meta

Test an IWSDK app for Meta VR Glasses — gaze-and-pinch input, the glasses' narrower field of view, and gaze preview on a Quest without eye tracking. Use when the user targets Meta VR Glasses, asks for gaze or eye-tracking input, or wants to check that content…

Verify ray clicks, UIKit selections, and DistanceGrabbable interactions with emulated XR controllers. Use for pointing, selecting, pressing spatial UI, or moving an object through a distance grab.

Build or modify manifest-backed IWSDK UIKitML with bounded preview, placement, and runtime verification. Use for spatial panels, browser HUDs, UIKitML layout, fonts, editor previews, and runtime element behavior.

Single entry point for IWSDK development. Invoke first for every IWSDK implementation request. Routes fresh builds to an internal planning playbook and bounded changes to an established app to an internal iteration playbook.

Compose and review IWSDK scenes from existing manifest assets using scene JSON, placement, scale, contacts, prefabs, patterns, lighting, environment, cameras, and final framing. Does not author geometry or materials; create or repair an individual 3D asset…

Test environment system (authored DomeGradient and IBLGradient, component schemas) against the poke example using the iwsdk CLI.

Find and click a target object in XR. Use when testing UI interactions, clicking buttons, or verifying interactable elements work correctly.

Parallel test orchestrator. Runs all 9 test suites concurrently via Task sub-agents and the iwsdk CLI. Handles build, example setup, dev servers, agent launch, polling, retries, and result aggregation.

Build a production UI Toolkit for Meta Ray-Ban Display media collection with a horizontal Carousel of image Cards and a static reading detail route. Use when real media is the primary collection, selecting an item opens detail, and selection/focus must…

Build or review UI Toolkit for Meta Ray-Ban Display Container, StaticContainer, Panel, Surface, Card, CardStack, Carousel, MediaWrapper, Scrim, and Vignette compositions. Use for interactive/static materials, information grouping, custom widgets, image cards,…

Build, revise, or review polished production Meta Ray-Ban Display React interfaces with the public `@wearables-ui-toolkit/mrbd` library. Use for UI Toolkit for Meta Ray-Ban Display applications, routes, layouts, focus/D-pad navigation, materials, responsive…

Discover and route to the complete UI Toolkit for Meta Ray-Ban Display skill library for building production Meta Ray-Ban Display React applications with `@wearables-ui-toolkit/mrbd`. Use first for any broad, ambiguous, multi-component, or unfamiliar toolkit…

Build, debug, or review UI Toolkit for Meta Ray-Ban Display App, Page, Header, ScrollView, VerticalList, Pager, SubNavigationPager, SubNavigation, PaginationIndicator, SwipeIndicator, route transitions, React Router and Next.js App Router integration,…

Audit, test, or validate production UI Toolkit for Meta Ray-Ban Display interfaces for accessibility, focus/D-pad navigation, responsive layout, WebView rendering, performance, component states, route restoration, scroll boundaries, popup behavior,…

Build or review UI Toolkit for Meta Ray-Ban Display actions using Button, ButtonRail, ButtonGroup, ButtonDivider, QuickReplyButton, ActionHint, and the InputTextView built-in action. Use for horizontal actions, text submission, overflowing rails, anchors,…

Build or review UI Toolkit for Meta Ray-Ban Display text, icons, avatars, app badges, notification badges, tags, chips, container headers, ReadMoreTextView, TextSwitcher, and IconImage. Use for typography hierarchy, icon sources/tint, person or duo identity,…

Receive synchronized PCM audio frames through a Camera stream on iOS

Capture standalone high-quality photos from connected glasses on iOS

Stream, video frames, photo capture, resolution/frame rate configuration

Swift patterns, async/await, naming conventions, key types for DAT SDK iOS development

Use the Wearables DAT MCP server for live DAT documentation search with `search_dat_docs`, Muse Code, Claude Code, Codex, Cursor, and MCP Inspector

Common issues, Developer Mode, version compatibility, state machine diagnosis

Display capability setup, display-capable device selection, UI DSL, icons, buttons, images, and video playback

SDK setup, Swift Package Manager integration, Info.plist configuration, and first connection to Meta glasses

SDK setup, Gradle integration, AndroidManifest configuration, and first connection to Meta glasses

Receive synchronized PCM audio frames through a Camera stream on Android

Capture standalone high-quality photos from connected glasses on Android

Session and Stream capability setup, video frames, photo capture, resolution and frame rate configuration

Kotlin patterns, DatResult, session and capability conventions for DAT SDK Android development

Use the Wearables DAT MCP server for live DAT documentation search with `search_dat_docs`, Muse Code, Claude Code, Codex, Cursor, and MCP Inspector

Receive navigation, button, capture, and drag input events from connected glasses on Android

Use this whenever debugging an Android DAT app with local DAT Inspector MCP tools, live device events, Meta AI app/device boundary issues, permissions, registration, sessions, streaming, or user reports that the app cannot communicate with glasses.

