myclaudecode

站在巨人肩膀上创建高质量 Skill —— 在创建新 skill 之前，帮助用户发现并整合领域专家的成熟方法论。当用户请求"帮我创建一个关于 X 的 skill"或"我想做一个能 Y 的 skill"时触发。此 skill 指导方法论选择，然后交由 skill-creator 生成最终 skill。

CRITICAL - Guide for using Claudish CLI ONLY through sub-agents to run Claude Code with OpenRouter models (Grok, GPT-5, Gemini, MiniMax). NEVER run Claudish directly in main context unless user explicitly requests it. Use when user mentions external AI models, Claudish, OpenRouter, or alternative models. Includes mandatory sub-agent delegation patterns, agent selection guide, file-based instructions, and strict rules to prevent context window pollution.

Telegram 生态开发全栈指南 - 涵盖 Bot API、Mini Apps (Web Apps)、MTProto 客户端开发。包括消息处理、支付、内联模式、Webhook、认证、存储、传感器 API 等完整开发资源。。

snapDOM is a fast, accurate DOM-to-image capture tool that converts HTML elements into scalable SVG images. Use for capturing HTML elements, converting DOM to images (SVG, PNG, JPG, WebP), preserving styles, fonts, and pseudo-elements.

CCXT cryptocurrency trading library. Use for cryptocurrency exchange APIs, trading, market data, order management, and crypto trading automation across 150+ exchanges. Supports JavaScript/Python/PHP.

CoinGecko API documentation - cryptocurrency market data API, price feeds, market cap, volume, historical data. Use when integrating CoinGecko API, building crypto price trackers, or accessing cryptocurrency market data.

Cryptofeed - Real-time cryptocurrency market data feeds from 40+ exchanges. WebSocket streaming, normalized data, order books, trades, tickers. Python library for algorithmic trading and market data analysis.

Hummingbot trading bot framework - automated trading strategies, market making, arbitrage, connectors for crypto exchanges. Use when working with algorithmic trading, crypto trading bots, or exchange integrations.

Comprehensive Polymarket skill covering prediction markets, API, trading, market data, and real-time WebSocket data streaming. Build applications with Polymarket services, monitor live trades, and integrate market predictions.

PostgreSQL database documentation - SQL queries, database design, administration, performance tuning, and advanced features. Use when working with PostgreSQL databases, writing SQL, or managing database systems.

TimescaleDB - PostgreSQL extension for high-performance time-series and event data analytics, hypertables, continuous aggregates, compression, and real-time analytics

Auto-detect network issues and force proxy usage with proxychains4. Use this skill when encountering connection timeouts, DNS failures, or blocked network access. Default proxy is http://127.0.0.1:9910

Claude Code 高级开发指南 - 全面的中文教程，涵盖工具使用、REPL 环境、开发工作流、MCP 集成、高级模式和最佳实践。适合学习 Claude Code 的高级功能和开发技巧。

Claude AI cookbooks - code examples, tutorials, and best practices for using Claude API. Use when learning Claude API integration, building Claude-powered applications, or exploring Claude capabilities.

无头模式 AI CLI 调用技能：支持 Gemini/Claude/Codex CLI 的无交互批量调用，包含 YOLO 模式和安全模式。用于批量翻译、代码审查、多模型编排等场景。

Common agent patterns and templates for Claude Code. Use when implementing agents to follow proven patterns for proxy mode, TodoWrite integration, and quality checks.

YAML frontmatter schemas for Claude Code agents and commands. Use when creating or validating agent/command files.

XML tag structure patterns for Claude Code agents and commands. Use when designing or implementing agents to ensure proper XML structure following Anthropic best practices.

Optimize CLAUDE.md following best practices from humanlayer.dev - apply after /init to transform verbose output into focused, high-leverage project context

Use this skill to query your Google NotebookLM notebooks directly from Claude Code for source-grounded, citation-backed answers from Gemini. Browser automation, library management, persistent auth. Drastically reduced hallucinations through document-only responses.

Extract subtitles/transcripts from YouTube videos. Triggers: "youtube transcript", "extract subtitles", "video captions", "视频字幕", "字幕提取", "YouTube转文字", "提取字幕".

Use when user wants to execute long-running tasks that require multiple sessions to complete. This skill manages task decomposition, progress tracking, and autonomous execution using Claude Code headless mode with auto-continuation. Trigger phrases: "autonomous", "long-running task", "multi-session", "自主执行", "长时任务", "autonomous skill".

