Skills
99,064 packaged capabilities and playbooks for agents. Install any of them with one command.
Development
UI/UX design intelligence for web and mobile. Includes 50+ styles, 161 color palettes, 57 font pairings, 161 product types, 99 UX guidelines, and 25 chart types across 10 stacks (React, Next.js, Vue, Svelte, SwiftUI, React Native, Flutter, Tailwind, shadcn/ui, and HTML/CSS). Actions: plan, build, create, design, implement, review, fix, improve, optimize, enhance, refactor, and check UI/UX code. Projects: website, landing page, dashboard, admin panel, e-commerce, SaaS, portfolio, blog, and mobile app. Elements: button, modal, navbar, sidebar, card, table, form, and chart. Styles: glassmorphism, claymorphism, minimalism, brutalism, neumorphism, bento grid, dark mode, responsive, skeuomorphism, and flat design. Topics: color systems, accessibility, animation, layout, typography, font pairing, spacing, interaction states, shadow, and gradient. Integrations: shadcn/ui MCP for component search and examples.
Install and work with uifork, a CLI tool and React component library for managing UI component versions. Use when the user wants to version components, test UI variations, gather stakeholder feedback, or work with uifork commands like init, watch, new, fork, promote.
Select and correctly use the public capabilities of @veltra/* (desktop components, ai AI chat, sheet spreadsheets, styles themes, utils, compositions, directives, icons, vite) in Vue 3 projects. Mandatory when developing interfaces, forms, tables, themes or icons; when writing UForm / approval forms / modal forms you must first read the form examples (field binding, no more v-model); search this skill first before implementing equivalent UI capabilities yourself or introducing another component library.
React and Next.js performance optimization guidelines from Vercel Engineering. This skill should be used when writing, reviewing, or refactoring React/Next.js code to ensure optimal performance patterns. Triggers on tasks involving React components, Next.js pages, data fetching, bundle optimization, or performance improvements.
Standardized AI-assisted product delivery workflow for turning a new idea or messy repository into a disciplined build loop with `design-document.md`, `tech-stack.md`, `implementation-plan.md`, and a persistent `memory-bank/`. Use in Codex or Claude Code when bootstrapping greenfield work, normalizing a repository into a document-first process, or executing implementation one validated step at a time with `progress.md` and `architecture.md` kept current.
Comprehensive guide for creating VS Code extensions from scratch, including project scaffolding, API usage, activation events, and packaging. Use when user wants to create/build/generate/develop a VS Code extension or plugin, asks about VS Code extension development, needs help with VS Code Extension API, discusses extension architecture, wants to add commands/webviews/language support, or mentions scaffolding a VS Code project.
Helps work with vvvv gamma's Channel system from C# — IChannelHub, public channels, [CanBePublished] attributes, hierarchical data propagation, channel subscriptions, bang channels, and spread sub-channels. Use when reading or writing public channels from C# nodes, publishing .NET types as channels, working with IChannelHub, subscribing to channel changes, managing hierarchical channel state, or implementing reactive/observable data flow. Trigger for any mention of IChannel, IChannelHub, reactive binding, observable state, two-way data binding, or TryGetChannel in a vvvv context.
Helps with .NET integration in vvvv gamma — NuGet packages, library references, .csproj project configuration, the [assembly: ImportAsIs] attribute, vector type interop, and async patterns. Use when adding NuGet packages, configuring build settings, referencing external .NET libraries, setting up the ImportAsIs assembly attribute, working with System.Numerics/Stride type conversions, or when nodes aren't appearing in the node browser due to missing assembly configuration.
Helps set up C# library projects that provide nodes to vvvv gamma — project directory structure, Initialization.cs with AssemblyInitializer, service registration via RegisterService, IResourceProvider factories, ImportAsIs / ImportNamespace / ImportType selection, category organization, aspects (Advanced/Internal/Hidden) via [Smell] and category keywords, .csproj setup, and dynamic node factories via RegisterNodeFactory. Also covers contributing changes to an existing/upstream vvvv library — fork → branch → PR workflow, editable source packages (--package-repositories / --editable-packages), and the .vl-document diff problem. Use when creating a new vvvv library, VL package, NuGet package for vvvv, deciding which import attribute to use, organizing categories, controlling which public types become nodes, registering services or node factories, setting up the project structure, or contributing a fix/feature/PR to a library you don't own (e.g. VL.StandardLibs). Trigger when the user says 'create a package', 'make a library', 'distribute nodes', 'organize categories', 'hide internal helpers from the node browser', 'mark nodes advanced', 'clean up the node browser', 'publish a VL package', 'contribute to vvvv', 'file a PR on a vvvv library', or 'edit an existing library'.
