Skills
98,873 packaged capabilities and playbooks for agents. Install any of them with one command.
Development
Set up or audit a project for coding agents - the machine checked first with set-up-machine, `AGENTS.md` as the one rules file with `CLAUDE.md` pointing at it, the issue tracker, triage labels, domain docs and release lifecycle, the folder standard's `.gitignore`, and project harness files kept allow-only. Use for a new or existing project, to audit a project's agent setup, or when a skill finds no issue tracker configured.
Ship a NEW capability to vigiles so it actually reaches a user — a new export, public function, subpath, CLI flag, or hook-vocabulary word. Use when about to add, or having just added, a feature / export / public API to this repo. Runs the executable checks a green `npm run check` does NOT make — reachable from a public door, API-surface diff READ, a public doc home, the experimental_ decision, a gate on a frozen tree. NOT for bug fixes, refactors, doc-only or test-only edits.
Use when a Spec Pack is complete and its reusable assets need to be promoted to the project SSOT (ADR/contract/ops/NFR/registry), and there is a risk of copying the whole pack and polluting the project, skipping spec-context, or mistaking merge-back for a git merge.
Ask, plan & execute skill for adding STRK20 privacy to a Starknet project. Use when a developer wants to add privacy to the Starknet app open in this session — private/shielded transfers, confidential balances, private payments, private swaps or DeFi, hiding user↔account links — mentions STRK20, privacy pool, shielding, viewing keys, or the Privacy Wallet API, or wants an existing STRK20_INTEGRATION_PLAN.md executed. Inspects the open repo, interviews the developer, picks the right integration route, writes a repo-specific integration plan, and — after the developer approves it — executes the plan phase by phase (app code only, never Cairo contracts).
Structure content for screen reader and assistive technology use. Chains: heading-structure, alt-text-design, table-accessibility, form-labelling. Use when building a new page, document, or content template and you want to get the structural accessibility right from the start.
Use when executing multi-task plans where each task can be implemented independently by a subagent. Triggers when a plan has 3+ independent tasks, when speed of execution is important, when tasks have clear acceptance criteria suitable for delegation, or when two-stage review gates (spec compliance and code quality) are needed for iterative fix cycles.
Review or implement interface accessibility for semantics, keyboard operation, focus, contrast, status communication, zoom, and assistive technology. Use when accessibility is explicitly requested, required by the product contract, or a changed interaction creates substantial accessibility risk. Do not activate for every visual edit or use it as a generic design audit.
Implement or review application behavior, APIs, state transitions, data flow, and business rules with explicit contracts and failure handling. Use for logic-bearing changes across frontend or backend systems. Do not use for visual-only or copy-only work.
Build, redesign, or visually refine product interfaces using project evidence, real content, functional states, and deliberate composition. Use for implementation work on websites, apps, dashboards, landing pages, or component systems. Do not use for read-only audits or logic-only changes.
Common utilities and features for Syncfusion JavaScript controls. Use this skill when the user needs to implement animations, drag-and-drop, state persistence, RTL support, localization, globalization, security, templates, and advanced features for Syncfusion JavaScript controls.
Use when hierarchical task breakdown is needed, when dependency mapping between tasks is required, when effort estimation and parallelization planning is needed, or when creating work breakdown structures. Triggers on /decompose command, when complex tasks need to be broken into manageable subtasks, when critical path analysis is needed for scheduling, or when identifying tasks that can run concurrently.
Use when breaking work into discrete steps, tracking progress through multi-step implementations, or managing implementation task lists. Triggers when an approved plan needs to be converted into tracked tasks, when progress reporting is needed during execution, or when checkpoint reviews are required between task batches.
Test-driven development. Use when the user wants to build features or fix bugs test-first, mentions TDD or "red-green-refactor", asks for tests that prove a behavior, wants a bug reproduced as a failing test, or wants integration tests. Not for only running an existing test suite.
