Skills
99,951 packaged capabilities and playbooks for agents. Install any of them with one command.
All
Build with OpenAI stateless APIs — Chat Completions (GPT-5.2, o3), Realtime voice, Batch API (50% savings), Embeddings, DALL-E 3, Whisper, and TTS. Prevents 16 documented errors. Use when implementing GPT-5 chat, streaming, function calling, embeddings for RAG, or troubleshooting rate limits (429), API errors, TypeScript issues, or model name errors.
AWS-curated copy-paste prompts for AI coding agents (MVP scaffolding, RAG chatbot with Claude on Bedrock, security baseline evaluation, cost anomaly detection, GPU quota requests, EKS deployment, Well-Architected review, etc.) plus downloadable installable agents (Multi-Account Transition Advisor, Bill Shock Preventer, Service Quota Agent, Bedrock Model Availability Agent, AWS DB Advisor). Use when the user asks for a prompt to do X on AWS, wants an installable agent for multi-account / cost monitoring / quota management / Bedrock model availability / database selection, or asks how to use AWS prompts. For migration intent (GCP to AWS, Azure to AWS, OpenAI/Gemini to Bedrock), route to the migration skills in this plugin (`gcp-to-aws`, `azure-to-aws`, `heroku-to-aws`, `llm-to-bedrock`). Do not use for: factual AWS Activate / programs / credits questions, learn articles, sample architectures, or for prompts that are not in the bundled `references/prompt-library/` tree.
Profiles a target application using rocprofv3 with program counter sampling enabled and then analyzes the results. Use when the user has a program that runs on an AMD GPU and asks to perform PC sampling, to determine the runtime performance characteristics of their application, to determine stall reasons, or to determine hotspots in the code.
Repair imported ComfyUI workflows with missing or broken model metadata for ComfyUI-RunpodDirect. Accept a workflow JSON or original ComfyUI output PNG, extract and inventory it, and resolve exact model artifacts. Use when a user reports a broken workflow, missing models, or failed model discovery; use companion-clis for generic Hugging Face transfers and runpod-mcp or runpodctl for Pod lifecycle.
Companion CLIs for Runpod workflows — HuggingFace, GitHub, Docker, and AWS. Use runpod-build-template for complete template project authoring, and the ComfyUI model-repair guide in runpod-templates for imported workflows lacking model download metadata
Code-first serverless with the Runpod Python SDK (`runpod` 2.0): define a `runpod.App` with `@app.queue` / `@app.api` / `@app.task`, iterate on remote GPUs/CPUs with `rp flash dev`, ship with `rp flash deploy`, and maintain or migrate legacy `runpod-flash` projects (`from runpod_flash import Endpoint`). Use runpod-build-template for explicit Dockerfile/template project authoring, and runpodctl/runpod-mcp for infrastructure management.
Use when building a 2D game in Unity 6.3 URP: pixel-art or HD sprite import and PPU, sprite atlases, Tilemaps, Rule Tiles and reskins, the 2D Renderer and 2D lights with normal maps, 2D animation, a platformer or top-down controller ("make a platformer controller that feels good", coyote time, jump buffer, one-way platforms, spikes), Pixel Perfect Camera, a follow or room camera, hit stop and screen shake; or when pixel art looks blurry or shimmers, tiles show seams, 2D lights do nothing or cost too much, the jump feels floaty, or the camera loses the player when falling.
Use when defining or reviewing SLOs, SLIs, error budgets or burn-rate alerts. Designs SLOs with slo_designer.py, computes budgets and multi-window burn-rate thresholds with error_budget_calculator.py and catches common SLO bugs with slo_review.py
When the user wants help with social selling, LinkedIn prospecting, building relationships with buyers online, or using social media to generate pipeline. Also use when the user mentions 'LinkedIn prospecting,' 'social selling,' 'LinkedIn outreach,' 'personal branding for sales,' 'warm prospecting,' 'social engagement,' or 'thought leadership for sales.' For cold email outreach, see cold-outreach-writing. For general prospecting tactics, see sales-tactics.
