Real-world AI workflows for creators.

A curated collection of system prompts and tool definitions from production AI coding agents

Learn AI and LLMs from scratch using free resources

User-Centered Product Development Prompt Templates & Agent Configurations

Make Claude talk like a human: 17 installable output styles for Claude Code, built on credited methodologies

Local, read-only audit for stale AGENTS.md, CLAUDE.md, and generic SKILL.md instructions.

An atelier for your Agent: spec-driven workflows, deep thinking, and code quality.

Operator-grade AI agent skills for Claude Code, Cursor, Codex, and opencode.

The Enterprise-Grade Multi-Agent Orchestration Framework. Website: https://swarms.ai

Provider-neutral Agent Skill for Codex, Claude Code, and agentic harness design.

Reusable UI/UX design skills for AI coding agents — Codex, Claude Code, ZCode, and more.

AI Skills That Actually Do Things — 中文優先的 Claude Code / Codex agent skills 合集 · Reusable bilingual skills for any LLM workflow

Hermes Agent skill for grading SOUL.md identity files with a research-backed rubric and public-safe field guide.

Protocol-layer harness for DeepSeek: Python witness stack — posterior verification that keeps the protocol honest. dsh doctor --node probes included.

Claude Code, Codex, and multi-agent configuration system: principles, hooks, skills, and workflow patterns for AI-assisted development

Optimize any AI agent’s skills, tools/MCP, and prompts against your own evals.

Prompt packs that make any AI agent a LaTeX expert — fix errors, polish writing, format for venues, read papers, recover source

Master OpenCode, the open-source AI coding agent — setup, agents, skills, plugins, MCP, Zen & headless CI.

flow + prompt = flompt - Visual AI Prompt Builder. Decompose, edit as flowchart, recompile into optimized machine-readable prompts

✨ A customizable copilot-instructions.md ruleset & prompts to guide GitHub Copilot toward secure coding defaults in Java, Node.js, C# and Python. Blocks risky patterns, teaches safe habits.

📚 Two books on harness engineering — the design philosophies behind Claude Code & Codex: constraints, query loops, context governance, multi-agent verification. harness-books.agentway.dev

A portable memory protocol for AI agents — load it as standing rules; a curation discipline + reference spec + optional cap hook.

Build, Evaluate, and Optimize AI Systems. Includes evals, RAG, agents, fine-tuning, synthetic data generation, dataset management, MCP, and more.

Official agent skills from Black Forest Labs for FLUX image and video generation — prompting guides and API integration patterns for Claude Code, Codex, and any agentskills.io-compatible agent.