Generic multi-domain research framework with domain-aware scheduling. Model-agnostic and domain-agnostic - perform...
AI & LLM
LLM integrations, prompt engineering, and AI orchestration
8,092 技能
Generic multi-agent verification framework with balanced expert analysis. Model-agnostic and domain-agnostic -...
管理 oh-my-opencode 的 agent 和 category 模型配置。当用户需要查看当前模型配置、修改特定 agent/category...
Guide for creating effective skills. This skill should be used when users want to create a new skill (or update an...
为通用 AI 助手安装技能。当用户请求列出可用技能、从 Git 仓库（GitHub/GitLab/Gitea）或本地目录安装技能到特定 AI 助手（Codex、Roo、Claude、Copilot、Cursor 等）的指定作用域时使用此技能。
AgentMail MCP server for email tools in AI assistants. Use when setting up AgentMail with Claude Desktop, Cursor, VS...
Add email capabilities to AI agents using popular frameworks. Provides pre-built tools for TypeScript and Python...
Give AI agents their own email inboxes using the AgentMail API. Use when building email agents, sending/receiving...
Academic reference agent that identifies claims needing citations, searches PubMed/bioRxiv/medRxiv, and adds...
Heavy3 Code Audit - Multi-model code review for coding agents (Lite: DeepSeek, Pro: GPT+Gemini+Grok)
Blender best practices and Python code snippets for the Blender MCP server. Use when creating 3D models,...
Auto-update PROJECT_STATE.md after each git commit with AI-powered summaries. OpenClaw Skill
Intelligent document audit system for syntax and semantic verification, legal or technical document compliance...
Browser automation for E2E testing. Use when testing user journeys, verifying UI behavior, or running end-to-end tests.
Provides Oracle CLI integration for GPT-5.2 Pro review loops. Use when running external model reviews, multi-model...
Orchestrate parallel task execution with dependency analysis and self-healing. Use when running Ralph with multiple...
Contains the actual prompts and iteration requirements for each workflow phase. Use these prompts directly - they...
Implements Doodlestein's iterative review methodology. Contains exact prompts for plan review, beads review, code...
Guide UI design exploration using tasteboard for references, keystone for primary screen, and variants for...
|
|
|
Automatically extract reusable patterns from Claude Code sessions and save them as learned skills for future use.
A formal evaluation framework for Claude Code sessions, implementing eval-driven development (EDD) principles.