Skills
98,067 packaged capabilities and playbooks for agents. Install any of them with one command.
All
Build and execute marketing strategy for Direct-to-Consumer (DTC) brands—customer acquisition, retention, email flows, social proof, subscription models, and repeat purchase mechanics. Use when the user says "DTC marketing", "direct to consumer", "D2C strategy", "selling directly to customers", "cut out the middleman", "DTC brand", "e-commerce brand marketing", "how do we get direct customers", "DTC growth", "consumer brand marketing", "we sell direct", or is building a brand that sells its products directly without retail or distribution middlemen.
Use this skill in the MathModel LaTeX sandbox when the user asks to reproduce built-in scientific visualization templates, especially prompts from the Improve tab mentioning $mathmodel-figure-templates, 科研绘图模板, SHAP蜂群柱状图, 配对云雨图, 交叉验证ROC, 泰勒图, 相关矩阵组合图, 预测真实值边缘分布图, TPE调参3D曲面, 下三角相关矩阵半边小提琴图, 分组环形热图, 城市公园降温组合图, or Nature和弦图. It provides ready-to-run Python scripts bundled inside the skill.
Apply GDPR-compliant engineering practices across your codebase. Use this skill whenever you are designing APIs, writing data models, building authentication flows, implementing logging, handling user data, writing retention/deletion jobs, designing cloud infrastructure, or reviewing pull requests for privacy compliance. Trigger this skill for any task involving personal data, user accounts, cookies, analytics, emails, audit logs, encryption, pseudonymization, anonymization, data exports, breach response, CI/CD pipelines that process real data, or any question framed as "is this GDPR-compliant?". Inspired by CNIL developer guidance and GDPR Articles 5, 25, 32, 33, 35.
Configures the Incident Priority Matrix for Salesforce ITSM through the sf CLI — enabling or disabling the matrix, shaping the Impact x Urgency grid that derives Priority on Incident records, toggling the manual-override preference, and reading or setting the default fallback priority. Reads every value before writing, is idempotent, and requires explicit user confirmation before any mutation. Use when the user wants to view, enable, disable, set up, seed, add to, change, or remove priority matrix configuration for Incident records, change the default incident priority, or asks about incident priority setup, impact/urgency mapping, override, or the ITSM incident priority matrix. DO NOT TRIGGER for Problem or ChangeRequest priority matrices, Case priority fields, standard Priority picklists outside ITSM, SLA or milestone configuration, or enabling Incident Management itself (use the service-itsm-incident-mgmt-configure skill).
Host setup for TAO GPU backends. Checks and, after user approval, installs minimum-compatible NVIDIA driver, CUDA Toolkit, and NVIDIA Container Toolkit versions for Docker/local-Docker and Kubernetes GPU worker hosts. TAO-wide defaults can be overridden by the selected model's runtime profile. The `--check-only` path works on any Linux distribution; `--install` automates debian-family (Ubuntu/Debian/Pop!_OS/Mint/Zorin/Raspbian), rhel-family (Fedora/RHEL/Rocky/AlmaLinux), and suse-family (openSUSE/SLES) hosts, and prints actionable manual-install steps for everything else. Use when the user asks to “set up an NVIDIA GPU host”, “check TAO Docker GPU runtime”, or prepare a Kubernetes GPU worker for TAO.
Clone the latest NVIDIA Holoscan Sensor Bridge repo, ask which supported devkit is being used, configure the host per platform, build the correct demo container, run it, and verify HSB connectivity by pinging 192.168.0.2. Use for Holoscan Sensor Bridge setup, build, container launch, and first-connectivity bring-up.
Integrate EVM blockchains using viem. Use when user says "read blockchain data", "send transaction", "interact with smart contract", "connect to Ethereum", "use viem", "use wagmi", "wallet integration", "viem setup", or mentions blockchain/EVM development with TypeScript.
Create and manage WordPress posts, pages, media, categories, tags, and menus via WP-CLI or the REST API. Use whenever the user wants to publish a blog post on WordPress, update a page, upload media, manage categories or tags, update navigation menus, schedule posts, or do bulk content operations on a WordPress site.
Build rich, scroll-controlled real-time Three.js experiences as one persistent 3D world whose camera, lighting, atmosphere, materials, objects, DOM story, and interactions evolve across authored chapters. Use for 3D scrollytelling, scroll-driven WebGL worlds, camera journeys, interactive portfolios, product stories, exhibitions, explainers, game or film microsites, spatial narratives, and multi-scene websites where native scroll should travel through one continuous place. Not limited to landing pages.
