{"owner":"Azure","repo":"azure-sdk-for-js","hasSkills":true,"totalSkillsCount":5,"totalTokensCount":2749,"categories":["root-instruction","copilot-instructions","mcp-config","marketplace","plugin-manifest"],"hasMcp":true,"mcpConfig":{"mcpServers":{"azure-sdk-for-js":{"command":"npx","args":["-y","@modelcontextprotocol/server-azure-sdk-for-js"]}}},"found":["AGENTS.md",".github/copilot-instructions.md",".cursor/mcp.json",".claude-plugin/marketplace.json",".claude-plugin/plugin.json"],"skills":{"AGENTS.md":"# AGENTS.md\n\nResolver for agent-facing guidance in this repo. Each section points\nat the canonical location — content lives there, not here. If you find\nyourself duplicating a rule across docs, the duplicate is wrong.\n\n## What is this repo\n\nTypeScript / JavaScript SDKs for Azure services. Monorepo managed by\n`pnpm` + Turborepo.\n\n- Packages live under `sdk/*` (e.g. `sdk/web-pubsub/web-pubsub`).\n- Shared tools in `common/tools/*` (eslint plugin, dev-tool, warp).\n- Engineering tooling under `eng/*`; deep-dive docs under `documentation/*`.\n- Contributor onboarding: see `README.md` and `CONTRIBUTING.md`.\n\n## Where to find guidance\n\n| Task / topic                                                            | Where to look                                                                 |\n| ----------------------------------------------------------------------- | ----------------------------------------------------------------------------- |\n| Build / test / lint / format / release a package                        | `.github/skills/sdk-workflow/SKILL.md`                                        |\n| Add a feature to a package under `sdk/`                                 | `.github/skills/find-package-skill/SKILL.md` (check the registry FIRST)       |\n| Generate or regenerate SDK code from TypeSpec                           | `.github/skills/azsdk-common-generate-sdk-locally/SKILL.md`                   |\n| Release / publish a package                                             | `.github/skills/azsdk-common-sdk-release/SKILL.md`                            |\n| Management SDK release rotation / PR approval                           | `documentation/mgmt-release-rotation-runbook.md`                             |\n| Resolve APIView feedback                                                | `.github/skills/azsdk-common-apiview-feedback-resolution/SKILL.md`            |\n| Troubleshoot a CI / pipeline failure                                    | `.github/skills/azsdk-common-pipeline-troubleshooting/SKILL.md`               |\n| Audit or register ADO pipelines for `ci.yml` files                      | `.github/skills/ado-pipeline-audit/SKILL.md`                                  |\n| Create a new package-specific skill                                     | `.github/skills/create-package-skill/SKILL.md`                                |\n| Copilot code review (CCR)                                               | `.github/skills/code-review/SKILL.md` (routes to canonical reviewer guidance) |\n| Review criteria (architecture, perf, security, deps, tests, docs, mgmt) | `.github/instructions/reviewer/*.instructions.md`                             |\n| Test framework, recorder lifecycle, asset-sync                          | `documentation/Quickstart-on-how-to-write-tests.md`                           |\n| TypeSpec / codegen workflow                                             | `documentation/Generate-code-from-TypeSpec.md`                                |\n| Linting rules and troubleshooting                                       | `documentation/linting.md`                                                    |\n| Dependency management                                                   | `documentation/dependency-management.md`                                      |\n| Authoritative API design guidelines                                     | https://azure.github.io/azure-sdk/typescript_design.html                      |\n| Other deep dives                                                        | `documentation/` (browse the directory)                                       |\n\n> **Before pushing any code change** — including changes outside `sdk/` — run\n> the checks defined by CI for the affected package locally. Package managers\n> and scripts vary for non-workspace `eng/*` tools. See\n> `.github/skills/sdk-workflow/SKILL.md` § \"Before you push\".\n\nThe skills above carry workflow guidance the rest of this repo's\ncontributor docs assume agents will find. Read them on demand — don't\nload them all up front.