Leverage OpenAI Codex/GPT models for autonomous code implementation. Triggers: "codex", "use gpt", "gpt-5", "gpt-5.2", "let openai", "full-auto", "用codex", "让gpt实现".

Handle errors, timeouts, and failures in multi-agent workflows. Use when dealing with external model timeouts, API failures, partial success, user cancellation, or graceful degradation. Trigger keywords - "error", "failure", "timeout", "retry", "fallback", "cancelled", "graceful degradation", "recovery", "partial success".

Interactive feature development workflow from idea to implementation. Creates requirements (EARS format), design documents, and task lists. Triggers: "kiro", ".kiro/specs/", "feature spec", "需求文档", "设计文档", "实现计划".

MANDATORY tracking protocol for multi-model validation. Creates structured tracking tables BEFORE launching models, tracks progress during execution, and ensures complete results presentation. Use when running 2+ external AI models in parallel. Trigger keywords - "multi-model", "parallel review", "external models", "consensus", "model tracking".

Coordinate multiple agents in parallel or sequential workflows. Use when running agents simultaneously, delegating to sub-agents, switching between specialized agents, or managing agent selection. Trigger keywords - "parallel agents", "sequential workflow", "delegate", "multi-agent", "sub-agent", "agent switching", "task decomposition".

Run multiple AI models in parallel for 3-5x speedup with ENFORCED performance statistics tracking. Use when validating with Grok, Gemini, GPT-5, DeepSeek, or Claudish proxy for code review, consensus analysis, or multi-expert validation. NEW in v3.1.0 - SubagentStop hook enforces statistics collection, MANDATORY checklist prevents incomplete reviews, timing instrumentation examples. Includes dynamic model discovery via `claudish --top-models` and `claudish --free`, session-based workspaces, and Pattern 7-8 for tracking model performance. Trigger keywords - "grok", "gemini", "gpt-5", "deepseek", "claudish", "multiple models", "parallel review", "external AI", "consensus", "multi-model", "model performance", "statistics", "free models".

Implement quality gates, user approval, iteration loops, and test-driven development. Use when validating with users, implementing feedback loops, classifying issue severity, running test-driven loops, or building multi-iteration workflows. Trigger keywords - "approval", "user validation", "iteration", "feedback loop", "severity", "test-driven", "TDD", "quality gate", "consensus".

GitHub Spec-Kit integration for constitution-based spec-driven development. 7-phase workflow. Triggers: "spec-kit", "speckit", "constitution", "specify", ".specify/", "规格驱动开发", "需求规格".

Track progress in multi-phase workflows with TodoWrite. Use when orchestrating 5+ phase commands, managing iteration loops, tracking parallel tasks, or providing real-time progress visibility. Trigger keywords - "phase tracking", "progress", "workflow", "multi-step", "multi-phase", "todo", "tracking", "status".

Validate OpenAPI, Swagger, and GraphQL schemas match backend implementation. Detect breaking changes, generate TypeScript clients, and ensure API documentation stays synchronized. Use when working with API spec files (.yaml, .json, .graphql), reviewing API changes, generating frontend types, or validating endpoint implementations.

ShipAny 中文文档 - AI SaaS 快速构建平台

使用 Skill Seekers MCP 工具生成 Claude AI 技能的完整工作流指南

Use when you need direct browser control - teaches Chrome DevTools Protocol for controlling existing browser sessions, multi-tab management, form automation, and content extraction via use_browser MCP tool

⚡ PRIMARY TOOL for: 'what's the architecture', 'system design', 'how are layers organized', 'find design patterns', 'audit structure', 'map dependencies'. Uses claudemem v0.3.0 AST structural analysis with PageRank. GREP/FIND/GLOB ARE FORBIDDEN.

Multi-agent code analysis orchestration using claudemem. Share claudemem output across parallel agents. Enables parallel investigation, consensus analysis, and role-based command mapping.

⚡ PRIMARY TOOL for semantic code search AND structural analysis. NEW: AST tree navigation with map, symbol, callers, callees, context commands. PageRank ranking. ANTI-PATTERNS: Reading files without mapping, Grep for 'how does X work', Modifying without caller analysis.

⚡ AUTO-INVOKE when user asks: 'audit', 'investigate', 'how does X work', 'find all', 'where is', 'trace', 'understand', 'map the codebase', 'comprehensive'. MUST run BEFORE Read/Glob when planning to read 3+ files. Prevents tool familiarity bias toward native tools.

Integration guide for using detective skills across plugins. Maps agent roles from frontend, bun, and other plugins to appropriate detective skills. Developer agents should use developer-detective, architect agents should use architect-detective, etc.