Skills
99,448 packaged capabilities and playbooks for agents. Install any of them with one command.
Development
Turn on Cache Components in a Next.js app and resolve the blocking routes it surfaces. Use when the user wants to enable, adopt, or migrate Cache Components, flip the `cacheComponents` flag, work through a flood of blocking-prerender / instant validation errors, run the `cache-components-instant-false` codemod, or decide between opting routes out with `export const instant = false` and fixing them in place.
Expert Next.js developer specializing in Next.js 14+, App Router, Server Components, and modern React patterns. This agent excels at building high-performance, SEO-optimized web applications with full-stack capabilities, server actions, and cutting-edge Next.js features.
Apply to any non-trivial work, not just bulk work: edits, migrations, analyses, checks. Build the tool that does it or proves it (codemod, script, generator, or a skill your subagents follow) instead of working by hand. The tool is the artifact a reviewer can rerun
Apply to multi-step work (sweeps, migrations, runs of similar edits) and to how you stack commits and PRs. Break work into small units that each end in a verifiable state, check each before the next, and order delivery so the sequence proves itself to a reviewer.
Use when defining, validating, serializing, or configuring data with Pydantic v2 in Python — BaseModel, Field constraints, field/model validators, model_dump serialization, pydantic-settings, TypeAdapter, enums, Literal, and discriminated unions — or when fixing code that still uses v1-era idioms (class Config, .dict()/.json(), @validator). Produces correct, idiomatic, current Pydantic v2 code. Keywords: pydantic, BaseModel, ConfigDict, model_validate, validator, settings.
Help users write correct R code for async, parallel, and distributed computing using mirai. Use when users need to run R code asynchronously or in parallel, write mirai code with correct dependency passing, set up parallel workers, convert from future or parallel, use mirai_map, integrate with Shiny or promises, or configure cluster/HPC computing.
Build responsive HTML emails with React Email components. Covers email structure (Html, Head, Body, Container), content components (Text, Heading, Button, Link, Img), layout (Section, Row, Column), styling with inline CSS and Tailwind, custom fonts, preview text, and rendering to HTML. Use when creating transactional emails, marketing templates, or email design systems. Use for email rendering, preview, Tailwind email styling, and provider integration with Resend, Nodemailer, or SendGrid.
Reference documentation patterns for API and symbol documentation. Use when writing reference docs, API docs, parameter tables, or technical specifications. Triggers on reference docs, API reference, function reference, parameters table, symbol documentation.
Release remotion-bits to GitHub, Cloudflare, and npm. Use when bumping the package version, updating CHANGELOG.md, building the registry, creating the release commit, pushing master, opening a prefilled GitHub release form, deploying docs, and publishing to npm.
Discover, evaluate, score, and compare Rust crates for adoption — search crates.io, fetch metadata from 4 sources (crates.io API, docs.rs, GitHub API, RustSec advisory DB), apply a weighted 0-100 scoring model across adoption/maintenance/documentation/maturity/community/license, flag red concerns (unmaintained, advisories, no docs, single-maintainer), and recommend the best fit. Use when users ask "which crate should I use for X", "is this crate maintained/safe/popular", "compare these 3 crates", or need to pick a dependency before adoption; hand post-adoption governance (cargo-deny, license policy, advisory response) to rust-dependencies, semver and breaking-change classification to rust-semver, and manifest mechanics to rust-cargo-build.
Design SDKs that developers love to use—APIs that feel native, error messages that guide, and experiences that reduce friction. This skill covers creating SDKs that drive adoption through exceptional developer experience rather than aggressive marketing. Trigger phrases: "SDK design", "developer experience", "API design", "SDK DX", "error messages", "type safety", "IDE integration", "SDK versioning", "migration guides", "client library design", "making SDKs feel native", "SDK best practices"
shadcn-vue component integration for Inertia Rails Vue 3 (NOT Nuxt): forms, dialogs, tables, toasts, dark mode, and more. Use when building UI with shadcn-vue components in an Inertia + Vue app or adapting shadcn-vue examples from Nuxt. Wire shadcn-vue inputs to Inertia Form via name attribute and #default scoped slot. Flash toasts require Rails flash_keys initializer config.