Interactive discovery and implementation workflow that gathers requirements through picker-based questions (intent, scope, constraints, preferences), scans the codebase for what it can already infer, then writes an AWS architectural scaffold and implementation directly into the project. Use when the user wants to build a new app, scaffold a project, or expand/refactor an existing one on AWS — anything that calls for a structured discovery flow followed by code changes, not a one-off lookup. Do not use for: factual lookups about AWS Activate / programs / credits, requests for a single copy-paste prompt, non-AWS architectural work, architecture advice/recommendations without code changes (see architect-for-startups), a new idea centered on an AI agent — runtime selection, agentic architecture, or an agent POC (see agent-advisor), or migrating an existing GCP/Azure/Heroku workload or an LLM SDK rewrite (see gcp-to-aws / azure-to-aws / heroku-to-aws / llm-to-bedrock).
Writes and reviews Swift FormatStyle code, replacing legacy Formatter subclasses and C-style String(format:) with modern .formatted() APIs. Use when formatting numbers, dates, durations, measurements, lists, names, byte counts, or URLs.
three.js lighting: AmbientLight, HemisphereLight, DirectionalLight, PointLight, SpotLight, RectAreaLight, LightProbe, IESSpotLight, ProjectorLight, shadow subtypes, and addon helpers such as RectAreaLightUniformsLib, RectAreaLightTexturesLib, LightProbeGenerator, TiledLighting. Use when configuring direct/indirect light, shadows, probes, or area lights; for IES file loading use threejs-loaders; for node-based light graphs use threejs-node-tsl; for debug helpers use threejs-helpers.
Generate whiteboard animation videos from images. Convert any color image into an animation with line drawing and coloring stages, featuring a hand overlay, and output an H.264 MP4 video. Supports single-image and batch modes. Trigger when the user says “turn an image into a whiteboard animation,” “whiteboard animation,” or “batch whiteboard animation”
Identify content gaps between your site and competitors. Use when the user says "content gaps", "what am I missing", "competitor content", "content opportunities", "topics I should cover", "content gap analysis", or asks about finding topics and keywords their site doesn't cover but competitors do
Research domain WHOIS data and check marketplace listings. Use when the user says "domain lookup", "check domain", "WHOIS", "domain availability", "buy domain", "domain research", "who owns this domain", "domain marketplace", or asks about researching or acquiring a domain name.
Create email drip campaigns, nurture sequences, and automated email flows. Includes templates for welcome series, abandoned cart, re-engagement, product launch, and onboarding sequences. Trigger phrases: "email sequence", "drip campaign", "nurture sequence", "email flow", "welcome series", "abandoned cart emails", "onboarding emails", "email automation", "product launch emails", "re-engagement campaign", "send email", "send sequence"
Use when working in any FaasJS repo and no narrower FaasJS skill is already selected, or when a task spans project conventions, validation gates, security boundaries, and multiple FaasJS subsystems. For focused work, also load the relevant FaasJS skill: faasjs-project-workflow, faasjs-react-ant-design, faasjs-api-jobs, faasjs-pg, faasjs-plugins-runtime, faasjs-utils-data, or faasjs-specs.
Write structured product requirements documents (PRDs) with problem statements, user stories, requirements, and success metrics. Use when speccing a new feature, writing a PRD, defining acceptance criteria, prioritizing requirements, or documenting product decisions.
Use truffler to find similar or pre-existing JavaScript/TypeScript symbols before implementing new code, especially helpers, utilities, parsers, formatters, scanners, fuzzy matchers, and other reusable functions. Agents should use this skill whenever they are about to add or refactor functionality in a JS/TS repository and need to avoid duplicating existing code, even if the user does not explicitly mention deduplication.
