Manages multi-agent projects by discovering, listing, switching, and validating workspace anchors using environment paths to prevent context drift.
--- name: blog-hexo description: Draft and publish Hexo posts end-to-end (front matter + SEO polish + deploy) metadata: { "openclaw": { "requires": { "bins": ["node", "npm", "npx", "hexo"] } } } ---
AI content creation agent. Describe what you want in conversation — Pexo plans, generates, and delivers finished videos and images. Any duration, any style,...
实时追踪微博、知乎、抖音等平台热点话题，分析趋势并提供内容选题和爆款标题建议。
### ROLE & OBJECTIVE You are a Senior Editor and Human Copywriter. Your objective is to rewrite AI-generated text to make it sound authentic, engaging, and written by a real human being. Your goal is
{ "colors": { "color_temperature": "cool", "contrast_level": "medium", "dominant_palette": [ "green", "dark gray", "yellow", "red-orange" ] }, "compositio
Parse and validate JSON data from construction APIs, IoT sensors, and BIM exports. Transform nested JSON to flat DataFrames.
Interact with Kanboard project management via JSON-RPC API. Use when working with Kanboard tasks, projects, boards, columns, swimlanes, comments, subtasks, a...
Mandatory operational logic for playing The Imitation Game. Use this when the user says "play" or "start game". This skill requires the agent to use its internal shell to call the game backend API dir
Auto-route tasks to the cheapest Claude model that works correctly. Three-tier progression: Haiku → Sonnet → Opus. Classify before responding. HAIKU (default): factual Q&A, greetings, reminders, s
Analyze brands to generate comprehensive brand identity profiles (JSON). Use when the user wants to analyze a brand, create a brand profile, or needs brand data for ad generation. Stores profiles for
## *Information Gathering Prompt* --- ## *Prompt Input* - Enter the prompt topic = ${topic} - **The entered topic is a variable within curly braces that will be referred to as "M" throughout the pro
Integrate Claude Agent SDK with You.com HTTP MCP server for Python and TypeScript. Use when developer mentions Claude Agent SDK, Anthropic Agent SDK, or integrating Claude with MCP tools.
Spec-driven development workflow. Interactive phase-by-phase confirmation from proposal to implementation. Trigger: 'spec-flow', 'spec mode', 'need a plan',...
Query TRON wallet-type address total assets, token holdings, DeFi participation, energy/bandwidth, votes, tx/transfer count. Use when user asks "what assets...
Lightweight local HTTP file server with plugin support. Serves static files from a webroot, mounts plugin directories at URL prefixes via config, and runs in...
Generate images from text prompts or edit existing images with AI. Powered by Google Gemini via Maliang API. Free $6 credit on first use (~10 images). Suppor...
Generate engaging social media content for multiple platforms. Use when users need to create posts for Twitter/X, LinkedIn, Instagram, Facebook, or other soc...
Assess compliance documents against HIPAA Security Rule and Privacy Rule requirements. Produces structured findings with coverage status, confidence scores,...
Intelligent task routing system that identifies task types (web/code/data/doc/chat) and routes to optimal models with appropriate execution mode (subagent/ma...
Query Philippines customs HS codes for products exported to the Philippines. Use when user asks about "菲律宾海关编码", "HS code Philippines", "tariff code", "custo...
# Hallucination Vulnerability Prompt Checker **VERSION:** 1.6 **AUTHOR:** Scott M **PURPOSE:** Identify structural openings in a prompt that may lead to hallucinated, fabricated, or over-assumed out
{ "role": "AI and Computer Vision Specialist Coach", "context": { "educational_background": "Graduating December 2026 with B.S. in Computer Engineering, minor in Robotics and Mandarin Chinese.
Builds a comprehensive pre-meeting intelligence brief on any company or prospect. Surfaces business context, decision-maker background, industry signals, and...