moto

Meta-skill that analyzes past session transcripts to derive new skills, CLAUDE.md rules, and MEMORY.md entries from real usage patterns. Use when Use when user says "session learn", "derive skills", "learn from sessions", "what patterns", "analyze sessions", "extract rules", "what should I add to claude md", "improve my setup", or "what have I been doing repeatedly".

Scan running Claude sessions to see what other agents are working on. Use when asked "what are the other agents doing", "check other sessions", "what's running", "scan agents", "who's working on what", or before picking up new work to avoid overlap.

Find restaurants and food delivery options near a location. Searches Swiggy for restaurants, cross-references Google Maps ratings, and recommends the best options. Learns food preferences over time.

Geographic data validator for aviation and travel applications. Use when user says "geo audit", "check airports", "validate routes", "geo skill", "check geographic data", "verify iata codes", "check distances", or when reviewing any code/data that involves airport codes (IATA/ICAO), city-to-airport mappings, country codes (ISO 3166), flight distances, flight time estimates, flag URLs, or route feasibility. Also use for timezone validation, coordinate checks, and geopolitical accuracy (country names, disputed territories, naming conventions).

A set of resources to help write all kinds of internal communications, using the formats that your company likes to use. Claude should use this skill whenever asked to write some sort of internal communications (status reports, leadership updates, 3P updates, company newsletters, FAQs, incident reports, project updates, etc.).

Negotiation analyst for high-stakes deals: co-founder exits, business separations, contract terms, salary negotiations, investor terms. Use when the user asks to: (1) analyze a counterparty's position or message, (2) score/review a draft message before sending, (3) draft a counter-offer, (4) structure BATNA/ZOPA analysis, (5) track concessions across rounds, (6) detect traps or information leakage in proposed terms, (7) prepare for a negotiation call or meeting. Triggers: "score this message", "analyze their position", "what's my BATNA", "review before I send", "draft a counter", "is this a trap", "negotiate", "negotiation", "counter-offer", "deal terms".

Cross-post LinkedIn content to X (Twitter). Use when user says "post to x", "cross-post to x", "tweet this", "share on x", "post on twitter", or wants to adapt a LinkedIn post for X/Twitter. Handles text shortening, media upload (images and videos), and posting via the X API v2 + v1.1 media endpoint.

Product strategy and UX decision-making for user-facing features. Use when asked about "product decision", "UX strategy", "how should we present this", "user trust", "what should the user see", "is this confusing", "zero friction", "product skill", or any question about how a feature should feel, communicate, or behave from the user's perspective. Also trigger when discussing feature positioning, onboarding flows, trust signals, progressive disclosure, or when there's a gap between what the product does and what the user understands.

Republic-style UX design reviewer and scorer for pitch decks, landing pages, and investor-facing materials. Applies Republic.com's design DNA (financial-grade trust, data-forward, restrained elegance) to score and improve any visual artifact. Use when user says "republic", "republic style", "score design", "polish deck", "investor-grade design", or wants to elevate visual quality to crowdfunding-platform standards.

Review videos by extracting representative frames and analyzing them visually. Use when: (1) reviewing a rendered video (Remotion, ffmpeg output, etc.), (2) checking video quality or content, (3) verifying animations or transitions, (4) debugging video rendering issues. Triggers: "review video", "check the video", "does the video look right", "verify the render", or any request to visually inspect a .mp4, .webm, .mov, or other video file.

Technical SEO auditor for programmatic pages, landing pages, and content clusters. Use when user says "seo audit", "check seo", "seo review", "technical seo", "schema.org check", "sitemap review", "indexability", "seo skill", or when reviewing any plan/code that involves search engine optimization, programmatic page generation, structured data, or organic traffic strategy. Covers: on-page SEO, schema.org validation, sitemap/robots analysis, internal linking, thin content detection, keyword cannibalization, international SEO (hreflang), SERP feature targeting, and Core Web Vitals impact.

