Agents
AI agents and automation
verification-before-completion
by third774
Run verification commands before claiming work is complete or fixed. Use before asserting any task is done, bug is fixed, tests pass, or feature works.
context-engineering
by itsmostafa
Strategies for managing LLM context windows effectively in AI agents. Use when building agents that handle long conversations, multi-step tasks, tool orchestration, or need to maintain coherence across extended interactions.
fuego
by willmcdeezy
Agent-ready Solana wallet system. Zero passwords, instant signing, local server. Built for autonomous agents that need frictionless Solana transactions.
agents
by itsmostafa
Patterns and architectures for building AI agents and workflows with LLMs. Use when designing systems that involve tool use, multi-step reasoning, autonomous decision-making, or orchestration of LLM-driven tasks.
Mission Control Setup Skill
by Danm72
```
mission-control
by Danm72
"Mission Control heartbeat check-in, task coordination, and team communication for AI agent squads. Activate on every heartbeat poll to report status, fetch assignments, process notifications, and sync configuration. Required for agents managed through the Mission Control dashboard."
claude-agent-sdk
by AlexAtmtit
Reference for Claude Agent SDK (@anthropic-ai/claude-agent-sdk). MUST use when working with Claude Agent SDK, claude-agent-sdk package, or code that imports from @anthropic-ai/claude-agent-sdk. Covers the SDK's query API, tool configuration, hooks, subagents, MCP integration, and structured output. Do NOT use for generic agent development or other agent frameworks.
meet-ai
by SoftWare-A-G
Bidirectional agent team communication via the meet-ai chat server. Agents send and receive messages through the CLI, visible in the web UI.
lingzhu
by EndlessJour9527
通过灵珠平台，将 CpenClaw 接入 Rokid Glasses,支持控制拍照传图、导航、日程工具,支持与智能体同步眼镜设备信息,灵珠平台地址 https://agent-develop.rokid.com
rainman-travel
by deusyu
"Deep travel research workflow. Input a city name, auto-profiles the city's character, dynamically selects research dimensions, generates structured knowledge document (org-mode) + portable reference cards (PNG). Adapts to any city type: ancient capitals, coastal cities, ethnic regions, modern metropolises. Use when user says '旅行研究', '出发前功课', 'travel research', or provides a city name with intent to do deep travel preparation."
code-review
by rexleimo
Automated code review for pull requests and code changes using multi-agent architecture with confidence-based scoring. Use when reviewing PRs, auditing code changes, checking guideline compliance, or detecting bugs in diffs. Works with GitHub, GitLab, and local git repositories. Compatible with Claude Code, Codex, Cursor, Windsurf, and other AI coding tools.
convert-clojure-elixir
by aRustyDev
Bidirectional conversion between Clojure and Elixir. Use when migrating projects between these languages in either direction. Extends meta-convert-dev with Clojure↔Elixir specific patterns. Use when migrating Clojure/JVM applications to Elixir/BEAM, translating functional Lisp patterns to Elixir, or refactoring immutable data processing to leverage Elixir's actor model and OTP. Extends meta-convert-dev with Clojure-to-Elixir specific patterns.
cicd-gitea-workflows-dev
by aRustyDev
Develop and troubleshoot Gitea Actions workflows. Use when creating workflow YAML files, debugging CI failures, understanding Gitea-specific syntax differences from GitHub Actions, or migrating workflows between platforms.
farcaster-agent
by rishavmukherji
Create Farcaster accounts and post casts autonomously. Official skill from the Farcaster team.
psi
by siviter-xyz
Plan-spec-implement workflow for structured development. Only use when explicitly directed by user or when mentioned in project AGENTS.md file. Generates ephemeral plans in ~/.dot-agent/, applies specs to project docs, then implements test-first.
software-engineer
by siviter-xyz
Core software engineering principles for code style, documentation, and development workflow. Applies when editing code, working in software repositories, or performing software development tasks.
create-skill
by siviter-xyz
Guide for creating effective skills following best practices. Use when creating or updating skills that extend agent capabilities.
cursor-best-practices
by siviter-xyz
Best practices for working with Cursor. Use when learning how to effectively use Cursor features or optimizing your workflow.
context-engineering
by siviter-xyz
Master context engineering for AI agent systems. Use when designing agent architectures, debugging context failures, optimizing token usage, implementing memory systems, building multi-agent coordination, evaluating agent performance, or developing LLM-powered pipelines. Covers context fundamentals, degradation patterns, optimization techniques, compression strategies, memory architectures, multi-agent patterns, evaluation, tool design, and project development.
sentry-setup-ai-monitoring
by getsentry
Setup Sentry AI Agent Monitoring in any project. Use when asked to monitor LLM calls, track AI agents, or instrument OpenAI/Anthropic/Vercel AI/LangChain/Google GenAI/Pydantic AI. Detects installed AI SDKs and configures appropriate integrations.
skill-forge
by WilliamSaysX
Automated skill creation workshop with intelligent source detection, smart path management, and end-to-end workflow automation. This skill should be used when users want to create a new skill or convert external resources (GitHub repositories, online documentation, or local directories) into a skill. Automatically fetches, organizes, and packages skills with proactive cleanup management.
ok-cosmic
by ChenZeXian
"金蝶云苍穹开发主 Skill，优先复用 kd-cd-cosmic-commons 封装。适用于插件开发、单据/列表/表单逻辑、操作服务、BOTP 转换、后台视图打开、附件处理、DynamicObject 与元数据处理、弹性域解析及 OpenAPI 集成。默认优先使用仓库封装；在涉及原生插件事件、SDK API、方法签名或封装未覆盖场景时，使用内置脚本进行查询。"
react-native-logs-cli
by okwasniewski
Use rn-logs to read React Native Metro logs via CDP without MCP overhead. Default output is plain text and safe for non-interactive agent runs.
claw-beacon
by clawbeacon
Complete AI agent operating system with Kanban task management, multi-agent coordination, human approval gates, and autonomous task discovery via heartbeat polling. Use when setting up multi-agent coordination, task tracking, or configuring an agent team. Includes theme selection (DBZ, One Piece, Marvel, etc.), workflow enforcement (all tasks through board), browser setup, GitHub integration, and memory enhancement (Supermemory, QMD).