Agent skill that turns big tasks into a reviewable stack of draft PRs. Works with Devin, Claude, Codex, and any harness supporting the Agent Skills │ standard.
Fresh Commits
// most recent commits — actively being worked on
// observatory (3738)
ConardLi's open-source Skills collection, featuring web design, knowledge retrieval, image generation, and more.
Private local meeting rooms where Codex, Claude Code, and other agents collaborate live.
Multi-agent Claude Code plugin: parallel specialized reviewers (bugs, security, CLAUDE.md compliance, git history, test coverage), confidence scoring, termin…
TikZ for paper diagrams, without hand-writing TikZ — copyable icons, editable templates, and a Claude Code skill
Examples of my Claude Code infrastructure with skill auto-activation, hooks, and agents
Pressure-tested Claude skill: decompose hard tasks risk-first, verify with pasteable evidence, decide what to do next. Built with skill-TDD against observed…
Live hardware status display for Claude — model, current tool, tokens, context and rate limits on a LilyGo T-Display S3 Long. Works with Claude Desktop (Cowo…
Skill de otimização de LinkedIn e currículo, usável em Claude Code, Cursor e Codex
AI Fluency — see how you actually build with AI. A fluency score, builder archetype, and 4-competency skill map from your local Claude Code transcripts. 100%…
Local AI coding session analyzer — privacy-first, read-only Claude Code transcript parser with builder archetypes and efficiency scoring
A Fort Boyard–style water clock for your Claude Code context window — /clear before you're trapped in the context-rot room.
Run Claude Code (or another coding agent) unattended, inside a disposable microVM, with its work committed to git so you can review everything from your host.
A macOS app to browse and manage the memory files Claude Code keeps for your projects.
Run Claude Code as a worker on a dedicated Mac. It keeps working after you close your laptop.
本地自托管的 Grok Build → Claude Code / OpenAI 兼容代理 | Local self-hosted Grok Build compatibility proxy
README-ROAST — Your README is lying to you. A Claude Code skill that generates brutally honest alternate READMEs with 5 personas. Honesty Score, badges, CI i…
A Claude skill that builds PPTX decks matching your real designer decks: extracted design DNA, measured word budget, render-QA loop.
Turn your markdown vault into a compounding knowledge wiki (Karpathy inspired). Six agent skills - knowledge grows with every conversation. Works with Obsidi…
A Codex / Claude Code skill for rebuilding visually complex documents into page-aligned Markdown.
"Done" means nothing — a menhera-style completion gate for Claude Code that blocks empty completion claims until tests actually ran green and no TODOs are le…
Track how much time you spend using Claude Code to AI-code
One local, searchable index of your AI coding-agent history Claude Code, Codex, Cursor, Gemini & more. Keyword + semantic search, MCP server, CLI & VS Code e…
23 specialist Blender skills for Claude Code, Cursor & Kiro - MCP-powered production pipeline from blockout to engine export.
ACP-friendly Node.js SDK for local coding agents: run Codex, Claude Code, Cursor, OpenCode, and Pi with streaming, abort, and session resume.
Windows-native replica of Claude Science research workbench
Benchmark-calibrated per-subagent reasoning effort for Claude Code. Classify the subtask, dispatch the cheapest tier a blind grader still accepts. Pilot-prov…
Ultrademo is an automated demo video generator for any websites, SaaS applications, etc. - executed conveniently through a Claude Code skill.