Claude Skills
The open format is called Agent Skills and works in Claude Code, Codex, Cursor and other agents — most people know it as Claude Skills.
Every Agent Skill we could find on GitHub, deduplicated by content. 86 961 files from 2 125 authors, of which 68 678 are unique — the rest is the same skill repackaged into someone else's repository. For each one: what it weighs in tokens, whether it ships runnable scripts, and which MCP servers it needs.
> End-to-end hiring signal composite. Takes any set of companies, detects job postings that your product augments or replaces, finds relevant people (the hiring manager, buyers, champions, users), and drafts personalized outreach using the job role as the hook. Tool-agnostic — works with any company source, job board, contact finder, and outreach platform.
> Set up a complete outbound email campaign in Smartlead. Asks the user for campaign goal, audience, messaging, schedule, and mailbox allocation. Creates the campaign, adds leads, saves email sequences, sets schedule, and assigns available mailboxes. Use when a user wants to launch email outreach via Smartlead.
> End-to-end LinkedIn outreach campaign builder. Takes leads from Supabase, upstream skills, or CSV. Aligns on campaign goal and tone, writes personalized LinkedIn message sequences (connection request + follow-ups + optional InMail), presents for review, and exports for the user's outreach tool (Dripify, Botdog, Expandi, or manual CSV). Logs to Supabase outreach_log.
> End-to-end news-triggered signal composite. Takes any piece of news — an article, LinkedIn post, tweet, announcement, event, trend, regulation, product launch, acquisition, layoff, expansion, or any other public event — and evaluates whether the companies or people mentioned are ICP fits. If yes, identifies the connection between the news and your product, finds the right people to contact, and drafts personalized outreach using the news as the hook. Tool-agnostic. Accepts both company-level and person-level news triggers. article, tweet, blog post) or mentions a company/person they "came across", "saw", or "found" from any external source and asks about relevance, fit, ICP match, or whether to reach out. The user does NOT need to explicitly say "outreach" — any signal evaluation request from an external source triggers this.
> End-to-end leadership change signal composite. Takes any set of companies, detects recent leadership changes (new VP+, C-suite hires and promotions), evaluates relevance to your product, and drafts personalized outreach. Uses Apollo People Search (free) for fast detection + Apollo Enrichment (1 credit/person) for employment history, start dates, LinkedIn URLs, and verified emails.
> Email campaign/sequence performance review composite. Pulls campaign data (sends, opens, replies, bounces), reads actual email copy and subject lines, analyzes reply content (objections, positive interest, questions), and produces a diagnostic report covering quantitative metrics, copy quality, lead quality, and actionable recommendations. Tool-agnostic — works with Smartlead (MCP), Instantly, Outreach, Lemlist, Apollo, or CSV data.
AI video conversations - create real-time video calls with AI personas
Send SMS text messages to phone numbers. Use when the user asks to send a text, send an SMS, text someone, message a phone number, or send a notification via text message.
> find decision-maker contacts, personalize messaging, launch campaign.
AI-powered web scraping - extract data using natural language prompts
Logo.dev - search for company domains by brand name
Extract structured data from web pages using AI
> End-to-end champion/buyer/user job change signal composite. Takes a set of known people (past buyers, champions, power users), detects when they move to a new company, researches the new company for ICP fit, and drafts personalized outreach leveraging the existing relationship. Tool-agnostic — works with any people source, detection method, and outreach platform.
Search eBay listings - find items, auctions, deals, and compare prices
Test and document API endpoints - validate responses, check status, generate examples
Search Amazon products - find items, compare prices, read reviews
Browser automation - control browser sessions, scrape pages, and run AI agents
Find and install skills from the Orthogonal skill library. Use when you need capabilities you don't have, want to discover available skills, or need to add new tools to your agent.
Hyperlocal weather data - precipitation, temperature, wind, soil moisture and more
Identity verification via phone/email OTP and AML screening using Didit API
Analyze images with AI - extract text, describe content, detect objects
Multi-platform search - YouTube, Amazon, eBay, Walmart, TikTok, Instagram, and more
Verify phone numbers using SMS one-time codes via the Didit API. Use when you need to confirm a user owns a phone number, implement SMS-based 2FA, or validate phone during signup/onboarding flows.
Process PDFs - extract text, tables, and structured data from documents
Get prediction market odds and prices from Polymarket and Kalshi
Create, structure, and package agent skills. Use when designing new skills, updating existing skills, or helping users build skills with scripts, references, and assets. Triggers on requests to create skills, write SKILL.md files, or structure skill directories.
Web scraping with structured data extraction - define your output schema
Book restaurant reservations via browser automation. Use when asked to make dinner reservations, book a table, or find availability at restaurants. Supports OpenTable, Resy, and direct restaurant booking sites.
Prediction markets data - Polymarket, Kalshi markets, prices, positions, and trades
Get current weather and forecasts using free APIs (no API key required). Use when asked about weather, temperature, forecasts, or climate conditions for any location.
> Search the Wayback Machine for archived versions of websites. Extract cached pages, customer lists, testimonials, and partner directories from sites that have changed or gone offline. Uses the free CDX API — no API key needed.
