发现 content media llm ai 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。
Work on Agent Studio chat (UI + streaming) and the /api/chat route. Use for tasks like message rendering, reasoning display, editing/regenerate, Zustand chat stores, model/settings UI, and OpenRouter or Vercel...
This skill should be used when the user asks to "save learnings", "remember this for next time", "add this to CLAUDE.md", "update your instructions", or wants to extract lessons from the current conversation.
Read and analyze Inspect AI evaluation log files using the Python API. Extract samples, messages, events, and metrics from .eval files.
This skill helps identify repetitive task patterns and create reusable commands. When users repeatedly ask for similar types of work, this skill recognizes patterns and creates command templates with documented...
Best practices for writing AGENTS.md, agent configs, and skill files based on industry research
Facebook automation including posting with privacy settings, interactions, messaging, and navigation workflows
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 Codex's capabilities with specialized knowledge, workflows, or too...
Guide for creating high-quality MCP (Model Context Protocol) servers that enable LLMs to interact with external services through well-designed tools. 사용 시기: (1) MCP 서버 구축 시 (2) 외부 API를 MCP로 통합 시...
Global project rules, identity, platform constraints, PM authority, and mandatory design system for the Wakti AI app.
Turn experiment reports and development notes into summaries and reusable skills. Adapts behavior based on project domain (research, unsloth, cuda) by reading registry.json. Triggers on or requests for lessons...
Plan experiments or development tasks using past knowledge. Adapts behavior based on project domain (research, unsloth, cuda) by reading registry.json. Triggers on or questions like "What should we try next?"
Configure Claude Code with symlinks to knowledge base agents and skills
Invokes 300+ AI models via OpenRouter API for text completion, image generation, and model discovery. Use when delegating tasks to external models (GPT-5.2, Gemini 3, Llama, Mistral, etc.). Triggers on "use Ope...
Daily log conventions for agent memory between sessions. Use when: "daily log", "today's note", "what happened today", "session start", "check context".
Tri-SSD（三層スライス仕様駆動）のワークフローを統括する。 AI/LLMコードエージェントを前提とした仕様駆動開発フレームワーク。 三層モデル（L1 ビジョン・要求、L2 技術基盤、L3 機能仕様）を通じて、 要件から実装までの...
This skill guides the process of creating context-free queries for a web search agent (another Claude instance with web search tools). Use this when you need expert guidance from web research but the search age...
Supabase backend development: database, RLS, Edge Functions, queries. USE WHEN: creating tables, migrations, RPC functions, Edge Functions, RLS policies, query optimization, Supabase infrastructure. NOT FOR: Fl...
Guide to creating gptme plugins with tools, hooks, and commands.
Analyze your gptme conversation history for insights like token usage, costs, model preferences, and usage patterns - inspired by Spotify Wrapped.
Terminal session manager for AI coding agents. Use when user mentions "agent-deck", "session", "sub-agent", "MCP attach", or needs to (1) create/start/stop/restart/fork sessions, (2) attach/detach MCPs, (3) man...
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 to...
Run GPT-5.2 Codex (gpt-5.2-codex high) via OpenAI Codex CLI to review code for bugs, issues, and architecture problems. Use when the user wants a second opinion on code, requests a code review from an external...
Communicate with other Claude Code sessions via nclaude. Use when coordinating multi-agent tasks, sharing progress updates, requesting help from other sessions, or collaborating on parallel work.
This skill configures automatic task delegation between agents in Synapse A2A. Configure delegation rules via settings files (.synapse/settings.json and .synapse/delegate.md) or the interactive config TUI (syna...
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。