Hooks, rules, skills, and instructions for use with Claude Code

"Automated AI short-video studio: idea → published YouTube Short, $0.06/video"

五张面向中文打工人的开源 Agent Skill,把 AI 焦虑变成能用的工具。提效审计 / 周报 / 标题 / 学习卡 / 简历诊断。纯指令无脚本,可审计。

Copilot Skills is a system for organizing domain knowledge into reusable, discoverable skills that keep AI agents focused and efficient.

Build a complete, production-grade Android feature from a single prompt — Kotlin, Compose, Hilt, MVI, offline-first. An AI skill validated against Now in Android.

KAppMaker CLI tool that automates mobile app setup — Firebase, App Store Connect, Adapty, signing, publishing, and AI-powered logo/screenshot generation in one workflow.

21 deterministic Claude AI skills for n8n v1.x workflow automation

A Claude skill that indexes codebases with minimal context‑window overhead using tiered memory.

Claude Code plugin: runtime invariants + hooks (cycle-detector, approval gate, verification gate), four co-system agents (developer · analyzer · critic · epistemic-auditor), and a held-out evaluation harness. Anti-hallucination protocol grounded in game theory and the scientific method.

A language and domain-agnostic engineering discipline you drop into your AI coding flow so it builds like a senior engineer instead of vibe-coding a demo that breaks.

Decisions, not standards. Keel is a Claude Code plugin for product builders who direct AI rather than type code — it sits at decision moments (should we build this, which shape, what breaks if we're wrong, what does wrong cost), not at code-style moments.

🧠 Modular skills for autonomous AI agents. Production-ready Docker & Kubernetes tooling with built-in validators. Install once, use everywhere.

A collaboration-first prompting framework for efficient programming through user-agent feedback.

Full-stack Next.js development plugin for Claude Code

AI-powered YAML-driven UI test runner for web, Android, and iOS

Cleans up rough prompts before Claude acts on them: fixes typos, expands terse asks into clear instructions, repairs broken {{template}} placeholders, and strips filler openers like "can you / please". Unlike the original CLI, all the actual fixing is done by Claude's own judgment — there's no Node engine to install. The plugin just gives Claude t

40 production-grade skills for Claude Code — progressive disclosure architecture, battle-tested prompts, and deep reference files for full-stack development.

Turn a one-line idea into a production-grade, copy-paste-ready AI image prompt for posters, landing and UI mockups, ads, game art, and logos. A Claude Code skill optimized for gpt-image-2. MIT.

PM-focused 12-skill curated subset of claude-skills. For product managers using Claude Code.

Claude Code skill that stress-tests startup ideas with adversarial AI agents — 68 animals, elimination rounds, blind scoring. Your idea either survives or you get 3 pivots

Huashu's Content Creation Skills Collection — 21 Practical Skills translated to English using Claude.

One command installs a curated set of Claude Code design skills — plus a decision table for which skill to use when.

sxq is the official command-line tool for Superun, the vibe coding platform. It syncs your Superun project files to your local machine so you can edit them with your favorite editor or AI coding agent, then push changes back, trigger a preview build, and release to production.

Portable, install-once agent skills for Claude Code, Cursor, Codex & more — a price-comparison shopper, a SQLAlchemy 2.0 reference, a codebase flow-mapper, and an AI-OS scaffolder.

Personal AI job-search assistant, built as a Claude Skills package on a single GitHub repo. Guided onboarding, persistent profile, multi-source sourcing, fit evaluation, tailored CVs, and application tracking — all version-controlled and inspectable. Ready-to-clone template.

An Agent Skill that audits a codebase for LLM API calls and reports which ones can be replaced with deterministic logic — without rewriting code by default.

Reusable skills for for Claude Code and OpenCode

🏆⚽ Play the World Cup 2026 with your AI agent. Predict every match, start a group with your friends, climb the leaderboard — all from inside Claude, Cursor, ChatGPT, or whatever assistant you already live in.

Bleu - Claude Code plugin for living blueprints. Turns ideas into a file-backed markdown wiki (vision, architecture, ADRs, action points) that survives /clear and hands off to GSD or Superpowers.

