Skills
96,770 packaged capabilities and playbooks for agents. Install any of them with one command.
Development
Integrates the CrazyGames JavaScript SDK (v3) into a browser or HTML5 game. Handles SDK initialization, user authentication and profile retrieval, persistent key/value storage, interstitial and rewarded ad breaks, adblock detection, responsive banner ads, gameplay lifecycle hooks (loadingStart/Stop, gameplayStart/Stop, happytime), and optional Xsolla Pay Station in-app purchases with analytics order tracking. Use when the user mentions CrazyGames, wants to publish or integrate a game on CrazyGames, or needs to add SDK features like ads, user accounts, game events, storage, or in-game purchases to a browser/HTML5/JavaScript game.
Integrates the GameDistribution JavaScript SDK (GD SDK) into a JavaScript or HTML5 game, covering SDK initialization, interstitial and rewarded ad display, banner ads, ad callback handling, and game lifecycle events. Use when the user asks about GameDistribution, GD SDK, game ads, HTML5 game monetization, ad integration, or wiring up ads and lifecycle events in a JavaScript or HTML5 game.
Use the HyperFrames CLI development loop: init, add, catalog, capture, lint, check, snapshot, compare, grade-compare, preview, play, present, beats, keyframes, single or batch render, publish, cloud, cloudrun, feedback, lambda, doctor, browser, info, upgrade, skills, compositions, timeline, history, clean, docs, benchmark, telemetry, transcribe, auth, tts, and remove-background. Also use when diagnosing build or render failures. validate, inspect, and layout are deprecated aliases; use check. Covers local, HeyGen-hosted cloud, AWS Lambda, and Google Cloud Run rendering.
The HyperFrames composition contract — build one renderable project. Use for composition structure, the `data-*` timing attributes, `class="clip"`, tracks, sub-compositions, variables, framework-owned media playback, deterministic-render rules, and validation. Read before writing composition HTML.
Analyze a game, find what needs work, and implement the highest-impact improvements. Use when the user says “improve my game,” “make my game better,” “fix my game,” “what's wrong with my game,” or “polish my game.” Run repeatedly—each pass finds the next most impactful thing to fix. Do NOT use for adding specific new features (use add-feature) or initial game creation (use viral-game for one-shot builds, make-game for milestone-driven projects)
Use when integrating the Lagged JavaScript SDK into an HTML5 game published on Lagged.com, adding Lagged leaderboards, handling Lagged ad placements, or setting up user authentication via the Lagged API. Initializes the Lagged SDK (window.LaggedAPI), retrieves player profile data, submits scores to native leaderboards, unlocks achievements, and integrates interstitial and rewarded ads for games on the Lagged.com game portal.
Integrates the MSN JavaScript SDK (`window.$msstart`) into JavaScript games running on Microsoft Start. Handles SDK initialization, player authentication, cloud save key/value storage, display banner and interstitial/rewarded ad lifecycles, native sharing, leaderboard score submission, and in-app purchases. Use when the user mentions MSN SDK setup, MSN ads integration, game monetization with MSN, adding MSN features to a JavaScript game, `$msstart`, `msstart` script, MSN cloud save, or MSN IAP.
Integrates the Poki JavaScript SDK (PokiSDK) into JavaScript browser games. Initializes PokiSDK, configures interstitial and rewarded ad breaks (commercialBreak, rewardedBreak), manages gameplay lifecycle events (gameplayStart, gameplayStop), and sets up loading progress tracking (gameLoadingFinished). Use when the user mentions Poki, PokiSDK, web game monetization, game portal integration, ad breaks in browser games, or distributing an HTML5 game on the Poki platform
Review an existing game codebase for architecture, performance, and best practices. Use when the user says "review my game", "code review", "check my game architecture", "is my game well structured", or "audit my game code". Do NOT use for making changes — this is read-only analysis. Use improve-game to implement fixes.
Build a strategy-driven time-slot generator with availability in a Next.js App Router app: daily ranges, Nth-weekday-of-month rules, one-off slots and whole-day slots, authored in local wall-clock time and stored as UTC instants, with seats, bookings, blackouts, host busy time, shared resources and working hours subtracted, a listing route and a booking route that re-checks capacity in the write transaction. Use when: (1) an app needs appointment, class, rental or reservation slots generated from rules rather than stored one by one, (2) slot code gives wrong days around DST, wrong weekdays far from UTC, a week view with one day, or times that change with the server's time zone, (3) strategies must be validated, pinned to a zone, or moved off wall-clock-as-UTC storage, (4) two guests can book the last seat at once, (5) the user mentions: time slots, slot generator, availability, booking slots, opening hours, slot strategy, RANGE, PERIODICITY, DAY_RANGE, ONCE, slotInterval, slotDuration, slotsLimit, daysLimit, first Monday of the month, last Friday, overnight slots, lead time, booking window, timeOffset, IANA time zone, DST, fromZonedTime, storageVersion, slot ID, md5, overbooking, capacity check, book_slots, slot-no-longer-available, slot-has-not-enough-capacity. Carries a dependency-free engine on Intl with a 23-test suite run under four process time zones, slot IDs that stay stable for existing bookings, one availability map for listing and booking, and a capacity re-check inside the booking transaction on both backends. Next.js App Router route handlers on the Node.js runtime; Firestore or Supabase/Postgres behind the SlotStore seam. Not a calendar UI, not RRULE or iCalendar recurrence, not payments or booking-flow screens.