Audit the developer experience of any platform that sends outbound webhooks or event destinations to its customers, and produce a structured YAML audit file with scored findings and prioritized recommendations. Use whenever the task is to review, assess, grade, or critique a company's webhook/event- delivery DX: their signup and onboarding, signing and verification, retry and delivery semantics, event catalog and payloads, setup surfaces (UI/API/CLI/IaC/SDK), consumer-facing observability, local dev, and local-to-production transition. Trigger this for a 'webhook DX review', 'event destinations audit', or an 'outbound webhook assessment', even if the user names a specific company (e.g. 'review Acme's webhooks') rather than the word audit. The output is a YAML audit file conforming to `schema/audit.schema.yaml`; whoever consumes it downstream renders their own presentation.
Generates secure Aptos Move V2 smart contracts with Object model, Digital Asset integration, security patterns, and storage type guidance. Includes comprehensive storage decision framework for optimal data structure selection. Triggers on: 'write contract', 'create NFT collection', 'build marketplace', 'implement minting', 'generate Move module', 'create token contract', 'build DAO', 'implement staking'. Ask storage questions when: 'store', 'track', 'registry', 'mapping', 'list', 'collection'.
Analyze mini-program project source code (including minified/obfuscated code), identify core business steps, extract network interfaces and JSAPI calls, generate a skill subpackage compliant with the wx.modelContext specification (with atomic interfaces + atomic components), and complete the app.json / project.config.json configuration integration. Trigger in these scenarios: turning mini-program page capabilities into mini-program AI atomic interfaces, generating skills/ subpackage code, deriving MCP tools from a source project, code generation for mini-program AI development mode. Handles static generation only; after generation completes, hand off to wxa-skills-validate for validation.
Set up codebase intelligence for AI agents. Runs the agentifind CLI to extract code structure using LSP (pyright/tsserver) with tree-sitter fallback, then synthesizes a CODEBASE.md navigation guide. Run this skill to get a complete codebase map in .claude/ directory.
Create, audit, or trim AGENTS.md and its harness mirrors (CLAUDE.md, GEMINI.md, .github/copilot-instructions.md, .cursor/rules) so build/test commands stay accurate and the file stays under each harness's size cap. Use when the user says "create AGENTS.md", "audit AGENTS.md", "trim AGENTS.md", "AGENTS.md is stale", "CLAUDE.md drift", "agent instructions hygiene", or invokes /agents-md. Covers nested AGENTS.md for monorepo packages, nearest-file precedence, and the bundled scripts/agents_md_check.py measurement script. Do NOT use for `.github/copilot-instructions.md` authoring or Copilot code-review configuration — that is /github-copilot-repo-instructions. Do NOT use for personal, per-user, or machine-global instruction files (`~/.claude/CLAUDE.md`, personal Copilot instructions) — those are out of scope for this repository-scoped skill.
Comprehensive ahooks React hooks library specialist. Expert in all 76+ ahooks hooks including state management, effects, data fetching, performance optimization, DOM utilities, and advanced patterns. Use when working with ahooks library, need React hooks utilities or want to learn best practices.
Enter explore mode to investigate ideas, systems, problems, and requirements before planning. Use ultra mode, explicitly or through config, when the user wants a durable adaptive research bundle with an index and only the justified C4, ADR, or dependency artifacts.
Configure ATC clean core and Cloud Readiness checks using the SAP Cloudification Repository, and map ATC findings to clean core levels (A, B, C, D). Use when users ask about ATC check variants for cloud readiness, clean core compliance, clean core levels, released/classic/internal/noAPI object classification, cloudification repository setup, objectReleaseInfo or objectClassifications JSON files, ATC exemptions, changelog for SAP objects, SAP Cloud ERP or SAP Cloud ERP Private API validation, or migrating custom code to ABAP Cloud. Triggers include "configure ATC cloud readiness", "set up clean core check", "cloudification repository URL", "released APIs check", "which level is this ATC finding", "ATC priority 1 clean core", "ATC exemption", "changelog for SAP objects", or "which JSON file for my S/4HANA version".
Use whenever the user mentions cached_tokens=0,total_cached_tokens,cache_read_input_tokens,cache_creation_input_tokens,cache_write_tokens,prompt_cache_key,prompt_cache_options,prompt_cache_breakpoint,previous_interaction_id,cache_control/cachePoint,TTFT,KV reuse; prefix_cache_retention_interval,prefix_caching_hash_algo,Mamba/SWA/hybrid,cross-process block hash; LLM cost or speed regressed,repeated long prompts,speeding up agents; LLM request shape changes: tools,schemas,response_format,model/router,agent loops,compaction; Not for generic prompt writing,RAG,token counts,non-LLM perf
Define custom attributes, custom object types, and site preferences for B2C Commerce using metadata XML. Use this skill whenever the user needs to add a field to products, orders, or customers, create a new custom object type, set up site preferences, or extend the B2C data model. Also use when they ask about system-objecttype-extensions.xml, custom-objecttype-definitions.xml, attribute groups in Business Manager, or data model definitions — even if they just say "add a field to products" or "I need a new object type".
