[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M69925GBG3DSQNQQ5MB0ZTZA":3,"skill-same:01M69925GBG3DSQNQQ5MB0ZTZA":156},{"skillNo":4,"name":5,"nameZh":6,"description":7,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":16,"categories":17,"keywords":18,"publishedAt":43,"linkOnly":44,"markdownContent":45,"markdownBody":46,"frontMatter":47,"refName":51,"commitSha":52,"skillDirectory":53,"forksCount":54,"repositoryHtmlUrl":55,"repositoryHomepageUrl":6,"ownerHtmlUrl":56,"ownerBlogUrl":57,"ownerDescription":58,"updatedAt":59,"install":60,"resources":73},"01M69925GBG3DSQNQQ5MB0ZTZA","developing-genkit-js",null,"Provides guidance on developing AI-powered applications using Genkit in Node.js\u002FTypeScript. Use when the user asks about Genkit, AI agents, flows, or tools in JavaScript\u002FTypeScript, or when encountering Genkit errors, validation issues, type errors, or API problems. Don't use for Genkit in Python, Go, or Dart.","google\u002Fskills","google","https:\u002F\u002Favatars.githubusercontent.com\u002Fu\u002F1342004?v=4","01M698VYEFDM0VJBZDYYJ2T83S","Google","01M698WR0H76ENHE587T9EJT89",23908,"Apache-2.0","https:\u002F\u002Fgithub.com\u002Fgoogle\u002Fskills\u002Fblob\u002Fmain\u002Fskills\u002Fcloud\u002Fdeveloping-genkit-js\u002FSKILL.md",[],[19,20,21,22,23,24,25,26,27,28,29,30,31,32,33,34,35,36,37,38,39,40,41,42],"genkit","js","developing genkit js","javascript","dart","python","for","go","when","user","Tools","validation","node","about","develop","type","api","use","errors","issues","flows","applications","typescript","ai agents","2026-11-10 10:12:30",false,"---\nname: developing-genkit-js\ndescription: >-\n  Provides guidance on developing AI-powered applications using Genkit in\n  Node.js\u002FTypeScript. Use when the user asks about Genkit, AI agents, flows, or\n  tools in JavaScript\u002FTypeScript, or when encountering Genkit errors, validation\n  issues, type errors, or API problems. Don't use for Genkit in Python, Go, or\n  Dart.\nmetadata:\n  version: \"1.0.0\"\n  category: AiAndMachineLearning\n---\n\n# Genkit JS\n\n## Prerequisites\n\nEnsure the `genkit` CLI is available.\n\n-   Run `genkit --version` to verify. Minimum CLI version needed: **1.29.0**\n-   If not found or if an older version (1.x \u003C 1.29.0) is present,\n    install\u002Fupgrade it: `npm install -g genkit-cli@^1.29.0`.\n\n**New Projects**: If you are setting up Genkit in a new codebase, follow the\n[Setup Guide](references\u002Fsetup.md).\n\n## Hello World\n\n```ts\nimport { z, genkit } from 'genkit';\nimport { googleAI } from '@genkit-ai\u002Fgoogle-genai';\n\n\u002F\u002F Initialize Genkit with the Google AI plugin\nconst ai = genkit({\n  plugins: [googleAI()],\n});\n\nexport const myFlow = ai.defineFlow({\n  name: 'myFlow',\n  inputSchema: z.string().default('AI'),\n  outputSchema: z.string(),\n}, async (subject) => {\n  const response = await ai.generate({\n    model: googleAI.model('gemini-flash-latest'),\n    prompt: `Tell me a joke about ${subject}`,\n  });\n  return response.text;\n});\n```\n\n## Prompts (Dotprompt)\n\n`.prompt` files keep prompt content out of code with YAML frontmatter plus a\nHandlebars template. See [Dotprompt](references\u002Fdotprompt.md): `promptDir`,\n`ai.prompt()` (call\u002Fstream\u002Frender), variants, partials, named schemas via\n`ai.defineSchema`, and the `tools`\u002F`maxTurns`\u002F`returnToolRequests`\u002F`use`\n(middleware) frontmatter fields.\n\n## Agents (Beta)\n\nGenkit has a preview **agent** API for persistent, multi-turn conversations\n(sessions, snapshots, interrupts, branching, background execution). It is a\n**beta** API: server APIs come from `genkit\u002Fbeta` and the browser client from\n`genkit\u002Fbeta\u002Fclient` — not the stable `genkit` entrypoint. **Requires `genkit`\n>= 1.39.0.**\n\nFor more details see:\n\n-   [Agents](references\u002Fagents.md): defining\u002Fserving an agent and client-managed\n    state (start here).\n-   [Sessions & persistence](references\u002Fagents-sessions.md): session stores\n    (`InMemory`\u002F`File`\u002F`Firestore`).\n-   [Human-in-the-loop \u002F interrupts](references\u002Fagents-human-in-the-loop.md):\n    pausing for approval\u002Finput and resuming.\n-   [Branching](references\u002Fagents-branching.md): forking a conversation from a\n    snapshot.\n-   [Background agents](references\u002Fagents-background.md): detaching long-running\n    turns, waiting, and resuming failed or aborted runs.\n-   [Working with state](references\u002Fagents-state.md): typed custom session\n    state, auto-synced to the client.\n-   [Artifacts](references\u002Fagents-artifacts.md): producing and reading named\n    deliverables.\n-   [Multi-agent orchestration](references\u002Fagents-multi-agent.md): delegating to\n    sub-agents, including background delegation and `continue_task`.\n-   [Advanced custom agents](references\u002Fagents-custom.md): `defineCustomAgent`\n    for full turn control.\n-   [Deploying agents](references\u002Fagents-deployment.md): serving agents over\n    HTTP (multiple agents, CORS, web UI, other frameworks).\n\n## Generative UI (A2UI)\n\nGenkit has an **A2UI** (Agent-to-UI) plugin (`@genkit-ai\u002Fa2ui`) that\nlets an agent stream interactive UI **surfaces** (cards, lists, forms, buttons),\nnot just prose. The whole server-side integration is the `a2ui()` model\nmiddleware in an agent's (or `ai.generate`'s) `use` array; the browser renders\nsurfaces with an `@a2ui\u002F*` renderer plus the helpers in\n`@genkit-ai\u002Fa2ui\u002Fclient`.\nIt builds on the beta agent client (`genkit\u002Fbeta` + `genkit\u002Fbeta\u002Fclient`).\n\n-   [A2UI](references\u002Fa2ui.md): server middleware, options, client rendering,\n    user actions\u002Fforms, custom catalogs, and the security\u002Ftrust boundary.