Browse Skills

Propagator-based parallel structure for exploiting knowledge differentials

Convert Microsoft Outlook Personal Storage Table (.pst) files into AI-friendly formats (Markdown, JSON, CSV). Use this skill to extract emails, metadata, and attachments from legacy email archives for analysis, context, or migration.

Audit and improve CLAUDE.md files in repositories. Use when user asks to check, audit, update, improve, or fix CLAUDE.md files. Scans for all CLAUDE.md files, evaluates quality against templates, outputs quality report, then makes targeted updates. Also use when the user mentions "CLAUDE.md maintenance" or "project memory optimization".

Comprehensive quality audit for Claude Code agents, skills, and commands with comparative analysis

CLAUDE.md file generation and optimization for Claude Code projects. Capabilities: initialize project instructions, analyze codebase context, optimize existing CLAUDE.md, apply Anthropic best practices, reduce token usage, improve effectiveness. Actions: init, create, optimize, enhance CLAUDE.md files. Keywords: CLAUDE.md, project instructions, Claude Code setup, project context, codebase analysis, Anthropic best practices, token optimization, project configuration, AI instructions, coding guidelines, project rules, workspace setup. Use when: initializing CLAUDE.md for new projects, optimizing existing project instructions, setting up Claude Code for a codebase, improving AI coding guidelines.

Build MCP servers in Python with FastMCP to expose tools, resources, and prompts to LLMs. Supports storage backends, middleware, OAuth Proxy, OpenAPI integration, and FastMCP Cloud deployment. Prevents 30+ errors. Use when: creating MCP servers, or troubleshooting module-level server, storage, lifespan, middleware, OAuth, background tasks, or FastAPI mount errors.

This skill automatically detects when CLAUDE.md files need updates based on codebase analysis. It identifies new patterns, code violations, stale documentation, and anti-patterns, then proposes specific markdown diffs showing exactly what CLAUDE.md sections should be added, modified, or removed. When codebase architecture changes, new patterns emerge, or documented practices diverge from actual code, this skill analyzes the robo-trader project structure and generates actionable recommendations with confidence scores. Should be invoked after major feature completions, during code reviews, or as periodic maintenance scans.

Create an AI Product Strategy Pack (thesis, prioritized use cases, system plan, eval + learning plan, agentic safety plan, roadmap). Use for AI product strategy, LLM/agent strategy, AI roadmap, AI-first product direction.

Use when user asks to "deep review the code", "thorough code review", "multi-pass review", or when orchestrating Phase 9 review loop. Provides review pass definitions (code quality, security, performance, test coverage, specialists), signal detection patterns, and iteration algorithms.

移除 Google Gemini(Nano Banana)生成圖片中的浮水印，使用逆向 Alpha 混合演算法精確還原被覆蓋的像素

Master advanced prompt engineering techniques to maximize LLM performance, reliability, and controllability in production. Use when optimizing prompts, improving LLM outputs, or designing production prompt templates.

Add voice message transcription to FFT_nano using OpenAI's Whisper API. Automatically transcribes WhatsApp voice notes so the agent can read and respond to them.

Add a professional footer to README files with engagement prompts, community channels, and call-to-action for subscriptions. Use when you need to enhance your README with a footer that encourages interaction and builds community.

Generate today's journal note when the user says /today or asks for a daily log. Use template `00_inbox/日记模版.md` (fallback `00_inbox/日记模板.md`), create the note in `99_学习情况记录`, add a Chinese-first global situation dashboard (map + a concise table summary + finance/tech bullets under the map) for the latest 24 hours, list unfinished tasks from existing notes in `99_学习情况记录`, and list today's tasks extracted from `Overview & Study Record.md` as markdown checkboxes.

Scans for project documentation files (AGENTS.md, CLAUDE.md, GEMINI.md, COPILOT.md, CURSOR.md, WARP.md, and 15+ other formats) and synthesizes guidance. Auto-activates when user asks to review, understand, or explore a codebase, when starting work in a new project, when asking about conventions or agents, or when documentation context would help. Can consolidate multiple platform docs into unified AGENTS.md.

Analyze Claude Code session logs - extract thinking blocks, tool usage stats, error patterns, debug trajectories. Triggers on: introspect, session logs, trajectory, analyze sessions, what went wrong, tool usage, thinking blocks, session history, my reasoning, past sessions, what did I do.

Guide for creating effective skills. This skill should be used when users want to create a new skill (or update an existing skill) that extends Claude's capabilities with specialized knowledge, workflows, or tool integrations.

Generate tests with expert routing, framework detection, and auto-TaskCreate. Triggers on: generate tests, write tests, testgen, create test file, add test coverage.

Search claude-mem's persistent cross-session memory database. Use when user asks "did we already solve this?", "how did we do X last time?", or needs work from previous sessions.

Diagnose and fix claude-mem installation issues. Checks PM2 worker status, database integrity, service health, dependencies, and provides automated fixes for common problems.