Generate high-quality images using Doubao (豆包) AI image generation. Use when the user asks for AI-generated images, artwork, illustrations, or any visual con...
Extracts and analyzes Cursor IDE chat history to identify key discoveries, obstacles, and solutions, saving findings to the journal.
Extract reusable UI/UX design systems from frontend codebases: design tokens, global styles, components, interaction patterns, and page templates. Use when analyzing any frontend repo (React/Vue/Angul
Mulch Self Improver — Let your agents grow 🌱. Captures learnings with Mulch so expertise compounds across sessions. Use when: command/tool fails, user corre...
Run a unified SEO and GEO audit for a website, page, or domain. Use when the user asks for a full SEO audit, GEO audit, AI visibility review, EEAT review, en...
--- name: paper-parse description: Parse academic PDF papers into markdown with figure extraction. metadata: { "openclaw": { "emoji": "📄", "requires": { "bins": ["uv"] }
Generates professional slide deck images from content. Creates outlines with style instructions, then generates individual slide images. Use when user asks t...
Format and deliver rich Telegram messages with HTML formatting via direct Telegram API. Auto-invoked by the main session for substantive Telegram output — no other skills need to call it. Decision r
Aggregates and summarizes the latest AI news from multiple sources including AI news websites and web search. Provides concise news briefs with direct links...
Extract structured data (names, dates, amounts, entities) from unstructured text documents using AI. Returns clean JSON with extracted fields.
Create ClawhHub-ready OpenClaw skills with correct structure, scanner criteria, security rules & publish checklist. No credentials or binaries required.
深度多步网页研究。迭代搜索、页面抓取、综合分析，生成带引用的 Markdown 报告。触发词：deep search、deep research、深度搜索、深度研究、深度思考、深
SEO content brief creation with keyword research, search intent analysis, and content structure. Covers SERP analysis, heading hierarchy, word count targets,...
--- name: wip-x version: 1.0.1 description: X Platform API. Read posts, search tweets, post, upload media. homepage: https://github.com/wipcomputer/wip-x metadata: category: social,api api_base: h
Generate high-performing YouTube video scripts, titles, thumbnails, descriptions, and chapter markers from any topic or content
Integration scripts for the creative agent swarm managed by overstory (Claude Code). Use when configuring or running researcher, social media, blog, or scrib...
Call 32 real-world APIs — flights, hotels, weather, crypto prices, DeFi yields, stock quotes, web search, geocoding, IP reputation, blockchain data, code exe...
MCP skill for canva. Provides 22 tools: upload-asset-from-url, resolve-shortlink, search-designs, get-design, get-design-pages, get-design-content, get-prese...
Convert PDF, DOC, DOCX, and PPTX office documents to Markdown, supporting legacy .doc files with text extraction and basic formatting preservation.
Generate consistent, template-based Mermaid diagrams for technical content. Supports 12 diagram types (architecture, flowchart, sequence, concept-map, radial...
Compare academic research papers side-by-side to identify similarities, differences, and research gaps. Use when user wants to compare 1-5 papers via DOIs, U...
Perform high-performance web scraping, crawling, and Google search with multi-engine support and structured data extraction via AnyCrawl API.
Provides functionality to interact with SpreadJS tables in the web applications built by Forguncy (aka 活字格), specifically for extracting table data and colum...