Skills
98,873 packaged capabilities and playbooks for agents. Install any of them with one command.
Development
Builds production-quality, accessible, responsive user-facing UIs. Use when building or modifying interfaces and pages, creating components, implementing layouts, meeting WCAG accessibility requirements, managing state, or when the output needs to look and feel production-quality rather than AI-generated.
Ship the current branch — evaluate its SemVer release impact, refresh the docs, write the changelog entry for the version this merge will mint, file its human follow-ups, run the fast checks, push, and open or update the PR. Use when a feature branch is ready for review, or when the user says "ship it", "open a PR", or "push this".
Visant motion and micro-interaction system: easing/duration tokens mirrored in CSS and framer-motion, plus motion-lint and URL measurement. Use on "animation", "transition", "make it smoother", "apple-like", "loading", "skeleton", "animação", "deixa mais suave", "tela de espera", "micro-transições", /visant-motion.
Builds or changes an Apigee X proxy that acts as an AI or LLM gateway. Use it to route between models with aliases, or to add token quotas, spending budgets, Model Armor prompt and response inspection, prompt-token burst limits or FAQ semantic caching.
Use to build, extend, and troubleshoot browser based mapping applications with OpenLayers and ArcGIS services. Covers how to combine OpenLayers with ArcGIS basemaps, feature services, vector or raster tiles, location services, geocoding, routing, places, elevation, or secure ArcGIS resources. Includes ESM setup, ol-mapbox-style, ArcGIS REST JS, API keys and OAuth, projections, queries and pagination, styling, popups, editing, attribution, and performance.
Standards and quality gates for code comments, JSDoc/docstrings, technical documentation, and git commit messages. Use to evaluate or write high-signal, concise documentation and eliminate AI comment fluff, over-explanation, ghost commentary, commit message storytelling, and stylistic tells.
Turns a PRD into User Stories that a developer - human or agent - can build without guesswork: one User Story per in-scope feature, in As a/I want/So that format with at least two Gherkin scenarios, PRD conflicts documented rather than silently resolved, and open points stated as exact questions for the business. Use when the BA role receives a PRD, or when asked to write, draft or split user stories from a PRD, in any domain
Upgrades an Android app (Java or Kotlin) that uses the Navigation SDK for Android (com.google.android.libraries.navigation) from 7.x to 8.0. Covers the AGP 9.0.1 / Gradle 9.1.0 toolchain floor, targetSdk 37 and the Play Location Purpose Declaration, removed transitive dependencies (kotlin-reflect, Glide), androidx.car.app 1.3.0, and the 8.0 API changes: removed DisplayOptions.showTrafficLights / showStopSigns and onGpsAvailabilityUpdate, new RouteStatus.ROUTING_TIMEOUT, terrain map type during navigation, and deprecations of ListenableResultFuture, SupportNavigationFragment, setAudioGuidance, FollowMyLocationOptions, and NavigationTransactionRecorder Waypoint overloads. Use when upgrading NavSDK to 8.0, fixing a build that broke after the bump, or auditing what 8.0 changes for an app. Don't use for iOS.
Address the maintainers' review comments on a draft PR that the Issue triage workflow opened, unattended inside the PR revision GitHub Actions workflow (.github/workflows/revision.yml), which a needs-revision, needs-revision-mac or needs-revision-win label on the PR starts. Changes the code as the comments ask, verifies it on the runner, and leaves one commit for the workflow to push to the same PR. Only for that workflow.
Find, inspect and control processes and ports with the proc CLI (macOS, Linux, Windows), with JSON output for agents. Use it instead of lsof, ps, pgrep, pkill, kill, netstat, pstree or top whenever you need to: see what is on a port or free it (EADDRINUSE, "address already in use", a dev server that won't start); find processes by name, PID, file or project directory; inspect a process (command, cwd, parent, uptime, CPU, memory); stop, kill, pause, resume or wait for processes; trace why a port is busy; find orphaned, stuck or leftover processes, such as dev servers, watchers and headless browsers that you or another agent started; or clean up background work before finishing a task. Also use when the user mentions proc, ports, PIDs, signals (SIGTERM, SIGKILL, SIGSTOP) or a slow machine
Turns a gameplay video (generated by a video model such as MiniMax H3 Max or Seedance, or any clip) into a real, playable WebGL game in Three.js whose every image, 3D model, sound and music track is generated with fal, then proves it: side-by-side frames of the video and the game, and a scenario that plays the game with the keyboard and films its best seconds. Ships scripts to study the video (frames, palette, cuts), run and log fal models, record a playtest at the real frame rate, compare game and video, and find the liveliest window of a take. Use when the user wants a video, an AI gameplay clip or a game concept "turned into a game", "made playable", "recreated in the browser" or "rebuilt in Three.js/WebGL". Not for game engines (Unity, Unreal, Godot) or for copying existing commercial games.