Use for direct work with GitHub: inspecting remote source or repository state, searching hosted code, invoking GitHub CLI (`gh`) commands such as `gh search` and `gh api`, or performing another operation against GitHub. Don’t use for ordinary local Git work unless the user explicitly requests `gh`. Don’t use for tasks limited to viewing or interacting with GitHub in a browser.
Use when the user is working on a Spree Commerce project — anything involving Spree models, controllers, customization patterns (decorators, subscribers, services), Spree conventions like prefixed IDs / Spree::Model namespacing / Spree.user_class / Spree::Current, or asking how Spree works. Activates broadly for any task in a Spree backend.
Starts working on a new feature branch using git-flow. This skill should be used when the user asks to "start a feature", "create feature branch", "begin new feature", "git flow feature start", or wants to start a new feature. Accepts either a branch name or a natural-language description.
Begins a hotfix for a production issue using git-flow. This skill should be used when the user asks to "start a hotfix", "create hotfix branch", "fix a critical bug", "git flow hotfix start", or wants to begin a hotfix. Accepts either an explicit version or a natural-language description of the fix.
Build self-contained static HTML artifacts opened in a browser: interactive diagrams, dashboards, infographics. Pure HTML5+CSS3+inline SVG, zero toolchain. Triggers on: "interactive HTML", "open in browser", "HTML artifact", "visual dashboard", "HTML infographic". NOT for PNG/SVG output, use concept-to-image. NOT for throwaway prototypes that answer a state-model or layout question, use prototype
Use when integrating Stigg's drop-in UI components — paywall / pricing table, customer portal, checkout, and the credit widgets (balance, utilization, usage chart, grants table, auto-recharge status, auto-recharge configuration). Triggers include "Stigg paywall", "pricing table", "customer portal", "Stigg checkout", "credits widget", "credit balance widget", "Paywall component", "CustomerPortal component", "render Stigg widget", "widget designer", "client-side security", "stigg widgets storybook". Skip for headless gating logic — use stigg-entitlements.
Root-cause fix discipline for a debugging session already underway. Use when about to propose or apply a fix for a bug or test failure, when tempted to patch a symptom (add a null check, wrap in try-catch, bump a timeout, add a retry), and when a previous fix didn't work. /diagnosing-bugs builds the repro; this governs the fix.
Backend work on a Taruvi app: provisioning datatables, Cerbos policies, roles, users, buckets, secrets, analytics queries, or raw SQL via the Taruvi MCP server; and authoring Python function bodies that run in the Taruvi function runtime (`def main(params, user_data, sdk_client)`) for multi-resource cascades, event/cron handlers, public webhooks, and external API calls. Triggers: "create a datatable", "Frictionless schema", "Cerbos policy", "serverless function", "scheduled job", "analytics query", "sdk_client", `manage_function`, `execute_raw_sql`. Skip for Refine frontend work — use `taruvi-refine-providers` instead.
Guide for incrementally migrating JavaScript codebases to TypeScript. Covers tsconfig configuration, file-by-file migration, typing strategies for legacy code, handling `any`, and common pitfalls. Use when the user wants to convert JS to TS, add types to existing code, configure TypeScript in a JS project, or improve type safety.
Write, validate, render, and convert UIKitML for pmndrs/uikit interfaces. Use when working with .uikitml files, authoring spatial 3D UI or UI targeting VR/AR, using Three.js, @react-three/fiber, or IWSDK, choosing default/Lucide/Horizon components, fixing UIKitML validation errors, or using the @drawcall/uikitml CLI.
Fine-tune LLMs with Unsloth using GRPO or SFT. Supports FP8, vision models, mobile deployment, Docker, packing, GGUF export. Use when: train with GRPO, fine-tune, reward functions, SFT training, FP8 training, vision fine-tuning, phone deployment, docker training, packing, export to GGUF.