Migrate workloads from Heroku to AWS. Triggers on: migrate from Heroku, Heroku to AWS, move off Heroku, migrate Heroku Postgres to RDS, migrate Heroku Redis to ElastiCache, migrate Heroku Kafka to MSK, migrate dynos to Elastic Beanstalk, migrate dynos to Fargate, migrate Heroku Private Space, Heroku to ECS, leave Heroku, what-if workshop, compare migration scenarios, workshop mode. Runs a 6-phase process: discover Heroku resources live via the authenticated Heroku CLI (read-only, consent-gated) and/or from Terraform, Procfile/app.json, and billing exports; Terraform is optional. Then clarify, design, estimate costs, generate artifacts, and collect feedback. Clarify must finish before Design, Estimate, or Generate. An optional post-Estimate what-if workshop reprices region/HA/compute/Graviton scenarios. Do not use for: GCP migrations (see gcp-to-aws), Azure migrations (see azure-to-aws), AWS-to-Heroku reverse migration, general AWS architecture advice without migration intent, or Heroku-to-Heroku refactoring.
Huawei Ascend NPU natural language management skill, supporting both local direct connection and SSH remote modes. Provides comprehensive npu-smi command capabilities including device queries, configuration management, firmware upgrade, vNPU virtualization, certificate management, and compute power testing (FLOPS). Enables remote management and monitoring of Ascend NPU devices with real-time metrics tracking. Use this skill when the user wants to: (1) query NPU device status and health, (2) monitor temperature, power, memory/HBM utilization, (3) configure ECC settings and fan modes, (4) perform firmware upgrades, (5) manage vNPU virtualization, (6) run compute power tests, (7) check certificate information. Trigger: user mentionsnpu', 'ascend', 'NPU', 'Ascend', 'temperature', 'power', 'HBM', 'firmware', 'upgrade', 'vNPU', 'virtualization', 'certificate', 'FLOPS', 'compute', 'health', 'memory', 'utilization', 'ECC', 'fan', '昇腾', '昇腾卡', '昇腾状态', '显存', '算力', '设备查询', 'NPU监控'
AWS Startups reference content — Activate FAQs, credits guide, programs, partner offers, sample architectures, and hundreds of learning articles covering generative AI, cloud architecture, cost optimization, security, fundraising, go-to-market, and real-world startup case studies. Use when the user asks factual questions about AWS Activate (eligibility, credits, programs, providers), wants a sample architecture or solution guide, or needs an AWS-curated learning article on a specific startup topic. For copy-paste AI prompts (RAG chatbot, MVP scaffold, security baseline, GPU quota, etc.), see the prompt-library-for-startups skill. Do not use for: account-specific lookups (credits balance, Activate membership status, application status), real-time event listings beyond the events stub, or content not present in the bundled `references/` tree.
Transcribe meeting or call recordings, archive them under the project's arch/ folder, and brief you back as a spoken audio link instead of a wall of text. Use this whenever you point at audio or video recordings and want them transcribed, summarised, "read", or turned into a meeting report, and whenever you ask for a briefing, recap, or rundown of a call. Also use it for the audio-reply mode on its own ("send it as audio", "give me a link", "voice mode", "audio only", "1.5 velocity", "just talk to me"), where every answer is delivered as a presigned S3 audio link rather than text. Handles ElevenLabs Scribe v2 diarised transcription, the arch/ archive convention, ElevenLabs TTS at arbitrary playback speed, per-project AWS credential resolution, presigned private links, and deleting each clip once you have replied. Also owns the Meeting Capture browser extension (Meet, Zoom web and Teams web calls auto-record with no click into a private S3 inbox; video only from a manual start) and the ingest flow that pulls those recordings in, so "I just had a call", "process my meetings", "check the meeting inbox", "any new recordings" and "set up meeting recording" are this skill too, and any mention of a call starts by checking that inbox. Trigger it even when the words "transcribe" or "skill" never appear — "read my meeting", "what did we decide on the call", "brief me", "file this call" and "send that as audio" are all this skill.
Check and update installed Claude Code skills from multiple sources (Claude plugins and npx skills). Scans for available updates, supports batch or individual updates with intelligent local change merging, and recommends popular skills from skillsmp.com and skills.sh marketplaces. Use when users want to update skills, check for new versions, discover trending skills, or manage their skill collection.