Modernize an existing website (association, shop, practice, old Jimdo, Wix or WordPress site) for someone without prior knowledge. Start the inventory immediately without asking: list all pages, every feature (forms, registrations, appointments, PDFs, prices, galleries, maps, languages) and all content, with photos of the old site in docs/bestand.md. Then ask only for information known to the person, and proceed through planning and design to the new site without losing any feature without their consent. Use the skill for “modernize …”, “modernize our website”, “our site is outdated”, “renew website”, “relaunch”, “move away from Jimdo, Wix or WordPress”, “redo the old site”, and immediately when someone sends only a website address (https://…) with no other words.
Build interactive games using Augmented Reality (AR) and camera-based motion and gesture tracking for Smart TVs, Interactive Flat Panels (IFP), digital whiteboards, or laptop webcams. Students can interact at the front of the classroom without touching a physical screen.
Cut a Semantic Versioning release in any repository: find the version source, decide MAJOR, MINOR or PATCH from the commits since the last tag, update the manifest, the changelog and any current-release line, then commit and create an annotated tag, leaving the push to the user. Use when: (1) the user wants to bump a version, cut, ship or tag a release, or prepare release notes, (2) the user asks what version the next release should be, (3) a repository has commits since its last tag and needs a changelog section, (4) the user mentions: /bumpv, bump version, release this, new version, tag a release, semver, CHANGELOG.md, Keep a Changelog, chore(release), git describe, annotated tag, --follow-tags, package.json version, Cargo.toml, pyproject.toml, "what version should this be". Carries a version-source table for Node, Rust, Python, Go, PHP, Ruby, .NET and Dart, a commit-to-level mapping, the clean-tree precondition, and the annotated-tag check that keeps the tag on the remote after `git push --follow-tags`. Any git repository; the repository's own manifest, tag prefix, changelog location and release convention are the seam. Not a publisher: it never pushes, never creates a GitHub Release and never runs a package registry publish, and it versions one package, not a monorepo workspace
Use when running coinagerie or npx @coinagerie/cli, printing a codebase's vocabulary, checking or writing a glossary, choosing between --check, --write, and a bare run, reading the glossary block or JSON it printed, reading the missing and stale words named by a failed check, finding which words are still undefined, or wiring a glossary check into CI, a commit hook, or an Nx target.
Use when writing or changing a coinagerie.config.ts, choosing which files are scanned, excluding paths or words, reading another glossary into exclude.words, merging a word family with fold, declaring markdown or JSON glossary destinations, sharing one base configuration across folders, or when a configuration is rejected, a keyword list will not import, or a word is wrongly listed in the glossary.
Use when writing or improving a definition in a coinagerie glossary, filling a bare `- **word**:` bullet or an empty JSON value, reviewing a definition that restates its word or reads like a dictionary entry, or explaining a word whose meaning in this codebase differs from its everyday English meaning.
Use when coinagerie --check exits non-zero, a run names missing or stale words, refuses a glossary it cannot parse, or rejects a configuration or command line, when --write deleted a definition, when a glossary headword looks wrong or surprising, when a check passes locally and fails in CI, or before adding a word to exclude.words, narrowing include, or deleting a glossary block to make a failing check pass.
Install, set up and use the tailwindcss-concentric plugin to fix and prevent mismatched nested corner radii in Tailwind CSS v4 projects. Use when the user asks to add or set up tailwindcss-concentric, to audit or fix nested border radii, or when building or reviewing UI where a rounded element sits inside a padded or bordered rounded parent (cards with media, buttons in search bars or toolbars, segmented controls, selection rings, modals, input groups), when you see hard-coded inner radii such as rounded-[calc(...)], or when the user mentions concentric, nested, inner or outer corner radius
Contextualizes the business of an existing system (brownfield) for AI-first work: builds the capability map (what the system does today), surfaces business rules hidden in code, and creates the business ↔ code glossary with the ARCH, all with evidence, then pauses for human approval. Use when the BA role starts on an existing system without a PRD or backlog, or when asked to document what a legacy system does, extract its business rules, or build a domain glossary
Contextualizes an existing repository (brownfield) for AI-first work on it: verifies how to start and test it, creates the CodeGraph index, reconstructs the actual layer map, documents inherited decisions as ADRs, assembles the pattern catalog (canon vs. legacy), the debt map and verifiable build rules, all with file:line evidence, then pauses for human approval. Use when the ARCH role starts on an existing codebase without a PRD, or when asked to contextualize, onboard, document, map or understand a legacy/brownfield repository before working on it
Find the mistakes agents keep repeating in this repo and make each one impossible. Try architecture first, then types, then a lint whose error names the fix, then a test, and write docs last. Prove each check fails on a real past mistake. Repeat this each time the operator corrects you. Use for /correct.
