Skills
101,174 packaged capabilities and playbooks for agents. Install any of them with one command.
All
Obtain translated versions of patent titles and abstracts through the Eureka patent data platform. This skill is triggered when users request patent abstract translation, patent title translation, translated patent abstracts, patent content in other languages, patent abstracts in Chinese/English/Japanese, or need to look up the abstract or title of a specific patent by patent ID or publication number, including Eureka patent abstracts, patent abstract translation, patent title translation, Eureka patent, patent translation, and abstract lookup. It should also be triggered when users mention Eureka or patent abstract lookup, even if they do not explicitly say “translate.”
Obtain translated patent claims through the Eureka patent data platform. This skill is triggered when users ask about patent claims, claim translation, viewing claims in a specific language (Chinese, English, or Japanese), querying patent rights by patent ID or publication number, analyzing claim text, Eureka claims, claim translation, patent claim translation, Eureka patent, or patent translation. Even if the user does not explicitly mention “translating patent claims,” trigger this skill whenever their request involves obtaining patent claim content in a specific language.
Production pipeline for mathematical and technical animations using Manim Community Edition. Creates 3Blue1Brown-style explainer videos, algorithm visualizations, equation derivations, architecture diagrams, and data stories. Use when users request: animated explanations, math animations, concept visualizations, algorithm walkthroughs, technical explainers, 3Blue1Brown style videos, or any programmatic animation with geometric/mathematical content.
Compatibility alias for `marketing-automation`. Use when an existing prompt, setup surface, workflow, or legacy catalog entry explicitly references `marketing-skills-collection` but the real need is still broad product or growth marketing routing across CRO, copywriting, SEO, lifecycle messaging, analytics, pricing, launches, retention, and experiments. Prefer `marketing-automation` for canonical general use. Triggers on: marketing-skills-collection, legacy marketing skill name, old marketing prompt pack, migrate marketing alias.
Define product metrics with a North Star, input/output tree, and counter-metrics. Use when asked to define metrics, set up measurement, choose KPIs, pick a north star metric, or build a metrics framework. Prevents vanity metrics and gaming.
Expert knowledge for Microsoft Foundry Local (aka Azure AI Foundry Local) development, including best practices, decision-making, configuration, integrations and coding patterns. Use when compiling HF models with Olive, using CLI/SDK, embeddings/chat, audio, tool calls, or REST apps, and for other Microsoft Foundry Local-related development tasks. Not for Azure Local (use azure-local), Microsoft Foundry (use microsoft-foundry), or Microsoft Foundry Classic (use microsoft-foundry-classic).
Expert guidance for writing safe, reversible Active Record migrations in Rails applications. Use when creating a migration, adding a column, removing a column, changing schema, modifying a table, creating a table, adding an index, adding a foreign key, renaming a column, changing column type, database migration, schema change, rolling back, migration error, data migration, multi-database migration, or any database structure change.
Create or update content for the agegr/mindmap-ppt static presentation project from a prose draft, article, speech, report, or notes. Use when Codex needs to turn a written document into the project's project/source.js Markdown mind-map data, choose which nodes need illustrations, generate or request GPT Image 2 illustrations matching the project's restrained presentation style, place assets under project/, and validate the result with npm run check. Operates only within the current working directory
Enforces designed interaction feedback instead of the framework default — every committing interaction acknowledged in the same frame, motion that decorates state but never IS the state (the end state is identical with animations off), a named catalog of moments each declaring its trigger, duration role, haptic slot and reduced-motion fallback at design time, haptics as a HapticTheme event-to-intensity map fired exactly once on the commit frame (never per animation frame, never per coalesced input, never heavyImpact for an error) behind one central toggle, every animation interruptible so a tap resolves it to its end state, a bounded celebration that plays once and never loops or blocks input, an explicit stop condition on every repeating animation (off-route, backgrounded, reduced motion), and feedback on more than one channel so haptics and sound survive reduced motion. Use when adding or tuning an animation, a success or error state, a haptic, a celebration, or a screen transition.
