Claude Code skills & agent prompts I actually reach for — copy-paste, no deps. Writeups at seangeng.com.

Data Pro Max: The Ultimate AI-Powered Intelligence Suite for Data Science, Survey Analysis, and Professional Reporting.

Prompt Distance (PD): a whitepaper-grade metric for how many prompts away a project is from not existing

Spec-driven multi-agent teamwork for any skills-capable agent (Claude Code, Codex, and more) — plan, dispatch, monitor, QA. No framework lock-in.

Portable /goal-writer agent skill for Claude Code and OpenAI Codex — drafts goal+rider document pairs (≤4,000-char goal + phased rider) per goal-engineering best practices

The batteries included framework for building Agent Skills.

Skills from famous (or infamous) computer science tomes - "PhD-level intelligence." | 让AI替你读烦人的大部头

Inspectable engineering workflows for OpenAI Codex.

A self-evolving AI Agent Skill (agentskills.io standard) that turns Claude Code, Cursor, Windsurf, or OpenCode into a personalized X (Twitter) social media manager. Features automated onboarding, voice-pattern extraction, algorithm-optimized posting/replying, and self-improving memory logs.

Skills for your AI agent to audit, rewrite, and build landing pages that convert. Every move grounded in a scored benchmark of real pages, not generic advice.

Research-first scouting agent skill for dependency, API, SaaS, prior-art, and build-versus-buy decisions before writing code.

Human-in-the-loop autonomous optimization — an agent skill that iterates change → measure → keep/discard against any objective metric. Generalizes Karpathy's autoresearch.

Agent-agnostic operating procedures for reviewing, debugging, testing, refactoring, and hardening software.

A skill package and helper scripts to turn prompts into Manim teaching videos with optional narration, muxing, and cover generation.

pump.fun trading skill for OpenClaw - launch and browse tokens, execute trades, manage wallets

Collection of my Agent Skills and books.

Agent skills for the Truesight MCP. Step-by-step workflow playbooks for scoring inputs, building live evaluations, error analysis, and the review loop. Works with Claude Code, Cursor, ChatGPT, VS Code, Windsurf, and any client that supports the agent skills standard.

AI assistant skills for the Marker.io MCP. Triage feedback, spot patterns, ship fixes.

Disciplined software engineering for coding agents: plan → review → build loops that actually terminate, with bounded rounds, fresh-reviewer exit gates, and TDD. Plugin for Claude Code and Codex.

Natural-language time tracking via a Claude skill — say what you did, an AI parses it into your Notion database and asks instead of fabricating when unsure.

Markdown registry for AI agent libraries with indexed HEAD/BODY content.

Agent skill for precise code navigation: locate functions fast, read less, save tokens.

AI Agent Skills for SEO auditing , 11 SKILL.md files that teach Cursor, Claude Code, Copilot & more to perform comprehensive SEO audits. Zero dependencies.

Claude code plugin to interact with fal ai

Your agents forget every correction. otto makes them stick.

Python CLI, TUI, and MCP server for searching Japanese restaurants on Tabelog

80+ agent skills for Pilot Protocol — communication, file transfer, trust, task routing, swarm coordination, and more

Agent Skills for Altertable

Agent Skill for creating and maintaining TYPO3 extension documentation | Claude Code compatible

Generate AI agent skills (SKILL.md) from TypeScript API docs — TypeDoc plugin + CLI + Docusaurus/VitePress

Lightweight, agent-facing routed knowledge base skill that gives coding agents durable project memory.

Local-first, open-source alternative to Anthropic's Claude Design. MIT-licensed, BYO agent CLI — Claude Code, Kimi, Codex, or any SDK-compatible model. Composable skills · three edit paths · designs as plain HTML/JSX/CSS folders · run locally, no cloud round-trip. Generate banners, thumbnails, websites, animations, design systems.

Cogniac agent skills

MCP server for Scholar Sidekick — resolve any scholarly identifier (DOI, PMID, PMCID, ISBN, arXiv, ISSN, ADS, WHO IRIS) into 10,000+ CSL styles or nine export formats, single or batch.

让本地 AI Agent 在线管理你的远程服务器。Zero-overhead SSH multiplexing CLI for AI agents — manage remote servers like local commands.

Agent skills for setting up and operating Estuary data pipelines through your AI assistant.

Composable agent skills (playbooks) for building enterprise-grade web services — covering architecture, resilience, testing, security, and observability.

Tier 1/2/3 system for designing agent skills.

Miniprogram skills tool - npx mp-skills 让小程序快速接入微信小程序 AI 开发模式——小程序 Skill 开发工具，支持快速创建新的 AI 小程序和 Skill，或将现有小程序改造为支持 AI 开发模式，并内置 AI 评测校验工具，保障 Skill 执行质量和稳定性

Portable, self-contained coding-agent skills

Shared public skills developed by Skill Engineer

vibe coding 是一次次问答，决策就这样一点点堆成产品。docstrata 用 grilling 把这些决策分层写进文件，有迹可循，有路可走。

Agent-first Telegram CLI with structured JSON/JSONL and skills for Claude Code, Codex, Antigravity, GitHub Copilot, Grok, Cursor, Amp, and other AI agents.

Deep KiCad skills for coding agents

本地优先的抖音视频、封面、直接音频和用户主页作品列表采集下载 Skill。

集中版控 Claude Code 使用者層級設定(skills / hooks / settings.json / CLAUDE.md),以 symlink 連回家目錄 — 換機或重灌時 git clone + install.sh 一鍵還原。

🐟 Suanfish Design System — 33 specialized AI design agents across 7 tiers with REJECT mechanism. Multi-agent design language SKILL for Claude Code / Codex CLI / Copilot CLI. v2.5 adds AI-native Path G (streaming · tool-calls · reasoning · citations · artifacts).

A collection of agent skills that give AI agents structured, reusable workflows for tackling complex problems.

Agent skills for search, RAG, and document parsing with Mixedbread. Install with: npx skills add mixedbread-ai/skills

更符合中国宝宝体质的学术研究PPT审稿&改进建议Skill

The only Telegram skill your AI agent needs. Read messages, parse channels, download voice notes. User API via Telethon.

Shared AI agent skills

Curated, polished agent skills for building calm native apps and running AI coding agents well. Works with Claude Code, Codex, and Cursor.

Comprehensive SEO optimization Agent Skills for Claude Code & Codex — technical SEO, structured data (JSON-LD), Core Web Vitals, E-E-A-T, and site audits based on Google's official guidelines. English & Japanese.

Shipshape is a context-isolated spec-driven development workflow for coding agents. Specs are durable. Code is disposable. Agents are replaceable.

A curated collection of papers & repos on Auto-Skill (self-evolving agents) and Auto-Rubric (rubric learning from preferences) for LLM alignment & customization.

Cross-agent marketplace of Universal Design Principles skills for Claude Code, Codex, Cursor, Gemini CLI, and other AI agents.

A comprehensive library of modular Agent Skills for Flutter & Dart development

徐望瀚日常工作中使用和维护的可复用 agent skills。

Claude Code 自我提升计划