Claw0X_skills

Analyze YouTube channels, track competitor activity, and discover content opportunities. Use when users need to monitor YouTube channels, analyze a niche or category for content gaps, identify viral patterns, or plan content strategy. Handles competitive intelligence, market discovery, and trend analysis for YouTube creators.

Analyze SERP competition for any keyword. Use when you need to check if a keyword is worth targeting. Scores competition across 5 dimensions, identifies authority sites, assesses content depth, and provides go/differentiate/avoid recommendation.

Full-site keyword research with three-phase funnel. Use when you need to find SEO keyword opportunities for a website. Analyzes site topics, expands 30+ candidate keywords, runs SERP competition analysis on top 10, and recommends top 3 keywords with actionable landing page suggestions.

Generate SEO-optimized page structures from keywords. Use when you need to create landing pages, guide pages, comparison pages, or hub pages from trending keywords. Handles search intent classification, template selection, meta tag generation, schema markup, and SERP competitor analysis.

Audit web pages for P0 SEO compliance. Use when developers need to validate server-side metadata, image alt tags, keyword density, FAQ sections, and breadcrumb navigation before publishing. Handles Next.js App Router pages and returns actionable fix recommendations.

Translate text between 50+ languages with auto-detect and batch mode. Use when agents need multilingual content pipelines, global communication, or document translation. Handles Chinese, Japanese, Korean, Arabic, Hindi, and more.

Strip ads, navigation, and sidebars from any article URL or HTML. Use when agents need clean reading content for LLM context, article summarization, or RAG pipelines. Returns title, clean text, excerpt, and word count.

Send transactional emails in bulk with template variables. Use when agents need notification pipelines, outreach campaigns, or drip sequences. Supports HTML templates with {{variable}} substitution.

Parse, filter, sort, and transform CSV data. Use when agents need ETL processing, data pipeline glue, report generation, or spreadsheet automation.

Scrape Google SERP results: titles, URLs, snippets, and related searches. Use when agents need SEO research, competitor tracking, SERP analysis, or web research without API keys.

Validate JSON data against a JSON Schema. Use when agents need to verify API responses, validate pipeline data, check CI quality gates, or ensure config files match expected structure. Returns detailed error paths.

Fetch top news by topic from major outlets via RSS feeds. Use when agents need daily briefings, media monitoring, news research, or trend tracking. Supports technology, business, science, world, health, sports topics.

Generate QR codes as SVG for URLs, text, vCards, WiFi credentials. Use when agents need marketing materials, business cards, product packaging, or shareable links. Returns SVG and base64 data URI.

Apply regex patterns to text and return all matches with capture groups and positions. Use when agents need log parsing, data cleaning, pattern detection, or text extraction. Supports flags, named groups, and multiple patterns.

Capture full-page or viewport screenshots of any URL. Use when agents need visual testing, OG image generation, content archiving, or website monitoring.

Query DNS records (A, AAAA, MX, TXT, CNAME, NS) for any domain. Use when agents need domain research, security analysis, email deliverability checks, or infrastructure discovery.

Extract named entities from text: people, organizations, locations, dates, emails, URLs, phone numbers, and monetary values. Use when agents need to parse unstructured text into structured data for CRM enrichment, news analysis, or document processing.

Convert HTML pages to clean Markdown for LLM consumption. Use when building RAG pipelines, preparing web content for AI context windows, or extracting readable content from HTML. Strips scripts, styles, nav, ads. Preserves headings, links, lists, code blocks, and tables.

Get country, city, ISP, timezone, and proxy/VPN flag from any IP address. Use when agents need fraud detection, geo-targeting, analytics enrichment, or access control. Handles IPv4 and IPv6, detects private/reserved ranges.

Extract top keywords and keyphrases from text using TF-IDF scoring. Use when agents need to tag content, optimize SEO, build search indexes, or summarize topics. Returns ranked single words and multi-word phrases with frequency counts.

Extract text from images, screenshots, and scanned documents. Use when users need to digitize printed text, process receipts, read screenshots, or extract content from photos. Handles English text with confidence scoring.

Validate, normalize, and classify phone numbers globally. Use when agents need to verify phone format, detect country of origin, identify carrier type, or score phone number risk for lead qualification and fraud prevention.

Classify text into predefined or custom categories. Use when agents need to route tickets, moderate content, categorize emails, or tag documents. Uses keyword matching and TF-IDF scoring. No external API needed.