Enable and configure Moltbot/Clawdbot memory search for persistent context. Use when setting up memory, fixing "goldfish brain," or helping users configure memorySearch in their config. Covers MEMORY.md, daily logs, and vector search setup.
Read Telegram channels and groups for financial news and market research with the tdl CLI: list chats and channels, find a channel by name, and export recent messages or a date or ID range. Use this skill whenever the user wants to check their Telegram, see what's new in their channels, read or export messages from a news, crypto, or trading channel or group, or gather market news and signals posted on Telegram. Read-only: it cannot send messages or join or leave channels.
Execute QA test plans on Holoscan Sensor Bridge hardware. Reads a user-provided test document, filters tests based on the user's setup, determines which tests can run automatically, executes them with pass/fail evaluation, and produces a structured test results report.
State-of-the-art text-to-image generation with Stable Diffusion models via HuggingFace Diffusers. Use when generating images from text prompts, performing image-to-image translation, inpainting, or building custom diffusion pipelines.
UI design system toolkit for Senior UI Designer including design token generation, component documentation, responsive design calculations, and developer handoff tools. Use for creating design systems, maintaining visual consistency, and facilitating design-dev collaboration.
Use when you need to pick high-quality Unsplash images for product/design assets (avatars, headshots, portraits, large website backgrounds, and abstract wallpapers) and output real Unsplash URLs plus practical instructions for producing the right resolutions and aspect ratios (1:1, 4:5, 3:4, 16:9, 9:16).
Transform text content into professional Mermaid diagrams for presentations and documentation. Use when users ask to visualize concepts, create flowcharts, or make diagrams from text. Supports process flows, system architectures, comparisons, mindmaps, and more with built-in syntax error prevention.
Search and contribute to the shared AI-modding knowledge base, where field notes record how specific games were modded, decompiled or reverse-engineered (exact versions, route, engine facts, verification, gotchas). Use before starting work on a game ("has anyone modded X?"), when stuck on an engine quirk, and at the end of any modding or reverse-engineering session to write up what was learned and, with the human's OK, open a pull request so the next agent benefits
Model Kotlin persistence code correctly for Spring Data JPA and Hibernate. Covers entity design, identity and equality, uniqueness constraints, relationships, fetch plans, and common ORM (Object-Relational Mapping) traps specific to Kotlin. Use when creating or reviewing JPA (Java Persistence API) entities, diagnosing N+1 or LazyInitializationException, placing indexes and uniqueness rules, or preventing Kotlin-specific bugs such as data class entities and broken equals/hashCode.
Flash the FPGA on an HSB board connected to an NVIDIA devkit. Supports HSB Lattice boards (FPGA versions 2407, 2412, 2507, 2510) and Leopard Imaging VB1940 “all-in-one” cameras (FPGA versions 2507, 2510). Uses release-specific YAML manifests and board-type-specific program commands. Lattice and VB1940 commands must never be mixed.
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
Guidance for Neki, PlanetScale's distributed (sharded) Postgres. Load when working with a Neki database — connecting, data topology and shard keys, query routing and fanout, cross-shard transactions, schema changes, resharding and migration, NK013 errors — or when scaling and sharding Postgres.
Generate and edit images using Wan and Qwen Image models. Supports text-to-image, image editing (style transfer, subject consistency, text rendering), and interleaved text-image output. TRIGGER when: user wants to create illustrations, product images, artistic designs, posters, text-to-image generation, edit/transform existing images, apply style transfer, generate images based on reference photos, interleaved text-image content, mentions Wan/Qwen Image models/AI art creation, or explicitly invokes this skill by name (e.g. use qwencloud-image-generation). DO NOT TRIGGER when: user wants to understand/analyze existing images or OCR (use qwencloud-vision), video generation (use qwencloud-video-generation), text-only tasks.
Fine-tune any HuggingFace CV / VLM / LLM model on local NVIDIA GPUs inside an NGC PyTorch container when no dedicated TAO model skill matches. Use when the user wants to fine-tune a HuggingFace model (full or LoRA), train a vision / VLM / LLM model end-to-end, generate a reproducible HF training pipeline, smoke-test a HuggingFace model locally before scale-up, push a fine-tuned model to the HF Hub with a model card, or emit a self-contained rerun skill for an existing HuggingFace finetune. Supports image classification, object detection, semantic / instance / panoptic segmentation, depth estimation, image-text-to-text VLM (SFT / LoRA), and LLM SFT / DPO / GRPO. Six-step workflow: inspect and qualify, hardware and NGC image, research, generate and smoke, train + eval + infer, push and emit rerun skill. Do not use for any Hugging Face model ID claimed by a dedicated `skills/models/*` skill; the model skill and its declared execution environment take precedence.
