How to reuse ANY integration check's results in a feature via the universal CheckResultsService (apps/api integration-platform). Use whenever a feature needs data produced by an integration check — "show 2FA status on People", "surface AWS S3 findings in X", "reuse a check's results", "per-user/per-resource results from a connected integration", "which integrations feed task T". Read this BEFORE writing your own IntegrationCheckResult / CheckRunRepository query — don't hand-roll it.
Ground truth for Firefox's internal chrome UI — the DOM structure (browser.xhtml) and built-in CSS that userChrome themes target. Use when writing or fixing textfox CSS and you need to know a real selector, element ID, attribute, or Firefox's own default styling — instead of guessing. Triggers: "what selector", "what element is X", "did this break", "firefox renamed/removed", "userChrome", "why doesn't this rule apply", "find the real DOM node", any time CSS targets Firefox internals. Always targets the LATEST Firefox release (the only version textfox supports).
Token-efficient map of the Downloader (bezzad/Downloader) .NET library plus its enforced C# code-style rules. Use this BEFORE grepping or reading broadly when working in this repo: locating the file that owns a behavior (downloads, chunks, redirects, resume, throttling, events, HTTP), or writing/editing C# so it matches house style. Read the named file directly instead of scanning.
Use when adding a new cmake.* command to CMake Tools. Touches package.json (contributes.commands), package.nls.json, src/extension.ts (funs array), and CHANGELOG.md. Triggers: "add command", "register command", "new command palette entry".
Use when adding a new cmake.* configuration setting. Touches package.json (contributes.configuration), package.nls.json, src/config.ts (interface + getter), docs/cmake-settings.md, and CHANGELOG.md. Triggers: "add setting", "new setting", "add configuration".
Use when writing or reviewing code that must work in both CMake Presets and Kits/Variants modes. Covers configure, build, test, environment, and generator paths. Triggers: "presets vs kits", "useCMakePresets", "works in both modes".
Build on-device AI features in React Native and Expo apps with React Native ExecuTorch. Use when adding AI to a mobile app without cloud dependencies — chatbots and assistants, image classification, object detection, OCR, semantic or instance segmentation, style transfer, image generation, pose estimation, speech-to-text, text-to-speech, voice activity detection, semantic search with embeddings, tokenization, privacy filtering / PII redaction, or vision-language image understanding. Also use when the user mentions offline AI, on-device ML, privacy-preserving AI, reducing cloud API cost or latency, running models locally on mobile, or downloading and managing ML models. Covers initExecutorch, every public hook (useLLM, useClassification, useObjectDetection, useOCR, useVerticalOCR, useSemanticSegmentation, useInstanceSegmentation, useStyleTransfer, useTextToImage, useImageEmbeddings, usePoseEstimation, useSpeechToText, useTextToSpeech, useVAD, useTextEmbeddings, useTokenizer, usePrivacyFilter, useExecutorchModule), tool calling, structured output, VLMs, model loading via Expo or bare resource-fetcher adapters, and error handling.