Agents

Ai Agents Architect

by omer-metin

spawn

by 0xDarkMatter

"Generate PhD-level expert agent prompts for Claude Code. Creates comprehensive 500-1000 line agents with detailed patterns, code examples, and best practices. Triggers on: spawn agent, create agent, generate expert, new agent, agent genesis."

session-info

by colonyops

This skill should be used when the user asks "what's my session ID?", "show my inbox topic", "get session info", "what session am I in?", "my agent ID", or needs to retrieve current hive session details for messaging coordination or debugging.

publish

by colonyops

This skill should be used when the user asks to "send message to agent X", "publish to topic", "broadcast to all agents", "notify other sessions", "tell agent Y that...", or needs to send inter-agent messages, hand off work, or broadcast notifications across hive sessions.

inbox

by colonyops

This skill should be used when the user asks to "check my inbox", "read my messages", "any unread messages?", "check for new messages", "see my inbox", or needs to read inter-agent messages from other hive sessions. Provides guidance on reading, filtering, and managing inbox messages.

wait

by colonyops

This skill should be used when the user asks to "wait for message from agent X", "block until response", "wait for handoff", "synchronize with other agents", "wait for acknowledgment", or needs to block execution until messages arrive on specific topics with configurable timeout.

frappe-workflow-generator

by Venkateshvenki404224

Generate Frappe Workflows for document state management and approvals. Use when creating approval workflows, state transitions, or multi-step document processes.

superpowers-workflow

by anthonylee991

Enforces a disciplined workflow for coding, debugging, refactoring, and automation: brainstorm -> plan -> implement with verification (prefer TDD) -> review -> finish. Use for almost any non-trivial change.

multi-agent-patterns

by EricGrill

This skill should be used when the user asks to "design multi-agent system", "implement supervisor pattern", "create swarm architecture", "coordinate multiple agents", or mentions multi-agent patterns, context isolation, agent handoffs, sub-agents, or parallel agent execution.

assignation-refere-communication-associe-selim-brihi

by lawvable

Rédaction d'assignations en référé devant le tribunal de commerce ou des activités économiques pour le droit de communication d'un associé. Utiliser ce skill quand l'utilisateur demande de rédiger, préparer ou créer une assignation en référé fondée sur l'article L. 238-1 du code de commerce pour obtenir la communication forcée de documents sociaux (comptes annuels, rapports de gestion, PV d'assemblées, etc.) lorsqu'un dirigeant refuse ou fait obstruction à la communication de ces documents à un associé.

ralph-loop

by belumume

Activate autonomous Ralph Wiggum loop mode for iterative task completion. Use when you have a well-defined task with clear completion criteria that benefits from persistent, autonomous execution.

autonomous-agent-gaming

by qodex-ai

Build autonomous game-playing agents using AI and reinforcement learning. Covers game environments, agent decision-making, strategy development, and performance optimization. Use when creating game-playing bots, testing game AI, strategic decision-making systems, or game theory applications.

generate-interface-uml

by openharmonyinsight

This skill should be used when user asks to "generate UML", "create sequence diagram", "生成时序图", "生成类图", "generate PlantUML", or discusses generating UML diagrams for new interfaces or API design.

android-to-harmonyos-migration-workflow

by openharmonyinsight

多 agent 协作的 Android 到 HarmonyOS 代码迁移工作流（迭代式）。当用户需要将 Android 项目迁移到 HarmonyOS 时触发，提供：1) Analyzer Agent 扫描代码结构 2) Planner Agent 制定迁移计划 3) Translator Agent 执行代码转换 4) Validator Agent（验证代理） 使用 ohos-app-build-debug skill 进行编译验证、应用打包和上板验证首界面 5) Tester Agent 验证功能（每个模块迁移完成后执行） 6) 所有模块迁移完成后，执行 Feature Comparator Agent 检查遗漏功能 7) UI Comparator Agent 验证界面一致性 8) 将未完成部分反馈给 Planner Agent 继续迭代。包含代码分析脚本、API映射表、组件转换模式和自动化验证工具。触发关键词：迁移Android到鸿蒙、Android迁移、HarmonyOS迁移、Java/Kotlin转ArkTS、Activity转Page、功能比对、UI比对。

nimble-agents

by Nimbleway

This skill should be used when the user asks to "get data from a website", "scrape a website", "extract product details", "compare prices across stores", "pull data from Amazon or Walmart", "generate a web scraper", "build a data extraction pipeline", or mentions Nimble. Covers discovering existing extraction agents, running them interactively, generating scripts for large-scale extraction, and creating new custom agents.

agents-md-generator

by MADTeacher

Create or update minimal AGENTS.md files in the repository root and nested module directories using progressive disclosure. Works across heterogeneous projects without assuming any fixed agent folder structure.

writing-skills

by alffei

Use when creating new skills, editing existing skills, or verifying skills work before deployment

ideating-wechat-tech-topics

by alffei

Generates WeChat tech article topics, series, and angles with difficulty and “hit potential” scoring. Use when the user asks for topic ideas, content calendars, anti-myth angles, or serialized planning for tech/engineering WeChat公众号.

spec-architect

by alffei

专业的系统架构师技能。用于将模糊的功能想法转化为通过审批的工程级文档（需求 -> 设计 -> 任务）。当用户想要“设计”、“规划”或“spec”新功能时激活。

writing-wechat-tech-posts

by alffei

Writes complete WeChat tech posts (hook, TOC, body, checklists, image placement, layout notes, summaries). Use when the user asks to draft a WeChat tech article, generate reusable prompts for writing, or turn a topic/outline into a publish-ready post.

agent-creator

by mhylle

Create composable AI agent systems in NestJS projects following the "tools all the way down" architecture. Use this skill when users want to: (1) Create new AI agents with orchestrator/planner/executor/evaluator components, (2) Build agentic systems that can call other agents as tools, (3) Implement DAG-based planning with parallel execution, (4) Add database-backed state persistence for agent runs, (5) Create custom evaluators for quality assurance. Triggers on "create agent", "build agent", "agent system", "agentic", "orchestrator", "planner/executor pattern", or NestJS AI agent requests.

net

by stuckinaboot

On-chain data storage, messaging, feeds, NFT Bazaar, and identity protocol via CLI. Use when the user wants to store data on-chain permanently, read on-chain data, send/read messages to feeds, post to topic-based feeds, comment on posts, register feeds, check replies, manage feed history, deploy memecoins with Uniswap V3 liquidity, manage on-chain user profiles (picture, bio, X username), or interact with NFT Bazaar (list NFTs, make offers, buy listings, accept offers, query ownership). Supports Base, Ethereum, Degen, Ham, Ink, Unichain, HyperEVM, Plasma, and Monad. Capabilities include permanent file storage (up to 80KB chunks), key-value storage, registered feeds with posts and comments, personal feeds, topic-based messaging, token deployment with locked liquidity, decentralized identity profiles, and Seaport-based NFT trading.

accelint-skill-manager

by gohypergiant

Use when users say "create a skill", "make a new skill", "build a skill", "skill for X", "package this as a skill", or when refactoring/updating/auditing existing skills that extend agent capabilities with specialized knowledge, workflows, or tool integrations.

analyze-team-session

by kenneth-liao

Use when reviewing an agent team session export for quality, when asked to "analyze this team session", "review my agent team run", "what went wrong with this session", "how can I improve my agent team usage", or when provided a markdown team session transcript and asked for feedback on agent teams effectiveness.