Skills
96,981 packaged capabilities and playbooks for agents. Install any of them with one command.
All
PyTorch deep learning patterns and best practices for building robust, efficient, and reproducible training pipelines, model architectures, and data loading. Use when writing or reviewing PyTorch training loops, model architectures, or data loading, or when a run will not reproduce.
Design optimal team structures, hiring plans, compensation strategies, and equity allocation for early-stage startups from pre-seed through Series A. Use this skill when planning headcount, determining which roles to hire next, setting compensation or equity ranges, designing org structure, or building a hiring budget aligned to funding milestones.
Find, use, and troubleshoot official Runpod Pod templates, including ComfyUI workflow model metadata repair. For creating or optimizing Dockerfiles and application template projects use runpod-build-template; deploy through runpod-mcp or runpodctl.
Recommend hotel rooms and complete a real booking end to end — reserve an OpenTravel direct property with a payment link (bank QR, card, or PayPal), check payment status, resend an expired link, or cancel a booking. Falls back to direct Booking.com/Agoda/Traveloka links for OTA-only hotels. Use when booking or reserving a hotel, getting room recommendations, paying for a stay, checking a confirmation code, or cancelling a reservation.
Generate short AI videos from text or images — text-to-video, image-to-video, and reference-based generation — with zero API key setup. Use when the user wants to create a video clip, animate an image, or generate video from a description.
Master on-call shift handoffs with context transfer, escalation procedures, and documentation. Use this skill when transitioning on-call responsibilities between engineers and ensuring the incoming responder has full situational awareness, when writing a shift summary that captures active incidents, ongoing investigations, and recent changes, when handing off mid-incident so a fresh engineer can take over the incident commander role without losing context, when onboarding a new engineer to the on-call rotation for the first time, or when auditing and improving the quality of existing handoff processes across teams.
Library-agnostic Flutter/Dart code review checklist covering widget best practices, state management patterns (BLoC, Riverpod, Provider, GetX, MobX, Signals), Dart idioms, performance, accessibility, security, and clean architecture. Use when reviewing Flutter or Dart code, whatever state management library the project uses.
Generate talking head avatar videos with Pruna P-Video-Avatar via inference.sh CLI. Turn a portrait image into a realistic speaking video with built-in TTS. 18x faster and 6x cheaper than competitors. Models: P-Video-Avatar, P-Image (for portrait generation). Capabilities: text-to-avatar, audio-driven avatars, 30 voices, 10 languages, 720p/1080p, built-in TTS, dynamic backgrounds, full-body control. Use for: AI presenters, product demos, explainer videos, virtual influencers, marketing, education, multilingual content, UGC, gaming avatars. Triggers: avatar video, talking head, ai avatar, p-video-avatar, pruna avatar, video avatar, ai presenter, digital human, virtual presenter, lipsync, talking avatar, ai spokesperson, heygen alternative, synthesia alternative, veed alternative, fabric alternative, omnihuman alternative
Fix or hand-configure an existing ElevenLabs API key. Use when a key stopped working (401 or invalid_api_key), when an administrator issued the key, when the user's role cannot create keys, or when the user already has a key and needs it in the right place. Checks whether ELEVENLABS_API_KEY is configured and valid, without reading it into the conversation. Not for first-time setup or adding ElevenLabs to a project (use onboarding).
Generate and edit images with OpenAI GPT-Image-2 via inference.sh CLI. Models: GPT-Image-2. Capabilities: text-to-image, image editing, inpainting, mask-based editing, multi-image reference, batch generation. Use for: product mockups, marketing visuals, image editing, concept art, inpainting, photo manipulation. Triggers: gpt image, gpt-image-2, openai image, chatgpt image, dall-e, dalle, openai image generation, gpt image edit, gpt inpainting, openai dall-e, gpt 4o image
Use this skill when the user wants to create a new Model Context Protocol (MCP) server in Python. Also use it to expose Python functions, an API, or a database to AI clients as MCP tools. The skill makes a uv project with the MCP Python SDK v2 (MCPServer), typed tools, in-memory tests, and client configuration. Do not use it for an MCP client or for a server in another language.