Fetch Open Graph tags, title, description, favicon, and canonical URL from any webpage. Use when agents need to generate link previews, crawl content metadata, or extract SEO information from URLs.

Learn from user answers and build persistent context. Use when agents need to remember user preferences, detect patterns in responses, and reduce repeated questions. Handles preference learning, pattern detection, and context management.

Advanced web search with precise date filtering and content type selection. Use when you need academic papers, GitHub repositories, research content, or specific date ranges. Handles neural search (semantic understanding), keyword search, and content type filtering (research papers, GitHub, news, PDFs). Perfect for research, competitive analysis, and content discovery.

Run structured browser workflows on modern websites. Use when a page requires JavaScript rendering, multi-step interaction, waits, screenshots, or rendered content extraction that plain HTTP scraping cannot handle.

Summarize any text, URL, or document text into concise, configurable output. Use when the user wants a quick brief, bullet summary, or executive digest of long content. Returns structured summary fields for research agents, email digests, and document triage. Deterministic and free to use.

Meta-skill for AI agent self-improvement. Analyzes runtime logs to detect error patterns, regressions, and inefficiencies, then generates structured improvement proposals. Use when the user or agent asks to analyze logs, diagnose failures, improve agent reliability, generate evolution proposals, or assess system health. Supports analyze, evolve, and status actions.

Remove signs of AI-generated writing from text. Use when the user asks to humanize text, make AI writing sound natural, remove AI patterns, rewrite to avoid AI detection, or clean up robotic-sounding content. Based on Wikipedia's 24 "Signs of AI writing" patterns. LLM-powered with regex fallback.

Teach your OpenClaw agent new tricks by creating custom skills. Use when you want your agent to do something it can't do yet — like "read my Google Calendar", "send Slack messages", "analyze my CSV files", or "search my company docs". Even if you just say "I wish my agent could do X", this skill helps you build it. No coding experience needed — just describe what you want in plain English.

Create new AI agent skills from scratch, improve existing skills, and optimize skill descriptions for better triggering accuracy. Use when users want to build a skill, write a SKILL.md, write handler code, evaluate skill quality, optimize skill metadata, or generate test cases. Covers the full skill development lifecycle from intent capture through deployment and iteration. Even if the user just says "I have an idea for a skill" or "help me package this as a skill", this is the right tool.

Search and discover skills from the live Claw0x catalog. Use when the user asks to find skills, browse the skill catalog, search for agent capabilities, list skill categories, or discover what tools are available. Returns real-time data with pricing, trust scores, and usage stats. Filter by category, keyword, or use case.

Generate production-ready TypeScript serverless function code from a skill description. Use when the user asks to generate skill code, create a new API handler, scaffold a serverless function, or auto-generate backend code from a README or description. Powered by Gemini LLM.

Capture learnings, errors, corrections, and patterns for continuous agent improvement via the Claw0x API. Use when a command fails unexpectedly, a user corrects agent output, a new pattern is discovered, or the agent needs to log and process improvement events. Returns structured insights, suggested rules, and batch summaries. Supports single events and batch processing.

Discover, evaluate, and recommend agent skills from the Claw0x catalog and community sources. Use when the user asks to find the best skill for a task, compare skills, get skill recommendations, browse available agent tools, or search across Claw0x native skills and community contributions from ClawHub, Anthropic, and VoltAgent. Returns ranked results with pricing, trust scores, and install commands.

Scan AI agent skills for security vulnerabilities, dangerous code patterns, and undeclared permissions. Three-layer analysis: dependency CVE scanning via OSV.dev, static code analysis, and permission auditing. Returns structured JSON risk report. Use when the user asks to scan a skill for security issues, check for vulnerabilities, audit permissions, or assess skill safety.

API-first email platform for AI agents. Use when the user or agent needs to send email, manage mailboxes, read incoming messages, or handle email workflows programmatically. Designed for autonomous agent-to-agent and agent-to-human email communication.

Extract text, metadata, and page structure from PDF files. Use when the user asks to parse a PDF, extract text from a document, get page count, read a PDF by URL, or analyze PDF metadata. Handles files up to 10MB. Server-side processing — no local dependencies required.

Scrape and extract structured data from any webpage. Use when the user asks to scrape a website, extract page content, get headings and links from a URL, or pull structured data from a web page. Returns title, headings, links, images, and paragraph text. Server-side — no browser needed.