Skills
98,873 packaged capabilities and playbooks for agents. Install any of them with one command.
All
Optimizes raw idea descriptions into structured prompts ready for the brainstorming workflow. TRIGGER when: user says "optimize for brainstorm", "prepare idea for brainstorm", "enhance this idea", "make this ready for brainstorming", "imposta per brainstorm", or wants to improve a feature idea before using /specs.brainstorm. DO NOT TRIGGER for code optimization, refactoring, or general prompt engineering tasks.
This skill should be used when the user asks to "write a chapter", "next chapter", "chapter outline", "draft chapter", "continue the story", "write a scene", "outline a chapter", or wants to write prose for a story project. NOT for planning a scene's structure, subtext, or outcome (use scene-craft), drafting without an outline (use discovery-drafting), or revising existing chapters (use revision-continuity).
Use this skill to diagnose and resolve what blocks a DevOps Center promotion of a work item's feature branch: Git merge conflicts and deployment failures. DevOps Center is Git-backed, so overlapping metadata changes surface as merge conflicts against the target stage branch, resolved with git (detect, resolve markers, commit, push). Deploy failures often cite a missing dependency a full promotion can fix when the component already exists on the branch. TRIGGER when the user wants to check a work item for conflicts before promoting, resolve merge conflicts or leftover conflict markers in metadata files (.xml, .object-meta.xml, .cls), reconcile a feature branch with its target stage branch, or diagnose why a DevOps Center promotion or deployment failed and whether a full promotion or a missing-dependency fix will resolve it. DO NOT TRIGGER for running the promotion itself (use dx-devops-promote), creating or updating work items (use dx-devops-work-item-manage), or deploying metadata directly to an org.
Use when generating or editing images with Scenario through MCP: text-to-image, image-to-image, instruction editing, inpainting or outpainting with a mask, background control, aspect ratio or resolution sizing, several outputs per run, or choosing between Scenario image models. Also when a run fails on prompt length, a plan-restricted model, or a reference image that was silently ignored. Keywords: txt2img, img2img, image edit, inpaint, mask, reference image, aspect ratio.
Describes the agent skills shipped with NemoClaw and how to access them by cloning the repository. Use when users ask about AI agent support, coding assistant integration, or the .agents/skills/ directory. Trigger keywords: nemoclaw agent skills, ai coding assistant, cursor, claude code, copilot
Upgrade any Pulumi provider to a newer version and reconcile the resulting diff. Use when users want to upgrade or update a provider (including editing package.json, requirements.txt, pyproject.toml, go.mod, or Pulumi.yaml to bump a provider SDK), check for breaking changes before or during an upgrade, fix resources that broke after a provider upgrade, or resolve unexpected replacements, creates, or deletes in a post-upgrade preview, including pulumi-gcp v10 errors such as a missing gcp.notebooks or gcp.iap.Brand type or a required secretDataWoVersion. Applies to all providers (aws, azure-native, gcp, kubernetes, aws-native, cloudflare, datadog, etc.) — not just Tier 1. Do NOT use for querying which stacks use what package versions; use skill `package-usage` for cross-stack audits. Do NOT use for general infrastructure tasks.
Apply when building, customizing, or deploying extensions for VTEX Sales App. Covers the complete 7-step workflow from prerequisite checks through code generation to deployment, including extension points (cart, PDP, menu), React hooks (useCart, usePDP, useCartItem, useCurrentUser, useExtension), TypeScript types, secure API integration patterns, and API documentation ingestion (OpenAPI, URLs, or inline specs) to generate typed integrations.
Use when THIS agent needs to pay for x402-protected content at runtime: hitting a paywall mid-task, settling it via AgentCore Payments, and applying operator-defined spend limits. Covers payment setup, policy, session budgets, and troubleshooting. Triggers on: "my agent hit a 402 while calling an API", "a tool call returned 402 Payment Required", "my agent needs to pay for x402-protected content", "let the agent pay for content, capped at $5 per session", "set a spend limit for the agent", "ProcessPayment failed", or "why did my agent refuse to pay". Not for BUILDING payment capability for end users, including wallets and framework middleware; use agents-build and references/payments.md. For non-paid APIs via Gateway use agents-connect. For inbound auth use agents-harden. For project scaffolding use agents-get-started.
Use for any cold outreach or SDR email or follow-up sequence to prospects who did not opt in, before drafting. Scores the sequence for length, personalization and spam risk with email_sequence_analyzer.py. Opted-in nurture: email-sequence.