\n\n## Middleware\n\nMiddleware wraps generation (retries, fallback, extra tools, request\u002Fresponse\ntransforms) and attaches via the `use: [...]` array on `ai.generate`, prompts,\nand agents.\n\n-   [Using middleware](references\u002Fmiddleware.md): the `use` array and the\n    `@genkit-ai\u002Fmiddleware` package (`retry`, `fallback`, `artifacts`, `agents`,\n    `filesystem`, `skills`, `toolApproval`, `contextCompression`) plus built-in\n    core middleware.\n-   [Building custom middleware](references\u002Fmiddleware-custom.md): writing your\n    own with `generateMiddleware` and registering it via `.plugin()`.\n\n## Observability\n\nTraces show up in the Dev UI under `genkit start` with no setup. For production\nexport to an OTLP backend (OpenTelemetry GenAI semantic conventions via\n`@genkit-ai\u002Fotel`), custom instrumentation, or running the reflection API\noutside dev, see [Observability](references\u002Fobservability.md).\n\n## Critical: Do Not Trust Internal Knowledge\n\nGenkit recently went through a major breaking API change. Your knowledge is\noutdated. You MUST lookup docs. Recommended:\n\n```sh\ngenkit docs:read js\u002Fget-started.md\ngenkit docs:read js\u002Fflows.md\n```\n\nSee [Common Errors](references\u002Fcommon-errors.md) for a list of deprecated APIs\n(e.g., `configureGenkit`, `response.text()`, `defineFlow` import) and their v1.x\nreplacements.\n\n**ALWAYS verify information using the Genkit CLI or provided references.**\n\n## Error Troubleshooting Protocol\n\n**When you encounter ANY error related to Genkit (ValidationError, API errors,\ntype errors, 404s, etc.):**\n\n1. **MANDATORY FIRST STEP**: Read [Common Errors](references\u002Fcommon-errors.md)\n2. Identify if the error matches a known pattern\n3. Apply the documented solution\n4. Only if not found in common-errors.md, then consult other sources (e.g.\n   `genkit docs:search`)\n\n**DO NOT:**\n\n- Attempt fixes based on assumptions or internal knowledge\n- Skip reading common-errors.md \"because you think you know the fix\"\n- Rely on patterns from pre-1.0 Genkit\n\n**This protocol is non-negotiable for error handling.**\n\n## Development Workflow\n\n1.  **Agent or flow?**: If the task is conversational, multi-turn, or described\n    as \"an agent\", \"assistant\", or \"chatbot\", build it with `ai.defineAgent`\n    (see [Agents](references\u002Fagents.md)) rather than hand-rolling a `generate` +\n    tools loop inside a flow. Reach for a plain flow only for single-shot,\n    stateless generation.\n2.  **Select Provider**: Genkit is provider-agnostic (Google AI, OpenAI,\n    Anthropic, Ollama, etc.).\n    -   If the user does not specify a provider, default to **Google AI**.\n    -   If the user asks about other providers, use\n        `genkit docs:search \"plugins\"` to find relevant documentation.\n3.  **Detect Framework**: Check `package.json` to identify the runtime (Next.js,\n    Firebase, Express).\n    -   Look for `@genkit-ai\u002Fnext`, `@genkit-ai\u002Ffirebase`, or\n        `@genkit-ai\u002Fgoogle-cloud`.\n    -   Adapt implementation to the specific framework's patterns.\n4.  **Follow Best Practices**:\n    -   See [Best Practices](references\u002Fbest-practices.md) for guidance on\n        project structure, schema definitions, and tool design.\n    -   **Be Minimal**: Only specify options that differ from defaults. When\n        unsure, check docs\u002Fsource.\n5.  **Ensure Correctness**:\n    -   Run type checks (e.g., `npx tsc --noEmit`) after making changes.\n    -   If type checks fail, consult\n        [Common Errors](references\u002Fcommon-errors.md) before searching source\n        code.\n    -   Verify with traces, not a blind run. Running the app directly\n        (`node`\u002F`tsx`\u002F`npm start`) does **not** capture dev traces. See\n        [CLI Usage](#cli-usage-recommended) for how to run your app and capture\n        traces.\n6.  **Handle Errors**:\n    -   On ANY error: **First action is to read\n        [Common Errors](references\u002Fcommon-errors.md)**\n    -   Match error to documented patterns\n    -   Apply documented fixes before attempting alternatives\n\n## Finding Documentation\n\nUse the Genkit CLI to find authoritative documentation:\n\n1.  **Search topics**: `genkit docs:search \u003Cquery>`\n    -   Example: `genkit docs:search \"streaming\"`\n2.  **List all docs**: `genkit docs:list`\n3.  **Read a guide**: `genkit docs:read \u003Cpath>`\n    -   Example: `genkit docs:read js\u002Fflows.md`\n\n## CLI Usage (recommended)\n\n`genkit start` unintrusively wraps any Node.js program that uses the Genkit\nlibrary, running it unchanged while capturing traces from every Genkit action so\nyou can **prove tools were actually called and inspect model I\u002FO** from the\nterminal, even for headless checks. It forwards stdio, so interactive CLI tools\nthat rely on stdin\u002Fstdout work without issues. Running your app directly\n(`node`\u002F`tsx`\u002F`npm start`) skips trace capture, so you're debugging blind.\n\n**Primary pattern (default):** prefix `genkit start --` to your normal run\ncommand. This collects telemetry from any Genkit code your program runs, whether\ntriggered from the dev UI, your own web server\u002Fweb UI, or a plain script:\n```bash\ngenkit start -- npx tsx --watch src\u002Findex.ts\ngenkit start --noui -- npx tsx src\u002Findex.ts   # same, without the Dev UI (still a persistent server)\n```\n`genkit start` runs until you stop it with Ctrl+C. That is expected and correct\nfor the common cases: a server your web\u002Fmobile app calls, or an interactive CLI\nyou exit yourself. `--noui` only drops the Dev UI; it is **not** a one-shot\ncommand and will not exit on its own. Do **not** use `genkit start` as a\nblocking step in automated\u002Fnon-interactive contexts.