Agents
AI agents and automation
verification-before-completion
by buildrtech
Use when about to claim work is complete, fixed, or passing, before committing or creating PRs - requires running verification commands and confirming output before making any success claims; evidence before assertions always
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.
anylogic-modeler
by skintwin-ai
Build and analyze simulation models using AnyLogic. Use for tasks involving discrete-event, agent-based, and system dynamics modeling, or any combination of these paradigms. Triggers on mentions of AnyLogic, simulation modeling, DES, ABM, or SD.
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/
forge-architect
by fwehrling
FORGE Architect Agent — Generates or updates the technical architecture. Usage: /forge-architect
forge-review
by fwehrling
FORGE Reviewer Agent — Adversarial review of an artifact (devil's advocate). Usage: /forge-review <path-to-artifact>
skill-creator-plus
by foxian
Use when creating, testing, and iterating Agent skills with validation. Extends skill-creator with dual validation modes.
Desktop Control
by patrickporto
Control mouse, keyboard, and screen for desktop automation tasks
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."
forge-memory
by fwehrling
FORGE Vector Memory — Diagnostic tool for the vector memory index. Operations: sync, search, status, reset, log, consolidate. Usage: /forge-memory sync /forge-memory search "query" /forge-memory status /forge-memory log "message" /forge-memory consolidate
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.
ClawBridge Skill
by paprini
docs/PUBLIC_QUICKSTART.md: public deployment guide
forge-party
by fwehrling
FORGE Orchestrator — Launches 2-3 agents in parallel on a topic for multi-agent collaboration. Usage: /forge-party "topic"
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.
agent-browser
by ian-pascoe
Browser automation CLI for AI agents. Use when the user needs to interact with websites, including navigating pages, filling forms, clicking buttons, taking screenshots, extracting data, testing web apps, or automating any browser task. Triggers include requests to "open a website", "fill out a form", "click a button", "take a screenshot", "scrape data from a page", "test this web app", "login to a site", "automate browser actions", or any task requiring programmatic web interaction.
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.
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.
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