\n\n## Hard rules\n\nRules agents have violated in the past and which the eval suite at\n`eng/agent-evals/` actively regression-tests. Each one is here because\nit has no static-analysis enforcement today (otherwise it would be a\nlint rule or CI check, not an eval).\n\n- Build a single package with `pnpm turbo build --filter=<pkg>... --token 1`.\n  Do **not** use `npm run build` at the package level — turbo workspace\n  linking breaks it.\n- Do **not** edit files under `<package>/generated/`. Those are\n  regenerated on every `tsp-client` run. Customizations go in `src/`\n  or via TypeSpec decorators. See `documentation/modular-customization.md`.\n- `snippets.spec.ts` files are documentation source, **not** real tests.\n  Don't refactor, delete, or \"fix\" them as part of test cleanup. They're\n  consumed by `dev-tool run update-snippets` to keep README code blocks\n  in sync.\n- Options bags on client methods extend `OperationOptions` from a core\n  package (`@azure-rest/core-client`, `@azure/core-client`, or\n  `@azure/core-rest-pipeline` depending on the package lineage).\n- Do **not** disable `@azure/eslint-plugin-azure-sdk` rules with\n  `eslint-disable` directives. Fix the underlying issue.\n- Do **not** hand-roll long-running operations. Use the LRO primitives\n  in `@azure/core-lro` and `@azure/core-client`. Review\n  `sdk/core/core-lro` for the latest patterns.\n- Always consult `.github/skills/find-package-skill/SKILL.md` (and the\n  relevant package-specific `SKILL.md` if one is registered there)\n  **before** modifying a package under `sdk/`.\n- When pushing new commits to an **existing** pull request, re-check that\n  the PR description still matches the current changes. If iterating has\n  made it inaccurate or incomplete, update the description in the same\n  step — don't leave a stale description behind.\n\n## Where new guidance belongs\n\nRules for the agent that maintains this file:\n\n- A rule that applies to **all** package work → here, \"Hard rules\"\n  section, **only if** it's eval-covered. Don't add hard rules without\n  a corresponding eval in `eng/agent-evals/` — the eval is what\n  prevents the rule from silently drifting.\n- A workflow that's specific to one task type (build, generate,\n  release, ...) → a new or existing skill in `.github/skills/`.\n- Reviewer-only behavior → `.github/instructions/reviewer/`.\n- Deep-dive how-to or tutorial → a new file under `documentation/`,\n  then a row in the \"Where to find guidance\" table above pointing at\n  it.\n- Package-specific tribal knowledge → a package-owned skill at\n  `sdk/<svc>/<pkg>/.github/skills/<name>/SKILL.md`.\n- Contributor-facing prose (workflows, prerequisites, setup) →\n  `CONTRIBUTING.md`, not here. AGENTS.md is for agent-routing only.\n\nIf a fact would belong in two places, pick the more-specific one. Link\nfrom the less-specific to the more-specific, don't copy.\n\n<!-- BEGIN:turborepo-agent-rules -->\n\n# This is NOT the Turborepo you know\n\nTurborepo configuration, task behavior, and CLI commands can vary between installed versions and may differ from your training data. Resolve the `turbo` package from this file's directory or relevant workspace; in monorepos, it may not be visible from the repository root. For example, run `node -p \"require.resolve('turbo/package.json')\"` from a workspace that depends on `turbo`.\n\nRead `docs/README.md` inside that installed package first, then read the relevant pages from its `docs/` directory before changing Turborepo configuration or commands. Heed deprecation notices. These bundled docs match the installed package version and are available without network access.\n\nThis block is written and re-added by `turbo` before repository-scoped commands when an AI agent is detected. In the Turborepo source repository, its template is defined in `crates/turborepo-cli/src/cli/agent_guidance.rs`. Removing the managed block while updates are enabled means a later qualifying invocation will add it again. Set `\"agentGuidance\": false` in the root `turbo.json` or `turbo.jsonc` to opt out; this does not remove an existing block. Keep the block committed with your work to avoid an uncommitted change on the next agent invocation.\n<!-- END:turborepo-agent-rules -->\n",".github/copilot-instructions.md":"# Repository guidance has moved\n\nAgent-facing guidance for this repository now lives in\n[`AGENTS.md`](../AGENTS.md) at the repository root. It acts as a\n**resolver**: each topic points at its canonical home (skills under\n`.github/skills/`, reviewer instructions under\n`.github/instructions/reviewer/`, and deep-dive docs under\n`documentation/`) so the same rule isn't duplicated across files.