Provides verified corrections for IAM behaviors that AI agents frequently get wrong — policy evaluation edge cases, trust policy gotchas, STS session limits, Organizations quirks, and SAML/MFA specifics. Also provides structured workflows for IAM role management and baseline policy generation from application source code or a Terraform plan JSON. Covers condition operator safety (ForAnyValue/ForAllValues with Null checks), bucket policy deny patterns (VPC endpoint restrictions, org paths), confused deputy protection, and service role creation for AWS services (Glue, CloudTrail, Lambda, ECS, etc.) with aws:SourceAccount/aws:SourceArn trust conditions. Applies when creating IAM roles, writing IAM or bucket policies, generating policies from application source code or a Terraform plan JSON, working with STS, Organizations, or condition operators, or any task needing a service or execution role. Does not cover non-IAM authorization like Cognito user-pool policies or app-level RBAC
A content publishing risk check for creators. It reviews sentence by sentence the titles, body text, image text, subtitles, voiceover, comments, account profiles and video frames of self-media, social media and content platforms, judging separately what the platform's machines may detect and what substantive issues the content itself has, and gives specific locations and minimal edit actions; when the video's contextual boundaries need to be made clear, it additionally generates accurate three-line overlay text. Use it when users ask to check sensitive words, to clear risks before publishing, where a post might violate rules, whether a Xiaohongshu post can be published, or what disclaimer to put on a video. It preserves strong opinions, emotional tension, personal style and shareability hooks.
Generate videos with ByteDance Seedance 2.0 via inference.sh CLI. Unified model for text-to-video, image-to-video, and reference-to-video with synchronized audio, up to 1080p, 4-15s duration. Pro and Fast variants. Studio variants with private asset library for portrait consistency. Use for: social media videos, music videos, product demos, animated content, AI video with sound. Triggers: seedance, seedance 2, bytedance video, seedance t2v, seedance i2v, seedance r2v, video with audio, seedance 2.0, bytedance seedance, seedance studio
Regression testing strategies for AI-assisted development. Sandbox-mode API testing without database dependencies, automated bug-check workflows, and patterns to catch AI blind spots where the same model writes and reviews code. Use when adding regression coverage to AI-assisted code, or when the same model both wrote and reviewed a change.
Troubleshoot production issues using backend function logs and workflow run history. Use when investigating app errors, debugging function calls, diagnosing why a scheduled job or automation failed, or diagnosing production problems in Base44 apps.
Generate images with Pruna P-Image models via inference.sh CLI. Models: P-Image, P-Image-LoRA, P-Image-Edit, P-Image-Edit-LoRA. Capabilities: text-to-image, image editing, LoRA styles, multi-image compositing, fast inference. Pruna optimizes models for speed without quality loss. Triggers: pruna, p-image, pruna image, fast image generation, optimized flux, pruna ai, p image, fast ai image, economic image generation, cheap image generation
Routes serverless requests to a compute form factor and the skill that owns it. Applies first to Lambda, API Gateway, EventBridge, Step Functions and event-driven work while the compute, orchestration or integration choice is open — API backends, webhooks, jobs, cron, queue/stream consumers, durable workflows, event routing, Step Functions vs Durable Functions, and Pipes vs native event source mappings for queues and streams. Decides Event Functions on-demand vs Managed Instances, Web Functions, MicroVMs, EventBridge rules/Scheduler/Pipes/bus, HTTP vs REST API. Owns shared Lambda references (cold starts, SnapStart, concurrency, event sources, function URLs, throttling, troubleshooting). Defers to the specialized skill once a request commits to one form factor or service, or describes its defining feature, even unnamed (durable checkpointing and automatic step retries, Firecracker sandbox, managed instances, Node.js server). Not for EC2, ECS/EKS/Fargate or Amplify hosting.
Use when the user asks to 'buy BTC', 'sell ETH', 'place a limit order', 'place a market order', 'cancel my order', 'amend my order', 'long BTC perp', 'short ETH swap', 'open a position', 'close a position', 'set take profit', 'limit take profit', 'immediate TP', 'set stop loss', 'self-trade prevention', 'stpMode', 'auto-cancel on close', 'trailing stop', 'pending order', 'chase order', 'iceberg', 'TWAP', 'split order', 'large order', 'set leverage', 'check my orders', 'fill history', 'buy a call', 'sell a put', 'option chain', 'implied volatility', 'IV', 'Greeks', 'delta', 'gamma', 'event contract', 'buy Yes', 'buy No', 'buy Up', 'buy Down', 'prediction market', or any request to place, cancel, or amend spot, swap, futures, options, or event contract orders on OKX CEX. Covers conditional (TP/SL/trailing) algo orders. Requires API credentials. Do NOT use for market data (okx-cex-market), account balance (okx-cex-portfolio), or bots (okx-cex-bot).
Comprehensive AI prompt engineering safety review and improvement prompt. Analyzes prompts for safety, bias, security vulnerabilities, and effectiveness while providing detailed improvement recommendations with extensive frameworks, testing methodologies, and educational content.
Write and maintain technical documentation. Trigger with "write docs for", "document this", "create a README", "write a runbook", "onboarding guide", or when the user needs help with any form of technical writing—API docs, architecture docs, or operational runbooks.