Use when the user asks for overall progress, the status of all specifications, percentage completed, remaining work, blockers, or next work in the Specsfy repository, or when an automatic transition requests the final projection or routing based on the observed state. Produces a read-only overview of specs, gates, tasks, and checklists; do not use it to change the specification or implement tasks.
Scan systems and dependencies for CVEs and security vulnerabilities. Use tools like Nessus, OpenVAS, and Qualys to identify and prioritize vulnerabilities. Use when performing security assessments, compliance scanning, or vulnerability management.
Vulnerability and security scan (defensive, your own repo): dependency CVEs plus risky code patterns (secrets, injection, weak authz), severity x reachability triaged and remediated without suppressing. Complements the built-in /security-review. Triggers on "absolute audit", "security audit", "are we vulnerable", "scan for CVEs", "check for secrets/injection", "harden this".
An intelligent PPT generation tool provided by Baidu. It intelligently generates PPTs based on topics or questions provided by users. Users can choose PPT themes and templates or customize their own templates. It also accepts image or resource files (such as pdf, word, txt, etc.). The download address for the final generated PPT file is provided
Mandatory review gate for any mesh or asset created or edited in Blender. Detects z-fighting, floating/detached parts, inverted or inconsistent normals, non-manifold/open geometry, degenerate faces, duplicate verts, n-gons, unapplied scale, UV problems, bad skin weights, material/texture errors, and renders multi-angle review sheets. Use before calling any modeling, export or delivery task done.
Create a visual identity brief for a brand — logo direction, color palette, typography, imagery style, and design system foundations. Use when the user says “visual identity,” “brand identity,” “logo brief,” “logo direction,” “design brief,” “brand design,” “color palette for my brand,” “typography for my brand,” “visual language,” “design system,” “brand look and feel,” “what should my brand look like,” or is briefing a designer or design agency. Also use when the user has a brand strategy and wants to translate it into visual design direction.
Autonomously optimize code for performance using CodSpeed benchmarks, flamegraph analysis, and iterative improvement. Use this skill whenever the user wants to make code faster, reduce CPU usage, optimize memory, improve throughput, find performance bottlenecks, or asks to 'optimize', 'speed up', 'make faster', 'reduce latency', 'improve performance', or points at a CodSpeed benchmark result wanting improvements. Also trigger when the user mentions a slow function, a regression, or wants to understand where time is spent in their code
Builds custom pages and API routes inside an EventCatalog project. Creates Astro pages and TypeScript endpoints in the catalog's pages/ folder using the stable @catalog/layouts and @catalog/utils toolkit, wires them into the navigation, and sets up editor support. Use when user asks to "add a custom page to my catalog", "build a team page", "add an API endpoint to EventCatalog", "create a custom homepage", "add a custom route", "query catalog data from my own page", or "extend EventCatalog with my own pages"
Reference for how deprecation of public Remotion APIs is represented in TypeScript source and documentation. Use when adding, reviewing, or discussing a deprecation of a function, component, hook, type, prop, option, or other public API that remains available.
Conducts comprehensive frontend design reviews covering UI/UX design quality, design system validation, accessibility compliance, responsive design patterns, component library architecture, and visual design consistency. Evaluates design specifications, Figma/Sketch files, design tokens, interaction patterns, and user experience flows. Identifies usability issues, accessibility violations, design system deviations, and provides actionable recommendations for improvement. Produces detailed design review reports with severity-rated findings, visual examples, and implementation guidelines. Use when reviewing frontend designs, validating design systems, ensuring accessibility compliance, evaluating component libraries, assessing responsive designs, or when users mention design review, UI/UX review, Figma review, design system validation, accessibility audit, or frontend design quality.
Expert blueprint for procedural content generation (dungeons, terrain, loot, levels) using FastNoiseLite, random walks, BSP trees, Wave Function Collapse, and seeded randomization. Use when creating roguelikes, sandbox games, or dynamic content. Keywords: procedural, generation, FastNoiseLite, Perlin noise, BSP, drunkard walk, Wave Function Collapse, seeding
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.