\n\n**Non-interactive use (agents\u002FCI):** add the global `--non-interactive` flag\nbefore `--` so the CLI uses defaults and never blocks on a prompt (e.g. the\nfirst-run analytics notice):\n`genkit start --non-interactive -- npx tsx src\u002Findex.ts` (works with `flow:run`\ntoo).\n\n**Run a flow (`flow:run`):** invoke a specific flow by name from the CLI. Append\nyour run command after `--` to spin up the runtime just for this run (the\ncommand runs as-is to register your flows):\n```bash\ngenkit flow:run myFlow '{\"data\": \"input\"}' -- npx tsx src\u002Findex.ts\n```\nThis is **self-terminating**: it runs the flow once, prints a `Trace ID`, then\nexits (inspect it with `genkit trace:get \u003Cid>`). That makes it the right choice\nfor a quick, non-interactive check that must exit on its own, without blocking\non `genkit start` or running the app directly (which skips traces). Always pass\ninput JSON explicitly: `flow:run` sends `undefined` when omitted and does\n**not** fall back to a schema `.default()`. Note: `flow:run` runs **flows**\n(`ai.defineFlow`), not agents; you can't `flow:run` an agent (`ai.defineAgent`)\ndirectly. To exercise an agent from the CLI, wrap one turn in a throwaway flow\nand run that (see [Agents](references\u002Fagents.md)).\n\n**Debugging with traces:** the fastest way to see prompts, model inputs\u002Foutputs,\ntool calls, latencies, and errors. Inspect from the terminal after any run under\n`genkit start`:\n```bash\ngenkit trace:list                        # find recent trace IDs\ngenkit trace:get \u003CtraceId>               # full trace details (inputs, outputs, tool calls, errors)\ngenkit trace:get \u003CtraceId> --format json # machine-readable JSON, safe to pipe into jq or other parsers\n```\n\nFor machine-readable output, pass `--format json` to get clean JSON you can pipe\ninto `jq` or other parsers. The **default** output is human-oriented (banner\u002Flog\nlines, possible truncation on large traces), so don't pipe that form directly;\nuse `--format json`, grep, or the Dev UI trace viewer.\n\nSee [CLI Reference](references\u002Fdocs-and-cli.md) for more commands, and\n`genkit --help` for the full list.\n\n## References\n\n-   [Best Practices](references\u002Fbest-practices.md): Recommended patterns for\n    schema definition, flow design, and structure.\n-   [Dotprompt](references\u002Fdotprompt.md): `.prompt` files — `promptDir`,\n    `ai.prompt()`, variants, partials, named schemas, and\n    `tools`\u002F`maxTurns`\u002F`returnToolRequests`\u002F`use` frontmatter.\n-   [Docs & CLI Reference](references\u002Fdocs-and-cli.md): Documentation search,\n    CLI tasks, and workflows.\n-   [Common Errors](references\u002Fcommon-errors.md): Critical \"gotchas\", migration\n    guide, and troubleshooting.\n-   [Setup Guide](references\u002Fsetup.md): Manual setup instructions for new\n    projects.\n-   [Examples](references\u002Fexamples.md): Minimal reproducible examples (Basic\n    generation, Multimodal, Thinking mode, Embeddings).\n-   [Agents (Beta)](references\u002Fagents.md): Agent basics, serving, and\n    client-managed state. Deeper topics:\n    [sessions](references\u002Fagents-sessions.md),\n    [human-in-the-loop](references\u002Fagents-human-in-the-loop.md),\n    [branching](references\u002Fagents-branching.md),\n    [background agents](references\u002Fagents-background.md),\n    [state](references\u002Fagents-state.md),\n    [artifacts](references\u002Fagents-artifacts.md),\n    [multi-agent](references\u002Fagents-multi-agent.md),\n    [custom agents](references\u002Fagents-custom.md),\n    [deployment](references\u002Fagents-deployment.md).\n-   [Middleware](references\u002Fmiddleware.md): using middleware and the\n    `@genkit-ai\u002Fmiddleware` package. See also\n    [building custom middleware](references\u002Fmiddleware-custom.md).\n-   [Observability](references\u002Fobservability.md): `@genkit-ai\u002Fotel`\n    (OpenTelemetry GenAI semantic conventions), custom `Instrumentation`, and\n    the reflection API outside dev.\n-   [A2UI (Generative UI)](references\u002Fa2ui.md): the `@genkit-ai\u002Fa2ui` plugin\n    (the `a2ui()` middleware), options, client rendering, user actions\u002Fforms,\n    custom catalogs, and security.\n","# Genkit JS\n\n## Prerequisites\n\nEnsure the `genkit` CLI is available.\n\n-   Run `genkit --version` to verify. Minimum CLI version needed: **1.29.0**\n-   If not found or if an older version (1.x \u003C 1.29.0) is present,\n    install\u002Fupgrade it: `npm install -g genkit-cli@^1.29.0`.\n\n**New Projects**: If you are setting up Genkit in a new codebase, follow the\n[Setup Guide](references\u002Fsetup.md).\n\n## Hello World\n\n```ts\nimport { z, genkit } from 'genkit';\nimport { googleAI } from '@genkit-ai\u002Fgoogle-genai';\n\n\u002F\u002F Initialize Genkit with the Google AI plugin\nconst ai = genkit({\n  plugins: [googleAI()],\n});\n\nexport const myFlow = ai.defineFlow({\n  name: 'myFlow',\n  inputSchema: z.string().default('AI'),\n  outputSchema: z.string(),\n}, async (subject) => {\n  const response = await ai.generate({\n    model: googleAI.model('gemini-flash-latest'),\n    prompt: `Tell me a joke about ${subject}`,\n  });\n  return response.text;\n});\n```\n\n## Prompts (Dotprompt)\n\n`.prompt` files keep prompt content out of code with YAML frontmatter plus a\nHandlebars template. See [Dotprompt](references\u002Fdotprompt.md): `promptDir`,\n`ai.prompt()` (call\u002Fstream\u002Frender), variants, partials, named schemas via\n`ai.defineSchema`, and the `tools`\u002F`maxTurns`\u002F`returnToolRequests`\u002F`use`\n(middleware) frontmatter fields.