Skills
100,696 packaged capabilities and playbooks for agents. Install any of them with one command.
All
CUDA profiling skill for NVIDIA GPU performance analysis. Use when profiling kernels with Nsight Systems or Nsight Compute, interpreting roofline models, diagnosing memory-bound vs compute-bound kernels, or annotating code with NVTX ranges. Activates on queries about Nsight, NCU, ncu CLI, GPU roofline, occupancy metrics, or CUDA profiling workflow
Official Dailybot agent skill pack — report progress, check messages, send emails, announce agent status, complete check-ins, give kudos (to users or teams), resolve teams, run the full forms lifecycle (list, submit, update, transition between workflow states), author check-ins and forms from scratch (create/configure questions, workflow states, permissions, reminders, scheduling, AI settings, sharing), send/edit chat messages on the team's Slack/Teams/Discord/Google Chat (including report-style threads, sending as a user's identity, and interactive buttons with approval flows, workflow triggers, modals, and callbacks), open (or reuse) a Slack group DM with the bot and post a report to it, ask the Dailybot AI a question headlessly, browse/read/trigger the workspace (`me` / `org` / `user get`, kudos browsing, workflows), manage organization Labels (`dailybot label` CRUD + assign/batch on forms, check-ins, workflows) and private Featured stars, manage Plan (Beta — boards, backlog, sprint/kanban columns, owners, attachments, bulk with dry run, project updates, milestones, goals, open-org structure for non-guest members, agent-attributed work on a handed task with `task brief` — `dailybot plan tasks` for the workspace and `dailybot plan task` for one task), and manage per-repo API keys through `.dailybot/env.json` (pack baseline `dailybot-cli >= 3.9.0`; Plan needs `>= 3.25.0`). Routes to the right sub-skill based on intent. Use when the developer mentions Dailybot or wants to interact with their team
Device tree skill for Linux hardware description. Use when writing DTS/DTSI, bindings, overlays, phandles, or debugging OF platform probe failures. Activates on queries about device tree, DTS syntax, phandle, devicetree bindings, DT overlay, or OF graph.
Methodology for iteratively improving agent-facing instructions (skills / slash commands / CLAUDE.md / code-gen prompts) via bias-free executor + two-sided evaluation (self-report + instruction-side metrics). Meta-skill, invoke ONLY when the user explicitly asks for an "empirical" eval of a prompt or skill, or for the Iter-0 description / body consistency check. Do NOT auto-invoke after every skill edit; this loop is operator-triggered by name.
/c-level-agents:execute [decision] — Generate a 90-day execution plan with weekly milestones, DRIs, and check-in cadence from an approved decision. Use when a logged decision needs to become an operating plan — e.g. turning an approved market-entry call into weekly milestones with DRIs.
Create distinctive, production-grade frontend interfaces with high design quality. Use this skill when the user asks to build web components, pages, artifacts, posters, or applications (examples include websites, landing pages, dashboards, React components, HTML/CSS layouts, or when styling/beautifying any web UI). Generates creative, polished code and UI design that avoids generic AI aesthetics
Expert patterns for multi-platform exports including export templates (Windows/Linux/macOS/Android/iOS/Web), command-line exports (headless mode), platform-specific settings (codesign, notarization, Android SDK), feature flags (OS.has_feature), CI/CD pipelines (GitHub Actions), and build optimization (size reduction, debug stripping). Use for release preparation or automated deployment. Trigger keywords: export_preset, export_template, headless_export, platform_specific, feature_flag, CI_CD, build_optimization, codesign, Android_SDK.
When the user wants help with Google Ads budget pacing, monthly budget tracking, campaign budget allocation, shared budgets, budget forecasting, underspending or overspending campaigns, or how to distribute spend across campaigns to hit targets. Triggers on 'budget pacing', 'campaign budget', 'underspending', 'overspending', 'monthly budget target', 'shared budget', 'budget allocation', 'budget optimization', 'hit budget target', 'budget forecast', 'limited by budget', or 'how to allocate budget across campaigns'. For bid strategies and how they interact with budget see google-ads-bidding.
Migrates a project from Metabase static embedding to guest embeds (web components via embed.js). Use when the user wants to migrate/convert/switch/upgrade from static embedding to guest embeds, from signed embed iframes to web components, or replace /embed/ iframes with metabase-dashboard/metabase-question components.
