Skills
101,174 packaged capabilities and playbooks for agents. Install any of them with one command.
All
Routes Tilebox tasks and implementation-oriented Earth observation or geospatial processing. Use for satellite, aerial, SAR, hyperspectral, or raster imagery; STAC or provider-catalog ingestion; AOI and time-series analysis; mosaics, spectral indices, classification, segmentation, change detection, and object detection; or environmental, agricultural, disaster, maritime, urban, and infrastructure monitoring—even when Tilebox is not named. For new processing projects, orchestrates workflow initialization, Python authoring, deployment, and job execution.
Text-to-video and image-to-video generation via Together AI, including keyframe control, model and dimension selection, asynchronous job polling, and video downloads. Reach for it whenever the user wants motion generation on Together AI rather than still-image generation or text-only inference.
Optimize token consumption in Claude Code through cache management, context forking, model selection, and input filtering. Use when user mentions high token costs, context window bloat, slow sessions, cache invalidation, verbose agent output, heavy MCP load, or any context management issues. Covers four critical axes - cache misses, context bloating, wrong model/effort level, and verbose input formats. Triggers on "tokens", "cost", "expensive", "context", "cache", "slow session", "optimize", or symptoms of token waste even without explicit mention.
Transcribe audio or video files using the TextOps API. Use this skill whenever the user wants to transcribe a video or audio file, mentions an mp4/mp3/wav/m4a file and wants text out of it, asks for transcription or תמלול, or wants to convert spoken audio to text. Also triggers for YouTube, Facebook, Instagram, and Twitter/X links. Also use it when the user wants a video or recording transcribed and summarized (e.g. "תמלל ותסכם", "תסכם לי את הסרטון", "transcribe and summarize") — it includes Hebrew summary instructions. Always trigger this skill even if the user just says "תמלל את זה" or "I want to transcribe this file". Also trigger this skill when the user asks what this skill can do, what features it has, "מה אתה יכול לעשות?", "what can you do?", or any similar capability question.
Transcribe audio/video using trx CLI and post-process results with agent corrections. Use when: (1) user wants to transcribe a video or audio file, (2) user shares a YouTube/Twitter/Instagram URL for transcription, (3) user says "transcribe", "subtitles", "srt", "transcript", (4) user wants to fix/clean up a whisper transcription, (5) user asks to extract text from a video.
TVC advertising creative director skill for Nano Banana Pro keyframe prompts and Seedance video scripts. Specialized for television commercials and brand advertising — from a product brief to production-ready keyframe prompts and cinematic video scripts. Three core capabilities: (1) Cinematic Product Breakdown — multi-phase product micro-films with precise camera choreography, component disassembly animations, feature visualization, and material macro shots; (2) Brand World Crosscut — interweaving product close-ups with in-context usage scenes via match cuts between phases (outdoor cameras with skydiving/skiing, luxury cars with mountain roads); (3) Lifestyle Film — product stays in the brand world throughout (worn/held/carried), highlighted through cinematography rather than studio cutaways, ideal for wearables and lifestyle products. Covers TVC narrative models, product cinematography, brand world integration, multi-grid storyboards, and video prompts. Use this skill whenever users want to create TVC ads, product commercials, brand films, product hero videos, or any advertising visual content — even if they just say 'help me make a product video', 'I need a TVC storyboard', or '帮我做一条产品广告'.
Patterns for delegating UI work to agents: one synthesis agent versus specialized agents, multi-agent pipelines for research, design, implementation, and review, and clean handoffs between them. Use when a UI task is too large for one pass or you are designing an agent workflow for components or design systems.
Frontend UI/UX design intelligence - activate FIRST when user requests beautiful, stunning, gorgeous, or aesthetic interfaces. The primary skill for design decisions before implementation. 50 styles, 21 palettes, 50 font pairings, 20 charts, 8 stacks (React, Next.js, Vue, Svelte, SwiftUI, React Native, Flutter, Tailwind). Actions: plan, build, create, design, implement, review, fix, improve, optimize, enhance, refactor, check frontend UI/UX code. Projects: website, landing page, dashboard, admin panel, e-commerce, SaaS, portfolio, blog, mobile app, .html, .tsx, .vue, .svelte. Elements: button, modal, navbar, sidebar, card, table, form, chart. Styles: glassmorphism, claymorphism, minimalism, brutalism, neumorphism, bento grid, dark mode, responsive, skeuomorphism, flat design. Topics: color palette, accessibility, animation, layout, typography, font pairing, spacing, hover, shadow, gradient.
