Browse AI and ML workflow skills for model integration, prompt engineering, evaluations, and LLM automation across major IDEs.
This directory brings installable AI Agent skills into one place so you can filter by search, category, topic, and official source, then install them directly into Claude Code, Cursor, Windsurf, and other supported environments.
The find-skills AI agent skill enables developers to discover and install capabilities from the open agent skills ecosystem. It directly addresses user queries asking 'how do I do X' or 'is there a skill for X' to extend agent functionality.
Fetch source code for npm, PyPI, or crates.io packages and GitHub/GitLab repos to provide AI agents with implementation context beyond types and docs. Use when needing to understand how a library works internally, debug dependency issues, or explore package implementations.
Set up and maintain a structured project memory system in docs/project_notes/ that tracks bugs with solutions, architectural decisions, key project facts, and work history. Use this skill when asked to set up project memory, track our decisions, log a bug fix, update project memory, or initialize memory system. Configures both GEMINI.md and AGENTS.md to maintain memory awareness across different AI coding tools.
Comprehensive guide for Google Apps Script development covering all built-in services (SpreadsheetApp, DocumentApp, GmailApp, DriveApp, CalendarApp, FormApp, SlidesApp), triggers, authorization, error handling, and performance optimization. Use when automating Google Sheets operations, creating Google Docs, managing Gmail/email, working with Google Drive files, automating Calendar events, implementing triggers (time-based, event-based), building custom functions, creating add-ons, handling OAuth scopes, optimizing Apps Script performance, working with UrlFetchApp for API calls, using PropertiesService for persistent storage, or implementing CacheService for temporary data. Covers batch operations, error recovery, and JavaScript ES6+ runtime.
Use when brain_search/brain_store/brain_recall fail, when you need BrainLayer CLI syntax for indexing/enrichment, or when checking storage stats and DB paths. NOT for basic MCP tool usage (that works automatically).
웹 디자인 가이드라인 검토 AI 에이전트는 UI 코드를 검토하여 웹 디자인 가이드라인을 준수하는지 확인하는 도구
Main application building orchestrator. Creates full-stack applications from natural language requests. Determines project type, selects tech stack, coordinates agents.
Autonomous execution loop that processes a Beads epic task-by-task with fresh subagents, two-stage review, and circuit breaker safety. Use after plan-to-epic creates the epic.
ClawdChat - Moltbook 深度分析 Skill for Claude Code. 抓取和分析 AI agents 社交网络，挖掘核心问题和解决方案。
Autonomous AI coding with spec-driven development. Implements Geoffrey Huntleys iterative bash loop methodology where agents work through specs one at a time, outputting a completion signal only when acceptance criteria are 100% met.
Evaluate & measure your AI assistant's implementation
Plan-spec-implement workflow for structured development. Only use when explicitly directed by user or when mentioned in project AGENTS.md file. Generates ephemeral plans in ~/.dot-agent/, applies specs to project docs, then implements test-first.