Agent skill for shipd.ai Olympus quest submissions — repo eligibility, originality sweeps, hidden tests, Dockerfile traps, and the full verify loop. npx installer for Claude Code, Cursor, and AGENTS.md agents.

dfo pvf agent skill

Humanize AI-written text — a portable agent skill that writes or rewrites prose to remove AI tells. Works in Claude Code, Cursor, Codex, OpenClaw.

Three complementary agent skills for academic research: WRITES papers, FINDS papers on a topic, READS any paper as a visual experience (mind maps, flowcharts, plain-English). Runtime-neutral, works with 50+ agents. Install: npx skills add aniketkrs/research-paper

drawing UI consistently with agents, at the top of Design System + Component Library

Agent skills for Bun 🍞

wan 2.7 text to image： https://www.wan27.xyz

You don’t need to be skillful — your agent’s got all the skills. Being skillless is totally fine.

Pattern-based scaffold for systematic AI agent work, with honest capability boundaries. Inspired by observed Claude Mythos Preview behaviors.

Generate, audit, and refresh Google Ads responsive search ad copy in 6 languages. 10 Claude Code / claude.ai skills. Open source.

VS Code extension development guide for AI coding agents. Install: npx skills add lewiswigmore/agent-skills

Make any repo AI native — fewer skills, conventions over steps, so any agent can cold-start, implement, self-verify, and write its decisions back.

My Claude Code skills. wong turns your work day into a study guide you can actually read. dormammu breaks your code until it works. agamotto summons a ruthless AI critic to tear your plans apart.

Agent skill that packages codebase context and runs up to 5 ChatGPT GPT-5.5 Pro Extended Thinking audit rounds via Chrome until plans are accepted.

Reusable skills for AI coding agents (pi, Claude Code, Agent Skills standard)

Agent Skills for Happy Hacking Space's open-source security tools. Compatible with Claude Code, OpenAI Codex, Gemini CLI, and Cursor.

Institutional-grade six-stage stock research pipeline for retail investors, as a Claude Code Agent Skill. Taiwan/US/HK/China-A markets. Research only, never places orders. 散戶自用的機構級個股研究流程，僅供研究參考不下單。

Skill for building memory by agent itself

Research workrooms for AI agents: evidence retrieval, citation audit, adversarial review, peer review gates, and clean final reports.

Claude Agent Skills for Yocto Project, OpenEmbedded, and BitBake workflows - AI coding assistant skills for recipes, layers, images, BSPs, SDKs, metadata, QA, sstate, and build troubleshooting.

Self-evolving skill packs that give Claude Code & Codex judgment, not knowledge — decidable rules, per-playbook regression quizzes for models, and a project harness generator. zh-TW canon + full EN mirror.

Cross-agent skill that turns any research topic into a polished, interactive HTML field guide — sidebar nav, ⌘K search, SVG ecosystem map, 2×2 strategic matrix, 22-part editorial structure, VC/CB Insights depth. Claude / Codex / Gemini / Cursor.

把 Claude Code 的开发会话提取成时间线骨架，并生成公众号长文。A Claude Code skill that turns your dev sessions into a publishable story.

Drop-in skill for aislop — the engineering standards layer and quality gate for AI-written code. Install via 'npx skills add scanaislop/aislop-skill'.

agentic-dev-docs 是一个面向 Codex 的文档优先开发规划 skill。它不会直接替你开工写产品代码，而是先把项目想法、需求说明或开发任务整理成一套可以交给 Codex 新窗口执行的“主控开发控制包”。 这套控制包的目标是让后续开发过程更可控：先明确项目画像、阶段边界、权限矩阵、workstream 分工、Review 和审计规则，再由唯一的 A 主控智能体协调执行。

Let your agent proactively recall local Copilot CLI sessions and reconnect past ideas.

An open-source framework that configures AI as a genuine tutor — not an answer machine.

多智能体群聊工作台：本地圆桌 Agent 用于方案讨论，战略分析、风险复盘。自定义名人角色进行群聊争论出最佳方案

🧩 A type-safe and composable architecture for modular monolith development in TypeScript.