\n\nStart there. This file is intentionally kept as a lightweight redirect\nso tooling and pipelines that reference `.github/copilot-instructions.md`\nby path continue to resolve during the transition.\n",".cursor/mcp.json":"# Model Context Protocol (MCP) Configuration\n\nPath: `.cursor/mcp.json`\n\n[View Raw Content on GitHub](https://raw.githubusercontent.com/Azure/azure-sdk-for-js/HEAD/.cursor/mcp.json)",".claude-plugin/marketplace.json":"# Claude Plugin Marketplace Catalog\n\nPath: `.claude-plugin/marketplace.json`\n\n[View Raw Content on GitHub](https://raw.githubusercontent.com/Azure/azure-sdk-for-js/HEAD/.claude-plugin/marketplace.json)",".claude-plugin/plugin.json":"# claude-plugin Plugin Manifest\n\nPath: `.claude-plugin/plugin.json`\n\n[View Raw Content on GitHub](https://raw.githubusercontent.com/Azure/azure-sdk-for-js/HEAD/.claude-plugin/plugin.json)"},"files":{"AGENTS.md":"# AGENTS.md\n\nResolver for agent-facing guidance in this repo. Each section points\nat the canonical location — content lives there, not here. If you find\nyourself duplicating a rule across docs, the duplicate is wrong.\n\n## What is this repo\n\nTypeScript / JavaScript SDKs for Azure services. Monorepo managed by\n`pnpm` + Turborepo.\n\n- Packages live under `sdk/*` (e.g. `sdk/web-pubsub/web-pubsub`).\n- Shared tools in `common/tools/*` (eslint plugin, dev-tool, warp).\n- Engineering tooling under `eng/*`; deep-dive docs under `documentation/*`.\n- Contributor onboarding: see `README.md` and `CONTRIBUTING.md`.\n\n## Where to find guidance\n\n| Task / topic                                                            | Where to look                                                                 |\n| ----------------------------------------------------------------------- | ----------------------------------------------------------------------------- |\n| Build / test / lint / format / release a package                        | `.github/skills/sdk-workflow/SKILL.md`                                        |\n| Add a feature to a package under `sdk/`                                 | `.github/skills/find-package-skill/SKILL.md` (check the registry FIRST)       |\n| Generate or regenerate SDK code from TypeSpec                           | `.github/skills/azsdk-common-generate-sdk-locally/SKILL.md`                   |\n| Release / publish a package                                             | `.github/skills/azsdk-common-sdk-release/SKILL.md`                            |\n| Management SDK release rotation / PR approval                           | `documentation/mgmt-release-rotation-runbook.md`                             |\n| Resolve APIView feedback                                                | `.github/skills/azsdk-common-apiview-feedback-resolution/SKILL.md`            |\n| Troubleshoot a CI / pipeline failure                                    | `.github/skills/azsdk-common-pipeline-troubleshooting/SKILL.md`               |\n| Audit or register ADO pipelines for `ci.yml` files                      | `.github/skills/ado-pipeline-audit/SKILL.md`                                  |\n| Create a new package-specific skill                                     | `.github/skills/create-package-skill/SKILL.md`                                |\n| Copilot code review (CCR)                                               | `.github/skills/code-review/SKILL.md` (routes to canonical reviewer guidance) |\n| Review criteria (architecture, perf, security, deps, tests, docs, mgmt) | `.github/instructions/reviewer/*.instructions.md`                             |\n| Test framework, recorder lifecycle, asset-sync                          | `documentation/Quickstart-on-how-to-write-tests.md`                           |\n| TypeSpec / codegen workflow                                             | `documentation/Generate-code-from-TypeSpec.md`                                |\n| Linting rules and troubleshooting                                       | `documentation/linting.md`                                                    |\n| Dependency management                                                   | `documentation/dependency-management.md`                                      |\n| Authoritative API design guidelines                                     | https://azure.github.io/azure-sdk/typescript_design.html                      |\n| Other deep dives                                                        | `documentation/` (browse the directory)                                       |\n\n> **Before pushing any code change** — including changes outside `sdk/` — run\n> the checks defined by CI for the affected package locally. Package managers\n> and scripts vary for non-workspace `eng/*` tools. See\n> `.github/skills/sdk-workflow/SKILL.md` § \"Before you push\".