Claude Code skill: autonomously research an ML task and run many bounded experiments to find the best config — karpathy/autoresearch loop in the ml-intern or…
Healthiest
// sorted by health — what's thriving right now
// observatory (1954)
Interviews you, then scaffolds a self-running agent loop. Cross-harness (Claude Code / Codex / Hermes / OpenClaw).
A Claude Code skill that scaffolds ready-to-run LangChain Deep Agents and dcode CLI agents into any project.
claude-code-ai-rate-reducer — a Claude ecosystem project on GitHub.
Interview-driven compliance guardrail for Claude Code — makes your AI build with HIPAA (and soon SOC2) principles baked in, keeping protected data out of non…
Is your project as good as the best out there? sota-scan benchmarks your repo against real top projects and hands you a scorecard + to-do list. A Claude Code…
An executable SEO system for Claude Code: 26-section knowledge base + 9 slash commands running live audits against GSC and DataForSEO
Fable-style verification gate for Claude Code: don't say done until it's verified. Port of the Codex plugin by Agent Korea (플라잉따릉이).
Agent skill for Google + Naver SEO on Next.js (Cursor & Claude Code)
Two AI coding agents — Claude & Codex — in one window. Stream every step, cross-review, watch the cost, and catch the AI that claims it did the work but didn…
Claude Code skill: visual understanding & image generation with multi-channel fallback
A Claude Code skill: turn any expert's YouTube library into a source-cited personal coach via NotebookLM. Fixed fork of ArtemXTech/personal-os-skills.
Start over, simpler — recover the real requirements from a project that went down a bad path and rebuild on the simplest maintainable stack. A Claude Code pl…
DergiPark academic search as a Claude-in-Chrome skill (keyword + advanced field search, PDF→text, references) — no CAPTCHA, runs in your own browser.
Internal Andrej Karpathy CLAUDE.md rules for Claude Code, fixes common LLM code generation flaws. Sourced from X leak, for learning & research.
互動式 IT 故障排除 Runbook,整合 Claude AI。涵蓋 CCTV、NAS、AD、Exchange、Outlook 等企業常見場景。純靜態 HTML,GitHub Pages 一鍵部署。AI-powered IT troubleshooting runbook for Active Director…
High-fidelity Claude Fable 5 (Mythos) environment emulation and automated multi-agent jailbreak (Pack Hunt) research laboratory.
ツール呼び出しの出力崩壊を検知し、クリーンになるまで粘って復旧させる Claude Code プラグイン
中文克苏鲁的呼唤 (CoC) KP 跑团技能 · Claude Code / Codex / ChatGPT — 场景配乐、玩家可见讲义图片、可配置控制模式与分队 | Chinese Call of Cthulhu Keeper skill with diegetic music, image handouts,…
Contract-based multi-agent skill framework for Claude Code & Codex — compile YAML runbooks into SKILL.md with loop, parallel, and checkpoint support.
Persistent persona modes for Claude Code: command-controlled personas (solo/parallel), a guided persona creator, and an on-demand team debate.
Doubt, until what remains is certain. An MCP server that recursively doubts every plan decision — grounding each in real evidence or asking you — until it co…
Claude Certified Architect: Foundations exam prep — interactive practice exam, 5 domain cheat sheets, and official sample questions
洁癖 Skill: audit Codex, Claude Code, and Cursor skill usage
Turn your Mac into a wireless trackpad, keyboard & Stream-Deck — controlled from any phone's browser. No app install. Open source, built with Claude Code.
AI-native methodology for Go backend microservices: rebuild your codebase from docs/ + .claude/skills/ alone — correct, IO-efficient, architecturally sound b…
15 creative techniques. Intensity slider 0.3-1.0. Drunk fusion mode merges with Drunk Claude. 4 output styles including playing cards. Transforms Claude into…
Autonomous Claude Code task runner — a menu-bar app that tracks your usage and runs a to-do queue headlessly the moment your limit resets. macOS / Windows /…
庖丁 — dissect any AI skill into an anatomy handbook: why it works, how it's built, what's worth stealing. 把 skill 解成一本解剖手册的 Claude Code skill