Manage technical projects from initiation through delivery and closure: choose and tailor predictive, iterative, Scrum, flow-based, or hybrid approaches; coordinate teams and vendors; track milestones, risks, issues, dependencies, forecasts, scope changes, and recovery. Use when a team has no project manager, a TPM needs decision-ready analysis, a project is slipping, or commitments and handoffs need coordination. Use `technical-program-management` instead when multiple related projects, teams, vendors, shared capacity, or benefits must be coordinated toward one outcome. Adapt depth to the user's expertise. Do not use for a standalone coding task, product discovery or strategy, only writing an implementation plan, only diagnosing Kanban flow, operating a ticket tool, incident command, or a release go/no-go decision; route those to specialists.
Write, review, and adapt SQL for TiDB with correct handling of TiDB-vs-MySQL differences (VECTOR type + vector indexes/functions, full-text search, AUTO_RANDOM, optimistic/pessimistic transactions, foreign keys, views, DDL limitations, and unsupported MySQL features like procedures/triggers/events/GEOMETRY/SPATIAL). Use when generating SQL that must run on TiDB, migrating MySQL SQL to TiDB, or debugging TiDB SQL compatibility errors.
Master TypeScript's advanced type system including generics, conditional types, mapped types, template literals, and utility types for building type-safe applications. Use when implementing complex type logic, creating reusable type utilities, or ensuring compile-time type safety in TypeScript projects.
Use when developing CKEditor 5 custom plugins for TYPO3 v12+ (v14.3 LTS bundles CKE5 v47; v13 shipped 41-42), configuring RTE presets, migrating from CKEditor 4, customizing toolbars, dark/light-mode context (on by default in v14, #106964), or fixing rich text editing issues. Triggers: CKE5, RTE config, YAML preset, editor plugin, jQuery removal, backend JS, CKEditor 47.
Packages uni-app projects as native Android APK/AAB and iOS IPA via offline packaging, covering manifest configuration, signing certificates, native plugin integration, and build distribution. Use when the user needs to package a uni-app as a native app, configure Android keystore or iOS provisioning, or set up offline build for distribution.
Unity 3D math correctness patterns. Catches common mistakes with coordinate spaces, Quaternion, Vector3, Plane, Bounds, Transform hierarchies, raycasting projection, and floating-point precision. PATTERN format: WHEN/WRONG/RIGHT/GOTCHA. Based on Unity 6.3 LTS documentation.
Unity game loop and progression design-to-code translation. Core loop scaffolding, session lifecycle, win/lose condition architecture, meta loop hooks, tunable difficulty, pacing & encounter timing. DESIGN INTENT format: INTENT/WRONG/RIGHT/SCAFFOLD/DESIGN HOOK. Based on Unity 6.3 LTS.
Unity New Input System correctness patterns. Catches common mistakes with action reading (triggered vs IsPressed vs WasPressedThisFrame), action map switching, rebinding persistence, InputValue lifetime, PassThrough vs Value, local multiplayer device assignment, and control scheme auto-switching. PATTERN format: WHEN/WRONG/RIGHT/GOTCHA. Based on Unity 6.3 LTS.
Use when starting a new feature branch, creating isolated development environments, or working on multiple tasks simultaneously without stashing or switching branches. Triggers: user says "worktree", "new branch for work", "parallel development", "isolated environment", needs to work on two things at once.
Build, develop, deploy, self-host, secure, and troubleshoot durable backend AI agents with Vercel Eve. Use when creating an Eve agent, adding tools, skills, subagents, channels, schedules, sandboxing, durable sessions, observability, or deploying Eve on Vercel or a Node host. Do not use for the separate Vercel AI SDK Agent APIs such as ToolLoopAgent or WorkflowAgent; use an AI SDK-specific skill for those.
Build, review, refactor, configure, or debug Voltra code using Voltra JSX, Voltra JS APIs, the Expo config plugin, and the Voltra CLI. Use when the user asks about charts, Live Activities, Dynamic Island UI, iOS widgets, scheduled widgets, Android widgets, ongoing notifications, image handling, app.json plugin config, React Native CLI setup, or Voltra push update flows.