\n\nThe skills above carry workflow guidance the rest of this repo's\ncontributor docs assume agents will find. Read them on demand — don't\nload them all up front.\n\n## Hard rules\n\nRules agents have violated in the past and which the eval suite at\n`eng/agent-evals/` actively regression-tests. Each one is here because\nit has no static-analysis enforcement today (otherwise it would be a\nlint rule or CI check, not an eval).\n\n- Build a single package with `pnpm turbo build --filter=<pkg>... --token 1`.\n  Do **not** use `npm run build` at the package level — turbo workspace\n  linking breaks it.\n- Do **not** edit files under `<package>/generated/`. Those are\n  regenerated on every `tsp-client` run. Customizations go in `src/`\n  or via TypeSpec decorators. See `documentation/modular-customization.md`.\n- `snippets.spec.ts` files are documentation source, **not** real tests.\n  Don't refactor, delete, or \"fix\" them as part of test cleanup. They're\n  consumed by `dev-tool run update-snippets` to keep README code blocks\n  in sync.\n- Options bags on client methods extend `OperationOptions` from a core\n  package (`@azure-rest/core-client`, `@azure/core-client`, or\n  `@azure/core-rest-pipeline` depending on the package lineage).\n- Do **not** disable `@azure/eslint-plugin-azure-sdk` rules with\n  `eslint-disable` directives. Fix the underlying issue.\n- Do **not** hand-roll long-running operations. Use the LRO primitives\n  in `@azure/core-lro` and `@azure/core-client`. Review\n  `sdk/core/core-lro` for the latest patterns.\n- Always consult `.github/skills/find-package-skill/SKILL.md` (and the\n  relevant package-specific `SKILL.md` if one is registered there)\n  **before** modifying a package under `sdk/`.\n- When pushing new commits to an **existing** pull request, re-check that\n  the PR description still matches the current changes. If iterating has\n  made it inaccurate or incomplete, update the description in the same\n  step — don't leave a stale description behind.\n\n## Where new guidance belongs\n\nRules for the agent that maintains this file:\n\n- A rule that applies to **all** package work → here, \"Hard rules\"\n  section, **only if** it's eval-covered. Don't add hard rules without\n  a corresponding eval in `eng/agent-evals/` — the eval is what\n  prevents the rule from silently drifting.\n- A workflow that's specific to one task type (build, generate,\n  release, ...) → a new or existing skill in `.github/skills/`.\n- Reviewer-only behavior → `.github/instructions/reviewer/`.\n- Deep-dive how-to or tutorial → a new file under `documentation/`,\n  then a row in the \"Where to find guidance\" table above pointing at\n  it.\n- Package-specific tribal knowledge → a package-owned skill at\n  `sdk/<svc>/<pkg>/.github/skills/<name>/SKILL.md`.\n- Contributor-facing prose (workflows, prerequisites, setup) →\n  `CONTRIBUTING.md`, not here. AGENTS.md is for agent-routing only.\n\nIf a fact would belong in two places, pick the more-specific one. Link\nfrom the less-specific to the more-specific, don't copy.\n\n<!-- BEGIN:turborepo-agent-rules -->\n\n# This is NOT the Turborepo you know\n\nTurborepo configuration, task behavior, and CLI commands can vary between installed versions and may differ from your training data. Resolve the `turbo` package from this file's directory or relevant workspace; in monorepos, it may not be visible from the repository root. For example, run `node -p \"require.resolve('turbo/package.json')\"` from a workspace that depends on `turbo`.\n\nRead `docs/README.md` inside that installed package first, then read the relevant pages from its `docs/` directory before changing Turborepo configuration or commands. Heed deprecation notices. These bundled docs match the installed package version and are available without network access.\n\nThis block is written and re-added by `turbo` before repository-scoped commands when an AI agent is detected. In the Turborepo source repository, its template is defined in `crates/turborepo-cli/src/cli/agent_guidance.rs`. Removing the managed block while updates are enabled means a later qualifying invocation will add it again. Set `\"agentGuidance\": false` in the root `turbo.json` or `turbo.jsonc` to opt out; this does not remove an existing block. Keep the block committed with your work to avoid an uncommitted change on the next agent invocation.