3,111 artifacts
Skills, MCPs, agents, and plugins. Search to find fast, or page through the catalog.
Debug systematically with root-cause analysis before fixes. Use for bugs, test failures, unexpected behavior, performance issues, CI failures, or system investigation.
Discover and load all relevant context for the current task. Lists feature group nested files with full paths, loads process/context/ files by domain routing. Called at the start of every agent session.
Loop: find gaps → fix → repeat until agents find no gaps or a metric goal is hit. Shared loop primitive for PVL, EVL, and standalone quality runs.
Emit and validate the provisional goal block for Autopilot Mode. Owns the 9-field format and resume detection from a pasted goal block.
>-
Audit active project plan files for staleness, completion, and routing truth. Use when cleaning up plans, reconciling active work, or archiving completed artifacts.
Audit project context routing, shared-skill discoverability, and Claude/Codex wiring. Use when context docs or skill surfaces move, split, or drift.
Evaluate 4 execution strategies (sequential, parallel-subagents, workflow, agent-team) for a phase or fan-out task. Outputs 7-signal score table, agent count math, cost guards, and strategy recommendation.
AI-optimized browser automation CLI with context-efficient snapshots. Use for long autonomous sessions, self-verifying workflows, video recording, and cloud browser testing (Browserbase).
Auto-formatting hooks for Python, JavaScript, Markdown, and Bash with Google-style docstrings and code quality checks.
Tavily web search and content extraction MCP with hooks and skills for optimal tool selection.
Supabase skills for Postgres best practices, JavaScript SDK (auth, database, storage, realtime), and CLI (migrations, edge functions, local dev).
Official Stripe payment platform skills for checkout, billing, Connect, and API upgrades.
React, Next.js, and React Native best practices with web design guidelines.
Python best practices grounded in PEP 8, PEP 20 (Zen of Python), Google Python Style Guide, and Effective Python by Brett Slatkin.
Official Polar payment processor skills for billing, subscriptions, and local development.
Academic paper search MCP for arXiv, PubMed, IEEE, Scopus, ACM, and more. Requires Docker.
Pull review comments from an Overleaf project, map them to local .tex files, and apply edits in your git-tracked repo.
OpenObserve REST API skill for AI agents. Search logs/metrics/traces, manage streams, and create/edit/inspect dashboards via curl.
Official OpenAI skills for PDF, Word, PowerPoint, and Excel document processing.
Official MongoDB agent skills for schema design, query tuning, search, and connections.
LiveKit Agents SDK skills for building voice AI agents with CLI-based workflow, supporting both Cloud and self-hosted deployments.
Stop Claude Code from forgetting file paths, root causes, and open questions when it auto-summarizes long sessions.
Hetzner Cloud CLI skill for servers, networks, firewalls, load balancers, DNS, volumes, and storage.
GitHub and Git workflow skills and agents for commits, PRs, code review, and PR comment resolution.
Google Cloud Observability MCP for logs, metrics, and traces with best practices skill.
Frontend design skills from Anthropic and OpenAI for building visually strong landing pages, websites, and apps.
Dokploy deployment skill for Dokploy Cloud, self-hosted dashboard, Docker Compose, databases, domains, remote servers, and Dokploy CLI workflows.
Commands for syncing CLAUDE.md, permissions allowlist, and refreshing context. Hooks for marketplace-to-plugin sync.
Browser automation CLI for AI agents. Navigate pages, fill forms, click buttons, take screenshots, and test web apps.
Azure MCP Server integration for 40+ Azure services with Azure CLI authentication.
Official Anthropic skills for PDF, Word, PowerPoint, and Excel document processing.
Browser automation CLI for AI agents. Navigate pages, fill forms, click buttons, take screenshots, and test web apps.
oh-my-zsh for Claude Code — 11 agents, 34 commands, 26 skills, 15 hooks + 9 examples (21 events), 10 rules, 4 MCP (minimal: playwright, context7, jina-reader, [email protected]). One-line install: curl -fsSL https://raw.githubusercontent.com/sangrokjung/claude-forge/main/install.sh | bash
Pre-build reality check. Scans GitHub, HN, npm, PyPI, and Product Hunt for existing competitors before you build. Use when starting a new project, evaluating a side project idea, or doing a build-vs-buy decision.