Build or change a Metabase data app on an rde machine: settles what the `metabase-data-apps` skill needs from the local setup (the remote-sync repository, the Metabase URL, the API key rde stores, how the app reaches Metabase), makes sure everything the app reads is Library content already synced into that repository, confirms every sync step with the user, and hands the build to it. Use only when an app is asked for explicitly: “build me an app for X”, “create a data app”, “make an internal tool / portal in Metabase”, “add a page / a form / a filter to my data app”. A dashboard, a question, or a metric is not an app; those stay with the `rde` skill.
This skill should be used when the user asks to "start a new story", "initialize a story project", "create a story", "new book", "set up a story", or wants to begin a new fiction writing project from scratch. NOT for a sequel or prequel (use series-continuity), or for finding the idea before a project exists (use premise-workshop).
Create and debug Cloudinary transformation URLs from natural language instructions. Use when building Cloudinary delivery URLs, applying image/video transformations (resizing, cropping, effects, overlays), optimizing media, or debugging transformation syntax errors. TRIGGER — read BEFORE writing a Cloudinary delivery URL, or SDK code that generates one (such as cloudinary.url() or an SDK image component), that resizes, crops, applies effects, css-style shape changes, overlays, or changes format or quality, even when it's a small part of a larger task and even if you already know the syntax.
The LinkedIn personal-profile growth playbook for 2026. Use when someone wants to "grow on LinkedIn," "get more LinkedIn followers/reach," "a LinkedIn strategy," "how the LinkedIn algorithm works," or how to use commenting/newsletters/video/connections to grow. Dwell time + early meaningful comments are the engine, personal profiles massively out-reach company pages, links go in the first comment, and strategic commenting on target accounts is the cheapest reach on the platform. Uses the LADDER framework. Reads brand-profile + voice-builder first. The agent drafts posts + comment copy and designs the system; a human does the live commenting/connecting/DMs; WoopSocial schedules posts; metrics come from native LinkedIn analytics (SSI as a directional check); nothing is fabricated. Single-post craft → linkedin-post-writer; company page → linkedin-company-pages.
Designs novel outlines, worldbuilding, and character profiles for requests such as writing a novel outline, designing the protagonist, creating a world, structuring the plot, outlining volumes or chapters, planning satisfying moments, or creating character sheets. Produces a complete world, character profiles, plot outline, chapter-level outline, and payoff plan, and checks names to avoid clashes with real people, places, or well-known IP. For large batches of detailed outlines, sub-agents generate in parallel, with each handling at most 3 chapters.
The model-agnostic AI-video router and brief — the counterpart to image-prompt. Use when someone asks "which AI video tool should I use," "make an AI video," "generate B-roll / a talking-head / a voiceover," "turn this long video into Shorts," or needs a video brief. Routes the job to the right tool by fit and writes a portable brief; the tool generates, the human assembles, WoopSocial schedules/publishes. Sits above the tool skills: veo-3, kling, luma (generative scenes), heygen, synthesia (avatars), ai-voiceover, captions-and-clipping. A real human on camera routes to talking-head-and-piece-to-camera. Never routes to discontinued tools
Analyzes public sentiment on Twitter/X for any topic, brand, or event using apidojo's Tweet scrapers on Apify. Triggers when the user asks to: analyze Twitter sentiment about a topic, measure public opinion on Twitter, see if sentiment is positive or negative about a brand or issue on X, analyze the emotional tone of tweets about an event, research how Twitter reacts to a news story, measure brand or product sentiment from tweets, or compare sentiment between two competing topics or brands on Twitter. Returns sentiment classification, top positive and negative tweets, volume over time, and key themes. Ideal for PR teams, market researchers, political analysts, and social listening platforms.
Review user journeys, public content, and codebases for potentially relevant EU AI Act provisions, with exact official citations, evidence gaps, application dates, and plain-language next actions. Use for EU AI Act issue-spotting, not final legal or compliance decisions.
Interact with TP-Link Omada SDN Controller Open API. Use when querying or managing Omada network devices, clients, sites, access points, switches, gateways, VLANs, firewall rules, VPNs, or any Omada controller configuration. Also use when the user mentions Omada, SDN controller, or needs to authenticate against the Omada API.
Professional AI assistant for the full PPT presentation workflow. It simulates the complete workflow of a top-tier presentation design company (requirements research, material gathering, outline planning, storyboard, design draft) and outputs high-quality HTML presentations. Triggered when the user mentions making a PPT, presentation, slides, report material, training courseware, pitch deck, or product intro page. It should trigger even when the user only says "make me an intro to X" or "I need to report Y to my boss," as long as structured multi-page presentation content is implied. It also applies to requests like "turn this document into a PPT" or "make a presentation on this topic." Works in English too: "make a presentation about...", "create slides for...", "build a pitch deck", "I need a keynote for...". Implicit intent should also trigger it: "visualize this data for my boss", "I need something for a pitch", "make this report presentable", "beautify my existing PPT", "redesign these slides". Improving or beautifying an existing PPT is also in scope.