Plans and generates the images and video clips an animated website needs with AI image and video models, without wasting money. Covers proposing the concept and asset list with exact prompts and costs before spending, keeping one style across every asset, start and end frames for clips that chain or loop, choosing a model by what it can do, calibrating cost, staying under rate limits, recovering failed jobs, fixing loops and outpaints, and logging every prompt so the project can be rebuilt. Use whenever a site needs generated heroes, characters, product shots, textures, background loops or camera-move clips, or when someone says "use Higgsfield", "use Runway", "use Kling", "use Veo", "generate the assets" or "animate this image"
Convert an HTML page into a single continuous-page PDF (one tall page, no pagination breaks), preserving desktop layout, backgrounds, and selectable text. Use when the user asks to turn an HTML file/report/proposal into a “single-page PDF,” “long PDF,” “不分页 PDF,” “单页 PDF,” “长图式 PDF,” or complains that an HTML-to-PDF export breaks into pages or cuts content. Supports optional string redaction with leak verification.
Assess a workload's operational excellence posture by analyzing CI/CD pipelines, observability instrumentation, deployment configs, and incident management patterns in the codebase to produce evidence-backed findings.
Use the public `orca` CLI to operate Orca-managed worktrees, folder contexts, terminals, repos, automations, artifacts, worktree comments, and the browser embedded inside the Orca app. Use when the user says "$orca-cli", "use orca cli", "Orca worktree", "child worktree", "cardStatus", "spawn codex/claude in a worktree", "read/wait/send Orca terminal", "terminal send", "full handoff", "handover", "give this to another agent", "another worktree", "Orca browser", "orca artifacts", "share HTML/Markdown", "public artifact link", or "control the browser inside Orca". Prefer this over raw `git worktree`, ad hoc PTYs, Playwright, or Computer Use when the task touches Orca-managed state. Use Computer Use for browser windows, webviews, or desktop UI outside Orca's embedded browser.
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
When the user wants to optimize pharmacy supply chain operations, manage medication distribution, ensure pharmaceutical compliance, or handle controlled substances. Also use when the user mentions “pharmacy logistics,” “drug distribution,” “controlled substances,” “340B program,” “formulary management,” “medication safety,” “specialty pharmacy,” “drug shortages,” “DEA compliance,” “pharmaceutical traceability,” or “DSCSA compliance.” For hospital materials management, see hospital-logistics. For clinical trial drugs, see clinical-trial-logistics.
This skill should be used when the user asks to “build my game”, “run my Phaser game”, “start dev server”, “deploy my game”, “fix build errors”, “configure Vite for Phaser”, “game won't build”, “TypeScript errors in Phaser”, “publish to itch.io”, or needs to compile, run, troubleshoot, or deploy a Phaser 4 project.
Pick the right library for a given frontend task from a curated, opinionated list — numbers, OTP inputs, charts, command menus, virtualization, drag and drop, toasts, state, styling, and more. Only runs when explicitly invoked; it does not trigger on its own.
Generate images using the Pollinations.ai API. Supports models such as flux, zimage, imagen-4, klein, klein-large, gptimage (free), and seedream, kontext, nanobanana, gptimage-large (paid). Use when the user asks to generate, create, or draw images from text prompts
Extract, analyze, and summarize simulation output data — pull spatial fields at specific timesteps, compute time-series trends and detect steady state, extract line profiles through the domain, generate statistical summaries and distributions, calculate derived quantities (gradients, fluxes, volume fractions, interface area), compare results against analytical solutions or experimental data, and produce automated analysis reports. Use when interpreting finished simulation results, checking mass or energy conservation, comparing two runs or meshes, extracting interface profiles from phase-field output, or preparing publication-quality analysis, even if the user only says "what do my results look like" or "did my simulation reach steady state."
Build products customers actually want. Apply Marty Cagan's Silicon Valley-tested framework to discover solutions that are valuable, usable, feasible, and viable. Use when: **Developing a new product** and validating what to build; **Prioritizing features** to ensure you're solving real problems; **Making pivot decisions** when the current direction isn't working; **Aligning the team** on which problems to solve; **Reducing risk** before committing development resources
Sets up new projects or improves existing projects with development best practices, tooling, documentation, and workflow automation. Use when user wants to start a new project, improve project structure, add development tooling, or establish professional workflows
Ququ’s perspective: a mindset centered on a woman’s value and power (Le Chuanqu). A pioneer of emotional commercialization and advocate of “relationships = exchange”; she calls herself the “McKinsey of emotions.” Four core mental models: value exchange, male/female competition, asset-based thinking, and risk-averse rationalism. Triggers: “Ququ perspective,” “in Ququ’s style,” “emotional commercialization,” “how to view this relationship,” “should I pursue this for money?” Suitable for analyzing the interests at play in relationships, identifying value mismatches in romantic relationships, and taking a non-moralizing view of “love as exchange.” Limitation: not suitable for questions seeking purely emotional connection; the tax evasion incident shows significant blind spots in her financial judgment. Research sources: 12 media reports (Jiemian, 36Kr, Tencent, The Paper, Sina); research current through 2026-04-13.