\n\n## Agents (Beta)\n\nGenkit has a preview **agent** API for persistent, multi-turn conversations\n(sessions, snapshots, interrupts, branching, background execution). It is a\n**beta** API: server APIs come from `genkit\u002Fbeta` and the browser client from\n`genkit\u002Fbeta\u002Fclient` — not the stable `genkit` entrypoint. **Requires `genkit`\n>= 1.39.0.**\n\nFor more details see:\n\n-   [Agents](references\u002Fagents.md): defining\u002Fserving an agent and client-managed\n    state (start here).\n-   [Sessions & persistence](references\u002Fagents-sessions.md): session stores\n    (`InMemory`\u002F`File`\u002F`Firestore`).\n-   [Human-in-the-loop \u002F interrupts](references\u002Fagents-human-in-the-loop.md):\n    pausing for approval\u002Finput and resuming.\n-   [Branching](references\u002Fagents-branching.md): forking a conversation from a\n    snapshot.\n-   [Background agents](references\u002Fagents-background.md): detaching long-running\n    turns, waiting, and resuming failed or aborted runs.\n-   [Working with state](references\u002Fagents-state.md): typed custom session\n    state, auto-synced to the client.\n-   [Artifacts](references\u002Fagents-artifacts.md): producing and reading named\n    deliverables.\n-   [Multi-agent orchestration](references\u002Fagents-multi-agent.md): delegating to\n    sub-agents, including background delegation and `continue_task`.\n-   [Advanced custom agents](references\u002Fagents-custom.md): `defineCustomAgent`\n    for full turn control.\n-   [Deploying agents](references\u002Fagents-deployment.md): serving agents over\n    HTTP (multiple agents, CORS, web UI, other frameworks).\n\n## Generative UI (A2UI)\n\nGenkit has an **A2UI** (Agent-to-UI) plugin (`@genkit-ai\u002Fa2ui`) that\nlets an agent stream interactive UI **surfaces** (cards, lists, forms, buttons),\nnot just prose. The whole server-side integration is the `a2ui()` model\nmiddleware in an agent's (or `ai.generate`'s) `use` array; the browser renders\nsurfaces with an `@a2ui\u002F*` renderer plus the helpers in\n`@genkit-ai\u002Fa2ui\u002Fclient`.\nIt builds on the beta agent client (`genkit\u002Fbeta` + `genkit\u002Fbeta\u002Fclient`).\n\n-   [A2UI](references\u002Fa2ui.md): server middleware, options, client rendering,\n    user actions\u002Fforms, custom catalogs, and the security\u002Ftrust boundary.\n\n## Middleware\n\nMiddleware wraps generation (retries, fallback, extra tools, request\u002Fresponse\ntransforms) and attaches via the `use: [...]` array on `ai.generate`, prompts,\nand agents.\n\n-   [Using middleware](references\u002Fmiddleware.md): the `use` array and the\n    `@genkit-ai\u002Fmiddleware` package (`retry`, `fallback`, `artifacts`, `agents`,\n    `filesystem`, `skills`, `toolApproval`, `contextCompression`) plus built-in\n    core middleware.\n-   [Building custom middleware](references\u002Fmiddleware-custom.md): writing your\n    own with `generateMiddleware` and registering it via `.plugin()`.\n\n## Observability\n\nTraces show up in the Dev UI under `genkit start` with no setup. For production\nexport to an OTLP backend (OpenTelemetry GenAI semantic conventions via\n`@genkit-ai\u002Fotel`), custom instrumentation, or running the reflection API\noutside dev, see [Observability](references\u002Fobservability.md).\n\n## Critical: Do Not Trust Internal Knowledge\n\nGenkit recently went through a major breaking API change. Your knowledge is\noutdated. You MUST lookup docs. Recommended:\n\n```sh\ngenkit docs:read js\u002Fget-started.md\ngenkit docs:read js\u002Fflows.md\n```\n\nSee [Common Errors](references\u002Fcommon-errors.md) for a list of deprecated APIs\n(e.g., `configureGenkit`, `response.text()`, `defineFlow` import) and their v1.x\nreplacements.\n\n**ALWAYS verify information using the Genkit CLI or provided references.**\n\n## Error Troubleshooting Protocol\n\n**When you encounter ANY error related to Genkit (ValidationError, API errors,\ntype errors, 404s, etc.):**\n\n1. **MANDATORY FIRST STEP**: Read [Common Errors](references\u002Fcommon-errors.md)\n2. Identify if the error matches a known pattern\n3. Apply the documented solution\n4. Only if not found in common-errors.md, then consult other sources (e.g.\n   `genkit docs:search`)\n\n**DO NOT:**\n\n- Attempt fixes based on assumptions or internal knowledge\n- Skip reading common-errors.md \"because you think you know the fix\"\n- Rely on patterns from pre-1.0 Genkit\n\n**This protocol is non-negotiable for error handling.**\n\n## Development Workflow\n\n1.  **Agent or flow?**: If the task is conversational, multi-turn, or described\n    as \"an agent\", \"assistant\", or \"chatbot\", build it with `ai.defineAgent`\n    (see [Agents](references\u002Fagents.md)) rather than hand-rolling a `generate` +\n    tools loop inside a flow. Reach for a plain flow only for single-shot,\n    stateless generation.\n2.  **Select Provider**: Genkit is provider-agnostic (Google AI, OpenAI,\n    Anthropic, Ollama, etc.).\n    -   If the user does not specify a provider, default to **Google AI**.\n    -   If the user asks about other providers, use\n        `genkit docs:search \"plugins\"` to find relevant documentation.\n3.  **Detect Framework**: Check `package.json` to identify the runtime (Next.js,\n    Firebase, Express).\n    -   Look for `@genkit-ai\u002Fnext`, `@genkit-ai\u002Ffirebase`, or\n        `@genkit-ai\u002Fgoogle-cloud`.\n    -   Adapt implementation to the specific framework's patterns.\n4.  **Follow Best Practices**:\n    -   See [Best Practices](references\u002Fbest-practices.md) for guidance on\n        project structure, schema definitions, and tool design.