codebases into structured summaries with Quick Stats, Tech Stack, Core Modules, Dependencies, Recent Changes, and Key Patterns...
Coordinates Serena MCP knowledge graph operations for Shannon Framework. Enforces standardized entity naming (shannon/* namespace), relation creation patterns, search protocols, and observation management. Prev...
Restore previous session state from Serena MCP checkpoints. Retrieves checkpoint by ID or auto-selects most recent, deserializes context, restores command/skill/phase/wave state. Use when: resuming after contex...
Use when testing Claude Code plugins programmatically, building SDK applications, encountering plugin loading failures (plugins array empty), getting AttributeError on message.type, or needing verified Claude A...
Update an existing skill based on troubleshooting or improvements discovered during usage. Use when user asks to "update a skill", "improve the skill", "fix the skill instructions", or after resolving issues wi...
Create a new Claude Code skill with proper structure, YAML frontmatter, and documentation. Use when user asks to "create a skill", "make a skill", "build a new skill", or "add a skill".
Build native Rust ML models with Candle framework. Use when implementing vision transformers, LLMs, or audio models with GPU acceleration.
Create new Claude Code skills with proper structure and conventions. Use when the user wants to create a new skill, scaffold skill templates, or understand skill anatomy.
默认按已收录数据中的 GitHub 仓库 Stars 排序。Stars 属于来源仓库，同一仓库的多个技能可能共享相同数值；它反映仓库关注度，不代表单个技能的安装量或质量评分。