Developer utilities and tools — CLI generation, skill scaffolding, agent delegation, system upgrades, evals, documents, parsing, audio editing, Fabric patterns, Cloudflare infrastructure, browser automation, meta-prompting, and aphorisms. USE WHEN create CLI, build CLI, command-line tool, wrap API, add command, upgrade tier, TypeScript CLI, create skill, new skill, scaffold skill, validate skill, update skill, fix skill structure, canonicalize skill, parallel execution, agent teams, delegate, workstreams, swarm, upgrade, improve system, system upgrade, check Anthropic, algorithm upgrade, mine reflections, find sources, research upgrade, PAI upgrade, eval, evaluate, test agent, benchmark, verify behavior, regression test, capability test, run eval, compare models, compare prompts, create judge, view results, document, process file, create document, convert format, extract text, PDF, DOCX, XLSX, PPTX, Word, Excel, spreadsheet, PowerPoint, presentation, slides, consulting report, large PDF, merge PDF, fill form, tracked changes, redlining, parse, extract, URL, transcript, entities, JSON, batch, YouTube, article, newsletter, Twitter, browser extension, collision detection, detect content type, extract article, extract newsletter, extract YouTube, extract PDF, parse content, clean audio, edit audio, remove filler words, clean podcast, remove ums, cut dead air, polish audio, transcribe, analyze audio, audio pipeline, fabric, fabric pattern, run fabric, update patterns, sync fabric, summarize, threat model pattern, Cloudflare, worker, deploy, Pages, MCP server, wrangler, DNS, KV, R2, D1, Vectorize, browser, screenshot, debug web, verify UI, troubleshoot frontend, automate browser, browse website, review stories, run stories, web automation, meta-prompting, template generation, prompt optimization, programmatic prompt, render template, validate template, prompt engineering, aphorism, quote, saying, find quote, research thinker, newsletter quotes, add aphorism, search aphorisms.
Guide the agent on creating visually distinctive, polished Vaadin 25 interfaces that go beyond default theme styling. This skill should be used when the user asks to "make it look good", "improve the design", "style the view", "make it visually appealing", "add polish", "design a UI", "create a beautiful interface", or when building a new view where visual quality matters. Also trigger when the user wants to add animations, visual effects, or build polished component compositions in a Vaadin application.
Configure input and output validation with .input() and .output() using Zod, Yup, Superstruct, ArkType, Valibot, Effect, or custom validator functions. Chain multiple .input() calls to merge object schemas. Standard Schema protocol support. Output validation returns INTERNAL_SERVER_ERROR on failure.
Design and troubleshoot weapp-tailwindcss dynamic class composition and runtime wrappers, covering @weapp-tailwindcss/runtime, merge, cva, variants, typography, theme-transition, ui, clsx, twMerge, weappTwIgnore, escape/unescape, rpx transformer, caching, and component class overrides. Use for dynamic classes, cn helpers, variant APIs, runtime package selection, or class escaping at runtime; not for initial bundler setup, React Native, or Lynx compiler configuration.
Companion skill for the Agent-Friendly APIs course on Vercel Academy. Use when the user mentions "agent-friendly APIs", "API documentation", "llms.txt", "the course", "teach me", or asks about agent-friendly docs, documentation patterns, or building Claude Code skills in the context of the Academy course.
Build, debug, modernize, or review ASP.NET Core applications with correct hosting, middleware, security, configuration, logging, and deployment patterns on current .NET. USE FOR: working on ASP.NET Core apps, services, or middleware; changing auth, routing, configuration, hosting, or deployment behavior; deciding between ASP.NET Core sub-stacks. DO NOT USE FOR: unrelated stacks; generic tasks that do not need this specific guidance. INVOKES: inspect the repository context, edit targeted files, and run relevant build, test, lint, or validation commands when changes are made.
Use when authoring an API specification — the engineering wire contract of an API surface: operations/endpoints, request + response schemas (fields, types, required/optional, constraints), auth, a complete error model, pagination/rate-limits, versioning, and worked examples. Guides the producer through the METHOD, not the outline: rendering the contract in the project's style (OpenAPI for REST, SDL for GraphQL, proto for RPC), typing every field, enumerating the ERROR CASES (not just the happy path), tracing each operation to a feature-spec behavior, and referencing the data-model rather than redefining it — to a bar where a client can call every operation and a server can implement it from the contract alone. Composes with a separate api-spec template tool and a deep-research capability. Assumes the upstream feature-spec (+ architecture-doc + data-model where present) — never a blank page. Not the persistence data-model, the consumer-facing API reference, the implementation, or reviewing a finished api-spec.
Exact-name Codex/OMX-compatible $autopilot front door for autonomous idea-to-verified-code work. Use when the user invokes $autopilot, autopilot, auto pilot, full-auto, or asks for an end-to-end build; route small focused edits to direct implementation and stricter spec-first loops to ooo or ralph.
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.