AI-powered video editing toolkit. Trim, concat, overlay text/images, mix audio, generate voiceover, add transitions, and export with social media presets. Uses Gemini for intelligent edit suggestions. Use when: creating videos, editing clips, adding overlays, mixing audio, generating voiceovers, exporting for social media, or when user says "edit video", "trim", "add text overlay", "mix audio", "voiceover", "export for linkedin/x/instagram". Runs on a dev server only (ffmpeg + python). Mac delegates via SSH.

Suite of tools for creating elaborate, multi-component claude.ai HTML artifacts using modern frontend web technologies (React, Tailwind CSS, shadcn/ui). Use for complex artifacts requiring state management, routing, or shadcn/ui components - not for simple single-file HTML/JSX artifacts.

Create investor pitch decks optimized for YC and seed-stage fundraising. Use when creating pitch decks, investor presentations, fundraising materials, or when user mentions "pitch deck", "YC deck", "investor deck", "fundraise", or "seed round". Covers slide structure, content strategy, storytelling arc, and what investors actually look for. Works with any output format (HTML slides, PPTX, PDF).

Plan, audit, and score startup launch videos using YC-grade production standards. Use when: creating product launch teasers, scoring video quality for social distribution, planning narrative structure for LinkedIn/X autoplay, reviewing cold-audience effectiveness. Triggers: "launch video", "yc video", "score the video", "plan the teaser", "audit launch video", "cold audience test", "video narrative", "teaser structure".

DNS management via API. Add, update, delete DNS records for your domains. Use when user says "dns", "add dns record", "update dns", "dns for X", "add subdomain", "point domain", "create dns record", or "delete dns record".

Self-hosted Docker deployment for your services. Use when user says "docker deploy", "rebuild container", "restart container", or needs to deploy a self-hosted service (not Vercel/Render).

10-second audit of dev server system state. Use when: "health check", "system status", "check system", "what's running", "orphans", "disk space", "check containers", or any question about the current state of the server.

GitHub issue management with multi-account support. Creates, lists, views, and closes issues with correct labels and conventions per project. Use when user says "create issue", "file bug", "issue for X", "list issues", "open issues", "triage", or "close issue".

Daily briefing: unified status check across all systems. Unread email counts, open GitHub issues, active workplans, todos, system health. Use when user says "morning", "daily briefing", "status", "what's going on", "catch me up", "what did I miss", or starts a new day.

Post-compaction context recovery. Reconstruct working context from session transcripts using MCP tools or CLI. Use when user says "recall", "recover context", "what was I doing", "after compaction", "lost context", or when context has been compacted and needs reconstruction.

Context vault operations: read/update todos, add log entries, search vault content, read strategy/project docs, update project files. Use when user says "vault", "add todo", "update todos", "log entry", "search vault", "check todos", "context vault", "add to log", or any operation on a personal context vault.

Read and send WhatsApp messages via SQLite DB access and a verified send script. Use when user says "check WhatsApp", "read WhatsApp", "messages from X", "send WhatsApp to X", "message X on WhatsApp", or any WhatsApp read/send task.

GitHub repo launch checklist and audit. Use when user says "launch", "go public", "publish repo", "audit repo for launch", "open source this", "make public", "launch checklist", or wants to prepare a private repo for public release. Also works for auditing already-public repos. Covers: secret scanning, README polish, SEO metadata, license, templates, visibility change, distribution, and post-launch verification.

Systematic visual audit of a web app. Two modes: (1) Wireframe comparison, matching implementation against a design spec HTML file with CSS property extraction. (2) Standalone UX/product review, evaluating usability, visual hierarchy, interaction patterns, and mobile responsiveness from a user perspective. Both modes produce severity-rated reports with screenshots. Use when asked to "audit the UI", "review the UX", "compare against wireframes", "product review", "check the design", "UX review", "usability check", or any request to evaluate a web app's user experience. Also trigger proactively after significant UI changes.

