Agents
AI agents and automation
agent-creator
by kimasplund
Comprehensive guide for creating high-quality specialized agents following v2 architecture patterns. Use this skill when users need to design and implement new agents, understand agent architecture, or learn best practices for agent creation.
docs-seeker
by brixtonpham
"Searching internet for technical documentation using llms.txt standard, GitHub repositories via Repomix, and parallel exploration. Use when user needs: (1) Latest documentation for libraries/frameworks, (2) Documentation in llms.txt format, (3) GitHub repository analysis, (4) Documentation without direct llms.txt support, (5) Multiple documentation sources in parallel"
iphone-game-tester
by omkarv
Autonomous iPhone game-testing agent. Use this skill any time the user wants to automate, play, click through, grind, farm, or test a game on their iPhone via iPhone Mirroring. Triggers on: "run the game loop", "auto-play the game", "click through the game", "farm levels", "collect rewards", "keep playing", "test my game", "grind for me", "just let it run", or any request involving automated tapping, level completion, menu navigation, reward collection, or card play on an iPhone game. Also use when the user asks to continue a previous game session or build on what was learned before. Always load the game-specific knowledge file on startup if one exists.
idempiere-zk
by comitsrl
"Disenar y construir UI en iDempiere usando ZK (ZUL/MVVM) y personalizaciones de tema (CSS/imagenes) empaquetadas en plugins OSGi. Usar cuando haya que crear/modificar pantallas ZK, formularios/componentes, o diferenciar Stage vs Produccion con un tema."
refactoring-agents
by arielperez82
Guides ecosystem-level refactors of agents in this repo. Use when agents
Agent Interrupt Skill - 中断 Agent 任务
by hmsss
中断消息会推送到 Agent 所在的群聊
agent-usage-stats
by huyiling1111
"选择要监控的 AI 助手 → 查看 token 消耗。支持 Hermes / Claude Code / CodeX / OpenClaw，每次都让你选"
SkillScout
by sauronnitin
github.com/sauronnitin/skillscout
w05-task-closure
by qiao-925
任务收尾规范，包含日志生成和优化分析。适用于主要交付完成后的收尾阶段。
commit-commands
by YPYT1
Streamline your git workflow with simple commands for committing, pushing, and creating pull requests
retrospective
by ymkz
Conduct agile retrospectives using KPT method. Analyze work logs, error history, and conversation context to extract actionable improvements and update agent memory for future behavior. Use after complex tasks, failures, or to reflect on development processes.
kais-movie-agent
by kaiger666888
"AI短片/短视频/短剧全流程自动制作管线。触发词：movie agent, 短片制作, AI短片, 视频管线, film pipeline, AI视频制作, 短视频管线, AI电影, 影片制作, AI短剧, 短剧制作, 视频自动化, 全自动视频, 一键生成视频, AI拍片, 视频工厂, 批量视频, 生成短片, make video, create film, video pipeline, movie production, AI filmmaker。覆盖需求确认→调研→剧本→美术方向→角色设计→配音→场景生成→分镜板→视频生成→后期合成的完整管线，支持git版本管理和断点续传。"
executive-ciso
by shaul1991
Executive CISO Agent. 보안 정책, 리스크 관리, 컴플라이언스를 담당합니다.
fusion-issue-author-user-story
by equinor
Draft and update user-story issues with role-action-value framing, workflow scenarios, repository-valid labels, and explicit publish confirmation.
buying-and-selling-items
by GauteR
Investigates items and prices for marketplace buying and selling; suggests listing descriptions from images and points out flaws and prices.
t3-dot-env-zod
by Onnokh
T3 Env setup with Zod for Next.js 16+ and Vite. Use for implementing or debugging @t3-oss/env-nextjs or @t3-oss/env-core schemas, experimental__runtimeEnv, client/server separation, build-time validation, presets, and Zod env-safe coercions.
personal-context-manager
by lj22503
［何时使用］当用户需要管理个人上下文（Context）时；当用户说"管理我的上下文""整理重要信息""记录关键认知"时；当检测到"决策背景""记忆外脑""认知地图""内心认知"等关键词时；基于 AI 时代个人上下文管理需求，打造思维树构建师
Agent Browser
by yuanxiao0115
A fast Rust-based headless browser automation CLI with Node.js fallback that enables AI agents to navigate, click, type, and snapshot pages via structured commands.
agentic-actions-auditor
by aleister1102
"Audits GitHub Actions workflows for security vulnerabilities in AI agent integrations including Claude Code Action, Gemini CLI, OpenAI Codex, and GitHub AI Inference. Detects attack vectors where attacker-controlled input reaches AI agents running in CI/CD pipelines, including env var intermediary patterns, direct expression injection, dangerous sandbox configurations, and wildcard user allowlists. Use when reviewing workflow files that invoke AI coding agents, auditing CI/CD pipeline security for prompt injection risks, or evaluating agentic action configurations."
work-tracking
by mohammed-io
Enforces mandatory work tracking before any file changes. Ensures 100% compliance with work file creation, progressive todo updates, and proper completion. Use this skill for ALL tasks, bug fixes, features, and improvements.
agent-onboarding
by kaijie0074-art
新手上手 Agent 的交互式教程引擎。当用户想第一次体验 Agent 能干什么、需要被一步步带着完成一个真实任务、或说出"带我上手 / agent 上手 / 新手教程 / 教我用 agent / 我是新手不会用 / 体验一下 agent / 第一次用 / 手把手教我 / 我想做个微信群整理(文章转视频/竞品监控/经营日报/个人官网/自动作业/竞赛材料 等)但不会"时触发。本 skill 让 Agent 化身"上手教练"，用选项卡带用户选项目→自检环境(缺工具自动装)→先用样例跑通→再用真实数据→一步步动手做完→可推飞书→做完讲清"你只说了X、Agent做了Y、下次你只要这句话"。面向零基础、尤其语音交互用户。不要用于：已经熟练的用户直接下指令做事(那就直接做，不用进教程)。
claude-codex-gemini-collab
by caohui-net
Use when the user wants persistent Claude/Codex/Gemini collaboration state, task creation, claim/complete, or handoff to Codex/Gemini. Prefer this over omc ask for collaboration protocol operations; do not use for one-off advisor questions.
eve-cli-primitives
by Incept5
Core Eve CLI primitives and capabilities for app developers. Use as the quick reference for commands and flows.
chain-of-responsibility-react
by progmichaelkibenko
Implements the Chain of Responsibility pattern in React. Use when the user mentions chain of responsibility, CoR, or when you need to chain handlers that each process and pass to the next—validation pipelines, contextual help, event handling, or any sequential pipeline.