agent-md

色彩科學／色度學完整中文學習筆記，包裝成 Claude Code skill，也支援 Codex。涵蓋 CIE 色度學、CIEDE2000、CIECAM02、色適應與演色性。

Skill pack that turns any coding agent (Claude Code, Codex, AGENTS.md-compatible) into a senior production engineer — FastAPI, PostgreSQL, Docker, deployment, security, observability.

OpenDream — open-source memory consolidation for AI agents. Reads past any LLMs sessions, dreams across them to extract patterns, and writes consolidated memory into AGENTS.md so the next session starts smarter. Local SQLite, BYO LLM, no SaaS.

Decision boundaries and installable skills for AI coding agents.

人味 Renwei — 书稿级中文去 AI 味 / Book-length Chinese AI humanizer. 51 rules covering AI tells, Euro-Chinese syntax, whole-book consistency & positive prose craft. Ships a token-free lint CLI. AGENTS.md compatible.

A portable, evidence-based AI personal trainer & nutritionist. Turns any file-capable agent (Claude Code, Codex, Cursor, opencode, Gemini CLI…) into a coach that programmes your training, logs sessions, calculates macros, builds meal plans — and remembers it all between conversations.

An AI job search system that refuses to invent things about you. Interviews you once, remembers on your machine, tailors applications from a verifiable fact ledger.

A tiny AGENT.md that helps coding agents write diffs you can kiss.

Stay in control of AI-written code without drowning in implementation details. Works with Claude Code, Codex, and any AGENTS.md-compatible agent.

Compile a project-specific AI dev team from your repo. Reads your code, runs a short interview, and generates grounded review agents + deterministic verification hooks for Claude Code, Codex, and Gemini CLI etc

Starter template for building projects with AI help.

融合多种棋类玩法的 3D 桌游（Three.js + TypeScript）。仓库纲领见 agent.md，提交规范见 git.md。

Reusable coding-agent kit for The Builder’s Handbook build-along books.

WRF protocol: AI workflow security infrastructure with dangerous command sentry alerts, context handoff, multi-task pause/resume, and human-AI contribution evidence.

ja/Codex Skills、AGENTS.md、LLMWikiと依存関係をローカルで確認・整理するWindowsアプリ en/A local Windows app for inspecting Codex Skills, AGENTS.md, LLMWiki, and their dependencies.

A compact operating system for coding agents that routes engineering tasks to focused playbooks, minimizes context usage, and enforces evidence-driven implementation and verification.

Regression testing for AI coding instructions. Catch stale repository references in AGENTS.md and CLAUDE.md.

An AI-agent-maintained knowledge wiki framework: instead of re-deriving answers from raw sources on every RAG query, agents ingest sources once and compile them into a structured, cross-linked, cited Markdown wiki organized into independent knowledge domains ("bundles") — works with Claude Code, Codex or any agent that can read markdown files.

Package manager and lockfile for agent skills (SKILL.md/AGENT.md/.cursorrules). Resolve, pin, hash, bundle, sign. Single Go binary.

Version your team's AI coding standards (skills + rules) as code, auto-sync them into Cursor, Claude Code and Copilot, and keep them fresh with a nudge -> skill -> PR loop. A GitOps-style starter template you can clone in under 5 minutes.