Use when uploading locally trained model weights (YOLO, RF-DETR, YOLO-NAS, PaliGemma, Florence-2) to Roboflow—covering the client-side Python SDK upload flow, safe API key handling, per-family packaging requirements, and upload verification.
Run the Build phase of an SDD/AgentSpec workflow from the Brainstorm, Define, and Design Markdown files and user interactions. Use when the user wants to implement an already specified feature: read the three artifacts, extract and order the File Manifest, recommend and confirm the execution mode, change only the planned code, verify incrementally, handle drift and LLM prompts, apply the migration from the manifest to the database (with project name and ref confirmation and read-back proof), run the blocking Verify Gate from Define, and generate BUILD_REPORT_{FEATURE}.md with evidence. Requires write access to the project/code and must finish with the SDD workflow completed and the BUILD_REPORT validated.
Run the Define phase of an SDD/AgentSpec flow based on the Markdown file generated by Brainstorm and clarification interactions with the user. Extract and structure the problem, users, goals, metrics, scope, constraints, and technical context; write acceptance tests in EARS, resolve ambiguities, calculate a Clarity Score, and define an objective Verify Gate. Use after SDD Brainstorm by RDD to generate a DEFINE_{FEATURE_NAME}.md ready for the next gate.
Produce the Design phase of an SDD/AgentSpec flow from the Brainstorm Markdown file, the DEFINE file, and technical clarification interactions with the user. Turn validated requirements into architecture, components, inline ADRs, file manifest, code standards, data flow, integrations, testing strategy, error handling, configuration, security, and observability. Use after SDD Define by RDD, especially when the user provides BRAINSTORM_*.md and DEFINE_*.md and wants to generate a DESIGN_*.md ready for SDD Build by RDD.
START HERE after installing Brad Frost's skills — run this once to get everything set up. Finds which of the skills you installed, runs the setup each one needs (the limits interview), and tells you how to use the ones that need no setup. Use when the user says "setup brad frost skills", runs /setup-brad-frost-skills, has just installed this collection, or asks how to get started with these skills.
Render video, poll render status, and upload local source files via the Shotstack API. Use when generating clips, building automated video pipelines, uploading footage/audio/images to use in an Edit, or orchestrating cloud video renders from a script, agent, or CI workflow. NOT for: real-time streaming or live broadcasting.
Investigate and reduce SigNoz telemetry ingestion cost and metric cardinality across metrics, logs, and traces. Find what drives SigNoz spend (via the Cost Meter), which metrics have runaway or unbounded label cardinality, and safe, dashboard-, alert-, and Infra-page-aware ways to cut volume. Make sure to use this skill whenever the user asks “why is my SigNoz bill so high,” “what's driving my ingestion cost,” “reduce telemetry volume,” “which metrics cost the most,” “cardinality health check,” or “what can I safely drop,” or otherwise asks about telemetry spend, ingestion volume, or metric cardinality, even if they don't say “cost” or “optimize” explicitly. Do not use it for LLM or AI-agent token spend; that is a trace query in signoz-generating-queries.
Integrate Sinch In-App Voice and Video SDK for real-time calling in Android, iOS, or JavaScript apps. Use when the user mentions In-App Calling, VoIP integration, WebRTC with Sinch, app-to-phone calling, video calling, or building voice/video features in a mobile or web app.
Performs quality control on single-cell RNA-seq data (.h5ad or .h5 files) using scverse best practices with MAD-based filtering and comprehensive visualizations. Use when users request QC analysis, filtering low-quality cells, assessing data quality, or following scverse/scanpy best practices for single-cell analysis.
This skill should be used when the user asks to “pentest SSH services,” “enumerate SSH configurations,” “brute force SSH credentials,” “exploit SSH vulnerabilities,” “perform SSH tunneling,” or “audit SSH security.” It provides comprehensive SSH penetration testing methodologies and techniques.
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.