Ready Agent 1 — is your codebase ready for the agents? Score agent-readiness (deterministic, cited, Level 1-5) and clear the gates.

Portable SKILL.md agent skills with automated LLM-eval harness (Microsoft Waza), using mock MCP server for evals. Cross-harness: Claude Code, Copilot, Cursor, OpenCode.

White-label content tooling for The AI Collective chapters. Instagram posts, carousels and reels in the brand identity, from Claude Code. Posts need no API key (local render). Built by the Florianópolis chapter.

Evidence-gated Agent Skill for migrating LabVIEW measurement software to Python with simulator, UI, hardware, data-parity, and EXE proof.

Opinionated Agent Skills for AI-native autodidacts — deep learning, dense papers, public proof. Opinionated Agent Skills for AI-native autodidacts — deep learning, dense papers, public proof. By School of the Bear

🧭 Audit and fix agent skill descriptions so they trigger reliably. For OpenClaw, Claude Code, and agentskills.io platforms.

TypeScript software architecture baseline with VS Code Agent Skills for AI coding, review, security, testing, API design, and delivery standards.

youtube-traffic-grabber - Claude Code Agent Skill (target LLM: Claude). Part of the mr-bridge.com toolkit.

Hermes Production Patterns是一套面向 Hermes Agent(https://github.com/NousResearch/hermes-agent) 的生产级工程模式集。 如果你已经装好了 Hermes，但发现： - 不知道怎么写一个「靠谱」的技能（Skill）？ - Cron 任务跑着跑着就跑偏了，没人发现？ - Agent 输出质量不稳定，全靠肉眼审查？ - 多个任务的状态全靠脑子记，一重启就断片？ - 错误一出来就把上下文炸了，Agent 直接失焦？ 这个项目就是为你准备的。 它不是什么「最佳实践」大合集——每一条模式都在真实的 7×24 运行环境中验证过，踩过坑，打过补丁，最终沉淀为可复用的工程公约。

求是 Skill 定制扩展版（基于 HughYau/qiushi-skill, MIT）：十大思想武器 + 决断收口 + 瞭望战略预见 + 一针见血文风

Project-standard skills for AI coding agents — engineering charters (Rust / Swift / Python / TypeScript / Kotlin + polyglot core) that make agent output trustworthy by construction.

A practical operating system for senior UX/UI and Product Designers who want to use advanced AI across the full product lifecycle: strategy, design systems, prototyping, project management, and design-to-code workflows.

DeepBLM — AI时代战略咨询方法论：IBM BLM扩展框架(14模块+执行四通道)、AI原生组织范式、Agent BU模式。用于企业AI/数字化战略转型。

AI Agent Skill for FIFA World Cup match summaries, daily recaps, public-source research, and optional football data providers.

Auditable forecasting skill for AI agents. Turns history, game theory, and psychohistory into testable predictions with scenarios, uncertainty, and Brier-scored ledgers.

Deploy websites to simple-host.app from your coding agent (Claude Code, Codex, Cursor) — one-command install. Static hosting + a per-site backend: state, collections, private pages, templates.

Personal AI agent skills I use in development workflows.

Codex skill for turning rough tasks into verifiable /goal prompts, Loop Cards, and multi-agent plans.

Agent skill for building Yggdrasil mesh-network apps in Go (via the ratatoskr library): embedded clients, HTTP/TCP/UDP servers, SOCKS5, port forwarding, peer management, NodeInfo/sigils — userspace, no TUN or root.

Agent Skill that beautifies a GitHub repo's storefront with verified facts: README redesign, badges, topics, social preview. No fake badges, ever.

Agent Skill for generating memory cards from files and web links with a zero-install local review frontend.

Install battle-tested skills into your AI coding agent in 30 seconds.

A pre-deploy security review skill for any AI agent (Claude, Codex, Gemini). Runs the 'Before You Deploy Your Vibe-Coded App' 8-category review on your real code.

Massive autonomous web research for AI coding agents. ⭐ Free Firecrawl alternative. No API keys. Open source. Sponsor ❤️

Agent Skill：让 Claude Code 等 AI Agent 一句话把消息推送到你的微信（Server酱/方糖）。npx skills add easychen/serverchan-skill

A Claude Code skill that migrates Arc browser spaces into Zen Browser, automatically, from the files. Folders, pins, and favorites carried over with nesting preserved.