Measure and speed up a Meta Ray-Ban Display webapp using Chrome DevTools Protocol only — no device required. Use when the user says the app is slow, takes too long to load or start, feels sluggish on glasses, when they ask how big the bundle is or how to make…

Create, redesign, or extend a web app for Meta Ray-Ban Display glasses. Use for application architecture, screens, routes, state, API-backed UI, persistence, offline behavior, or any product change; pair with ai-glasses-webapp-ui for toolkit setup and…

Make an existing Meta Ray-Ban Display web app controllable by the on-device assistant. Use when the wearer should operate the app by speaking to Meta AI, when the assistant should read or change app state, or for WebMCP, model context, tool registration, or…

Add a remote log sink and a passcode-gated web log portal to a webapp game, so logs from the game running on Meta Display Glasses can be read on a laptop. The glasses have no console and cannot be tethered to attach one, so the game POSTs batched log records…

Scaffold a new webapp game for Meta Display Glasses using Vite + TypeScript + Three.js + Vitest, with a renderer- and input-agnostic architecture. Supports both 2D and 3D games. Use when the user wants to start a glasses game, build a 2D or 3D game for smart…

Act as a demanding creative director for a game project — run a collaborative, milestone-structured iteration loop that holds a high quality bar and treats real playtesting as the ground truth. It surveys the game, presents a ranked slate of issues and lets…

Add Meta Ray-Ban Display glasses-specific sensors and input behavior: motion, orientation, compass, step detection, geolocation, neural-band activation/drag, D-pad game controls, or handwriting/voice text composition.

Validate and publish a finished Meta Ray-Ban Display glasses web app directly to Vercel production, confirm anonymous HTTPS access, and generate the Meta AI add-to-glasses QR code. No staging or passcode flow.

Comprehensive FBOSS code review with 11 parallel reviewers (5 generic + 6 FBOSS-specific). Covers reliability, engineering, code quality, silent failures, agent architecture, SAI/SDK, FSDB/thrift_cow, platform/config, testing, and cross-cutting design.…

FBOSS coding standards and patterns. Auto-loaded when writing code in fboss/ to catch architecture violations, SAI/SDK misuse, thrift_cow pitfalls, platform config errors, and testing gaps. For explicit multi-reviewer review, use /fboss-review instead.

Implement a new `fboss2-dev config <area> <attr> <value>` CLI command family mapping to `SwitchConfig` attributes. Figures out the correct action level (HITLESS / AGENT_WARMBOOT / AGENT_COLDBOOT), wires the handler through the full registration + build graph,…

Use when onboarding a new transceiver NPI end-to-end or partially — adding transceiver code, firmware, and/or conveyor nodes. Trigger phrases: new transceiver NPI, onboard transceiver, add firmware, conveyor nodes, HAL test node, link test config, new optic.…

Use when planning, implementing, or reviewing a new FBOSS hardware platform for wedge_agent, including PlatformType registration, platform descriptor and mapping inputs, generic SAI platform selection, ASIC traits, or exceptional platform-specific behavior.

Interactively plan, explain, and optionally execute FBOSS OSS Distro image workflows. Default to providing commands without running them; execute only when the user explicitly asks. Use whenever a user asks about the `fboss-image` CLI, distro manifests,…

Find and remove redundant FBOSS agent_hw_tests without losing coverage. Use when asked to reduce/combine/dedup HW tests, retire non-dataplane (set/get) tests where dataplane tests exist, or cut HW test runtime while keeping coverage. Report-first; applying…

Diagnose link flaps from wedge_agent and qsfp_service logs — determine software vs hardware root cause, point to evidence, suggest fixes or detection strategies

Monitor API health for a Meta app — check rate limits, call volume, and API deprecations. Use whenever a user asks whether their app is being throttled, is near its rate limits, how much of its call volume or quota is being used, or about deprecated Graph API…

Guide a developer through setting up a Meta API integration from scratch — discovers the right APIs, fetches setup guides, authentication requirements, permissions, and code examples. Use when the user wants to build with a specific Meta product (WhatsApp,…

Run a comprehensive health check on a Meta app — audits settings, security, compliance, app review status, rate limits, and API deprecations in one pass. Use when you want a full picture of an app's current state.

Prepare a Meta app for App Review — checks current status, outstanding requirements, granted privileges, and submission history. Use before submitting an app for review.

Check compliance status for a Meta app — surfaces open required actions, active violations, and recommendations with remediation guidance. Use to audit compliance posture or resolve compliance blockers.

Diagnose a Meta access token problem (expired, wrong scopes, wrong app, invalid) WITHOUT the token ever entering the agent or AI provider context. Guides the developer to inspect the token themselves via the Access Token Debugger web tool or the public…

Troubleshoot webhook issues for a Meta app — inspect active subscriptions, identify misconfiguration, and send test payloads to verify delivery. Use when webhooks aren't working as expected.