This skill provides reusable implementation patterns extracted from the better-chatbot project for custom AI chatbot deployments. Use this skill when building AI chatbots with server action validators, tool abstraction systems, workflow execution, or multi-AI provider integration in your own projects (not contributing to better-chatbot itself). Use when: building AI chatbot features, implementing server action validators, creating tool abstraction layers, setting up multi-AI provider support, building workflow execution systems, adapting better-chatbot patterns to custom projects Keywords: AI chatbot patterns, server action validators, tool abstraction, multi-AI providers, workflow execution, MCP integration, validated actions, tool type checking, Vercel AI SDK patterns, chatbot architecture
Use when defining voxel blocks in RON (`name`, `textures`, `flags`), building a runtime palette mapping `BlockId -> BlockDef`, baking per-block textures into a KTX2 atlas (`ktx2` + `zstd_rust` features), or binding the atlas as `StandardMaterial.base_color_texture` with an `ImageSampler` so meshed quads sample by face index. Generic Bevy 0.20 voxel-data patterns — no game-specific data baked in.
Use when targeting Bevy 0.20 at `wasm32-unknown-unknown`, choosing the `webgl2` or `webgpu` feature, setting `WgpuSettings { backends, priority: WgpuSettingsPriority::WebGPU }`, attaching to a canvas with `Window { canvas, fit_canvas_to_parent }`, generating glue with `wasm-bindgen`, or debugging asset HTTP 404s and `Task` cancellation in the browser.
This skill should be used for book-to-SFT pipelines: ePub extraction, literary segmentation, author-voice dataset construction, style-transfer training, LoRA workflows, and model evaluation for voice replication.
Report stale git branches with a keep, archive, or delete recommendation, and propose enabling delete-branch-on-merge. Use for "clean up stale branches", "delete merged branches", "delete branch on merge", "which branches are dead", or /branch-cleanup. Checks age, author, ahead/behind counts, merged status, open pull requests, and ruleset protection, then prints exact deletion commands that require explicit per-batch authorization before any push. Do NOT use for local git worktree management (worktree add, list, or prune) — that stays out of scope. One-time repository merge defaults and branch-protection rulesets belong to /gh-bootstrap; this skill reads and reports on that state but does not set it up.
Capture a full DevTools-protocol trace of any browser automation — CDP firehose, screenshots, and DOM dumps — then bisect the stream into per-page searchable buckets. Use when the user wants to debug a failed run, audit network/console/DOM activity, attach a trace to an in-progress session, or feed structured per-page summaries back into an agent loop so its next iteration learns from the last one.
Builds form components and data collection interfaces including contact forms, registration flows, checkout processes, surveys, and settings pages. Includes 50+ input types, validation strategies, accessibility patterns (WCAG 2.1), multi-step wizards, and UX best practices. Provides decision trees from data type to component selection, validation timing guidance, and error handling patterns. Use when creating forms, collecting user input, building surveys, implementing validation, designing multi-step workflows, or ensuring form accessibility.
Builds tables and data grids for displaying tabular information, from simple HTML tables to complex enterprise data grids. Use when creating tables, implementing sorting/filtering/pagination, handling large datasets (10-1M+ rows), building spreadsheet-like interfaces, or designing data-heavy components. Provides performance optimization strategies, accessibility patterns (WCAG/ARIA), responsive designs, and library recommendations (TanStack Table, AG Grid).
Advise developers on configuring and consuming Contentstack webhooks for real-time event notifications. Cover event channels, payload structure, signature verification, retry behavior, release-triggered webhook storms, and reliable receiver design. Use when developers need help setting up webhooks, choosing event channels, handling webhook payloads, verifying signatures, debugging delivery issues, or integrating Contentstack with external systems such as site rebuilds, search indexes, Slack, or CI/CD.
Guide for extracting code or pseudocode from images using OCR and implementing it correctly. This skill should be used when tasks involve reading code, pseudocode, or algorithms from images (PNG, JPG, screenshots) and executing or implementing the extracted logic.