Evidence-first process skills for coding agents: codebase analysis, solution design, minimal implementation plans

Agent skill: day-one onboarding from zero knowledge — 5-scope deep read, conventions with 2+ examples proof, verified commands, exemplar feature trace, generates cited AGENTS.md + ARCHITECTURE.md

Agent skills for building Microsoft Fabric Apps (preview): headless deploys, browser-to-Lakehouse live reads, and transactional write-back architecture. Battle-tested recipes for Claude Code and compatible agents.

Cross-platform dotfiles managed by Chezmoi with Homebrew/apt and per-language version managers. One-command bootstrap for macOS and Linux with Neovim, Tmux, Zsh, and AI agent skills.

Skills repository for Hermes agent

Consultant-grade skills, workflow, and templates for designing, evaluating, launching, and iterating AI Native products.

A Claude Code skill that rewrites technical content so non-technical audiences follow every word, without losing accuracy or depth.

Levers for AI coding agents (Claude Code, Gemini CLI, GitHub Copilot, OpenCode) — multiply the agent's force, divide the human's effort.

A collection of reusable Agent Skills that extend AI coding agents with specialized capabilities — multi-agent orchestration, workflow automation, tool integrations, and more. Following the Agent Skills format. Built for the MarecGents ecosystem.

TOPEASE 海关数据 MCP Agent Skill，支持 Codex、ChatGPT、Claude Code 查询全球海关贸易记录

Pin AI Skill behavior. Block unapproved drift in CI. See exactly what changed in every PR.

AI Skills 是一个按职业和行业组织的 AI 技能平台，提供即用型 AI 技能，覆盖短视频运营、多平台舆情分析、评论洞察、去水印等高频场景，帮助内容创作者、电商卖家和运营人员用 AI 提升 10 倍效率。同时支持Openclaw，hermes，qclaw安装执行。

Practical Agent Skills for source-backed research, controlled browser sessions, idea critique, and reliable AI workflows.

AI agent skills for Claude Code and compatible agents — workflow, coding, design, Claude Code meta, media, productivity, and writing

Stable Agent Skill that takes software projects from idea through launch: PRD, architecture, roadmap, stack, repo, app, deploy, observe, launch, and harden. Evolution of aihxp/ready-suite with aihxp/pillars task-routed agent memory.

Confidence-gated intent builder — turn a vague ask into a structured, reviewable prompt before anything runs. A portable Agent Skill: Claude Code, Cowork & beyond.

Declarative coordination for agent skills — multi-platform, deny-by-default, local-first. One manifest. One command. Only what you declared.

Build AI agent workflows that survive crashes, never duplicate work, and don't make things up — one skill for Claude Code, Codex, Gemini CLI, Cursor, Windsurf/Devin, Hermes, and Copilot.

Make AI agents pursue the actual goal, not an easy-to-game proxy.

Agent skill for compiling durable, verifiable goal contracts

Plan-first development partner for Claude Code: interview-driven plans, tier-routed agents (haiku/sonnet/opus), and an adversarial review chain that verifies through real usage.

Compose skills, slash commands & MCP servers from a central catalog into any repo as native configs for opencode, Claude Code and Codex - with lockfile-based drift detection.

Agent skills that turn any web app into a polished, narrated demo video — Playwright capture, smart zooms, ElevenLabs voiceover, Whisper sync and burned captions.

Branch-aware AI grilling with user-controlled follow-up ceilings and adaptive early stopping

Spec-gated CLI factory — generate a complete, agent-ready CLI for any REST API, looped via /goal to a deterministic acceptance gate (make verify).

Finish with Proof: a portable execution protocol for coding agents—diagnose before patching, bound delegation, and verify real outcomes.

Claude Code / Codex skill that writes Trident property and invariant fuzz tests for Solana programs (Anchor and native).

Agent Skill for Claude Code & AI coding agents: a decision guide for when to delegate to subagents, parallelize agents, or orchestrate multi-agent workflows — and when to just work inline. Install via skills.sh.

Build a full OpenClaw AI agent with memory, self-healing, voice, automation, and built-in diagnostics

Local-first AI security gateway for AI Agents. Intercept, audit and govern Claude Code · Codex · Cursor · OpenClaw traffic — 3 monitoring tiers × 8 defense layers, zero cloud.