Debugs issues users encounter with Tuist-generated projects by reproducing the scenario locally, building Tuist from source when needed, and triaging whether it is a bug, misconfiguration, or something that needs team input. Use when users report generation failures, build errors after generation, or unexpected project behavior.
MANDATORY - use before planning, building, or redesigning an ArcGIS application, including requests that do not specify an ArcGIS technology. For existing applications, use when a change could affect architecture, product, technology, data access, or authentication. Review context, clarify consequential unknowns, and route to relevant authentication and build skills.
Guides day-to-day work in Tuist-generated Xcode workspaces, including generation, build and test commands, and buildable folders. Use when working in a Tuist-generated project or when users mention `tuist generate`, `xcodebuild test`, or generated workspaces.
Operate Orca-managed worktrees, folder contexts, terminals, repos, automations, artifacts, skill sharing, worktree comments, and Orca's embedded browser through the `orca` CLI. Use when the user says "$orca-cli", "Orca worktree", "child worktree", "spawn codex/claude in a worktree", "read/wait/send Orca terminal", "handoff" / "handover" / "give this to another agent", "Orca browser", "orca artifacts", or "share skills". Prefer it over raw git worktree, ad hoc PTYs, or Computer Use when Orca state is involved. Use Computer Use only when a visible window needs GUI control that a CLI, filesystem, or API cannot do.
Read org state and change Setup through the Headless 360 (H360) MCP tools discover, describe, dispatch_readonly, and dispatch. Use when H360 tools are present and the answer is org state no skill or sf command reads: Setup settings, feature or license access, org-specific caps, health checks, release updates. Also H360 setup and errors (401, 403, 404, ROUTE_NOT_FOUND, INVALID_ARGUMENT). DO NOT TRIGGER for records, SOQL, schema, limits in sf org list limits, deploys, or which-plugin questions.
Use when studying a SaaS web product from the outside in order to rebuild, clone or copy it (ClickUp, Pipedrive, Notion, a CRM, a project tool), when documenting its UX, screens, components, data model, business rules or API through a browser the agent drives, when assessing what would block a clone from launching (permissioned integrations, regulation, certifications), or when an agent must explore a live SaaS account without damaging production data or notifying real people.
Prevent, detect, and repair AI coding slop and dirty engineering in repositories. Use for planning features, writing code, changing tests, reviewing pull requests, refactoring, hardening CI, debugging regressions, or auditing agent-generated changes. Enforces behavioral contracts, focused diffs, test integrity, repo conventions, security boundaries, and evidence-based completion.
Turn the changes in a git working tree into clean Conventional Commits: read the diff, run the repository's own check, stage by path, split unrelated changes into separate commits, write the message, and verify what landed. Use when: (1) the user wants to commit, save progress, record WIP or wrap up a finished task, (2) a working tree mixes unrelated changes that should become separate commits, (3) a change breaks existing usage and the release tooling must see it, (4) the user mentions: commit, commit this, commit my changes, save progress, WIP commit, conventional commit, commit message, git add, staged, untracked, BREAKING CHANGE, feat!, Co-Authored-By, pre-commit hook, "split this into commits". Carries the staging rules that keep secrets and build output out, the breaking-change markers that `bumpv` reads to choose a MAJOR release, the hook and amend rules, and a post-commit check that no attribution trailer landed. Any git repository and any stack; the repository's own check and documented conventions are the seam. Not a release tool, not a changelog writer and not a push or pull request flow
Look up MCU peripheral registers, bit fields, reset values, and addresses (based on CMSIS SVD), with sources and evidence labels for every finding. Supports address reverse lookup; register value decoding and write-value calculation; bit-field quick reference and bitmaps; interrupt number and NVIC enable hints; CMSIS-style macro generation; cross-chip and peripheral-level comparisons; address range queries; SVD quality checks; local chip inventory and environment checks; Markdown table output; and parsed-result caching. Use when the user asks about a register, bit field, reset value, peripheral base address, or interrupt number; wants to decode or compute a register value to write, generate register macros, compare register definitions across devices, or find or verify SVD files on the machine. Keywords: 寄存器、位域、复位值、SVD、外设地址、寄存器值、掩码、位图、中断号、IRQn、NVIC、宏定义、对比、整体对比、质量检查、SVD 位置、芯片清单、读改写、USART1->CR1、register、bitfield、mask、reset value、decode、interrupt. Not for: pin multiplexing, manual chapter search, errata lookup, or verifying register writes in code (use embedded-register-verify).
Align the current project's PRODUCT.md, DESIGN.md, GLOSSARY.md, and ARCHITECTURE.md after meaningful changes, and write the project Flow block on request. Use when the user says "update the docs", "sync the context", "keep the docs aligned", or "set up Flow here".
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.