Do business-to-business go-to-market work on Cargo — research accounts and buying committees, enrich and verify B2B contact records from licensed data providers, score and qualify leads, draft permission-based outreach for the user's own sequencer, sync to CRM, and monitor buying signals. Consent basis, suppression lists, and volume limits gate every step that touches a person (`references/acceptable-use.md`); bulk unsolicited messaging, purchased or scraped lists, and consumer targeting are refused. Triggers: "build me a list of", "find 50 <title> at <segment>", "who works at", "find work emails for these accounts", "enrich this CSV", "verify these emails", "build a TAM", "who fits our ICP", "who actually buys from us", "what data points should we collect on accounts", "our outbound is reaching the wrong people", "score these leads", "write a first-touch email", "push these to my CRM", "who changed jobs", "who just raised funding", "companies using <tech>", "who is hiring <role>", "find the buying committee", "portfolio companies of <investor>", "upload this audience to Google/Meta/LinkedIn ads". Providers: aiArk, anthropic, apolloio, bounceban, bouncer, brightData, builtwith, cargoSignals, cleon1, companyEnrich, contactOut, datagma, dropcontact, enrichCrm, enrichley, enrowio, exa, explorium, findyMail, firecrawl, forager, FullEnrich, g2, gemini, hunter, icypeas, kitt, leadMagic, linkedin, linkup, mixrank, neverBounce, oceanio, openAi, parallel, peopleDataLabs, perplexity, piloterr, pipecorn, prospeo, proxycurl, reverseContact, rocketreach, salesNavigator, serper, sillage, snitcher, societeInfo, storeleads, theirStack, theSwarm, typesafe, waterfall, x, zeroBounce. Reads phase guides, recipes, and per-provider playbooks before any paid call. Skip when: a run already happened and misbehaved — use cargo-diagnostics.
Use Link CLI's identity commands when a service requests a Link Agent Attestation Token (AAT) or signed user claims such as email. Covers acquiring and managing attestations, obtaining identity credentials, and presenting selected claims to a verifier through an HTTP client or browser automation.
Convert frontend code (Vite, React, Angular, Vue, etc.) to a Stitch Design by chaining static HTML extraction, design system extraction, and file upload. **ALWAYS** use this skill when the user's intent is to move existing web apps or React/Angular/Vue components into Stitch (e.g., requests to "save", "migrate", or "upload"). You must use this skill even for simple "save" operations, as it is the only way to ensure the design system is extracted and assets are properly linked
Provides reverse engineering techniques for CTF challenges. Use when the main job is to understand how a compiled, obfuscated, packed, or virtualized target works before exploiting or solving it, including binaries, APKs, WASM, firmware, custom VMs, bytecode, game clients, malware-like loaders, and anti-debug or anti-analysis logic. Do not use it when the vulnerability is already understood and the remaining task is exploitation; use pwn instead. Do not use it for pure web workflows, log or disk forensics, or standalone crypto problems unless reversing the implementation is the real blocker.
Generate and edit videos with Alibaba HappyHorse 1.0 models via inference.sh CLI. Models: HappyHorse T2V, I2V, R2V, Video Edit. Capabilities: text-to-video, image-to-video, reference-to-video, video editing with natural language, character preservation, 720P/1080P, up to 15 seconds. Use for: physically realistic video, video editing, character-consistent content, product demos, social media. Triggers: happyhorse, happy horse, alibaba video, happyhorse 1.0, dashscope video, alibaba happyhorse, video editing ai, ai video editor
Build and configure AI agents inside Cargo — create an agent, choose its model and temperature, write its prompt, attach knowledge for retrieval (RAG), connect MCP tool servers, manage memories, and deploy releases. Triggers: "create an agent", "make an agent that", "give the agent our docs", "attach this knowledge base", "attach this library to the agent", "add resources to the agent release", "connect an MCP server", "expose our tools as an MCP server", "use Cargo from Claude Desktop or ChatGPT", "change the agent model", "what does the agent remember", "deploy the agent", "the agent is answering wrong". Skip when: uploading the knowledge files themselves — use cargo-content; sending the agent a message or running it over records — use cargo-orchestration.
Administer a Cargo workspace and talk back to the Cargo team — invite and manage members, mint and rotate API tokens, organize plays, tools, and agents into folders, inspect roles, upload batch input files, and file reports. Triggers: "invite my teammate", "create an API token for CI", "who has access", "organize these into folders", "rotate that token", "upload this CSV for a batch" — and for feedback: "report this bug to Cargo", "send feedback to the Cargo team", "this CLI command is broken", "share this session with Cargo", "request a feature". Most commands need a token with admin access. Skip when: the question is about credits, plans, or invoices — use cargo-billing.