\n    -   **Be Minimal**: Only specify options that differ from defaults. When\n        unsure, check docs\u002Fsource.\n5.  **Ensure Correctness**:\n    -   Run type checks (e.g., `npx tsc --noEmit`) after making changes.\n    -   If type checks fail, consult\n        [Common Errors](references\u002Fcommon-errors.md) before searching source\n        code.\n    -   Verify with traces, not a blind run. Running the app directly\n        (`node`\u002F`tsx`\u002F`npm start`) does **not** capture dev traces. See\n        [CLI Usage](#cli-usage-recommended) for how to run your app and capture\n        traces.\n6.  **Handle Errors**:\n    -   On ANY error: **First action is to read\n        [Common Errors](references\u002Fcommon-errors.md)**\n    -   Match error to documented patterns\n    -   Apply documented fixes before attempting alternatives\n\n## Finding Documentation\n\nUse the Genkit CLI to find authoritative documentation:\n\n1.  **Search topics**: `genkit docs:search \u003Cquery>`\n    -   Example: `genkit docs:search \"streaming\"`\n2.  **List all docs**: `genkit docs:list`\n3.  **Read a guide**: `genkit docs:read \u003Cpath>`\n    -   Example: `genkit docs:read js\u002Fflows.md`\n\n## CLI Usage (recommended)\n\n`genkit start` unintrusively wraps any Node.js program that uses the Genkit\nlibrary, running it unchanged while capturing traces from every Genkit action so\nyou can **prove tools were actually called and inspect model I\u002FO** from the\nterminal, even for headless checks. It forwards stdio, so interactive CLI tools\nthat rely on stdin\u002Fstdout work without issues. Running your app directly\n(`node`\u002F`tsx`\u002F`npm start`) skips trace capture, so you're debugging blind.\n\n**Primary pattern (default):** prefix `genkit start --` to your normal run\ncommand. This collects telemetry from any Genkit code your program runs, whether\ntriggered from the dev UI, your own web server\u002Fweb UI, or a plain script:\n```bash\ngenkit start -- npx tsx --watch src\u002Findex.ts\ngenkit start --noui -- npx tsx src\u002Findex.ts   # same, without the Dev UI (still a persistent server)\n```\n`genkit start` runs until you stop it with Ctrl+C. That is expected and correct\nfor the common cases: a server your web\u002Fmobile app calls, or an interactive CLI\nyou exit yourself. `--noui` only drops the Dev UI; it is **not** a one-shot\ncommand and will not exit on its own. Do **not** use `genkit start` as a\nblocking step in automated\u002Fnon-interactive contexts.\n\n**Non-interactive use (agents\u002FCI):** add the global `--non-interactive` flag\nbefore `--` so the CLI uses defaults and never blocks on a prompt (e.g. the\nfirst-run analytics notice):\n`genkit start --non-interactive -- npx tsx src\u002Findex.ts` (works with `flow:run`\ntoo).\n\n**Run a flow (`flow:run`):** invoke a specific flow by name from the CLI. Append\nyour run command after `--` to spin up the runtime just for this run (the\ncommand runs as-is to register your flows):\n```bash\ngenkit flow:run myFlow '{\"data\": \"input\"}' -- npx tsx src\u002Findex.ts\n```\nThis is **self-terminating**: it runs the flow once, prints a `Trace ID`, then\nexits (inspect it with `genkit trace:get \u003Cid>`). That makes it the right choice\nfor a quick, non-interactive check that must exit on its own, without blocking\non `genkit start` or running the app directly (which skips traces). Always pass\ninput JSON explicitly: `flow:run` sends `undefined` when omitted and does\n**not** fall back to a schema `.default()`. Note: `flow:run` runs **flows**\n(`ai.defineFlow`), not agents; you can't `flow:run` an agent (`ai.defineAgent`)\ndirectly. To exercise an agent from the CLI, wrap one turn in a throwaway flow\nand run that (see [Agents](references\u002Fagents.md)).\n\n**Debugging with traces:** the fastest way to see prompts, model inputs\u002Foutputs,\ntool calls, latencies, and errors. Inspect from the terminal after any run under\n`genkit start`:\n```bash\ngenkit trace:list                        # find recent trace IDs\ngenkit trace:get \u003CtraceId>               # full trace details (inputs, outputs, tool calls, errors)\ngenkit trace:get \u003CtraceId> --format json # machine-readable JSON, safe to pipe into jq or other parsers\n```\n\nFor machine-readable output, pass `--format json` to get clean JSON you can pipe\ninto `jq` or other parsers. The **default** output is human-oriented (banner\u002Flog\nlines, possible truncation on large traces), so don't pipe that form directly;\nuse `--format json`, grep, or the Dev UI trace viewer.\n\nSee [CLI Reference](references\u002Fdocs-and-cli.md) for more commands, and\n`genkit --help` for the full list.\n\n## References\n\n-   [Best Practices](references\u002Fbest-practices.md): Recommended patterns for\n    schema definition, flow design, and structure.\n-   [Dotprompt](references\u002Fdotprompt.md): `.prompt` files — `promptDir`,\n    `ai.prompt()`, variants, partials, named schemas, and\n    `tools`\u002F`maxTurns`\u002F`returnToolRequests`\u002F`use` frontmatter.\n-   [Docs & CLI Reference](references\u002Fdocs-and-cli.md): Documentation search,\n    CLI tasks, and workflows.\n-   [Common Errors](references\u002Fcommon-errors.md): Critical \"gotchas\", migration\n    guide, and troubleshooting.\n-   [Setup Guide](references\u002Fsetup.md): Manual setup instructions for new\n    projects.\n-   [Examples](references\u002Fexamples.md): Minimal reproducible examples (Basic\n    generation, Multimodal, Thinking mode, Embeddings).