Web research API with OpenAI-compatible chat completions and async tasks
Web scraping, crawling, and AI-powered answer extraction at scale
Fast, high-quality web search with intelligent ranking and instant answers
Scrape websites, extract structured data, and automate browsers. Use when asked to scrape, extract, crawl, parse, or pull data from web pages or any URL.
Jina Search - fast web search returning SERP results
Web search and content fetching - search the web or extract content from URLs
Perplexity AI search and chat completions with real-time web data
AI-powered web search, crawling, extraction, and deep research
Neural web search - find similar content, extract pages, and run deep research
Search the web, platforms, and datasets. Use when asked to search, find, look up, research, or discover information from the web, YouTube, Amazon, eBay, news, academic sources, or any online platform.
Take screenshots of any website using Notte browser automation. Use when asked to screenshot, capture, or snap a webpage.
Fetch YouTube transcripts via APIFY API. Works from cloud IPs (Hetzner, AWS, etc.) by bypassing YouTube's bot detection. Free tier includes $5/month credits (~714 videos). No credit card required.
Fetch and read transcripts from YouTube videos. Use when you need to summarize a video, answer questions about its content, or extract information from it.
Web search, AI answers, content extraction, and async deep research
> Research a company's ideal customer profiles and build detailed synthetic buyer personas. Identifies 4-6 distinct buyer segments through web research, then creates rich, realistic personas with demographics, motivations, skepticism profiles, decision criteria, and language patterns. Use when you need to understand who your buyers are at a deep level — their motivations, objections, and how they evaluate solutions.
> Discover all customers of a given company by scanning websites, case studies, review sites, press, social media, job postings, and more. Use when you need competitive intelligence on who a company sells to.
Prepare for investor calls by pulling upcoming meetings from Google Calendar, deeply researching each investor and their firm (website scraping, portfolio analysis, thesis extraction), checking for competitor conflicts, and outputting an honest prep sheet with compatibility assessments. Use when asked to prep for investor meetings, fundraising calls, VC meetings, or demo day.
Research VCs, angels, and investors - portfolio, thesis, contact info
Research market trends, size, competitors, and growth opportunities
> Scan support tickets, Slack channels, NPS scores, and usage patterns to flag accounts showing early churn indicators. Produces a weekly risk scorecard with severity tiers, root cause hypotheses, and suggested save plays per account. Designed for seed/Series A teams where the founder or a single CSM manages all accounts manually.
> Scrape G2, Capterra, and Trustpilot reviews for your product and competitors, then extract recurring themes, objections, proof points, and exact customer language for use in messaging. Chains review-site-scraper with LLM analysis. Produces a weekly or monthly digest that feeds directly into copywriting, positioning, and sales enablement. Use when a marketing team needs to ground messaging in real customer language.
> Aggregate customer feedback from multiple sources — support tickets, NPS comments, Slack messages, G2 reviews, call transcripts, survey responses — into a unified VoC report with theme clustering, sentiment analysis, trend detection, and actionable recommendations for product, marketing, and CS teams. Chains review-site-scraper for public review data.
> Track product champions for job changes and qualify their new companies against ICP. Takes a CSV of known champions (with LinkedIn URLs), creates a baseline snapshot via Apify enrichment, then detects when champions move to new companies. Scores new companies on a 0-4 ICP fit scale. Outputs a downloadable CSV of movers with qualification verdicts.
> Handles disqualified and near-miss inbound leads gracefully. Drafts polite rejection emails, referral requests (right company wrong person), and nurture routing (future fit). Ensures no inbound lead gets ignored and every disqualification preserves the relationship. Tool-agnostic.
> on LinkedIn, new job postings, product usage patterns, funding announcements, and public company news. Produces a weekly expansion opportunity list with context and talk tracks. Chains web search, LinkedIn profile monitoring, and job posting detection.
Daily meeting preparation system that checks your calendar each morning, deeply researches external attendees (LinkedIn, company info, GitHub, past notes), and sends you personalized briefs via email (1 per person). Use when you want automated preparation for upcoming meetings with context about each person you're meeting.
> Pipeline analysis composite. Pulls deal/meeting data from any CRM or tracking system, analyzes the pipeline over a user-defined period (weekly, fortnightly, monthly, quarterly), and produces both an executive summary and a detailed diagnostic report. Covers volume, qualification rates, source effectiveness, stage velocity, stuck deals, and actionable recommendations. Tool-agnostic — works with any CRM (Salesforce, HubSpot, Pipedrive, Close, Supabase, CSV).
> Pre-sales-call intelligence composite. Deep dives on the person AND their company before a sales call, then maps findings to your product to generate talking points, objection prep, and a call strategy. Goes beyond generic attendee research — this is sales-specific intelligence that helps SDRs, AEs, and founders walk into calls with a plan. Tool-agnostic — works with any CRM, research source, and calendar.
> Check and improve your brand's visibility across AI search engines (ChatGPT, Perplexity, Gemini, Grok, Claude, DeepSeek). Set up tracking, run visibility analyses, audit your website for AI readability, and get actionable recommendations. Uses the npx goose-aeo@latest CLI.
Claude Skills — questions
Answers built from the skills we actually parsed.