Route explicitly authorized uinaf interface, brand-asset, and repository-copy work through the live design.uinaf.dev contract. Use only when explicitly invoked for a uinaf-owned repository or surface; never use for put.io, OpenClaw, or unrelated projects. The skill carries workflow, not design rules.
Unity save/load system architecture. Serialization format selection, save data DTOs, versioning and migration, cloud sync, PlayerPrefs scoping, auto-save strategies, mobile persistence. DECISION format: WHEN/DECISION/SCAFFOLD/GOTCHA. Based on Unity 6.3 LTS.
Unity state and behavior system architecture. FSM, Hierarchical FSM, Behavior Trees, stack-based state machines, Animator-vs-code decisions, state machine testing. DECISION format: WHEN/DECISION/SCAFFOLD/GOTCHA. Based on Unity 6.3 LTS.
Multi-lane AI verification system. When the user says "run this through Urithiru", "Urithiru check", "full tower", or similar, fan the query out to 5-7 AI models simultaneously via OpenRouter, collect independent responses, and synthesize the best answer as the orchestrator. Antigravity is ALWAYS the orchestrator — the models are lanes (specialists), not the decision-maker.
Evaluates market bubble risk through quantitative, data-driven analysis using the revised Minsky/Kindleberger framework v2.1. Prioritizes objective metrics (Put/Call, VIX, margin debt, breadth, IPO data) over subjective impressions. Features strict qualitative adjustment criteria with confirmation bias prevention. Supports practical investment decisions with mandatory data collection and mechanical scoring. Use when the user asks about bubble risk, valuation concerns, or profit-taking timing.
Relational database implementation across Python, Rust, Go, and TypeScript. Use when building CRUD applications, transactional systems, or structured data storage. Covers PostgreSQL (primary), MySQL, SQLite, ORMs (SQLAlchemy, Prisma, SeaORM, GORM), query builders (Drizzle, sqlc, SQLx), migrations, connection pooling, and serverless databases (Neon, PlanetScale, Turso).
Use when starting any conversation, receiving a new task, or when uncertain which skill applies - establishes how to find and use all 64 toolkit skills, requiring Skill tool invocation before ANY response including clarifying questions
Turns raw 9:16 talking-head clips into a finished, premium Instagram reel end to end: picks the cleanest take of every line across your clips, cuts dead air, punches in from 4K, cuts you out of the background for words behind your head, applies one of three designed looks (bold kinetic words, cool girl, cool dude), builds animated UI inserts with parallel sub-agents, adds subtle sound design, and checks every cut frame by frame inside the Reels safe zone. Trigger with /video-edit or phrases like 'edit these clips', 'I dropped clips in my downloads', 'cut this into a reel', 'make this reel look fire'.
Generate complete CRUD module code in Vue Vben Admin projects, including pages, forms, tables, and API interfaces. Must use this Skill when users say "generate CRUD", "create module", "add page", "write CRUD", "generate table page", "create xxx management", "generate xxx module". Do not skip even if the task seems simple. Do not generate code directly. All questions about component usage must be answered by reading the corresponding component documentation first, never from memory.
General-purpose desktop web prototype. Single self-contained HTML file built by copying the seed `assets/template.html` and pasting section layouts from `references/layouts.md`. Default for any landing / marketing / docs / SaaS page when no more specific skill matches.
A thinking mirror. Hand it a thing (an article, a hot take, someone asking for your opinion, a genuinely hard question, an industry trend) and get back a compact read that makes you think harder about it, grounded in values you wrote down or told it. Use when someone says "what do I make of this", "/what-do-i-make-of-this", "help me think about this", "someone asked my opinion on this", or "what should I make of this take", or pastes something and wants to understand it rather than be told about it. Tags every claim about the person as documented or inferred, and REFUSES to conclude, to interpret a source it could not read, or to draft their reply.