\n-   [Agents (Beta)](references\u002Fagents.md): Agent basics, serving, and\n    client-managed state. Deeper topics:\n    [sessions](references\u002Fagents-sessions.md),\n    [human-in-the-loop](references\u002Fagents-human-in-the-loop.md),\n    [branching](references\u002Fagents-branching.md),\n    [background agents](references\u002Fagents-background.md),\n    [state](references\u002Fagents-state.md),\n    [artifacts](references\u002Fagents-artifacts.md),\n    [multi-agent](references\u002Fagents-multi-agent.md),\n    [custom agents](references\u002Fagents-custom.md),\n    [deployment](references\u002Fagents-deployment.md).\n-   [Middleware](references\u002Fmiddleware.md): using middleware and the\n    `@genkit-ai\u002Fmiddleware` package. See also\n    [building custom middleware](references\u002Fmiddleware-custom.md).\n-   [Observability](references\u002Fobservability.md): `@genkit-ai\u002Fotel`\n    (OpenTelemetry GenAI semantic conventions), custom `Instrumentation`, and\n    the reflection API outside dev.\n-   [A2UI (Generative UI)](references\u002Fa2ui.md): the `@genkit-ai\u002Fa2ui` plugin\n    (the `a2ui()` middleware), options, client rendering, user actions\u002Fforms,\n    custom catalogs, and security.\n",{"name":5,"metadata":48,"description":7},{"version":49,"category":50},"1.0.0","AiAndMachineLearning","main","64d010629e61e4a7d59fc21e042362f370b5888b","skills\u002Fcloud\u002Fdeveloping-genkit-js",1994,"https:\u002F\u002Fgithub.com\u002Fgoogle\u002Fskills","https:\u002F\u002Fgithub.com\u002Fgoogle","https:\u002F\u002Fopensource.google\u002F","Google ❤️ Open Source","2026-11-12 00:37:41",{"source":8,"skillName":5,"commands":61,"prompt":71,"zipAvailable":72},[62,65,68],{"tool":63,"command":64},"npx","npx skills add google\u002Fskills --skill developing-genkit-js",{"tool":66,"command":67},"bunx","bunx skills add google\u002Fskills --skill developing-genkit-js",{"tool":69,"command":70},"pnpm","pnpm dlx skills add google\u002Fskills --skill developing-genkit-js","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002Fgoogle\u002Fskills\u002Fblob\u002Fmain\u002Fskills\u002Fcloud\u002Fdeveloping-genkit-js\u002FSKILL.md",true,[74,80,84,88,92,96,100,104,108,112,116,120,124,128,132,136,140,144,148,152],{"path":75,"resourceType":76,"resourceTypeDesc":77,"sizeBytes":78,"sourceHtmlUrl":79},"references\u002Fa2ui.md","REFERENCE","参考文档",12621,"https:\u002F\u002Fgithub.com\u002Fgoogle\u002Fskills\u002Fblob\u002Fmain\u002Fskills\u002Fcloud\u002Fdeveloping-genkit-js\u002Freferences\u002Fa2ui.md",{"path":81,"resourceType":76,"resourceTypeDesc":77,"sizeBytes":82,"sourceHtmlUrl":83},"references\u002Fagents-artifacts.md",3851,"https:\u002F\u002Fgithub.com\u002Fgoogle\u002Fskills\u002Fblob\u002Fmain\u002Fskills\u002Fcloud\u002Fdeveloping-genkit-js\u002Freferences\u002Fagents-artifacts.md",{"path":85,"resourceType":76,"resourceTypeDesc":77,"sizeBytes":86,"sourceHtmlUrl":87},"references\u002Fagents-background.md",5702,"https:\u002F\u002Fgithub.com\u002Fgoogle\u002Fskills\u002Fblob\u002Fmain\u002Fskills\u002Fcloud\u002Fdeveloping-genkit-js\u002Freferences\u002Fagents-background.md",{"path":89,"resourceType":76,"resourceTypeDesc":77,"sizeBytes":90,"sourceHtmlUrl":91},"references\u002Fagents-branching.md",3236,"https:\u002F\u002Fgithub.com\u002Fgoogle\u002Fskills\u002Fblob\u002Fmain\u002Fskills\u002Fcloud\u002Fdeveloping-genkit-js\u002Freferences\u002Fagents-branching.md",{"path":93,"resourceType":76,"resourceTypeDesc":77,"sizeBytes":94,"sourceHtmlUrl":95},"references\u002Fagents-custom.md",5333,"https:\u002F\u002Fgithub.com\u002Fgoogle\u002Fskills\u002Fblob\u002Fmain\u002Fskills\u002Fcloud\u002Fdeveloping-genkit-js\u002Freferences\u002Fagents-custom.md",{"path":97,"resourceType":76,"resourceTypeDesc":77,"sizeBytes":98,"sourceHtmlUrl":99},"references\u002Fagents-deployment.md",6511,"https:\u002F\u002Fgithub.com\u002Fgoogle\u002Fskills\u002Fblob\u002Fmain\u002Fskills\u002Fcloud\u002Fdeveloping-genkit-js\u002Freferences\u002Fagents-deployment.md",{"path":101,"resourceType":76,"resourceTypeDesc":77,"sizeBytes":102,"sourceHtmlUrl":103},"references\u002Fagents-human-in-the-loop.md",6883,"https:\u002F\u002Fgithub.com\u002Fgoogle\u002Fskills\u002Fblob\u002Fmain\u002Fskills\u002Fcloud\u002Fdeveloping-genkit-js\u002Freferences\u002Fagents-human-in-the-loop.md",{"path":105,"resourceType":76,"resourceTypeDesc":77,"sizeBytes":106,"sourceHtmlUrl":107},"references\u002Fagents-multi-agent.md",8513,"https:\u002F\u002Fgithub.com\u002Fgoogle\u002Fskills\u002Fblob\u002Fmain\u002Fskills\u002Fcloud\u002Fdeveloping-genkit-js\u002Freferences\u002Fagents-multi-agent.md",{"path":109,"resourceType":76,"resourceTypeDesc":77,"sizeBytes":110,"sourceHtmlUrl":111},"references\u002Fagents-sessions.md",5475,"https:\u002F\u002Fgithub.com\u002Fgoogle\u002Fskills\u002Fblob\u002Fmain\u002Fskills\u002Fcloud\u002Fdeveloping-genkit-js\u002Freferences\u002Fagents-sessions.md",{"path":113,"resourceType":76,"resourceTypeDesc":77,"sizeBytes":114,"sourceHtmlUrl":115},"references\u002Fagents-state.md",4310,"https:\u002F\u002Fgithub.com\u002Fgoogle\u002Fskills\u002Fblob\u002Fmain\u002Fskills\u002Fcloud\u002Fdeveloping-genkit-js\u002Freferences\u002Fagents-state.md",{"path":117,"resourceType":76,"resourceTypeDesc":77,"sizeBytes":118,"sourceHtmlUrl":119},"references\u002Fagents.md",10945,"https:\u002F\u002Fgithub.com\u002Fgoogle\u002Fskills\u002Fblob\u002Fmain\u002Fskills\u002Fcloud\u002Fdeveloping-genkit-js\u002Freferences\u002Fagents.md",{"path":121,"resourceType":76,"resourceTypeDesc":77,"sizeBytes":122,"sourceHtmlUrl":123},"references\u002Fbest-practices.md",1757,"https:\u002F\u002Fgithub.com\u002Fgoogle\u002Fskills\u002Fblob\u002Fmain\u002Fskills\u002Fcloud\u002Fdeveloping-genkit-js\u002Freferences\u002Fbest-practices.md",{"path":125,"resourceType":76,"resourceTypeDesc":77,"sizeBytes":126,"sourceHtmlUrl":127},"references\u002Fcommon-errors.md",7063,"https