发现 内容与媒体 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。
Engages structured analysis to explore multiple perspectives and context dependencies before responding. Use when users ask confirmation-seeking questions, make leading statements, request binary choices, or wh...
Guide learning and deep understanding through proven methodologies (Socratic, Feynman, Problem-Based). Use when user says "help me understand", "teach me", "explain this", "learn about", "socratic", "feynman",...
Troubleshoot Claude Code extensions and behavior. Triggers on: debug, troubleshoot, not working, skill not loading, hook not running, agent not found.
Model Context Protocol (MCP) server patterns for building integrations with Claude Code. Triggers on: mcp server, model context protocol, tool handler, mcp resource, mcp tool.
Senior Prompt Engineer & Agentic Orchestrator. Expert in Reasoning Models (o3), Tree-of-Thoughts, and Structured Thinking Protocols for 2026.
Senior SDK Master for @google/genai v1.35.0+, expert in Controlled Outputs, Multimodal Context, and Structured Intelligence.
Master of Voice-First Interfaces, specialized in sub-300ms Latency, Spatial Hearing AI, and Multimodal Voice-Haptic feedback.
Master of LLM Economic Orchestration, specialized in Google GenAI (Gemini 3), Context Caching, and High-Fidelity Token Engineering.
Analyze strategic positioning and explore future scenarios. Use when user wants "SWOT analysis", "competitive forces", "scenario planning", "what if", "strategic assessment", "market forces", "porter's", or nee...
Challenge and stress-test ideas through adversarial thinking. Use when user wants to "poke holes", "challenge this", "what could go wrong", "devil's advocate", "stress test", "red team", "pre-mortem", "review t...
Process change requests by analyzing impact on existing requirements and features. Determines if CR modifies existing feature (→ refinement) or requires new feature (→ requirement update + feature breakdown). T...
Break requirements into high-level features and create feature list in requirement-details.md. Calls feature-board-management to initialize feature tracking. Use when requirements are gathered and need to be sp...
Enhanced git operations using lazygit, gh (GitHub CLI), and delta. Triggers on: stage changes, create PR, review PR, check issues, git diff, commit interactively, GitHub operations, rebase, stash, bisect.
Senior DevOps & Automation Specialist. Expert in GitHub Actions, Issue Orchestration, and Advanced Git Internals.
Master of PDF engineering, specialized in AI-driven extraction, high-fidelity Generation (Puppeteer), and PDF 2.0 Security.
Dig to fundamental truths and real causes behind problems. Use when user asks "why does this happen", "what's the real problem", "root cause", "first principles", "jobs to be done", "JTBD", "five whys", "fundam...
Claude Code hook system for pre/post tool execution. Triggers on: hooks, PreToolUse, PostToolUse, hook script, tool validation, audit logging.
Modern file and content search using fd, ripgrep (rg), and fzf. Triggers on: fd, ripgrep, rg, find files, search code, fzf, fuzzy find, search codebase.
Close completed feature and create pull request. Use when human has validated the playground and feature is ready to ship. Provides procedures for final verification, PR creation, and documentation.
Guide for migrating tools from legacy switch statements to ToolExecutorRegistry handlers in Orient
Use this skill when you need to configure, create, or troubleshoot Claude Code hooks. This includes setting up PreToolUse hooks, PostToolUse hooks, UserPromptSubmit hooks, or any automation within Claude Code....
Expert on the ag-skill-factory project. Knows the entire codebase, skill creation workflow, Makefile commands, and project architecture. Activate this skill when working within the skill-factory repository.
Your project awareness buddy. Knows current state, reads docs, analyzes code, answers "where are we?" questions. Activate with "bro" or "project-bro".
Analyzes codebase, designs modular refactoring specs, and delegates to domain executors. Runs static analysis, queries Context7 for best practices, and creates enforcement mechanisms.
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。