Search Meta developer documentation for API guides, references, and tutorials. Use when looking up how a Meta API works, finding integration guides, or exploring platform capabilities.

Run Pyrefly benchmarks locally via Buck or Cargo, including PyTorch real-world LSP benchmarks. Use when user asks to benchmark pyrefly performance, run pyrefly bench, compare cold start vs error propagation, or update PyTorch benchmark pin.

Interprets a pyrefly mypy_primer error differential. Use when a pyrefly change alters which errors are reported (a new or retyped diagnostic, a new error kind, or an inference change). Classifies added and removed errors as true positives or negatives…

Reviews a comma separated pyrefly diff according to the pyrefly review best practices.

Produces a scorecard evaluating a pyrefly change on correctness and quality.

Port a PyTorch model to use pyrefly's tensor shape type system (Tensor[[B, C, H, W]], Int[T]). Use this skill whenever the user wants to add shape annotations to a PyTorch model, type a model with tensor dimensions, port a model to use shape tracking, or…

Use when Pyrefly computes a wrong tensor shape (or is missing one that can't be expressed in a stub signature) and you need to add or fix a shape-DSL rule. Requires a Pyrefly checkout (fbsource or a clone); not usable from a pip/site-packages install.

Use when adding a new PyTorch model to Pyrefly's shape-tracking example corpus under tensor-shapes/pyrefly-torch-stubs/examples — i.e. importing a model as a tested, corpus-quality reference port. This is maintainer-facing fbsource work. For porting your own…

Guide for adding new JSI functionality to the JavaScript Interface (JSI) layer. Use when the user asks to add, create, or implement new methods or features in the JSI Runtime interface. Covers all required files across JSI core, Hermes implementation,…

Guide for regenerating the Hermes sandbox, the C files in API/hermes_sandbox/external that wasm2c produces from a wasm build of the VM, and for changing HermesSandboxRuntime.cpp, the JSI runtime on top of it. Use when the user asks to regenerate or update the…

Rules for writing and reviewing GC-safe C++ code in the Hermes VM runtime. Use when writing, modifying, or reviewing C++ runtime VM code that uses internal Hermes VM APIs (as opposed to code using JSI). This includes working with GC-managed types…

This skill should be used when the user wants to analyze hermesvm binary size changes across a range of commits. Use when the user mentions "binary size", "size analysis", "size regression", "size increase", or asks to measure how commits affect the hermesvm…

Use when needing to reorder, split, drop, or amend git commits that are not the top commit, without interactive editor access. Covers programmatic rebase via GIT_SEQUENCE_EDITOR, commit splitting with automated hunk selection, and metadata changes (author,…

Guide for adding a new IR instruction to the Hermes compiler. Use when the user asks to add, create, or define a new IR instruction (Inst/Instruction) in the Hermes intermediate representation. Covers all required files and the patterns for each.

Use when running, debugging, updating, or creating Pysa end-to-end integration tests. Use when taint analysis tests fail, when expected output files need updating, or when working with .models, .cg, .hofcg, .overrides files under…

Use when you need to understand the Pyre or Pysa codebase architecture, find where specific functionality is implemented, or navigate the source directory structure. Use when working on OCaml code, debugging type checking or taint analysis issues, or…

Use when creating commits or diffs to apply the correct title prefix, reviewer, and test plan based on the area of the codebase being changed.

Use when debugging a Pysa false negative (missing taint issue), comparing two Pysa output directories, or finding where taint flow is lost.

Use when reading, writing, or debugging Pysa JSON model output (.models files). Use when working with taint models that describe sources, sinks, TITO, sanitizers, or issues in JSON format.

How to structure code so that humans can review it. Use whenever you write or modify code (packages, scripts, tests, website), before writing it.

Create, update, check the CI of, or merge a meta/docusaurus pull request. Use before running `gh pr create`, pushing commits to an existing PR, reading its CI checks or bot comments, or merging it. Docusaurus maintainers only.

Prove how code behaves before reporting it. Use before claiming that a change works, fails or is needed, in particular on another platform than the one you run on (like Windows from macOS).

Add, remove or upgrade npm dependencies in the Docusaurus monorepo. Use before editing any `package.json` dependency field, running `pnpm add`/`pnpm remove`/`pnpm update`, or changing `pnpm-lock.yaml`.

Create a Mononoke server-side hook with 3-diff split (tests, wiring, implementation), unit tests, and integration tests

Locate Eden implementations and trace behavior across Sapling, EdenFS, and Mononoke when the relevant code path is not already known.

Add or review structured error logging in EdenFS daemon (C++) — the ErrorLogger / EdenErrorInfo system that feeds the edenfs_errors table. Use when writing a catch block or handling a boxed/async exception (folly::Try / exception_wrapper / .thenError),…

Triage systemd-managed EdenFS issues on Linux devservers and OnDemands. Use when investigating EdenFS service failures, unexpected restarts, systemctl errors, edenfs_upgrade/edenfs_restarter problems, or when a user reports EdenFS is down on a systemd-enabled…