Art & Design

article-proof-check 是一个用于 SCI 论文 proof 阶段终校的 Codex skill。它面向作者收到期刊 proof、galley proof、校样、清样或 article proof 后的提交前最终检查，重点发现明确错误、出版排版问题、图表/引用/编号问题，以及需要作者确认的高风险信息。

article-humanizer-check 是一个用于检查学术文章、SCI 论文 proof 或正文中 AI 生成痕迹的 Codex Skill。它会识别过度模板化、宣传化、空泛化或 chatbot 式的表达，并给出局部、低干预的修改建议。

A draft-critique toolkit built from Glenn Kramon's Winning Writing at Stanford GSB and Rachel Konrad's cold-outreach guest lectures. 31 Claude skills, a browser Coach with span-level inline critic and refinement chat, plus a Chrome MV3 extension that runs the same critic in the Gmail side panel.

Production-grade Angular 21 + PrimeNG 21 enterprise architecture and Claude Code skill system for zoneless, Signals-first realtime applications with scalable frontend patterns, WebSocket architecture, Tailwind integration, and performance-focused engineering.

Private, self-hosted, Imgur-shaped image host on Cloudflare Workers (R2 + D1) — with a Claude Code skill + CLI.

Codex skills for mapping document format requirements to implementation plans and QA checks.

A complete set of Claude skills covering every phase of software development. Designed for JS/TS and Python stacks. Works for solo freelancers, small teams, and org developers.

A Claude Code skill for heuristic-driven exploratory testing with structured MCOASTER reporting. Invoke /exploratory-testing with a test charter and Claude will run a focused exploratory testing session using FEW HICCUPPS, SFDIPOT, I SLICED UP FUN, and more useful heuristics, then automatically produce an ET report with prioritised bug findings.

Claude Code skill — Marp beamer theme for academic talks. Inspired by neobeam; simplified tokens, bug-free tables and definition blocks.

Reusable Claude skills built for reliable outputs, not just better prompts.

A toolkit for Solidity smart contract auditors. SolAudit combines CLI analysis tools, Claude Code skills, and a local dashboard to take you from "I just received the code" to "here are my validated findings" — faster and with better coverage.

collection of claude-code skills for building nostr applications

Automated, auditable, and memory-informed Agentic SWMM framework for reproducible stormwater modeling, with QA verification, provenance tracking, calibration support, and integration-ready design for aiwmm, OpenClaw, Codex, or Hermes.

Tula is an open-source collection of OpenClaw skills, configurations, and patterns designed to transform a general-purpose AI agent into a personal health intelligence assistant.

A growing collection of AI agent skills I’ve built.

122 AI Agent Skills for full-lifecycle product development (PM × UI × Backend) | 覆盖产品全生命周期的122个AI Agent技能，从探索发现到增长运营，横跨产品×设计×后端三大领域

OpenClaw skill builder, scout, and a two-stage A/B evaluation framework for MLE agents

This project, maintained by @Flowerf19, contains a collection of custom skills, instructions, and prompt templates designed to enhance the capabilities of AI coding agents.

AI Agent Skill for end-to-end job hunting: 6-stage smart matching pipeline + resume optimization + interview prep + cross-session memory.

Web dashboard for managing OpenClaw agent skills, groups, and tag-based access control

Go CLI for London journey planning and live TfL arrivals, built for AI agents, OpenClaw skills, and time-critical transport alerts.

Official Claude Skills designed to support and enhance MACHHUB development workflows.

Codex skill for drafting California subpoena motion-to-compel packages, with OCR intake, exhibit/RJN tracking, authority-table discipline, section artifacts, separate statements, declarations, and Word-draft update workflow.

Local-first agent-orchestration CLI for Codex / Claude Code / OpenCode. 6 Rust modules — Compact-Reminder saves tokens on long sessions, Agent-Key auto-injects API keys so you don't re-config every session, Agent-Memory survives /compact — fix 7 coordination failures. Opt-in AiEconLab for econ research. v0.5.15 macOS/Linux/Windows binaries.