Build, fix, and ship apps on the Whop platform with current (Oct 2026) patterns. Use whenever the user mentions a Whop app, whop.com, @whop/sdk, WhopClient, @whop/react, @whop/iframe, Whop Elements, Frosted UI, x-whop-user-token, verifyUserToken, checkAccess, unwrapWebhook, Whop webhooks, checkout configurations, inAppPurchase, experience or dashboard views, `whop apps init/dev/deploy`, or Whop Platforms (connected accounts), even if they only say "my Whop thing" or paste old Whop code that needs updating.
Weave a wiki page into the knowledge graph: add it to index.md and add backlinks in both directions. Always use this skill when the user says /wiki-integrate, 'nothing links to this page', 'this page is an orphan', 'connect this page to related pages', 'add backlinks to this page', 'add this page to the index', or 'weave this page into the wiki'. Also use whenever a new page has just been created directly in a chat or a page has been significantly revised and may have new connection opportunities - even if the user doesn't explicitly ask for integration. Lightweight; only adds links and index entries, never rewrites content. When in doubt whether a page needs connecting after creation or revision, use this skill. Requires filesystem read/write access.
Answer a question using the compiled wiki knowledge base, synthesising a response with [[wikilink]] citations. Always use this skill when the user says /wiki-query, 'what does my wiki say about', 'what do I know about', 'check my notes on', 'search my wiki for', or 'what's the current state of [topic] in my notes'. Also use when the user asks a question and signals they want to draw on their own accumulated knowledge rather than general knowledge - phrases like 'what have we worked on regarding', 'based on my notes', 'what's my thinking on', or any question where the answer should come from personal knowledge rather than the model. Optionally files valuable answers as new wiki pages. When in doubt whether personal knowledge retrieval is being requested, use this skill. Requires filesystem read access.
Durable, type-safe queue workers with @falcondev-oss/workflow on Redis. Use when working with WorkflowNamespace / createWorkflow / defineWorkflow, handle() and returns<T>(), step.do / step.wait / step.waitUntil, workflow.run / runIn / runAt / work(), job.wait(), upsertSchedule cron schedules, groupId ordering and numeric priority, or the createRedis connection setup.
When the user wants to optimize workforce scheduling, create shift plans, or balance labor demand. Also use when the user mentions "staff scheduling," "labor planning," "shift optimization," "crew scheduling," "roster optimization," or "employee scheduling." For task assignment, see task-assignment-problem. For wave planning labor, see wave-planning-optimization.
Predict FIFA World Cup matches, full tournament paths, and champion probabilities through Codex-native subagents that analyze live news, weather, injuries, markets, Polymarket, tactics, and tournament context while updating a real-time web dashboard. Use when asked to forecast World Cup games, predict the full World Cup outlook, compare match forecasts, or show prediction progress live in a browser.
WordPress theme code review and block theme development patterns for WordPress 6.6+. Use when reviewing theme code, auditing theme.json schema, checking template hierarchy, validating block templates, analyzing global styles, verifying style variations, reviewing template parts, detecting hardcoded styles, checking classic-to-block migration, or when user mentions "theme review", "theme development", "theme.json", "block theme", "FSE", "Full Site Editing", "template parts", "template hierarchy", "global styles", "style variations", "classic theme", "child theme", "theme patterns", "theme.json validation", "hardcoded styles", "useRootPaddingAwareAlignments", "classic-to-block", "hybrid theme", "WordPress.org theme". Detects issues in theme.json structure, block templates, template parts, style systems, and classic theme migration patterns.
Write GitHub Actions workflows with proper syntax, reusable workflows, composite actions, matrix builds, caching, and security best practices. Use when creating CI/CD workflows for GitHub-hosted projects or automating GitHub repository tasks.
Comprehensive spreadsheet creation, editing, and analysis with support for formulas, formatting, data analysis, and visualization. When Claude needs to work with spreadsheets (.xlsx, .xlsm, .csv, .tsv, etc) for (1) Creating new spreadsheets with formulas and formatting, (2) Reading or analyzing data, (3) Modify existing spreadsheets while preserving formulas, (4) Data analysis and visualization in spreadsheets, or (5) Recalculating formulas
Help local fitness coaches promote classes they actually deliver: read their activated DNA, identify product strengths, target customers and pain points, match four types of course promotion content and existing marketing copy frameworks, schedule daily WeChat Moments posts, and write the copy. Use when the user asks how to sell a new class, post about a trial class, create a course promotion plan, or write that day’s course marketing copy. Not for Xiaohongshu posts, training other coaches, automated publishing, or fabricated sales.