\n<!-- END:turborepo-agent-rules -->\n",".github/copilot-instructions.md":"# Repository guidance has moved\n\nAgent-facing guidance for this repository now lives in\n[`AGENTS.md`](../AGENTS.md) at the repository root. It acts as a\n**resolver**: each topic points at its canonical home (skills under\n`.github/skills/`, reviewer instructions under\n`.github/instructions/reviewer/`, and deep-dive docs under\n`documentation/`) so the same rule isn't duplicated across files.\n\nStart there. This file is intentionally kept as a lightweight redirect\nso tooling and pipelines that reference `.github/copilot-instructions.md`\nby path continue to resolve during the transition.\n",".cursor/mcp.json":"# Model Context Protocol (MCP) Configuration\n\nPath: `.cursor/mcp.json`\n\n[View Raw Content on GitHub](https://raw.githubusercontent.com/Azure/azure-sdk-for-js/HEAD/.cursor/mcp.json)",".claude-plugin/marketplace.json":"# Claude Plugin Marketplace Catalog\n\nPath: `.claude-plugin/marketplace.json`\n\n[View Raw Content on GitHub](https://raw.githubusercontent.com/Azure/azure-sdk-for-js/HEAD/.claude-plugin/marketplace.json)",".claude-plugin/plugin.json":"# claude-plugin Plugin Manifest\n\nPath: `.claude-plugin/plugin.json`\n\n[View Raw Content on GitHub](https://raw.githubusercontent.com/Azure/azure-sdk-for-js/HEAD/.claude-plugin/plugin.json)"},"items":[{"name":"AGENTS.md","path":"AGENTS.md","rawUrl":"https://raw.githubusercontent.com/Azure/azure-sdk-for-js/HEAD/AGENTS.md","title":"AI Agent Protocol & Instructions","category":"root-instruction","format":"markdown","content":"# AGENTS.md\n\nResolver for agent-facing guidance in this repo. Each section points\nat the canonical location — content lives there, not here. If you find\nyourself duplicating a rule across docs, the duplicate is wrong.\n\n## What is this repo\n\nTypeScript / JavaScript SDKs for Azure services. Monorepo managed by\n`pnpm` + Turborepo.\n\n- Packages live under `sdk/*` (e.g. `sdk/web-pubsub/web-pubsub`).\n- Shared tools in `common/tools/*` (eslint plugin, dev-tool, warp).\n- Engineering tooling under `eng/*`; deep-dive docs under `documentation/*`.\n- Contributor onboarding: see `README.md` and `CONTRIBUTING.md`.\n\n## Where to find guidance\n\n| Task / topic                                                            | Where to look                                                                 |\n| ----------------------------------------------------------------------- | ----------------------------------------------------------------------------- |\n| Build / test / lint / format / release a package                        | `.github/skills/sdk-workflow/SKILL.md`                                        |\n| Add a feature to a package under `sdk/`                                 | `.github/skills/find-package-skill/SKILL.md` (check the registry FIRST)       |\n| Generate or regenerate SDK code from TypeSpec                           | `.github/skills/azsdk-common-generate-sdk-locally/SKILL.md`                   |\n| Release / publish a package                                             | `.github/skills/azsdk-common-sdk-release/SKILL.md`                            |\n| Management SDK release rotation / PR approval                           | `documentation/mgmt-release-rotation-runbook.md`                             |\n| Resolve APIView feedback                                                | `.github/skills/azsdk-common-apiview-feedback-resolution/SKILL.md`            |\n| Troubleshoot a CI / pipeline failure                                    | `.github/skills/azsdk-common-pipeline-troubleshooting/SKILL.md`               |\n| Audit or register ADO pipelines for `ci.yml` files                      | `.github/skills/ado-pipeline-audit/SKILL.md`                                  |\n| Create a new package-specific skill                                     | `.github/skills/create-package-skill/SKILL.md`                                |\n| Copilot code review (CCR)                                               | `.github/skills/code-review/SKILL.md` (routes to canonical reviewer guidance) |\n| Review criteria (architecture, perf, security, deps, tests, docs, mgmt) | `.github/instructions/reviewer/*.instructions.md`                             |\n| Test framework, recorder lifecycle, asset-sync                          | `documentation/Quickstart-on-how-to-write-tests.md`                           |\n| TypeSpec / codegen workflow                                             | `documentation/Generate-code-from-TypeSpec.md`                                |\n| Linting rules and troubleshooting                                       | `documentation/linting.md`                                                    |\n| Dependency management                                                   | `documentation/dependency-management.md`                                      |\n| Authoritative API design guidelines                                     | https://azure.github.io/azure-sdk/typescript_design.html                      |\n| Other deep dives                                                        | `documentation/` (browse the directory)                                       |\n\n> **Before pushing any code change** — including changes outside `sdk/` — run\n> the checks defined by CI for the affected package locally. Package managers\n> and scripts vary for non-workspace `eng/*` tools. See\n> `.github/skills/sdk-workflow/SKILL.md` § \"Before you push\".\n\nThe skills above carry workflow guidance the rest of this repo's\ncontributor docs assume agents will find. Read them on demand — don't\nload them all up front.\n\n## Hard rules\n\nRules agents have violated in the past and which the eval suite at\n`eng/agent-evals/` actively regression-tests. Each one is here because\nit has no static-analysis enforcement today (otherwise it would be a\nlint rule or CI check, not an eval).\n\n- Build a single package with `pnpm turbo build --filter=<pkg>... --token 1`.\n  Do **not** use `npm run build` at the package level — turbo workspace\n  linking breaks it.\n- Do **not** edit files under `<package>/generated/`. Those are\n  regenerated on every `tsp-client` run. Customizations go in `src/`\n  or via TypeSpec decorators. See `documentation/modular-customization.md`.\n- `snippets.spec.ts` files are documentation source, **not** real tests.\n  Don't refactor, delete, or \"fix\" them as part of test cleanup. They're\n  consumed by `dev-tool run update-snippets` to keep README code blocks\n  in sync.\n- Options bags on client methods extend `OperationOptions` from a core\n  package (`@azure-rest/core-client`, `@azure/core-client`, or\n  `@azure/core-rest-pipeline` depending on the package lineage).\n- Do **not** disable `@azure/eslint-plugin-azure-sdk` rules with\n  `eslint-disable` directives. Fix the underlying issue.\n- Do **not** hand-roll long-running operations. Use the LRO primitives\n  in `@azure/core-lro` and `@azure/core-client`. Review\n  `sdk/core/core-lro` for the latest patterns.\n- Always consult `.github/skills/find-package-skill/SKILL.md` (and the\n  relevant package-specific `SKILL.md` if one is registered there)\n  **before** modifying a package under `sdk/`.\n- When pushing new commits to an **existing** pull request, re-check that\n  the PR description still matches the current changes. If iterating has\n  made it inaccurate or incomplete, update the description in the same\n  step — don't leave a stale description behind.\n\n## Where new guidance belongs\n\nRules for the agent that maintains this file:\n\n- A rule that applies to **all** package work → here, \"Hard rules\"\n  section, **only if** it's eval-covered. Don't add hard rules without\n  a corresponding eval in `eng/agent-evals/` — the eval is what\n  prevents the rule from silently drifting.\n- A workflow that's specific to one task type (build, generate,\n  release, ...) → a new or existing skill in `.github/skills/`.\n- Reviewer-only behavior → `.github/instructions/reviewer/`.\n- Deep-dive how-to or tutorial → a new file under `documentation/`,\n  then a row in the \"Where to find guidance\" table above pointing at\n  it.\n- Package-specific tribal knowledge → a package-owned skill at\n  `sdk/<svc>/<pkg>/.github/skills/<name>/SKILL.md`.\n- Contributor-facing prose (workflows, prerequisites, setup) →\n  `CONTRIBUTING.md`, not here. AGENTS.md is for agent-routing only.\n\nIf a fact would belong in two places, pick the more-specific one. Link\nfrom the less-specific to the more-specific, don't copy.\n\n<!-- BEGIN:turborepo-agent-rules -->\n\n# This is NOT the Turborepo you know\n\nTurborepo configuration, task behavior, and CLI commands can vary between installed versions and may differ from your training data. Resolve the `turbo` package from this file's directory or relevant workspace; in monorepos, it may not be visible from the repository root. For example, run `node -p \"require.resolve('turbo/package.json')\"` from a workspace that depends on `turbo`.