GitHub
agent-studio-chat
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...
Skills IA content media llm ai
Découvrez les skills content media llm ai, comparez leurs dépôts et consultez leurs instructions.
Catégories: content media llm ai
content media llm ai Effacer les filtres
Explorer
GitHub
learn
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.
GitHub
read-inspect-eval
Read and analyze Inspect AI evaluation log files using the Python API. Extract samples, messages, events, and metrics from .eval files.
GitHub
task-recognizer
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...
GitHub
agents-authoring
Best practices for writing AGENTS.md, agent configs, and skill files based on industry research
GitHub
facebook-automation
Facebook automation including posting with privacy settings, interactions, messaging, and navigation workflows
GitHub
skill-creator
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...
GitHub
mcp-builder
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...
GitHub
wakti
Global project rules, identity, platform constraints, PM authority, and mandatory design system for the Wakti AI app.
GitHub
domain-retrospective
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...
GitHub
domain-advisor
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?"
GitHub
setup
Configure Claude Code with symlinks to knowledge base agents and skills
GitHub
openrouter
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...
GitHub
daily-log
Daily log conventions for agent memory between sessions. Use when: "daily log", "today's note", "what happened today", "session start", "check context".
GitHub
tri-ssd-orchestrator
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...
GitHub
querying-web-search-agent
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...
GitHub
backend-dev
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...
GitHub
gptme-plugin-development
Guide to creating gptme plugins with tools, hooks, and commands.
GitHub
gptme-wrapped
Analyze your gptme conversation history for insights like token usage, costs, model preferences, and usage patterns - inspired by Spotify Wrapped.
GitHub
agent-deck
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...
GitHub
skill-creator
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...
GitHub
oracle
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...
GitHub
nclaude-chat
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.
GitHub
delegation
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...
Le classement utilise les étoiles du dépôt GitHub indexé. Plusieurs skills peuvent partager ce nombre : ce n’est ni un nombre d’installations ni une note de qualité.