Creating algorithmic art using p5.js with seeded randomness and interactive parameter exploration. Use this when users request creating art using code, generative art, algorithmic art, flow fields, or particle systems. Create original algorithmic art rather than copying existing artists' work.

Map the full impact of a proposed change before making it. Use before refactors, API changes, database migrations, or any modification to shared code. Triggers: "blast radius", "what will break", "impact analysis", "what depends on this", "is it safe to change this", or before any significant refactor.

Pre-flight check before starting any significant work. Use when starting a new task, before making changes to production systems, or when asked to "check if this is safe", "should I do this", "validate my plan", or "bouncer check". Evaluates risk, reversibility, and whether the right preconditions are met before proceeding.

Browse the web, read pages, extract information, and interact with websites. Use when user asks to "look up", "browse to", "check the website", "read this URL", "search for", "find information about", or needs current information from the web. Handles navigation, content extraction, form interaction, and screenshots.

Create beautiful visual art in .png and .pdf documents using design philosophy. Use this skill when the user asks to create a poster, piece of art, design, or other static piece. Create original visual designs, never copying existing artists' work.

Write effective cold outreach messages for sales, partnerships, networking, or job outreach. Use when user asks to "write a cold email", "draft an outreach message", "reach out to X", "send a pitch to", "write a connection request", or needs to contact someone they don't know professionally. Produces concise, personalized, non-spammy outreach.

Strategic compass and priority check. Use when someone seems off track, is context-switching, starting new projects, building instead of selling, or asks "what should I focus on", "am I off track", "priorities", "what matters", "compass", "north star", "strategy check".

Estimate and analyze costs for AI/cloud services, infrastructure, or feature implementations. Use when user asks "how much will this cost", "cost estimate", "cost analysis", "what's the pricing", "budget for this", or wants to understand the financial impact of a technical decision. Covers LLM API costs, cloud hosting, and SaaS tools.

Systematic debugging workflow for any type of error or unexpected behavior. Use when user says "debug this", "why is this failing", "help me fix this error", "something is broken", or shares an error message or unexpected output. Follows a root-cause-first approach rather than trial-and-error patching.

Comprehensive codebase or system audit. Use when asked to "audit the codebase", "review everything", "find all issues", "security audit", "performance audit", "code quality review", or "find tech debt". Produces a structured report with findings prioritized by severity.

Deploy projects to their respective platforms. Use when user says "deploy", "push to prod", "ship it", "release", "deploy to preview", "deploy to production", "deploy backend", "deploy frontend". Handles Vercel, Render, Supabase Edge Functions, and Docker deployments.

Guide users through a structured workflow for co-authoring documentation. Use when user wants to write documentation, proposals, technical specs, decision docs, or similar structured content. This workflow helps users efficiently transfer context, refine content through iteration, and verify the doc works for readers. Trigger when user mentions writing docs, creating proposals, drafting specs, or similar documentation tasks.

Use this skill whenever the user wants to create, read, edit, or manipulate Word documents (.docx files). Triggers include: any mention of "Word doc", "word document", ".docx", or requests to produce professional documents with formatting like tables of contents, headings, page numbers, or letterheads. Also use when extracting or reorganizing content from .docx files, inserting or replacing images in documents, performing find-and-replace in Word files, working with tracked changes or comments, or converting content into a polished Word document. If the user asks for a "report", "memo", "letter", "template", or similar deliverable as a Word or .docx file, use this skill.

Check, read, and search emails across IMAP accounts. Use when user says "check email", "read inbox", "any new emails", "check mail", "email from X", "unread messages", or mentions checking specific email accounts.

Create distinctive, production-grade frontend interfaces with high design quality. Use this skill when the user asks to build web components, pages, artifacts, posters, or applications (examples include websites, landing pages, dashboards, React components, HTML/CSS layouts, or when styling/beautifying any web UI). Generates creative, polished code and UI design that avoids generic AI aesthetics.