:\u002F\u002Fgithub.com\u002Fgoogle\u002Fskills\u002Fblob\u002Fmain\u002Fskills\u002Fcloud\u002Fdeveloping-genkit-js\u002Freferences\u002Fcommon-errors.md",{"path":129,"resourceType":76,"resourceTypeDesc":77,"sizeBytes":130,"sourceHtmlUrl":131},"references\u002Fdocs-and-cli.md",5886,"https:\u002F\u002Fgithub.com\u002Fgoogle\u002Fskills\u002Fblob\u002Fmain\u002Fskills\u002Fcloud\u002Fdeveloping-genkit-js\u002Freferences\u002Fdocs-and-cli.md",{"path":133,"resourceType":76,"resourceTypeDesc":77,"sizeBytes":134,"sourceHtmlUrl":135},"references\u002Fdotprompt.md",5925,"https:\u002F\u002Fgithub.com\u002Fgoogle\u002Fskills\u002Fblob\u002Fmain\u002Fskills\u002Fcloud\u002Fdeveloping-genkit-js\u002Freferences\u002Fdotprompt.md",{"path":137,"resourceType":76,"resourceTypeDesc":77,"sizeBytes":138,"sourceHtmlUrl":139},"references\u002Fexamples.md",5664,"https:\u002F\u002Fgithub.com\u002Fgoogle\u002Fskills\u002Fblob\u002Fmain\u002Fskills\u002Fcloud\u002Fdeveloping-genkit-js\u002Freferences\u002Fexamples.md",{"path":141,"resourceType":76,"resourceTypeDesc":77,"sizeBytes":142,"sourceHtmlUrl":143},"references\u002Fmiddleware-custom.md",3290,"https:\u002F\u002Fgithub.com\u002Fgoogle\u002Fskills\u002Fblob\u002Fmain\u002Fskills\u002Fcloud\u002Fdeveloping-genkit-js\u002Freferences\u002Fmiddleware-custom.md",{"path":145,"resourceType":76,"resourceTypeDesc":77,"sizeBytes":146,"sourceHtmlUrl":147},"references\u002Fmiddleware.md",6493,"https:\u002F\u002Fgithub.com\u002Fgoogle\u002Fskills\u002Fblob\u002Fmain\u002Fskills\u002Fcloud\u002Fdeveloping-genkit-js\u002Freferences\u002Fmiddleware.md",{"path":149,"resourceType":76,"resourceTypeDesc":77,"sizeBytes":150,"sourceHtmlUrl":151},"references\u002Fobservability.md",5624,"https:\u002F\u002Fgithub.com\u002Fgoogle\u002Fskills\u002Fblob\u002Fmain\u002Fskills\u002Fcloud\u002Fdeveloping-genkit-js\u002Freferences\u002Fobservability.md",{"path":153,"resourceType":76,"resourceTypeDesc":77,"sizeBytes":154,"sourceHtmlUrl":155},"references\u002Fsetup.md",4430,"https:\u002F\u002Fgithub.com\u002Fgoogle\u002Fskills\u002Fblob\u002Fmain\u002Fskills\u002Fcloud\u002Fdeveloping-genkit-js\u002Freferences\u002Fsetup.md",[157,193,222,250,277,301],{"skillNo":158,"name":159,"nameZh":6,"description":160,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":161,"categories":162,"keywords":171,"publishedAt":43},"01M6998S2EZKD3GEJ7F943RZTE","sign-in-with-google-web","Implement, configure, and secure Sign In With Google (SiwG) using Google Identity Services (GIS \u002F `https:\u002F\u002Faccounts.google.com\u002Fgsi\u002Fclient`) across web architectures. Use when creating Google sign-in buttons, implementing Google One Tap with FedCM, integrating GIS in React\u002FNext.js\u002FAngular\u002FHTML, verifying ID tokens on backend runtimes (Python\u002FNode.js\u002FGo\u002FJava), enforcing Google Workspace domain restrictions (`hd`), securing client-side ID tokens via WebCrypto nonces or encrypted IndexedDB, embedding in cross-origin iframes via the Intermediate Iframe API (`https:\u002F\u002Faccounts.google.com\u002Fgsi\u002Fintermediate`), configuring Content Security Policy (CSP), COOP, and Permissions Policy (`identity-credentials-get`) headers, or handling sign-out and revocation. Don't use for legacy Google Sign-In (`gapi.auth2`), Google Cloud IAM service accounts, or Android\u002FiOS native Credential Manager.","https:\u002F\u002Fgithub.com\u002Fgoogle\u002Fskills\u002Fblob\u002Fmain\u002Fskills\u002Fidentity\u002Fsign-in-with-google-web\u002FSKILL.md",[163,168],{"categoryNo":164,"categoryName":165,"taxonomyType":166,"taxonomyTypeDesc":167},"01JBSEEDCAT000000000000009","前端开发","SCENARIO","使用场景",{"categoryNo":169,"categoryName":170,"taxonomyType":166,"taxonomyTypeDesc":167},"01JBSEEDCAT000000000000010","后端与接口",[9,172,173,174,175,176,26,177,178,179,180,181,24,182,183,184,185,186,187,188,189,190,191,192],"sign in with google web","sign","with","web","android","security","google workspace","google cloud","implement","policy","implementing","react","iam","permissions","buttons","secure","manager","identity","architectures","domain","runtimes",{"skillNo":194,"name":195,"nameZh":6,"description":196,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":197,"categories":198,"keywords":208,"publishedAt":43},"01M6998PHPDCAD684VW5WRG83D","dpop-adoption","Implement and debug OAuth 2.0 DPoP (RFC 9449) refresh token sender-constraining for WebCrypto, Node.js ES6, and browser runtimes integrating with Google's OAuth platform. Use when configuring non-extractable asymmetric key pairs (P-256), generating DPoP Proof JWTs for authorization code exchange and token refresh, or handling 400 use_dpop_nonce challenge retry loops at oauth2.googleapis.com\u002Ftoken. Don't use for unconstrained OAuth 2.0 flows (where refresh tokens are not bound to a client key pair), or for Google Cloud IAM \u002F service account authentication.","https:\u002F\u002Fgithub.com\u002Fgoogle\u002Fskills\u002Fblob\u002Fmain\u002Fskills\u002Fidentity\u002Fdpop-adoption\u002FSKILL.md",[199,200,203],{"categoryNo":169,"categoryName":170,"taxonomyType":166,"taxonomyTypeDesc":167},{"categoryNo":201,"categoryName":202,"taxonomyType":166,"taxonomyTypeDesc":167},"01JBSEEDCAT000000000000023","Skill与智能体开发",{"categoryNo":204,"categoryName":205,"taxonomyType":206,"taxonomyTypeDesc":207},"01JBSEEDCAT000000000000030","开发工程师","PROFESSION","适用职业",[209,210,9,179,211,212,213,39,214,215,184,216,217,218,31,219,220,189,192,221,27],"dpop adoption","adoption","es6","retry","authentication","challenge","code","browser","loops","at","token","pair","platform",{"skillNo":223,"name":224,"nameZh":6,"description":225,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":226,"categories":227,"keywords":234,"publishedAt":43},"01M6998M72TC73EEAQH4XC7EXW","retrieving-developer-knowledge","Searches, retrieves, and