NocoBase 2 only; never use in a NocoBase 3 project. Create and manage NocoBase data models through the available data-modeling surface. Use when users want to inspect or change collections, fields, relations, or view-backed schemas in a NocoBase app
Parameter-efficient fine-tuning for LLMs using LoRA, QLoRA, and 25+ methods. Use when fine-tuning large models (7B-70B) with limited GPU memory, when you need to train <1% of parameters with minimal accuracy loss, or for multi-adapter serving. HuggingFace's official library integrated with transformers ecosystem.
This skill should be used when the user asks to "research", "fact-check", "check the history", "is this accurate", "research notes", "sources", "historical accuracy", "technical accuracy", "how would this really work", "verify a detail", "interview an expert", "plan a site visit", "expert review", or needs to investigate and record the real-world facts a story relies on and the chapters that use them.
When you want to draft, update, convert, or export a slide deck for a React/Next.js slide system (${SLIDE_DECK_REPO:-$HOME/code/your-slide-deck-site}/src/app/slides/). Writes TypeScript Slide[] arrays using your primitives (Eyebrow, Heading, Accent, Body, BulletList, Divider, TwoCol, GradientText), 12 cycling brand gradients, optional sections for "where am I" context, and speaker notes. Inspired by zarazhangrui/frontend-slides — "show, don't tell" for narrative (presents 3 angles, you pick) plus density modes (speaker-led vs reading-first). Four modes — new (draft from brief), update (modify existing, with overflow guards), ppt (convert legacy PPTX → React deck), export (Playwright snapshot existing React deck to standalone HTML, PDF, or Vercel URL — keeps brand). Triggers on "/slide-deck," "/slides new," "/slides export," "/slides update," "/slides ppt," "draft a deck," "deck for [topic]," "talk on [topic]," "keynote on [topic]," "internal deck for [audience]," "convert this pptx," "export this deck."
Install, update, and manage Sui CLI versions with suiup. Use this skill when the user needs to install Sui, update to a newer version, switch between network-specific versions, resolve “command not found” or version mismatch errors, install additional toolchain components (Walrus, MVR, Move Analyzer), or troubleshoot suiup commands. Also use when the user sees “client/server api version mismatch” warnings or asks about suiup install, update, switch, or show
Analyze CRISPR-Cas9 genetic screens — MAGeCK gene-level scores, sgRNA count QC, replicate correlation, hit prioritization, and pathway GSEA on screen output. Use for genome-wide essentiality screens, synthetic-lethality discovery, dropout vs positive-selection screen analysis, target identification, and resistance-screen interpretation. Includes screen-QC and statistical thresholds.
This skill enables visual inspection of websites running locally or remotely to identify and fix design issues. Triggers on requests like “review website design,” “check the UI,” “fix the layout,” or “find design problems.” Detects issues with responsive design, accessibility, visual consistency, and layout breakage, then fixes them in the source code
Build modern full-stack web applications with Next.js (App Router, Server Components, RSC, PPR, SSR, SSG, ISR), Turborepo (monorepo management, task pipelines, remote caching, parallel execution), and RemixIcon (3100+ SVG icons in outlined/filled styles). Use when creating React applications, implementing server-side rendering, setting up monorepos with multiple packages, optimizing build performance and caching strategies, adding icon libraries, managing shared dependencies, or working with TypeScript full-stack projects.
Continuously collects over 1,000 daily articles with 100,000+ reads from public WeChat accounts across the internet and recommends popular articles that reach 100,000+ reads. Use when users want popular WeChat articles across all fields, daily recommendations of articles with 100,000+ reads, or viral articles in a specific field
Use when you need to add or review Flyway database migrations in a Spring Boot application — Maven dependencies, db/migration scripts, spring.flyway.* configuration, baseline and validation, and alignment with JDBC or Spring Data JDBC. This should trigger for requests such as Add or review Flyway migrations in a Spring Boot project; Configure spring.flyway or db/migration layout; Add versioned Flyway SQL migrations for Spring Boot; Review Spring Boot database migration ordering; Fix repeatable Flyway migrations in a Spring project. Part of Plinth Toolkit
This skill should be used when the user asks to "make an audiobook", "narration script", "narrator", "ACX", "Findaway", "pronunciation guide", "how long is the audiobook", "adapt to a screenplay", "Fountain", "screenplay", "picture book", "spreads", "illustration notes", "art notes", "comic script", "comics script", "graphic novel", "panels", "interactive edition", "turn the book into Ink or Twine", "translate the book", "translation", "foreign edition", "glossary for translators", or wants to turn a story project into another form or language, or to plan a picture book. NOT for writing a new branching or choose-your-own-adventure story (use interactive-fiction), or writing rhyming picture-book text (use verse-craft).