Author, validate, and enforce a CODEOWNERS file: detect an existing file, gather ownership evidence from directory structure and git history, write or update rules with correct CODEOWNERS syntax, validate the file against the GitHub API, and wire the ruleset rule that requires code owner review on pull requests. Use when the user says "add CODEOWNERS", "who owns this path", "require owner review", "validate CODEOWNERS", or invokes /codeowners. Idempotent — safe to re-run; diffs before overwriting and never auto-assigns an owner without confirmation. Do NOT use for branch rulesets in general (use /gh-bootstrap) or community health files such as README, LICENSE, CODE_OF_CONDUCT, and SECURITY (use /oss-hygiene) — this skill only covers the CODEOWNERS file and the review rule it feeds.
Coding standards for writing, editing, and reviewing code. Routes to language/framework-specific rules (Next.js, NestJS, Laravel, vanilla JS/TS, NativeScript, React Native/Expo, C#/.NET, Node Express/Fastify, Cocos Creator, Vue/Nuxt, Spring Boot, Django, FastAPI, Flask, Go HTTP) PLUS universal clean-code rules (functions, naming, objects/data, formatting, error handling, SOLID/KISS/DRY, universal structural rules) that apply to every language. Consult before any code change. Use when the user says "write a component", "add an endpoint", "refactor this", "review this diff/PR", or "is this clean?". Make sure to consult this skill for ANY code authoring or review task, even when the user does not explicitly ask for "standards" — every write/edit/review must comply.
Plan, run, and monitor Fireworks training from a coding agent. Covers managed SFT, DPO, ORPO, and RFT plus Training API serverless and dedicated workflows, complete cost and parameter confirmation, active monitoring, checkpoints, deployment, resume, and teardown. Use for explicit train, fine-tune, deploy, or resume requests. Use research when method, data, or evaluation is unclear; use debug for a stuck or failed run.
Use Convex Components to add isolated backend features and compose component APIs. Use for installing components, calling component APIs, authoring components, and handling component-specific constraints (Id types, env vars, pagination, auth). Use proactively when users mention components, workpool, workflow, agent component, or reusable backend modules. Examples: - user: "Install the Agent component" → add convex.config.ts + use() + components API - user: "Call component functions" → ctx.runQuery(components.foo.bar, args) - user: "Build a component" → defineComponent, schema, _generated, packaging - user: "Expose component API to clients" → re-export functions with auth
Implement Convex runtime features: HTTP actions, file storage, search (full text + vector), scheduling (crons + scheduled functions), and RAG patterns. Use for webhooks, uploads, search indexes, vectorSearch actions, and background workflows. Use proactively when users mention HTTP endpoints, files, search, embeddings, or cron/schedule. Examples: - user: "Add full text search" → define searchIndex + withSearchIndex query - user: "Upload files" → generate upload URL and persist storageId - user: "Vector search" → action with ctx.vectorSearch and doc fetch - user: "Run cleanup nightly" → cronJobs + function reference
For CRD proposers working across projects: draft or revise requirements, consolidate recipient responses, and continue Q&A. Recipients should use crd-respond for assessment and replies. Not for Kubernetes CRDs, code review, or direct implementation. Clarify your side's position and converge on a contract while preserving the rationale from each exchange.
Use when querying or mutating Datex Studio storage components via the `$db` predicate DSL — function-tier-only Mongo-backed access to `*-storage.json` configurations. Covers the fluent predicate operators (`.equals`, `.ne`, `.gt`/`.gte`, `.lt`/`.lte`, `.in`, `.isNull`/`.isNotNull`, regex via `.includes`, composed with `.and`/`.or` inside `.where`), result-row TypeScript-optionality semantics, the implicit `id` column, the `required: true` read-then-patch trap, and schema-change audit checklist. Flow datasources that back grids or selectors over `$db` are covered in the flow-db-datasources reference. Triggers: "query the storage", "add/update/remove rows in xxx_storage", "write a $db predicate", "filter by storage column", "$db predicate with AND/OR/null", "$db query returning wrong rows", "patch validation error", "TypeScript accepted my predicate but it doesn't work at runtime". For authoring the calling function itself, see function-creator.
Migrate legacy string-based logging in .NET/C# code to structured logging templates, insert CommandHandler logging scopes, and validate or update Serilog File sink settings in appsettings JSON files. Use when users ask to modernize ILogger or Serilog usage through safe rewrites, run dry-run logging migration previews, apply structured logging rewrites, or enforce JSON file sink formatter and path conventions. For general backend design and observability guidance use $software-csharp-backend, for NUnit test design use $qa-testing-nunit, and for pipeline changes use $ops-nuke-cicd.
Write idiomatic DSPy 3.2.x programs — typed Signatures, dspy.Module subclasses, Predict/ChainOfThought/ReAct/ProgramOfThought, and save/load. Use this when starting any new DSPy project or when fixing non-idiomatic DSPy code (hard-coded prompts, ad-hoc string templates, untyped outputs, non-serializable classes).
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.