Check and update the YETONG skill bundle in the currently installed instance. Use when the user says “update Ye Tong skills,” “upgrade YETONG,” “check for a new version,” or requests a skill bundle update within YETONG. Verify the complete runtime files against the fixed official GitHub repository, back up before updating, update only files registered to this bundle, and preserve character profiles and other skills. Character DNA activation is not required.
Use before high-stakes or multi-file coding (auth, databases, migrations), or when asked to plan carefully and avoid invented APIs. Runs discuss, map, decompose, execute and verify, checking every import and API exists. Not for trivial edits.
Use when the user needs to understand competitors — direct, indirect, and substitute tiers, positioning map, SWOT, ad and content benchmark, pricing comparison, and the market gap to attack, using SimilarWeb, Ahrefs, Semrush, and the Meta Ad Library. Trigger on 'competitor research', 'competitive analysis', 'what are competitors running', 'who else sells this', 'why do people pick them over us', 'benchmark us against the market'. Also use when the user sends a competitor link and asks for an opinion. Not for — understanding the customer rather than the rival, see `09-customer-insight-global`; turning difference into a statement, see `58-positioning-global`; paid targeting, see `51-audience-research-global`.
Dung khi can theo doi lien tuc nguoi ta noi gi ve thuong hieu, doi thu va nganh tren mang xa hoi — bo tu khoa giam sat, phan loai sac thai, bao cao tuan va thang, canh bao som, chi so brand health. Kich hoat khi user nhac 'social listening', 'theo doi thuong hieu', 'giam sat mang xa hoi', 'brand monitoring', 'khach dang noi gi ve minh', 'do sentiment', 'co ai nhac ten shop khong', 'canh bao som khung hoang'. Khong dung cho — khung hoang DA XAY RA va can xu ly ngay thi dung skill 66-crisis-playbook; mo xe chien luoc mot doi thu cu the thi dung skill 08-nghien-cuu-doi-thu; doc so lieu ads va web thi dung skill 13-phan-tich-du-lieu.
Comprehensive keyword research and analysis using DataForSEO API. Discover keyword opportunities, analyze search volume and difficulty, find related keywords, track rankings, and identify content gaps. Use when user says "keywords", "keyword research", "search volume", "keyword difficulty", "ranking keywords", "keyword ideas", "keyword suggestions", or "content gap".
Extract and analyze architecture diagrams from academic PDFs or existing figure images. Use this skill whenever the user provides a PDF or image containing an architecture diagram and wants to extract, analyze, or redraw it — including "从PDF提取架构图", "架构图分析", "extract figures from pdf", "architecture diagram extraction", "analyze this diagram". Runs a local PDF extraction script and produces structured redraw parameters for downstream prompt skills.
Plan what to test, how to test, and who should test for accessibility. Use when defining a testing approach, planning QA, setting up automated and manual testing, or deciding what level of accessibility testing a project needs. Triggers on: accessibility testing, how to test, test plan, automated testing, manual testing, screen reader testing, user testing, accessibility QA, what to test, testing strategy.
Use this skill to grade running ads as Red (stop), Yellow (hold), or Green (scale), detect creative fatigue, analyze LTV:CAC, and recommend scaling actions. Trigger it when reviewing campaign exports or deciding what to kill, keep, or scale.
AG-UI (Agent-User Interaction) protocol reference for building AI agent frontends. Use when implementing AG-UI events (RUN_STARTED, TEXT_MESSAGE_*, TOOL_CALL_*, STATE_*), building agents that communicate with frontends, implementing streaming responses, state management with snapshots/deltas, tool call lifecycles, or debugging AG-UI event flows.
Use when the user needs to build AI agents — tool use patterns, memory management, planning strategies, multi-agent coordination, evaluation, and safety guardrails. Triggers: user says "agent", "build an agent", "tool use", "agent loop", "multi-agent", "memory management", "guardrails", "agent evaluation".
New to MCP?
From what the protocol is to installing your first server, these answers cover most first questions.
An open protocol that defines how AI applications connect to external tools and data in a uniform way. Clients talk to the model; MCP servers provide tools, resources and prompt templates. They exchange standard messages, so one server can be reused by many clients.