A framework-agnostic, git-native standard for defining AI agents
Healthiest
// sorted by health — what's thriving right now
// observatory (5535)
MCP server and CLI tool for searching and downloading documents from Anna's Archive
A Claude Code SKILL for designing beautiful, consistent web pages — spec first, code second.
A Boris-style agentic orchestrator TUI that supervises headless Claude Code agents through a gated software-delivery pipeline — pointed at any repository.
Organisation for your agent teams inspired by time-tested Royal Navy operating procedures.
A gorgeous XeLaTeX class + Claude skill for fill-in study notes — read and fill, learn by active recall.
一键检测浏览器环境,看 Claude Code 是否判定你为中国用户。纯前端,100% 本地运行,不上传任何数据。
给智能体安装了思维导图,让 Codex/Claude code/Agent 在复杂问题上用“可见思维树 + 轻量 MCTS”来探索,而不是线性瞎试。
一个 Claude Code skill —— 一份可用的科研写作教练(中文)。
See your codebase as a living architecture map — then edit the map and let Claude build the code
Interviews you, then scaffolds a self-running agent loop. Cross-harness (Claude Code / Codex / Hermes / OpenClaw).
Claude Code skill: translate English PDFs to Chinese via pdf2zh, preserving layout/formulas/figures.
Unknown-discovery guidelines for Claude Code, derived from Thariq's (Anthropic) 'A Field Guide to Fable: Finding Your Unknowns'
ملفات ذاكرة/سياق جاهزة تجعل Claude Code يُنتج صفحات هبوط سينمائية فاخرة لأي منتج عبر Higgsfield — Drop-in DNA for cinematic, scroll-driven luxury landing pages.
Claude Code skill for auditing your MEMORY.md index — size, orphans, broken links, staleness
See which AI coding agent needs you — right in your tmux tab bar. A colored dot per window (working/blocked/idle) with off-screen sound alerts. Works with op…
@elijahaifl on instagram built out the steps to have any claude environment recreate your own personalized instagram analytics dashboard
A practical, no-hype workflow for AI coding agents: context, plan, implement, review, QA, ship, retro. Templates, two Claude Code skills, and a 40% context r…
Claude Code skill + subagent for setting up guardrailed agentic loops (loop engineering): headless, evaluator-optimizer, meta/prompt-refinement, and fan-out…
Autonomous no-human-in-the-loop optimization research for Claude Code
Internal Andrej Karpathy CLAUDE.md rules for Claude Code, fixes common LLM code generation flaws. Sourced from X leak, for learning & research.
Portfolio case study generator built as a Claude Code skill. Turns messy project notes into recruiter-ready UX, product, and design case studies in 9 story f…
Loop Engineering — a skill for designing & reviewing autonomous/semi-autonomous agent loops (Claude Code, Codex, Copilot, Gemini).
A Claude Code skill that writes a verified HANDOFF.md so a fresh session can resume long-running work without repeating dead ends.
The open-source MCP server behind ByteAsk Embedded Docs: a source-grounded, page-cited evidence-retrieval server for coding agents (Claude Code, Codex, Curso…
Claude Skill for Generative Engine Optimization and agent readiness. Get cited by ChatGPT, Perplexity, and Google AI Overviews. Expose MCP, llms.txt, and OAu…
Claude Code skill for optimizing oversized CLAUDE.md files using progressive disclosure
Persistent persona modes for Claude Code: command-controlled personas (solo/parallel), a guided persona creator, and an on-demand team debate.
Five AI agents for technical interview prep: coding, system design, and behavioral mock interviewers plus a knowledge-quiz coach and a coding-practice coach.…