Provides comprehensive guidance for Vue Router including route configuration, navigation, dynamic routes, nested routes, route guards, programmatic navigation, and route meta. Use when the user asks about Vue Router, needs to set up routing, implement navigation guards, handle route parameters, or manage route transitions.
Transform generated wiki Markdown files into a polished VitePress static site with dark theme and interactive Mermaid diagrams. Use when user asks to "build a site" or "package as VitePress", user runs the /deep-wiki, or user wants a browsable HTML output from generated wiki pages.
Runs a disciplined Discuss → Map → Decompose → Execute → Verify loop that grounds code in verified structure — no invented APIs, no assumed imports, no placeholder code — with a lazy-senior-dev YAGNI ladder that deletes unnecessary code before it is written. Use when a coding task is high-stakes, complex, or spans existing code (auth, databases, migrations, multi-file features), or when the user explicitly asks to plan carefully before coding, avoid hallucinated code, or work rigorously. Not for trivial edits, typos, or throwaway one-off scripts — those do not need the full loop.
Deep expertise on the ziflux Angular library — SWR caching for resource(). Use this skill whenever implementing cachedResource, cachedMutation, DataCache, or provideZiflux in Angular code. Also use when reviewing, debugging, testing, or cleaning up code that uses ziflux, or when the user asks about SWR caching patterns in Angular, data freshness lifecycle, or cache invalidation strategies. Triggers on: ziflux, cachedResource, cachedMutation, DataCache, SWR cache Angular, stale-while-revalidate Angular, cache invalidation Angular, optimistic updates Angular signals.
Build type-safe global state in React applications with Zustand. Supports TypeScript, persist middleware, devtools, slices pattern, and Next.js SSR. Use when setting up React state, migrating from Redux/Context API, implementing localStorage persistence, or troubleshooting Next.js hydration errors, TypeScript inference issues, or infinite render loops.
Generate Advanced Custom Fields (ACF) Local JSON configurations for WordPress from visual designs or HTML structures. Use when creating ACF field groups, converting designs to ACF schemas, building WordPress custom fields from mockups, or when working with ACF Pro Local JSON format. Supports flexible content, repeaters, clone fields, and all ACF field types.
Use this skill when reviewing or refactoring existing Rust code that carries an alien mental model — OO/enterprise ceremony from Java/C#, garbage-collected object graphs, exception-style control flow, or imperative loops ported onto the borrow checker. It is the adversarial, architecture-level counterpart to greenfield idiom advice — it names the paradigm the code betrays and prescribes the deep refactor that collapses it, up to deleting whole layers (single-impl DI traits, Deref inheritance, Manager/Service structs, reflexive builders, Rc<RefCell> webs, clone-until-it-compiles, bool/String state machines, sentinel returns, catch_unwind try/catch, reflexive Box<dyn>, blocking calls inside async, fire-and-forget spawns). Every rule is grounded in the codex-rs production workspace (openai/codex) — the prescriptions are what that codebase actually does and lint-enforces. Applies whenever the work is "make this Rust actually Rust", "flatten this architecture", or a pedantic review of code fighting the language.
Analyze a Figma COMPONENT_SET as a state machine for code generation — extract variant axes (state/size/etc.), map state variants to CSS pseudo-classes (hover→:hover, focus→:focus-visible, disabled→:disabled, error→[aria-invalid]), and compute per-variant visual diffs (only what changes per state). Use when generating an interactive component from a Figma variant set — triggers: 'analyze this component set', 'turn these variants into CSS states', 'generate a button/input/checkbox from Figma variants', 'what changes between the hover and default state', 'map Figma variants to component props', 'extract the state machine for this component'. Resolves bound variables to token names. NOT covered by the native MCP's get_design_context/get_metadata, which don't give you a variant-axis→CSS-state machine.
Deep-research analysis of a codebase, a topic, or both. Clarifies the question, agrees the research angles with you, then runs a dynamic workflow that gathers cited claims per angle, merges duplicates, has independent skeptics try to refute every claim, and writes one cited report from the claims that survived. Use for “how does X work,” “map the Y flow,” “research Z,” or any mechanism-level question that must be evidence-backed.
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.