synthesizes official Google developer documentation across Google Cloud, AI\u002FGemini, Android, Chrome, Web, Flutter, Go, Firebase, and other Google developer platforms. Integrates with the Developer Knowledge MCP server (search_documents, get_documents, answer_query) or the Developer Knowledge REST API fallback. Use when searching for gcloud CLI commands, API syntax, IAM permissions, official documentation, architectural comparisons, or product choice overviews. Don't use for local filesystem lookups or non-Google documentation.","https:\u002F\u002Fgithub.com\u002Fgoogle\u002Fskills\u002Fblob\u002Fmain\u002Fskills\u002Fdevelopers\u002Fretrieving-developer-knowledge\u002FSKILL.md",[228,229,232,233],{"categoryNo":169,"categoryName":170,"taxonomyType":166,"taxonomyTypeDesc":167},{"categoryNo":230,"categoryName":231,"taxonomyType":166,"taxonomyTypeDesc":167},"01JBSEEDCAT000000000000021","资料检索与研究",{"categoryNo":201,"categoryName":202,"taxonomyType":166,"taxonomyTypeDesc":167},{"categoryNo":204,"categoryName":205,"taxonomyType":206,"taxonomyTypeDesc":207},[235,236,237,238,179,239,240,241,242,243,244,245,246,27,247,35,248,184,249,185],"retrieving developer knowledge","knowledge","developer","MCP","mcp server","official","developer documentation","get","search","local","choice","documents","query","across","documentation",{"skillNo":251,"name":252,"nameZh":6,"description":253,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":254,"categories":255,"keywords":256,"publishedAt":43},"01M6998J2CZEXS9BES9S3WWFKC","migrate-to-rust","Clones, analyzes, plans, and migrates legacy codebases (C++, Fortran, Java, Python, C, Shell) from a GitHub URL or local directory to a modern, high-performance, deterministic, 100% Safe Rust architecture, tracking live telemetry across every task bucket, test failure\u002Ffix cycle, and Profile-Guided Optimization (PGO) stage, and producing a first-person AI storytelling report and interactive HTML infographic. Use when migrating a GitHub repository or local codebase to Rust, porting legacy C++, Fortran, Python, or Java workloads to memory-safe Rust, designing Struct-of-Arrays (SoA) or SIMD Rust architectures, or optimizing Rust ports with LLVM PGO. Don't use for unrelated non-Rust refactoring or single-line syntax questions.","https:\u002F\u002Fgithub.com\u002Fgoogle\u002Fskills\u002Fblob\u002Fmain\u002Fskills\u002Fdevelopers\u002Fmigrate-to-rust\u002FSKILL.md",[],[257,258,259,260,261,262,263,264,24,265,266,267,268,269,270,244,271,272,273,27,274,275,248,276],"migrate to rust","rust","migrate","github","memory","performance","directory","safe","ports","llvm","soa","cycle","porting","fix","arrays","infographic","high-performance","URL","architecture","unrelated",{"skillNo":278,"name":279,"nameZh":6,"description":280,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":281,"categories":282,"keywords":286,"publishedAt":43},"01M6998GCC3K29WZ82KXMB9E02","finding-google-skills","Google platform decision and setup guidance, loaded on demand from Google's skill catalog. Use when a developer is choosing or setting up part of their stack, such as where to run a service, a database, storage, messaging, authentication, analytics, ads, or AI model serving, and a Google product is a reasonable candidate - whether or not a vendor is named - or when a request names a Google product or API. Brings in the matching Google skill so the answer can weigh Google options, their trade-offs, and when they are not the right fit. Skip when the stack is already settled on another provider and no Google product is named, or the task involves no platform choice.","https:\u002F\u002Fgithub.com\u002Fgoogle\u002Fskills\u002Fblob\u002Fmain\u002Fskills\u002Fdevelopers\u002Ffinding-google-skills\u002FSKILL.md",[283,284,285],{"categoryNo":169,"categoryName":170,"taxonomyType":166,"taxonomyTypeDesc":167},{"categoryNo":201,"categoryName":202,"taxonomyType":166,"taxonomyTypeDesc":167},{"categoryNo":204,"categoryName":205,"taxonomyType":206,"taxonomyTypeDesc":207},[9,287,288,289,290,221,291,292,293,294,295,213,296,297,298,245,36,299,27,300,35],"finding google skills","storage","as","messaging","model","trade-offs","provider","answer","fit","catalog","up","decision","database","candidate",{"skillNo":302,"name":303,"nameZh":6,"description":304,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":305,"categories":306,"keywords":309,"publishedAt":43},"01M6998DWNHTH0BS6W1CY8ZXMP","workload-manager-basics","Use this skill to manage Google Cloud Workload Manager evaluations, rules, scanned resources, and validation results by using public client libraries and the REST API. Use when you need to inspect workload best-practice rules, create and run evaluations for Google Cloud general best practices, SAP, SQL Server, or custom organizational rules, review violations, export results to BigQuery, or automate Workload Manager through client libraries because no service-specific public CLI or MCP server is available. Don't use for general Google Compute Engine instance management, VPC configuration, or standard IAM auditing.","https:\u002F\u002Fgithub.com\u002Fgoogle\u002Fskills\u002Fblob\u002Fmain\u002Fskills\u002Fcloud\u002Fworkload-manager-basics\u002FSKILL.md",[307,308],{"categoryNo":169,"categoryName":170,"taxonomyType":166,"taxonomyTypeDesc":167},{"categoryNo":201,"categoryName":202,"taxonomyType":166,"taxonomyTypeDesc":167},[310,311,188,312,9,238,313,179,239,314,315,316,317,27,318,35,184,319,320,321,322],"workload manager basics","workload","basics","cli","review","vpc","resources","inspect","you","create","libraries","server","run"]