🏺 炼妖壶 — 多SKILL智能融合引擎。将两个或多个AI SKILL合并成一个更强的SKILL，通过五轮炼化流程(解析→比较→确认→融合→验证)实现1+1>2的组件级智能融合。

This skill helps an agent create, revise, evaluate, and standardize prompts and agent instructions. It emphasizes role, goal, context, examples, constraints, and reliability checks so prompts are clear, testable, and safer to reuse.

A Claude Code skill that manages Git/GitHub for every project: interviews you for new repos, then autonomously commits, pushes, pulls and branches with conventional commits. Supports local-only mode.

AI-agent skills for marketers, growth & business analysts — competitor teardowns, funnel audits, pricing analysis & more. 12 ready-to-use Agent Skills.

Agent Skill system for turning ecommerce product briefs, selling points, and reference assets into validated AI video-generation SKU Skill packages.

A harness for testing, benchmarking, and tuning PostgreSQL extensions in an isolated, reproducible environment.

A Claude Code plugin marketplace that codifies engineering craft: disciplined Python and data-engineering practice alongside deliberate session-knowledge workflows, packaged as reusable skills.

The package manager for AI agent skills - lint, search, scaffold and install SKILL.md skill packs across Claude Code, Cursor, Codex and Gemini. Zero dependencies.

Add and operate transactional email, SMS, push & web-push from your AI coding agent — no provider lock-in. Skills + MCP for Claude Code, Codex & Cursor.

Armor for coding agents: a playbook of Claude Code skills that make an agent prove its work, not describe it.

上岸 Offer 助手 · 中文求职 Claude Skill：摄入简历/GitHub仓库/文档建经历库，按JD生成STAR量化简历(严格防虚构)，并做大厂式由浅及深深挖面试

Read-only SysML v1 model analysis skills for CATIA Magic: navigate, inspect, audit, report. Free to use, works with Claude Code and other agents.

A model-agnostic Agent Skills library for explicit routing, bounded context, and verifiable agent behaviour.

Public Hermes skill export prepared from a private Hermes skill.

Compile GitHub repositories into audited, portable agent skills for Claude, Codex, Copilot, OpenClaw, and Hermes.

Free advise-only AI agent skills that keep Laravel and PHP projects healthy. They read your project and recommend fixes, never edit code. For ▎ Claude Code.

Agent Skills for AI-native startup founders — a founder-playbook hub + 12 per-function skills. Adapted from Linas Beliūnas's One-Person Unicorn + Anthropic's Founder's Playbook.

Turn abstract natural-language quant strategy ideas into runnable, guarded backtest code.

Verified, token-aware project memory for Codex with selective loading, context budgets, and Git-reviewable Markdown.

High-standard open-source agent skills from OFOX AI — one monorepo. Install: npx skills add ofoxai/skills

Request AI-Readiness and Marketing Signal scans and use prioritized findings from your coding agent.

Personal AI-agent skills I make or find useful

Agent Skills for Claude Code by LinkYourSkill — including 'lys-teach', a stateful, mission-grounded teaching skill that produces beautiful HTML lessons on the LinkYourSkill 'Dark Cosmic' design system.

A company research skill for Codex and Claude Code, covering moats, financial quality, valuation, competitive attacks, pre-mortems, and long-term tracking.

Public agent skills for Codex and Claude Code

One local-first AI companion that knows all of you — work, feelings, family, health, growth. Open framework, private data. · 一个真正懂你全部的本地 AI 助手：工作/情绪/家人/健康/成长一体，框架开源、数据只属于你。

lookdev — a Claude Code skill: a human-in-the-loop web studio to tune AI-generated output by eye.

ModelBound CLI — token optimization, skill pipeline, version management, and cloud sync from your terminal or CI.

MM Design Systems: Premium Agent Skills for UI/UX, System Design, Apple HIG, Material 3, and Frontend architecture.

Structured multi-persona AI decision council skill — one defensible recommendation from independent expert personas, adversarial review, and evidence-weighted synthesis

Unified Loop Theory: one recursive Codex skill for turning vague goals into objectives, probes, traces, judges, repairs, memory, and gates.