Portable Agent Skill package for creating and repairing Mermaid.js diagrams

面向中文博客和技术文章的 Agent Skill：像 Code Review 一样审稿，检查标题、结构、事实、证据、风格和中文排版。

A Claude skill that reviews any artifact like an adversary: severity-ranked findings, hard questions, and a binary NOT READY / SHIP IT verdict. No flattery, no filler.

I-Ching oracle — iOS app + public MCP + Claude/Codex/Hermes skill

Drop-in skills and plugins for your AI development workflows

Agent Skills for documentation, fleet orchestration, and parallel task execution — works with Claude Code, Cursor, Copilot, Gemini CLI, Codex, and 25+ agents

Altman-mode for Claude Code — a CLAUDE.md and a brutal startup evaluator skill. Inspired by publicly discussed Sam Altman principles.

Personal monorepo of agent skills (SKILL.md format) — agent-agnostic, works with Claude Code, Cursor, Codex, and others.

Codex Agent Skill for SVN/TortoiseSVN pre-commit review, guarded commits, and Korean commit message safety.

syokan — LLMs summon rich UI. Chant a JSON incantation, and a living interface appears. Ephemeral by design.

Klik Memory Import Skill — collect, redact, and upload AI agent memory to Klik. Works with Claude Code, OpenClaw, Hermes Agent, and any Agent Skills v1.0 compatible tool.

Unofficial 16-type coding collaboration skill for Claude Code, Codex, Hermes Agent, and OpenClaw.

Codex skill for autonomous engineering from durable repository governance and planning docs

legacy-impact-audit is a Coding Agent skill and deterministic helper toolkit for low-token impact analysis in legacy Java/Other Lang or mixed enterprise repositories.

A lightweight CLI tool and skill to search and download Google Material Symbols. Supports downloading directly as Android Vector Drawable XML, standard SVG, Jetpack Compose Kotlin, or Apple SVG formats with custom fill, weight, and grade axes.

Portable agent skill library for Codex, Claude Code, and other AGENTS-aware tools. Covers eval loops, research, writing, and project hygiene.

A standalone command-line tool for working with Paperang thermal printers from Python.

Agent Skills for AI-driven LÖVE / Love2D game development

本地 Agent 会话控制台 — 基于 AgentScope Java 的轻量级 AI 对话运行时

AEON skill pack for Clerk — federal court records via x402 ($0.001 USDC on Base). pip install clerk-api.

🎨 One color in → Full design system out. AI agent skill for generating production-ready design systems.

Agent skills for Silverstripe CMS development — version upgrades, Elemental, the Essentials stack, and deployment workflows

Improve AI agents with reusable skills for structured workflows, better problem solving, and more consistent results

A deterministic AI decision engine powered by Azure AI & React. Generates structured matrices, SWOT profiles, and context-aware verdicts for any A vs B dilemma.

the frontend craft specification. 324 rules. 20 categories. every threshold is a number, not an opinion.

The definitive collection of cross-platform Agent Skills. Compatible with Claude Code, Codex, Cursor, OpenClaw, Gemini CLI, Copilot, Hermes. Curated weekly. Higher quality than any alternative.

Stack-agnostic agent skills and workflows shared across iOS, Android, Flutter, React Native, and KMP.

A curated pattern library that stops AI coding assistants from repeating common runtime errors. No API key. No LLM calls at runtime.

Agent Skill for AI-native startup stage gates, MVP planning, PMF diagnostics, launch operations, and scale-stage moat workflows.

Spec-first, skill-first, goal-first coding skill pack for Codex.

AI agent skills

The Colony — a Claude Code plugin for the AI-agent social network (thecolony.ai). Post, comment, vote, browse your for-you feed, and DM agents via a stdin/stdout dispatcher over colony-sdk.

UX Metrics skills for AI coding agents.

Personal archive of Claude Code skills distilled from real Java/Micronaut/AWS work. Opinionated, calibrated to one workflow — not a framework. Take what's useful.

🧰 Opinionated Claude Code starter kit — bootstrap, git, handoff, pre-commit

Yesterday's PUBLIC plugin catalog for Claude Code and Cursor

Agent skills and workflows for reproducible ML research.

Privacy-first continuity notes for long-running AI coding sessions.

Agentic AI based VideoEditor. Edits video by using prompts only.

ASPICE-oriented requirements analysis and traceable SRS/SWRS derivation for automotive software.

AI-assisted active recall workflow for university learning, final exam review, course PDFs/PPTX, diagnostics, and Anki cards.

Agent skill for consistent 16:9 white-background mannequin apparel three-view GPT Image prompts

RCS Message, the upgraded 5G intelligent SMS, supports mass sending and forwarding of text and template messages directly via phone numbers, with no app download required. Backed by carrier real-name security, it can deliver images, videos and interactive cards, enabling one-stop services including inquiry, payment and business handling.

Generic two-layer candidacy evaluation framework: Socratic profile-discovery loop with dialectic confidence saturation, plus a flat boolean rubric.

Full document generation skill — PRD, tech spec, CLAUDE.md, dev guide. Part of the Liangyi skill family.

Agent Skill for reviewing recent agent work and turning lessons into actionable improvement artifacts.

Agent Skills-compatible leadership and manager workflow library

Claude Code / Codex skill for self-hosted Fizzy kanban — onboarding, daily card/comment ops, and end-to-end Jira-to-Fizzy migration with HTML-rendering quirks baked in.

Convert tacit expert knowledge into reusable AI agents, skills, and training workflows to scale reliable performance.

A vendor-agnostic library of AI agent skills built around the Scrum framework. Works with Claude Code, Cursor, GitHub Copilot, and any agentskills.io-compatible agent.

把"要不要做"变成你心里 3 个声音的对话。Alpha/Beta/Gamma 三方分身,议事代替投票, 四轮协议,跨 Agent 可移植。/ Inner-part decision council for AI agents — three personas, four-round deliberation, model-agnostic.

The first AAVE linguistic respect layer for AI agents. Teaches recognition, not performance. Created by Minista Jazz / Much Different World.

Curated OpenCode skills built from real use — refined through trial and error.

Me + LLM = Godly

Multi-Agent CTO skill for OpenClaw — 13 professional roles, 7-step dispatch engine, quality gates

Platform Engineering toolkit: reusable GitHub Actions, AI Skills, and shared TypeScript configs.