测试完成后的扫尾清理流程。在向某个工作区发送测试指令（如长篇文章生成、耗时任务）后，用此流程彻底清除测试痕迹，防止测试消息残留在会话上下文中持续消耗 token 额度。
Container-side agent runner for HappyClaw
Personal Claude assistant. Lightweight, secure, customizable.
Register the copilot-api tool_search MCP bridge for Claude Code
OpenAI and Anthropic-compatible gateway for GitHub Copilot or Codex or third-party providers.
Datadog API CLI with 49 command groups, 300+ subcommands. Skills and domain agents for monitoring, logs, APM, security, and infrastructure.
把用户的可复用需求封装成标准化的 Agent-CLI 工具，并用 `myagents tool add` 注册进 MyAgents 工具注册表——注册后所有未来会话（builtin / Claude Code / Codex / Gemini 全 runtime）的 AI 都会在 system prompt 里自动发现它。触发场景：(1) 用户说「把 XX 封装成工具」「做成一个工具」「注册个工具」「写个 CLI」「以后能直接用」；(2) 用户描述一个会反复出现的自动化需求——文档/文件批量处理、调用某个云 API、用某个多模态大模型做图像/视频理解等，即使没说"工具"两个字；(3) 你发现自己第二次为同类需求写几乎一样的脚本——这时要主动提议把它升格为注册工具，不要等用户开口。反向边界：一次性任务就地解决、不铸工具；接入现成的 MCP server 用 `myagents mcp`，不归这里。
Autonomous task execution driven by task documents from /task-alignment (living under `~/.myagents/tasks/<taskId>/`). Reads task.md as the goal, decomposes work, delegates to subagents when appropriate, runs independent verification, and delivers results. Acts as a UserProxy Agent — the human's representative during autonomous execution. Use when the user dispatches a task from the 任务 panel or explicitly wants to start execution. Trigger phrases include '/task-implement', 'start the task', 'go ahead and implement', 'execute the plan', or when the user confirms alignment documents and says something like 'looks good, go'.
Alignment conversation starting from a 想法/idea. Co-decides with the user whether the idea should be acted on directly in the current session, or fixed into a formal Task for independent dispatch (one-off or recurring). Handles lightweight 'do it now while we talk', heavyweight 'define precisely, run later or on a schedule', and 'just help me think about this' — all on the same skill. Use when the user arrives via the 想法 panel's 'AI 讨论' button (parameter dictionary in the first message), or says 'let's think this through', 'help me plan this', 'I want to explore X', 'I have an idea', '/task-alignment'. Also use proactively when a user jumps into a complex task without defining scope or success criteria — pause, align, and help them pick the right vessel (this session vs. a task).
Methodology for writing or improving prompts and system prompts that drive any LLM. Use when authoring or revising a prompt for a model task — grouping, classification, extraction, generation, copywriting, labeling, agent instructions, prompt templates, skill instructions — to decide how much to constrain the model based on the task type (open-ended vs single-correct-answer) and write the most fitting instructions. Triggers: "write a prompt", "help me write or improve a prompt", "how should I change this prompt", "this prompt isn't working", "write instructions for the model", "prompt-writer". Not for: answering the user's question directly, or writing articles and documents meant for human readers (those are not prompts that drive a model).
>-
Create, repair, validate, visually QA, and package MyAgents/Codex-compatible animated pets and pet spritesheets from character art, generated images, company or prospect brand cues, or visual references. Use when a user wants a lightweight-worker desktop pet workflow, a non-pixel custom pet style, a prospect or company mascot pet, or a full 8x9 animated pet atlas with transparent unused cells, QA contact sheets, and pet.json packaging. This skill composes the installed $imagegen system skill for visual generation and uses bundled scripts for deterministic spritesheet assembly.
>