GitHub
optimizing-claude-code
Audits repositories for Claude Code readiness and suggests improvements. Use when asked to check CLAUDE.md quality, review settings, audit project organization, or optimize for agentic work.
☆ 28View skill
testing security llm ai AI Skills
Discover testing security llm ai skills, compare source repositories and read the instructions for each workflow.
Categories: testing security llm ai
testing security llm ai Clear filters
Browse skills
GitHub
skills-manager
Lists, inspects, deletes, modifies, moves, and reviews skills for AI coding agents. Use when the user asks to view installed skills, list skills, delete a skill, remove a skill, move skills between scopes, shar...
☆ 28View skill
GitHub
claude-hooks-manager
Manage Claude Code hooks using natural language. Use when users want to add, list, remove, update, or validate hooks. Triggers on requests like "add a hook", "create a hook that...", "list my hooks", "remove th...
☆ 28View skill
GitHub
plan-executor
Expertise in executing finalized architectural plans. Use when the user asks to "implement the plan", "build the feature", or "execute the strategy".
☆ 28View skill
GitHub
plan-author
Expertise in acting as a Staff Engineer to generate comprehensive implementation plans. Use when the user asks to "plan a feature", "create a new plan", or "design an architecture".
☆ 28View skill
GitHub
prompt-design
基于 Anthropic 官方准则的提示词设计、优化和质量检查工具。适用场景： (1) 创建新提示词 - 用户说"帮我创建/设计一个XXX提示词" (2) 优化现有提示词 - 用户说"优化/改进这个提示词" (3) 检查提示词质量 - 用户说"检查/审查这...
☆ 28View skill
GitHub
ensemble
Gather perspectives from multiple AI models (Claude, Gemini, Codex) on complex problems. Launches parallel analysis agents and synthesizes their findings to identify consensus, disagreements, and blind spots.
☆ 28View skill
GitHub
directors
Run decisions by your personal board of directors - 8 influential thinkers who each bring a distinct lens. Get perspectives from Franklin, Buffett, Ford, Musk, Feynman, Banksy, Camus, and Brand on strategy, des...
☆ 28View skill
GitHub
greeting-helper
A simple skill that helps with greeting messages
☆ 28View skill
GitHub
mcporter
Use when you need to access MCP servers without installing them directly in Claude Code. MCPorter provides CLI access to any MCP server via npx, enabling tool discovery, direct calls, and ad-hoc connections. Us...
☆ 28View skill
GitHub
kernel-prompt-engineering
KERNELフレームワーク：1000時間のプロンプトエンジニアリングから発見された6つの原則。精度340%向上、時間67%削減を実現するエンタープライズ品質のプロンプト設計手法。AIへの指示を書く際に使用。
☆ 27View skill
GitHub
what-should-i-do-now
Help user decide what to work on next based on GTD's four criteria - context, time available, energy level, and priority. Use when user asks what to do or seems stuck on choosing. Handles rejection via refine-n...
☆ 27View skill
GitHub
clarify-item
Interview flow to understand what an inbox item is and determine its actionability. Use when processing inbox items to decide if they're actionable and what the next physical action is. Routes non-actionable it...
☆ 27View skill
GitHub
learning-system
Structured learning and spaced repetition system. Use when user wants to learn a topic, start a study session, review material, generate flashcards, create study notes, or track learning progress. Triggers on p...
☆ 27View skill
GitHub
refresh
Silently refresh AI context by reading project configuration and guidelines. Use when starting a new conversation, after context loss, or before major tasks.
☆ 27View skill
GitHub
critique
Challenge idea assumptions with skeptical VC-style evaluation. Use when user requests critique, validation, or 'is this a good idea' assessment.
☆ 27View skill
GitHub
start-session
Start a new learning session on a topic. Use when user wants to learn something new, begin studying, get taught a topic, or start a teaching conversation. Triggers on "teach me", "let's learn", "start session",...
☆ 27View skill
GitHub
synthesize
Synthesize information across multiple sources into a structured document. Processes sources in batches across sessions to handle more data than fits in context. Discovers and queues related sources automatical...
☆ 27View skill
GitHub
advise
Interactive conversational guidance - user implements with step-by-step advice. Use when you want hands-on implementation with expert guidance while maintaining control.
☆ 27View skill
GitHub
research
Deep research on a topic, creating persistent documentation for future reference. Use for technology decisions, competitive analysis, or complex topics.
☆ 27View skill
GitHub
adr
Create Architecture Decision Records through interactive conversation. Use when making technology choices, architecture patterns, or third-party service selections.
☆ 27View skill
GitHub
arifos-cool-protocol
Execute SABAR-72 cooling protocol for constitutional amendments and high-entropy operations with CLI integration. Use when user types /cool, mentions "cool down", "SABAR", "72 hour cooling", "constitutional ame...
☆ 27View skill
GitHub
dag-pattern-learner
Learns from DAG execution history to improve future performance. Identifies successful patterns, detects anti-patterns, and provides recommendations. Activate on 'learn patterns', 'execution patterns', 'what wo...
☆ 27View skill
GitHub
ai-engineer
Build production-ready LLM applications, advanced RAG systems, and intelligent agents. Implements vector search, multimodal AI, agent orchestration, and enterprise AI integrations. Use PROACTIVELY for LLM featu...
☆ 27View skill
The default order uses GitHub repository stars from our indexed data. Stars belong to the source repository and may be shared by multiple skills. They indicate repository interest, not skill installs or an independent quality score.