Model Apidog test scenarios: query, create, update, delete, and run test-scenario resources; import endpoint, test-case, or other scenario steps; add scenario reference steps; and orchestrate complex HTTP, condition, loop, wait, script, database, pre/post-action, variable, assertion, extractor, and debugging flows
Author useful, low-noise log alerts on services in a PostHog project. Use when the user asks to set up alerts for their logs, suggest alerts they should add, or evaluate whether a service is worth monitoring. Covers service triage, baseline characterisation, threshold drafting, back-testing via simulate, and shipping with a notification destination.
Build 3D objects, props, and room-scale structures in Roblox Studio via MCP. Use when: user asks to create, build, or place a single physical object — furniture, animals, vehicles, gates, towers, decorations, street props, room interiors, or any individual tangible structure. Triggers on: "○○を作って", "○○を置いて", "build me a ___", "create a ___", "make a ___" in the context of Roblox Studio. Also use when user mentions CSG, Union, Subtract, Part placement, or 3D modeling in Roblox. If the user is in a Roblox project and asks to "make" or "build" something physical, this skill should trigger even without explicit mention of "3D" or "Roblox". Scope boundary: applies if the result can be grouped into a single `Model`. For full maps, arenas, lobbies, hubs, or multi-zone environments → use building-maps instead. Dispatch rule: When the user requests multiple related/variant objects (e.g., "5 types of swords", "3 chair styles"), dispatch ALL variants to a SINGLE agent. Do NOT spawn parallel agents. Consistency requires sequential building by one agent.
When the user wants to write, rewrite, or improve marketing copy for any page — including homepage, landing pages, pricing pages, feature pages, about pages, or product pages. Also use when the user says "write copy for", "improve this copy", "rewrite this page", "marketing copy", "headline help", or "CTA copy." For email copy, see email-sequence. For popup copy, see popup-cro.
Build, document, and maintain design systems with design tokens, component specifications, pattern libraries, naming conventions, and governance processes. Conduct system audits, define component hierarchies, and establish shared design languages.
Drupal 9-11 core API patterns from Selwyn Polit's book “Drupal at Your Fingertips”. In-depth references cover services and dependency injection, hooks, events, plugins, entities, Form API, routes and controllers, Twig, caching, AJAX, database queries, configuration, Paragraphs, and Drupal Test Traits; every other chapter (views, blocks, migrate, drush, taxonomy, and more) is linked online. Use when writing or reviewing custom Drupal module or theme code and a worked example or API refresher is needed for one of these subsystems.
Import or upload local HTML or project files into Figma, choose editable Design frames, runnable Code Layers or standalone Code (also known as Make), and repair imported previews. Use only when the user explicitly names editable Design layers, a runnable Code Layer, or a standalone Code/Make file, or supplies a Figma file key/link as the import destination. Generic code or code-component requests need output clarification before using this workflow
Audit a Gradle project against the official Gradle best practices, report findings, and propose code changes to bring the build into compliance. Use this skill whenever the user wants to check, audit, lint, review, or validate a Gradle build — and also when they want to apply, adopt, fix, or enforce best practices. Trigger on phrases like 'check my build', 'audit gradle', 'best practices review', 'any issues with my build?', 'gradle health check', 'lint my build files', 'is my gradle setup correct?', 'apply gradle best practices', 'fix my build to follow best practices', 'make my build follow best practices', 'modernize my build', or simply 'check best practices'. Also trigger when the user asks about Gradle build quality concerns such as dependency management, build performance, build structure, or task wiring.
Work through a live objection or competitive threat—what's really being said, the response that has worked before, and the proof points to use, grounded in your own win/loss history and customer quotes. Use when the user says "they said we're too expensive", "how do I respond to [objection]", "[competitor] is in the deal", "help me handle this pushback", or pastes an objection from an email or call.
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.