GitHub
coders
Spawn AI coding assistants (Claude, Gemini, Codex, OpenCode) in isolated tmux sessions with git worktrees, Redis coordination, and session persistence. Use when you need to run multiple AI agents in parallel, c...
☆ 1View skill
research llm ai AI Skills
Discover research llm ai skills, compare source repositories and read the instructions for each workflow.
Categories: research llm ai
research llm ai Clear filters
Browse skills
GitHub
meta-architect-claudecode
Guide layer selection for Claude Code. Use when choosing between CLAUDE.md rules, skills, subagents, hooks, or MCP. Do not use for general coding questions or non-architecture tasks.
☆ 1View skill
GitHub
r2mo-rad-domain
R2MO Domain Intelligence Enhancer (AI Protocol)
☆ 1View skill
GitHub
toolkit-architect
Project scaffolding router for .claude/ configuration and local-first customization. Use when enhancing current project with skills, MCP, hooks, or subagents. Routes to specialized domain architects and toolkit...
☆ 1View skill
GitHub
qmd
Local search/indexing CLI (BM25 + vectors + rerank) with MCP mode.
☆ 1View skill
GitHub
skill-creator
Guide for creating production-ready Agent Skills. Use when creating new skills, improving existing skills, or diagnosing why a skill isn't working effectively. Covers skill quality standards, 5 skill type patte...
☆ 1View skill
GitHub
conversation-state-management
Implement DB-persisted conversation state for stateless AI agent servers. This skill should be used when users need to create/load conversations, append messages with role ordering, fetch history for agents, or...
☆ 1View skill
GitHub
openai-agents-sdk
Build AI agents using OpenAI Agents SDK with MCP server integration. Supports Gemini directly via AsyncOpenAI or OpenRouter for non-OpenAI models. Covers agent creation, function tools, handoffs, MCP server con...
☆ 1View skill
GitHub
ralph-router
Routes to appropriate Ralph skills based on agent role and task signals
☆ 1View skill
GitHub
plot-consistency-checker
Reviews plot structure, story beats, logic flow, and narrative continuity to identify contradictions, plot holes, pacing issues, or unrealistic elements.
☆ 1View skill
GitHub
chatkit-python
Build custom chat API backends for OpenAI ChatKit frontend using FastAPI. Covers chat endpoint implementation, SSE streaming, conversation persistence, and integration with OpenAI Agents SDK + Gemini via LiteLL...
☆ 1View skill
GitHub
repl
Persistent Python REPL server that avoids reloading heavy packages (torch, transformers, nnterp, vllm). Use when running multiple Python commands with heavy imports, loading ML models, or doing iterative testin...
☆ 1View skill
GitHub
subagents-knowledge
Complete guide to subagents for project-scoped workers in Claude Code. Use when creating .claude/agents/*.md files or adding context: fork to skills. Do not use for standalone plugin agent development.
☆ 1View skill
GitHub
skill-judge
Evaluate Agent Skills against official specifications and 8-dimensional scoring framework. Use when: (1) Reviewing SKILL.md files for quality, (2) Auditing skill packages for compliance, (3) Improving existing...
☆ 1View skill
GitHub
validate-skills
This skill should be used when the user asks to "validate skills", "check skill format", "verify agents", or "audit .claude directory".
☆ 1View skill
GitHub
openai-whisper
Local speech-to-text with the Whisper CLI (no API key).
☆ 1View skill
GitHub
api-claude-sync
Scans the .claude/ directory and updates CLAUDE.md to reflect current skills, rules, and agents
☆ 1View skill
GitHub
chat-api-orchestration
Implement single-endpoint chat API with deterministic request orchestration. This skill should be used when users need to create /api/{user_id}/chat endpoint, implement request validation, resolve conversation...
☆ 1View skill
GitHub
model-usage
Use CodexBar CLI local cost usage to summarize per-model usage for Codex or Claude, including the current (most recent) model or a full model breakdown. Trigger when asked for model-level usage/cost data from c...
☆ 1View skill
GitHub
skills-knowledge
Create self-sufficient skills following Agent Skills standard. Use when building autonomous capabilities with progressive disclosure. Do not use for general programming or non-Claude contexts.
☆ 1View skill
GitHub
orchestrator
Master coordinator agent that executes tasks by delegating to specialized agents in parallel, validating results, and ensuring quality
☆ 1View skill
GitHub
openai-whisper-api
Transcribe audio via OpenAI Audio Transcriptions API (Whisper).
☆ 1View skill
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. Use when building MCP servers to integrate external APIs or...
☆ 1View skill
GitHub
subagents-architect
Project-scoped context: fork router for .claude/agents/ with isolation and parallelism patterns. Use for creating, auditing, or refining subagents in current project. Routes to subagents-knowledge for coordinat...
☆ 1View 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.