Read-only operations; does not modify document contents. Reads Feishu cloud documents, knowledge base content, or spreadsheets and analyzes document structure. Supports regular docx, regular sheets, knowledge base docx, and knowledge base sheets. Use when the user asks to “view,” “read,” “analyze,” or “open” Feishu documents, knowledge bases, or spreadsheets. Supports reading via document ID, knowledge base token, or URL. Markdown is stored in /tmp only as an intermediate analysis state (it is not proactively saved as a user file); to export to a local path, use feishu-cli-export; to write, use feishu-cli-write.
Initialize Spec-Driven Development context — detects tech stack, conventions, architecture patterns, and bootstraps persistence backends. Triggers on 'sdd-init', 'init sdd', 'setup sdd', 'initialize sdd', 'setup project', 'initialize project context'. Creates/updates docs/specs/architecture.md & ontology.md (Constitution), and populates knowledge-graph.json.
Use when the user asks to generate, edit, extend, poll, list, download, or delete Sora videos, create reusable non-human Sora character references, or run local multi-video queues via the bundled CLI (`scripts/sora.py`); includes requests like: (i) generate AI video, (ii) edit this Sora clip, (iii) extend this video, (iv) create a character reference, (v) download video/thumbnail/spritesheet, and (vi) Sora batch planning; requires `OPENAI_API_KEY` and Sora API access.
Executes real end-to-end verification against a running application after specification implementation. Detects the application type, starts the local runtime (Docker, Node, Spring Boot, etc.), runs real tests (curl for REST APIs, Playwright for web SPAs, computer-use for desktop apps), verifies acceptance criteria from the functional specification, generates a markdown report, and tears down the environment. Use when: user asks to verify a completed spec with real tests, run e2e checks after implementation, validate acceptance criteria in a live environment, or test the feature for real after task completion.
Generate production-grade UI using real component patterns and best practices from 60+ documented interface components. Use when the user asks to build web interfaces, pages, dashboards, forms, navigation, or any UI — ensures modern, minimal, SaaS-quality output grounded in design system conventions rather than generic AI patterns.
Clone a game template from the gallery as a starting point. Use when the user says "use a template", "start from a template", "clone flappy-bird", "use the platformer template", or wants to quickly bootstrap a game from an existing example. Do NOT use for creating a game from scratch (use viral-game for one-shot builds or make-game for milestone-driven projects).
Turns one photo into a cinematic paper-collage animation in the style of Vox explainer documentaries (halftone cut-outs with a white scissor border, torn paper, aged paper grain, stop-motion moves, slow camera push-in). Codex generates the paper layers with the user's ChatGPT plan, the real photo is cut out and printed as halftone by code, an HTML page animates everything and is captured to an MP4 (1080x1920 by default). Use when the user says vox, Vox style, "anime cette photo", "animate this photo", paper collage animation, documentary collage, or sends a photo and an animation idea; also to change an animation already made ("do it with Napoleon", "add a train", "make it night").
Select and apply a fitting Awesome Design MD `DESIGN.md` style for frontend/UI work. Use when the user asks to design UI, redesign a page, beautify a frontend, create a dashboard, improve layout/visual hierarchy, change visual style, use a big-company design style, or mentions `DESIGN.md`, Awesome Design MD, big-tech styles, brand-inspired UI, Apple/Stripe/Linear/Cursor/Raycast/Voltagent/Binance/Coinbase/xAI-style interfaces.
Creates a structured competitive analysis comparing features, pricing, and positioning across 3-5 direct and indirect competitors, with a 2x2 map and actionable strategic recommendations. Use before entering a market, planning differentiation, or after losing deals. For market size rather than competitor positioning, use discover-market-sizing instead.
Product Led AI Development — guides founders from idea to launched product. Six capabilities: Idea (discover a product idea), Validate (pressure-test the idea against fatal flaws, problem reality, competition, and 2-week MVP feasibility), Plan (vision intake + document generation), Design (translate image references into a design.md spec), Launch (go-to-market strategy), and Build (roadmap execution). Use when someone says "PLAID", "plaid idea", "help me find an idea", "product idea", "idea from my business", "idea from my expertise", "plaid validate", "validate my idea", "pressure-test", "is this idea good", "find fatal flaws", "validate the problem", "plan a product", "define my vision", "generate a PRD", "product strategy", "plaid design", "design from image", "translate image to design", "create design.md", "extract design tokens", "plaid launch", "go-to-market", "launch plan", "GTM strategy", "launch playbook", "plaid build", "build the app", "start building", or "execute the roadmap".
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.