Extract insights for HUMANS on how to work effectively with AI agents. Analyzes interaction patterns to produce...
AI & LLM
LLM integrations, prompt engineering, and AI orchestration
9,003 skills
Core security functions for signing, verifying, and attesting to the safety of AI agent skills and code.
组合式数学推导与证明技能。适用于需要分步拆解、难度评估、在 SymPy 与 Lean4+Mathlib 间灵活切换、逐步验证并生成可审计草稿与正式稿的数学问题；可选启用 subagent 路由进行并行化解释/引理检索/证明骨架构建。
Generate SKILL.md files to make CLI tools discoverable by AI agents
Join and interact with CrabSpace - the MySpace-style social network for AI agents. Use when creating a profile,...
Session memory that compounds - remember decisions, patterns, and corrections across AI coding sessions. Includes...
Executes tasks using the Claude Code CLI (`claude`). Automatically determines the safest permission mode (plan,...
Executes tasks using the Codex CLI (`codex`). Automatically determines the least privilege required (Read-Only,...
Executes tasks using the Gemini CLI (`gemini`). Automatically determines the safest approval mode (plan, auto_edit,...
Decomposes complex or large-scale requirements into discrete, mutually exclusive sub-tasks that can be executed in...
Benchmarking AI models with Nvidia Aiperf and analyzing benchmark results. Use when the user wants to run...
Voice conversations with Claude about your projects. Call a phone number to brainstorm, or have Claude call you with updates.
Multi-language code quality standards for TypeScript, Python, Go, and Rust. Enforces type safety, security,...
Dynamic agent composition and management system. USE WHEN user says create custom agents, spin up custom agents,...
Efficiently navigate codebase documentation during Research phase. Use instead of Grep/Glob for finding...
Senior Python Backend Engineer skill for FastAPI. Use when scaffolding production-ready APIs, enforcing clean...
Run Gemini CLI for AI queries. Use when user asks to "run/ask/use gemini", compare Claude vs Gemini, or delegate...
Complete visual content system. USE WHEN user wants to create visual content, illustrations, diagrams, OR mentions...
Guide for creating high-quality MCP (Model Context Protocol) servers that enable LLMs to interact with external...
Senior Next.js 15+/16 Engineer skill for App Router. Use when scaffolding production apps, enforcing RSC patterns,...
Enforces modern Python 3.11+ coding standards, PEP 8 compliance, and type-hinting best practices automatically. This...
Multi-agent debate system. USE WHEN council, debate, perspectives, agents discuss. SkillSearch('council') for docs.
Compress verbose prompts & context before LLM processing. This skill should be used when input exceeds 1500 tokens,...
Pydantic v2 model patterns for req/res validation, MongoDB conversion, validation rules. Travel Panel conventions.