Updates cooked. to its newest version. Works out how it was installed and does the right thing for each. The official plugin from the marketplace gets the plugin update commands for ai-editor and creator-teardown. A fork the user owns (the power-user route, where they change the editor's own code) gets its new versions pulled from nextwork-projects/ai-video-editor-cooked and merged with their changes kept, after a backup branch, then the fast self-checks, with a rollback if they fail. A plain clone gets the fork route in three steps. Use when the user says "update the editor", "get the latest version", "sync my fork", "pull the new version", or asks how to stay up to date after changing the editor's code. Not for changing a style or a setting (that is taste or the home page), and not for maintainers turning feedback into fixes (that is improve).
Integrates the Y8 JavaScript SDK into JavaScript and HTML5 games. Covers SDK loading and initialization handshake, player authentication via Y8 login, cloud-backed user data storage, interstitial and rewarded ads through Google AdSense, native achievement unlocking and listing, and in-game leaderboard score submission and retrieval. Use when the user mentions Y8 SDK, Y8 API, Y8 integration, Y8 leaderboard, Y8 achievements, Y8 login, or adding Y8 features to a JavaScript or HTML5 game.
Integrates the Yandex Games JavaScript SDK (YaGames) into JavaScript games. Initializes the SDK and lifecycle hooks, manages player authentication and authorization, handles per-player cloud storage, controls ad placements (interstitial, rewarded video, sticky banner), implements in-app purchases and leaderboards, retrieves remote config flags, and supports social features such as review prompts and home-screen shortcuts. Use when the user mentions Yandex Games, YaGames, yandex sdk, deploying a game to the Yandex.Games platform, or integrating features like ads, leaderboards, in-app purchases, or player authentication into a Yandex-hosted JavaScript game.
Use this skill to initialize and integrate the YouTube Playables JavaScript SDK into an HTML5 game. Covers SDK bootstrapping, game lifecycle signaling, persistent save data management, interstitial and rewarded ads, leaderboard score submission, player language detection, and audio/pause lifecycle hooks. Use when the user asks about YouTube Playables, building or embedding games for YouTube, the YT game SDK, YT Playables integration, or making an interactive playable game on YouTube.
Create a new, isolated git worktree inside the repo's `.worktrees/` folder, with its own branch, from a brief requirement description or the explicit branch/folder name the user wants to use—so multiple tasks can be worked on in parallel without stashing or checking out within the same checkout. Use when the user asks to “create a worktree,” “new worktree,” “work in parallel,” “isolate this feature in its own folder,” “give me a separate checkout for X,” “set up a worktree for Y,” “work on multiple branches at once,” or “set up a parallel checkout,” or explicitly mentions the `.worktrees/` folder.
Shared vocabulary for designing deep modules. Use when the user wants to design or improve a module's interface, find deepening opportunities, decide where a seam goes, make code more testable or AI-navigable, or when another skill needs the deep-module vocabulary.
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.
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.
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
Write the release notes for a Playwright release - the Node.js notes in docs/src/release-notes-js.md together with the Python, Java and .NET translations, and the GitHub markdown for each language's release. Use when asked to write, translate or publish release notes
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
Use when the user asks to confirm feature trade-offs in a PRD or development plan item by item; not for quality reviews, writing documents from scratch, or implementation. Briefly explain each feature, its value, and the planned approach; revise the document after confirmation, rejection, or changes
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
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.
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.
Set up PostHog in a user's GitHub repository from a chat, without a terminal. Wizard, PostHog's setup agent, runs in the cloud, adds the SDK and first events, and opens a pull request. Use only when you can't read or edit the user's code, which is common in web chat apps such as ChatGPT on the web or Claude on the web. Typical requests: install, add, or set up PostHog in their app or repository, or open a pull request that adds PostHog. When you're working in the user's repository, use installing-posthog-in-a-codebase instead. Covers connecting GitHub, picking the repository, starting the run, polling it, and sharing the pull request.
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.
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.
Expert data extraction guide. Starts with a structured intake to understand the target. Always tries the cheapest path first (HTTP requests → browser fingerprinting → headless browser). Covers TLS/HTTP fingerprint impersonation (curl_cffi, primp, rnet), the modern stealth-browser stack (patchright, camoufox, nodriver), the anti-bot vendor matrix (Cloudflare, DataDome, Kasada, Akamai) with per-vendor bypass, CAPTCHA/Turnstile solving, proxy networks and managed unblockers (Zyte API, Web Unlocker) with geo-targeting, structured-data extraction (JSON-LD/microdata/OpenGraph), AI/LLM-driven and adaptive extraction (scrapling, crawl4ai, firecrawl), site-stack playbooks (Next.js App Router/RSC, Tableau, OData, PX-Web, SDMX, ASP.NET, GraphQL, SPAs), browser request injection, live request interception, and clean OOP architecture standards for scrapers and extracted data. Use whenever the user wants to scrape/extract data from a website or API
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).
Use the public `orca` CLI to operate Orca-managed worktrees, folder contexts, terminals, repos, automations, artifacts, worktree comments, and the browser embedded inside the Orca app. Use when the user says "$orca-cli", "use orca cli", "Orca worktree", "child worktree", "cardStatus", "spawn codex/claude in a worktree", "read/wait/send Orca terminal", "terminal send", "full handoff", "handover", "give this to another agent", "another worktree", "Orca browser", "orca artifacts", "share HTML/Markdown", "public artifact link", or "control the browser inside Orca". Prefer this over raw `git worktree`, ad hoc PTYs, Playwright, or Computer Use when the task touches Orca-managed state. Use Computer Use for browser windows, webviews, or desktop UI outside Orca's embedded browser.
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.