Generate a design system from an existing codebase or audit one for visual consistency: extract tokens (colors, typography, spacing, shadows) into design-tokens.json and CSS custom properties with DESIGN.md rationale and an interactive HTML preview, score the UI across 10 dimensions, and flag AI-slop patterns. Use when starting a design system, auditing visual consistency before a redesign, or reviewing a PR that touches styling
Make Cargo actually run something, or show what it would run — execute one connector action, run a multi-step workflow, trigger a batch across a whole segment or model, message an AI agent, build or edit a node graph, draw a workflow, tool or play as a diagram, and query the runtime tables (runs, batches, spans, records) with SQL. Triggers: "run this on all my contacts", "execute the action", "kick off a batch", "build a workflow", "schedule a play", "make it run every morning", "ask the agent", "show me the workflow", "what does this tool do", "visualize this play", "draw the graph", "explain this workflow", "how many runs failed today", "what is the output schema for this action", "add a step that". Skip when: explaining why a run misbehaved — use cargo-diagnostics; downloading result files — use cargo-analytics; committing the workflow as code — use cargo-project.
Get data out of Cargo and measure what ran — download a run output, export a segment or model to CSV or JSON, and pull run and batch success and error counts. Triggers: "download the results", "export this to CSV", "give me the file", "how many succeeded", "what is my error rate", "send me the enriched list", "get the output of that run", "how many records did it write". Skip when: asking why something failed or where credits went — use cargo-diagnostics; asking about credits, plans, or invoices — use cargo-billing.
Turn a one-line objective into a step-by-step construction plan for multi-session, multi-agent engineering projects: one-PR-sized steps with self-contained context briefs, dependency graph with parallel-step detection, adversarial review gate, and plan mutation protocol. Use when planning a large feature, refactor, or roadmap that spans multiple PRs or sessions; not for single-PR tasks or when the user says “just do it”
Work with the data inside a Cargo workspace — models (Companies, Contacts, Deals…), datasets, columns, relationships, records, and SQL over workspace storage. Triggers: "what models do I have", "show me the schema", "add a column for", "how many contacts do I have", "SELECT … FROM", "query my companies table", "join contacts to companies", "what is the DDL", "set up a webhook-fed model", "where does this field live", "import this into a model", "unify these models", "merge duplicate accounts", "link contacts to companies", "set up a relationship between". Skip when: querying run or batch telemetry rather than business data — use cargo-orchestration; naming a reusable filtered audience — use cargo-segmentation.
Understand what Cargo is costing — remaining credits, usage broken down by workflow, connector, or agent, subscription state, and invoice history. Triggers: "how many credits do I have left", "what did that cost", "why is my bill so high", "am I about to run out", "will this fit in our budget", "show me my invoices", "how much have I spent this month", "what plan am I on", "what do I get for free", "how many free credits", "can I afford this run", "add a card", "update my payment method", "why was my card declined". Needs a token with admin access. Skip when: attributing spend to specific nodes or cutting a play cost — use cargo-diagnostics.
Use this skill when building real-time, bidirectional streaming applications with the Gemini Live API, or migrating legacy Live models (2.0/2.5/3.1) to Gemini 3.8 Live. Covers WebSocket-based audio/video/text streaming, voice activity detection (VAD), background reasoning (extended thinking), asynchronous function calling, session management, ephemeral tokens, live transcription, and live translation. SDKs covered - google-genai (Python), @google/genai (JavaScript/TypeScript).
Generate videos with Pruna P-Video and WAN models via inference.sh CLI. Models: P-Video, WAN-T2V, WAN-I2V. Capabilities: text-to-video, image-to-video, audio support, 720p/1080p, fast inference. Pruna optimizes models for speed without quality loss. Triggers: pruna video, p-video, pruna ai video, fast video generation, optimized video, wan t2v, wan i2v, economic video generation, cheap video generation, pruna text to video, pruna image to video
Run a pre-mortem risk analysis on a PRD or launch plan. Categorizes risks as Tigers (real problems), Paper Tigers (overblown concerns), and Elephants (unspoken worries), then classifies as launch-blocking, fast-follow, or track. Use when preparing for launch, stress-testing a product plan, or identifying what could go wrong.
Read and write the workspace GTM knowledge base — the git-backed repository of markdown describing ICPs, personas, plays, proof points, objections, competitors, and signals — plus its runtime sandbox and typed knowledge graph. Triggers: \"document our ICP\", \"write up this persona\", \"what is our positioning\", \"add a battlecard\", \"capture this objection\", \"what do we know about <segment>\", \"update our context\", \"what is in the context repo\", \"who do we sell to\". Skip when: discovering who actually buys from you by analyzing won/lost data — that is cargo-gtm (this skill writes the conclusion down, it does not derive it); storing structured records rather than prose — use cargo-storage; attaching documents to an agent for RAG — use cargo-content.
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.