在 Claude Code / OpenClaw / Cursor 中直接运行 agency-orchestrator YAML 工作流——无需 API key，使用当前会话的 LLM 作为执行引擎。当用户提供 .yaml 工作流文件或要求多角色协作完成任务时触发。

当需要开始与当前工作区隔离的功能开发，或在执行实现计划之前使用——通过原生工具或 git worktree 回退机制确保隔离工作区存在

Interact with Freshdesk support platform - search/view/update tickets, reply to customers, add notes, look up contacts, and manage Knowledge Base articles. Use when you need to manage support tickets, look up customer information, or work with KB content.

Manage Next.js dev servers across worktrees. Start, stop, and read logs from dev servers. Agents can access logs from any running session, regardless of who started it.

Browser automation via HTTP server. Supports multiple concurrent sessions for multi-user testing, saved flows, and profile-based auth persistence.

Use when code changes are complete and ready for quality review, before committing or creating PRs. Triggers after implementing features, fixing bugs, or refactoring code. Also use when user asks to check code quality, analyze technical debt, review code smell, or mentions "fuck-u-code", "code quality", "shit mountain", "code review", "static analysis". Covers all 14 supported languages (Go, JS, TS, Python, Java, C, C++, Rust, C#, Lua, PHP, Ruby, Swift, Shell).

When the user wants to optimize any form that is NOT signup/registration — including lead capture forms, contact forms, demo request forms, application forms, survey forms, or checkout forms. Also use when the user mentions "form optimization," "lead form conversions," "form friction," "form fields," "form completion rate," or "contact form." For signup/registration forms, see signup-flow-cro. For popups containing forms, see popup-cro.

Guide for creating effective skills. This skill should be used when users want to create a new skill (or update an existing skill) that extends your capabilities with specialized knowledge, workflows, or tool integrations.

Advanced multi-agent orchestration with parallel workers, synthesis protocols, and coordinator lifecycle. Use when complex tasks require multiple agents working in parallel with intelligent result synthesis.

API — Tenancy — 17 abstractions. Tenant lifecycle and installation event handlers and use cases.

Schema-based permission system for API features. Use this skill when implementing authorization in use cases, defining permission schemas with createPermissionSchema, creating injectable permissions via createPermissionsAbstraction/createPermissionsFeature, checking read/write/delete/publish permissions, handling own-record scoping, or testing permission scenarios. Covers the full pattern from schema definition to use case integration to test matrices.

Google Tasks operations through gog.

Google Slides operations through gog.

Google People operations through gog.

Google Analytics operations through gog.

通过 camoufox-cli 持久化 session wechat-channel 发布视频到微信视频号，支持视频上传、标题描述填写、即时发布。

Design or screen protein sequences for solubility-aware constraints with SolubleMPNN-style workflows. Use when a task asks for soluble protein design, expression-friendly variants, or solubility risk filtering.

Dispatch Feynman research notebook or experiment jobs to Modal. Use when a task has explicitly chosen Modal for bounded cloud compute, GPU jobs, or reproducible remote execution.

GEO-first SEO analysis tool. Optimizes websites for AI-powered search engines (ChatGPT, Claude, Perplexity, Gemini, Google AI Overviews) while maintaining traditional SEO foundations. Performs full GEO audits, citability scoring, AI crawler analysis, llms.txt generation, brand mention scanning, platform-specific optimization, schema markup, technical SEO, content quality (E-E-A-T), and client-ready GEO report generation. Use when user says "geo", "seo", "audit", "AI search", "AI visibility", "optimize", "citability", "llms.txt", "schema", "brand mentions", "GEO report", or any URL for analysis.

Watch a video (URL or local path). Downloads with yt-dlp, extracts auto-scaled frames with ffmpeg, pulls the transcript from captions (or Whisper API fallback), and hands the result to Claude so it can answer questions about what's in the video.