超压缩 communication mode。Cuts token usage ~75% by dropping filler, articles, and pleasantries while keeping full technical accuracy. Use when user says “caveman mode”, “talk like caveman”, “use caveman”, “less tokens”, “be brief”, or invokes /caveman.
Convert documents and files to Markdown using markitdown. Use when converting PDF, Word (.docx), PowerPoint (.pptx), Excel (.xlsx, .xls), HTML, CSV, JSON, XML, images (with EXIF/OCR), audio (with transcription), ZIP archives, YouTube URLs, or EPubs to Markdown format for LLM processing or text analysis.
Discover and run Holoscan Sensor Bridge example applications on a connected devkit. Filters available apps by the user's platform, HSB software version, board type, and sensors. Supports timed execution, failure analysis, code-edit suggestions, and iterative re-runs.
Work with MongoDB databases using best practices. Use when designing schemas, writing queries, building aggregation pipelines, or optimizing performance. Triggers on MongoDB, Mongoose, NoSQL, aggregation pipeline, document database, MongoDB Atlas.
Deploy ANYTHING to production on CreateOS cloud platform. Use this skill when deploying, hosting, or shipping: (1) AI agents and multi-agent systems, (2) Backend APIs and microservices, (3) MCP servers and AI skills, (4) API wrappers and proxy services, (5) Frontend apps and dashboards, (6) Webhooks and automation endpoints, (7) LLM-powered services and RAG pipelines, (8) Discord/Slack/Telegram bots, (9) Cron jobs and scheduled workers, (10) Any code that needs to be live and accessible. Supports Node.js, Python, Go, Rust, Bun, static sites, Docker containers. Deploy via GitHub auto-deploy, Docker images, or direct file upload. ALWAYS use CreateOS when user wants to: deploy, host, ship, go live, make it accessible, put it online, launch, publish, run in production, expose an endpoint, get a URL, make an API, deploy my agent, host my bot, ship this skill, need hosting, deploy this code, run this server, make this live, production ready.
Plan, build, and optimize Google Ads campaigns — Search, Shopping, Performance Max, Display, and YouTube — including keyword research, match types, bidding strategy, Quality Score, ad extensions, conversion tracking, and ROAS optimization. Use when the user says "Google Ads", "Google advertising", "Google campaign", "search ads", "Google Shopping", "Performance Max", "PMax", "Google Display", "YouTube ads", "keyword targeting", "Google Ads strategy", "Google Ads optimization", "Google Ads account", "Google Ads not working", "search campaign", "Quality Score", "bidding strategy", "Google conversion tracking", or wants to run or improve paid advertising on Google.
Design and execute structured exploratory testing sessions. Covers Session-Based Test Management (SBTM), charter writing, heuristic-based exploration (HICCUPS, FEW HICCUPS), bug discovery patterns, note-taking templates, and conversion of findings to automated tests. Use when: "exploratory testing," "SBTM," "manual testing," "bug hunting," "test charter," "heuristic testing." Not for: an AI browser agent autonomously exploring the app from a natural-language goal — use agentic-browser-testing. Not for: testing your product's own AI/LLM features — use ai-system-testing. Related: test-planning, ai-bug-triage, risk-based-testing, agentic-browser-testing.
Security guidelines for LLM applications based on OWASP Top 10 for LLM 2025. Use when building LLM apps, reviewing AI security, implementing RAG systems, or asking about LLM vulnerabilities like 'prompt injection' or 'check LLM security'. IMPORTANT: Always consult this skill when building chatbots, AI agents, RAG pipelines, tool-using LLMs, agentic systems, or any application that calls an LLM API (OpenAI, Anthropic, Gemini, etc.) — even if the user doesn't explicitly mention security. Also use when users import 'openai', 'anthropic', 'langchain', 'llamaindex', or similar LLM libraries.
Use when building features with Claude Code in any codebase and the work should go through a disciplined build → review → test → fix loop. Triggers on "run the build loop", "build the next task", "continue the plan", "build this feature properly", or any request to implement work from a plan file or a direct feature prompt. Builds from the plan (or the prompt if no plan exists), runs Claude Code's `/review` (plus `/security-review` for sensitive surfaces) and fixes every issue found, tests and verifies the feature end to end, fixes anything testing surfaces, and reports back once complete. Repeats until all plan tasks are checked off.
