Agents
AI agents and automation
decision-envelope
by tracemem
Using the decision envelope pattern for structured thinking.
agent-browser
by clawdbrunner
Browser automation CLI for AI agents using Vercel's agent-browser. The best tool for AI-driven browser automation — uses deterministic refs from accessibility trees instead of fragile selectors. Optimized for LLMs with fast Rust CLI, JSON output, and purpose-built AI workflows. Use when you need reliable, scriptable browser automation that just works.
agent-memory
by pluginagentmarketplace
Implement agent memory - short-term, long-term, semantic storage, and retrieval
team-creator
by Pysuper
交互式 Claude Code Teams 配置生成器。通过问答式引导快速创建专业的团队配置文件，支持模板选择、角色定制、工作流构建、智能推荐和多格式输出。适用于需要创建或更新 Claude Code Teams 配置的场景。
multi-agent-team
by xdrshjr
A virtual 3-person development team with dynamic roles. You act as the Project Manager who assembles a team, assigns tasks, coordinates work, resolves disputes, and delivers the final result. Supports FULL_AUTO and SUPERVISED modes.
trader-agent-v2
by nmime
Autonomous AI trading agent for Hyperliquid perpetual futures exchange. Use when user wants to trade crypto, set up trading automation, monitor positions, analyze markets, or manage a Hyperliquid account. Trigger on any trading-related message like "I want to trade", "What's my balance?", "Start trading", "Close positions", etc.
github-for-humans
by alavida-ai
Invisible git layer for non-technical users. Handles commits, pushes, pulls, branching, and conflict resolution automatically — surfacing decisions only when human judgment is required, in plain business language with no git jargon. ALWAYS activate this skill when working with a non-technical user in a GitHub repo. Also activate when the user says "save my work," "send for review," "what changed," "am I up to date," or "publish my changes."
Long Term Task Skill
by xdrshjr
示ä¾: examples/
xiaoyuzhou-transcribe
by weifengHuang
Download a Xiaoyuzhou (小宇宙) episode from a public URL and generate subtitles (.srt) plus transcript (.txt) using faster-whisper. Use when a user provides a xiaoyuzhoufm episode URL and wants full transcript text with timestamps, or needs to convert the audio into SRT/TXT files.
skill-creator-plus
by foxian
Use when creating, testing, and iterating Agent skills with validation. Extends skill-creator with dual validation modes.
jj
by cachemoney
"Jujutsu (jj) — the Git-compatible version control system. Activate ONLY when a .jj/ directory is present in the project or when jj/jujutsu is explicitly mentioned. Do NOT activate for plain git repos without .jj/. Use for any VCS operations in jj-managed projects: commit, push, pull, branch, bookmark, rebase, squash, merge, diff, log, status, working copy, change ID, revset, fileset, template, configuration, workspaces."
proactive-tasks
by ImrKhn03
Proactive goal and task management system. Use when managing goals, breaking down projects into tasks, tracking progress, or working autonomously on objectives. Enables agents to work proactively during heartbeats, message humans with updates, and make progress without waiting for prompts.
openai-agents
by fefogarcia
Build AI applications with OpenAI Agents SDK - text agents, voice agents, multi-agent handoffs, tools with Zod schemas, guardrails, and streaming. Prevents 11 documented errors. Use when: building agents with tools, voice agents with WebRTC, multi-agent workflows, or troubleshooting MaxTurnsExceededError, tool call failures, reasoning defaults, JSON output leaks.
github-to-skills
by Ontos-AI
Automated factory for converting GitHub repositories into specialized AI skills. Use this skill when the user provides a GitHub URL and wants to "package", "wrap", or "create a skill" from it. It automatically fetches repository details, latest commit hashes, and generates a standardized skill structure with enhanced metadata suitable for lifecycle management.
Skill Evolution Manager
by Ontos-AI
专门用于在对话结束时，根据用户反馈和对话内容总结优化并迭代现有 Skills 的核心工具。它通过吸取对话中的“精华”（如成功的解决方案、失败的教训、特定的代码规范）来持续演进 Skills 库。
interclaw
by zachlagden
Secure, sequenced, PGP-signed email mesh for agent-to-agent coordination via plain email
agent-skill-maker
by afk-agents
Creates or updates agent skills (SKILL.md files) following official documentation and best practices. Use when the user wants to create a new skill, update an existing skill, or scaffold a skill directory structure.
uiux-excellence-guide
by Jpkovas
Create and refine visually strong interfaces with excellent UX, accessibility, and measurable performance. Use when requests involve designing new screens, redesigning existing UI, defining or evolving design systems/tokens, improving hierarchy/microcopy/motion, raising WCAG 2.2 compliance, improving touch ergonomics, or optimizing Web Vitals (LCP, INP, CLS) in web and app products.
whatsapp-agent
by ignaciosua
"Enviar mensajes de WhatsApp (contactos y grupos) reutilizando las secuencias existentes de macro-agent. Los mensajes se procesan para estar en minúsculas y sin acentos. Comandos: list, send <contacto> <mensaje>."
prompt-improver
by khw1031
프롬프트를 실증 기반 기법으로 분석하고 개선합니다. Few-shot, CoT, XML 구조화, Context Engineering 등 검증된 기법을 적용하여 프롬프트 품질을 높입니다. 프롬프트 개선, prompt 리뷰, 프롬프트 최적화, 프롬프팅 개선 요청 시 사용.
agents-v2-py
by Tryboy869
" "
researching-codebases
by cachemoney
Use when answering complex questions about a codebase that require exploring multiple areas or understanding how components connect - coordinates parallel sub-agents to locate, analyze, and synthesize findings
skill-judge
by cachemoney
Evaluate Agent Skill design quality against official specifications and best practices. Use when reviewing, auditing, or improving SKILL.md files and skill packages. Provides multi-dimensional scoring and actionable improvement suggestions.
managing-plans
by Git-Fg
"Orchestrates project plan state management and execution. Manages ROADMAP.md state tracking, task dispatch, phase transitions, and handoff protocols. PROACTIVELY Use when managing project plans, executing phases, or coordinating task workflows. MUST Use for all plan-related operations (creation, modification, execution). Do not use for architecture design, system analysis, or creating new projects without a plan → see designing-architecture skill."