[research-agent] Never send a human to do a machine's job.

Agent Skill for Evaluation-Driven Development (EDD) - guide AI evaluation strategies with the 50-40-10 rule

AI-ready community operations SOPs with safe automation, human approval, and verified execution.

可直接拖入工作目录的数学建模Agent Skill与Dify九库多模态MCP桥，支持Codex、Claude Code及其他Agent

Unattended PRD delivery for Claude Code

Agent Skills for nmBot.

Design, generate, package, repair, and verify polished app icons from briefs, brand assets, references, SVGs, existing icons, and generated concepts.

Reusable GitHub Actions workflow and Copilot skill for World Bank open source compliance.

Generate AI-powered PowerPoint presentations from academic papers with native math, diagram support, and multi-stage content analysis.

AI agent skills for building better software products.

Skills that guide AI coding agents to integrate with the Adaline platform — send traces, manage prompts, run evaluations, fetch deployments, and more. Compatible with Cursor, Claude Code, Codex, Windsurf, and 40+ other agents.

Governance-first agent command center for workflow automation, validation, policy, documentation sync, and execution discipline.

Watchlist-driven intelligence pipeline crawling LinkedIn, X, RSS, and email into one neutral signals brief.

高保真风格化对话代理。提供对方的聊天记录和表达习惯，Skill 学习后模仿对方的方式说话——让你感觉就像真人一样

Portable, self-contained snapshot of a complete Claude Code setup — 36 specialist agents, 134 skills, plugins, MCP servers & host tooling. Clone, claude login, run one script, restore the whole orchestration stack in ~20 min.

The skills guide Blazor development across all hosting models (Server, WASM, Hybrid, Auto) including data grid, chart, scheduler, rich text editor, gantt chart and more.

Lightweight HTML-to-Markdown parser for AI agent workflows — Python CLI and API around a fast Go engine, available on PyPI.

Loop engineering: two skills in the open Agent Skills format (idea-to-spec with a required grill step, spec-to-done with an evidence ledger and integrated done gate) for turning ideas into reviewed specs and driving them to an evidence-backed done. Works with Claude Code, Codex, Cursor, Gemini CLI, and any Agent Skills-compatible tool.

Single source of truth for AI coding rules across Claude Code, Cursor, Copilot, Codex, and more. Write once, sync everywhere.

Hyperliquid skill for AI agents — HyperEVM JSON-RPC, Info API, gRPC streaming, Orderbook WebSocket via Dwellir

Systems Thinking Workflow Architect helps an agent decompose complex problems and design reviewable process artifacts such as workflow maps, SOPs, decision trees, lead-generation processes, bottleneck analyses, and agent flow plans.

Debian packaging skill with comprehensive policy, debhelper, and language-specific knowledge for Ruby, Python, Rust, and Go. I mostly use this for personal, private packages not OSS Debian packages. This skill isn't ready for that.

Comment on local HTML pages — highlight, ask, or annotate; an AI agent applies the change and the page reloads with a tour. Bring your own pages, or have the skill generate one to comment on. Works with Claude Code, Cursor, or any agent CLI.

The mate who helps you ship. Agent skills that turn your AI into a skeptical, evidence-keeping cofounder-grade companion: stage diagnosis, venture memory, kill rules.

A Claude Code skill that ends your session with a song. Transcript -> Gemini (mood/vocal direction) -> Google Lyria 3 -> auto-play.

Host-agnostic exhaustive multi-agent orchestration as a portable Agent Skill — the /ultracode method on any coding agent that can spawn subagents.

A curated library of production-ready skills and tools designed to supercharge ClaudeCode, AntiGravity, Cline, RooCode and other agentic IDE extensions.

Public Agent Skills for Codex operations, Cursor operations, Claude operations, repo maintenance, skill maintenance, productivity, and engineering workflows.

Predict-before-reveal tutor inside your Claude Code / Codex session: after AI writes your code, it picks the one decision you can't explain, makes you guess why, then teaches the why on your own code.