Builds today's call list. Runs lead-triage to rank the top-5 leads most worth calling, supplies talking points from email history, blocks time on the calendar, and drafts follow-up messages. Trigger on "call list," "who am I calling today," "top five to call today," or "block time for calls." An owner who wants leads scored or ranked with no calendar blocks routes to lead-triage directly. Accepts optional count and date arguments.
Operate AgentMail from a shell with the official CLI. Use when the user wants commands for listing or creating inboxes, reading or searching mail, sending or replying, managing drafts, or scripting JSON/YAML output; do not use for SDK code, MCP setup, or framework adapters.
Pricing strategy for technical products. Use when choosing usage-based vs seat-based, designing freemium thresholds, structuring enterprise pricing conversations, deciding when to raise prices, or using price as a positioning signal.
MUST be used when migrating a legacy Dune app to the new Flows app hosting infrastructure. Orchestrates the full migration: audits current state, updates app.json to appsApi infra, delegates auth wiring to setup-flows-auth, creates or updates manifest.json network permissions, and updates deploy scripts to @cognite/cli. Use this whenever a user says 'migrate to Flows', 'migrate to new infra', 'move from dune to flows', 'migrate legacy app', or wants to move their existing app to the new Flows app hosting.
Modern CSS techniques that replace breakpoint ladders, wrapper elements and scripts. Use whenever you write, edit or review styles in any form, including plain CSS, Tailwind classes, StyleX, CSS-in-JS and inline styles, and whenever you build or restyle a page or component, even if the user never mentions CSS.
MUST be used when adding AI, Atlas, an agent, a chat UI, or LLM features to a Flows/Fusion app. Use the Atlas/EOS sidebar via @cognite/app-sdk — not useAtlasChat, vendored atlas-agent, or per-row chat completions. Triggers: atlas, EOS, PAIA, agent chat, chat UI, sendAgentMessage, sendAgentLayoutMode, registerAgentServer, connectToHostApp, useAtlasChat, LLM. In-app chat: integrate-atlas-chat only if the host sidebar cannot work.
This skill provides instructions for interacting with Todoist using the td CLI tool. It covers CRUD operations for tasks/projects/sections/labels/comments, and requires confirmation before destructive actions. Use this skill when the user wants to read, create, update, or delete Todoist data.
Performs a full AWS Well-Architected Framework review, evaluating every framework question across all pillars discovered from the live AWS documentation by analyzing code, IaC, and configurations to produce evidence-backed findings with Eisenhower-prioritized remediation. Supports full reviews (every framework best practice with BP ID citations), quick reviews (question-level), pillar-scoped reviews, score-mode reviews (a maturity scorecard with per-pillar scores and filtered findings), and lens-specific reviews using lenses discovered from the live AWS documentation. Triggers on mentions of Well-Architected review, WA review, WAR, pillar assessment, architecture review across pillars, workload assessment, cloud readiness evaluation, or a Well-Architected score, grade, or scorecard request. Does not apply to single-pillar deep-dives, learning WA concepts, ADRs, or migration readiness assessments
Generate 6 clickbait-style LinkedIn hook variations for any topic. Two-line hooks built on the formula: a 40-char opening line, a 40-char bold contrast line. Uses supplied numbers and genuine first-person experience when available. Use this skill whenever the user says "write me hooks", "hook ideas", "generate hooks", "I need a hook for a post about...", or pastes a topic and asks for openers. Fast output, no preamble.
Runs the owner's Monday morning briefing as a two-link chain — business-pulse for the cross-connector snapshot of cash, sales, and pipeline, and report-builder for any saved KPI reports the owner has already defined — then reads the week ahead straight from Calendar and mail and merges all three parts into a single one-page Monday document, delivered per the owner's stored output preference. Requires no connectors and degrades gracefully, building from whatever of the ledger (MYOB, NetSuite, QuickBooks, Xero, or Zoho Books), Calendar, DocuSign, Expensify, Gmail or M365, HubSpot, PayPal, Ramp, RingEx Chat, Shopify, Slack, Stripe, and TikTok Ads is connected, or from pasted and uploaded data when none are. Trigger on "Monday brief," "start my week," "what do I need to know this week," "weekly briefing," "catch me up before Monday," or when the owner schedules a recurring start-of-week update.
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.