Audit and reduce YAML frontmatter bloat in AgentSkill SKILL.md files. Automates deduplication, flattening, and noise removal.

Data service for Agent: enables more efficient retrieval of information on news, companies (including stocks), public services (meetings, weather), products(e-commerce), AI models and etc.

Hermes Agent distribution with Ask DongFeng bundled as a built-in control-loop framework skill

Evidence-based K-skincare + K-wellness consultation skills for Claude Code (and 18+ AI agents via Vercel skills). RCT-grounded. Multi-language. Plus standalone interactive CLI.

Six evidence-disciplined research workflow skills for coding agents. Install with npx skills, direct download, or git clone.

End-to-end spec-driven change workflow that fuses Superpowers process discipline with OpenSpec's spec-driven artifact lifecycle — from idea to archived living spec. Cross-platform (Claude Code + Codex).

自己跑、自己改、自己说了算的简易多 Agent 框架 · Conductor + Sub-agents · Skills + MCP · 多设备同步

zilin 的个人 Agent Skills 库，真实在用的开发能力，可被 Claude Code / Cursor 等 50+ agent 自动发现安装

Claude Code plugin orchestrating agentic coding sessions — primers, session logs, and knowledge consolidation

A collection of portable, domain-focused AI agents managed by kman.

Generated by Codex. Read with caution.

Research-backed AI self-audit skill for Claude Code / Codex / OpenClaw. Verifies high-stakes answers via independent re-solve + cross-method probe — not by critique. Honest about limits; every design choice has a paper citation.

Reusable agent skills for real repository work: review, implementation, release, documentation, and project hygiene.

Prove whether a SKILL.md actually changes agent behavior (with/without) and which CLI harness does a task best — agent-native subagents or CLI. agentskills.io-compatible. Site: https://cskwork.github.io/skill-ab-eval/

Théo's collection of Agent Skills for GitHub Copilot

Universal AI agent skills (Claude Code, Cursor, Codex, GitHub Copilot, OpenClaw). Build once, use everywhere.

An open protocol for human-AI teaming.

Opinionated Next.js 16 starter for building with AI agents — ship features fast while architecture and directory structure stay under control: fixed structure, enforced conventions, curated libraries, preinstalled skills, native toolchain.

Portable Codex agent harness and config monorepo with reusable roles, skills, validation, eval tooling, and safe project install sync.

Complete guide to minimal universal configuration files compatible with all major AI coding agents.

Sallyn's personal collection of reusable coding agent skills

High-agency agent skills for executable specs and end-to-end shipping.

Decision Foundation: a free agent skill for mapping every viable path before deciding.

Agent skills for popular work processes: GTD, OKR, PDSA, DMAIC, Design Thinking, Lean Startup, OODA, and research paper writing.

A handy toolbox of AI agent skills that are compliant with https://agentskills.io specification.

Local-first Agent Skill Runtime for packaging SOPs, schemas, preflight checks, run records, and MCP tools as executable skill capsules.

Practical AI skills for PowerShell maintainers: Pester, scripting patterns, UI tools, and more.

🧠 Self-growing Claude agent skill system — auto-discovers, fetches from GitHub, creates via web research, and self-improves. Works in Claude.ai + Claude Code.

Curated skills from 50k+ star repos for research, writing, and review, ranked candidates per scenario

Supervised Codex and Claude Code handoff workflow packaged as a project-local Agent Skill.

A collection of reusable skills for Claude Code agents, dedicated for swe and developers

My personal Claude Code skills. Engineering process, context hygiene, and AI-agent maintenance — straight from my .claude directory.

一个可运行的蓝图：在 AWS 上搭建企业私有、可治理的 AI 资源注册中心 —— 基于 Amazon Bedrock AgentCore Registry + AWS CodeArtifact。

Agent skills that turn Nobel laureates' public process ideas into reusable workflows.

Reusable agent skills for planning, packaging, and scheduling social media campaigns.

SkillGate v0.1 proves that a local deterministic CLI can inspect one local agent Skill package before harness admission and produce a bounded instruction/capability intake report without executing, installing, or trusting the Skill.

Local Python CLI for governed AI-agent skill requests, evals, and evidence-controlled capability review.

Reusable Agent Skills for research figures, frontend refreshes, design workflows, model consultation, social research, and security asset searches.

A collection of elite, modular, and validated AI agent skills and system rules for Google Antigravity.

Behavioral cross-agent testing for agent skills — run a skill on Claude Code and Codex and assert deterministic outcomes.

Acuris Address Validation & Geocoding agent context — Claude Code plugin, Cursor rules/docs, and open Agent Skill (agentskills.io) packaged from one source of truth.

agentic workflows and skills

Cross-project agent workflow skills — session onboarding, handoffs, PR review, and merge workflows

Google Gemini CLI için Türk hukuku Agent Skills (extension): 81 skill, 1002 alt-konu. Hukuki danışmanlık değildir.

Custom Cursor AI agent skills for mobile QA workflows — bug creation, JIRA refinement, RC revalidation, crash analysis, and build installation. Built for a large consumer mobile app (iOS/Android).

Catch duplicate vendor payments before release｜付款前发现重复供应商付款

Auditable, portable agent skills that turn open-source maintenance - review, debugging, verification, handoff - into repeatable workflows for Codex, OpenCode, and Pi

Turn a one-line prompt into a playable mobile game. Eight composable Claude Agent Skills take it from concept to a built Godot app: design, art, audio, and packaging.

Reusable tools, workflows, prompts, and architectures needed for Agentic AI development.

Agent Skills for running and debugging Dataverse / Dynamics 365 plugins and Custom APIs locally with the xg CLI

Huawei network device (USG firewall + S/CE switch) CLI skills pack for OpenClaw AI agent — also usable as a standalone cheatsheet.

Agent skill for profiling large CSV, Excel, and PDF table files into compact LLM-readable structure digests; tested on IMF BOP/PIP-style wide tables.

Platform-agnostic ecommerce domain knowledge for AI coding agents. Agent Skills package distributed via Claude Code Plugin Marketplace and skills.sh.

Intent-anchored reading skill - learn a codebase another agent built, with a Feynman/plain-speech gate on every output.

A reusable control-plane pattern for using Codex to build, maintain, and verify Hermes-powered messaging-agent systems.

Claude Code plugin orchestrating the Laravel 12 + Livewire 4 + Tailwind + Alpine + Flux UI development cycle: grill-with-docs, to-prd, to-issues, tdd (Pest), open-pr, simplify, review-branch, organize-docs, update-roadmap.

Portable, open catalogue of agent skills for Cursor, Claude Code, Windsurf, Copilot, and other AI coding assistants.

Public collection of AI agent skills by @ryzs. Compatible with Claude Code, Cursor, Codex, Copilot, Gemini, and other skills.sh-listed agents.