\n\nRead `docs/README.md` inside that installed package first, then read the relevant pages from its `docs/` directory before changing Turborepo configuration or commands. Heed deprecation notices. These bundled docs match the installed package version and are available without network access.\n\nThis block is written and re-added by `turbo` before repository-scoped commands when an AI agent is detected. In the Turborepo source repository, its template is defined in `crates/turborepo-cli/src/cli/agent_guidance.rs`. Removing the managed block while updates are enabled means a later qualifying invocation will add it again. Set `\"agentGuidance\": false` in the root `turbo.json` or `turbo.jsonc` to opt out; this does not remove an existing block. Keep the block committed with your work to avoid an uncommitted change on the next agent invocation.\n<!-- END:turborepo-agent-rules -->\n","isInternal":false,"tokens":1723,"sizeBytes":8251},{"name":"copilot-instructions.md","path":".github/copilot-instructions.md","rawUrl":"https://raw.githubusercontent.com/Azure/azure-sdk-for-js/HEAD/.github/copilot-instructions.md","title":"GitHub Copilot Instructions","category":"copilot-instructions","format":"markdown","content":"# Repository guidance has moved\n\nAgent-facing guidance for this repository now lives in\n[`AGENTS.md`](../AGENTS.md) at the repository root. It acts as a\n**resolver**: each topic points at its canonical home (skills under\n`.github/skills/`, reviewer instructions under\n`.github/instructions/reviewer/`, and deep-dive docs under\n`documentation/`) so the same rule isn't duplicated across files.\n\nStart there. This file is intentionally kept as a lightweight redirect\nso tooling and pipelines that reference `.github/copilot-instructions.md`\nby path continue to resolve during the transition.\n","isInternal":false,"tokens":126,"sizeBytes":590},{"name":"marketplace.json","path":".claude-plugin/marketplace.json","rawUrl":"https://raw.githubusercontent.com/Azure/azure-sdk-for-js/HEAD/.claude-plugin/marketplace.json","title":"Claude Plugin Marketplace Catalog","category":"marketplace","format":"json","content":"# Claude Plugin Marketplace Catalog\n\nPath: `.claude-plugin/marketplace.json`\n\n[View Raw Content on GitHub](https://raw.githubusercontent.com/Azure/azure-sdk-for-js/HEAD/.claude-plugin/marketplace.json)","tokens":300,"sizeBytes":201},{"name":"plugin.json","path":".claude-plugin/plugin.json","rawUrl":"https://raw.githubusercontent.com/Azure/azure-sdk-for-js/HEAD/.claude-plugin/plugin.json","title":"claude-plugin Plugin Manifest","category":"plugin-manifest","format":"json","content":"# claude-plugin Plugin Manifest\n\nPath: `.claude-plugin/plugin.json`\n\n[View Raw Content on GitHub](https://raw.githubusercontent.com/Azure/azure-sdk-for-js/HEAD/.claude-plugin/plugin.json)","tokens":300,"sizeBytes":187},{"name":"mcp.json","path":".cursor/mcp.json","rawUrl":"https://raw.githubusercontent.com/Azure/azure-sdk-for-js/HEAD/.cursor/mcp.json","title":"Model Context Protocol (MCP) Configuration","category":"mcp-config","format":"json","content":"# Model Context Protocol (MCP) Configuration\n\nPath: `.cursor/mcp.json`\n\n[View Raw Content on GitHub](https://raw.githubusercontent.com/Azure/azure-sdk-for-js/HEAD/.cursor/mcp.json)","tokens":300,"sizeBytes":180}],"systemPromptSnippet":"<yakaai_skills repo=\"Azure/azure-sdk-for-js\">\n<!-- File: AGENTS.md (Tokens: ~1723 | Category: root-instruction) -->\n# AGENTS.md\n\nResolver for agent-facing guidance in this repo. Each section points\nat the canonical location — content lives there, not here. If you find\nyourself duplicating a rule across docs, the duplicate is wrong.\n\n## What is this repo\n\nTypeScript / JavaScript SDKs for Azure services. Monorepo managed by\n`pnpm` + Turborepo.\n\n- Packages live under `sdk/*` (e.g. `sdk/web-pubsub/web-pubsub`).\n- Shared tools in `common/tools/*` (eslint plugin, dev-tool, warp).\n- Engineering tooling under `eng/*`; deep-dive docs under `documentation/*`.\n- Contributor onboarding: see `README.md` and `CONTRIBUTING.md`.\n\n## Where to find guidance\n\n| Task / topic                                                            | Where to look                                                                 |\n| ----------------------------------------------------------------------- | ----------------------------------------------------------------------------- |\n| Build / test / lint / format / release a package                        | `.github/skills/sdk-workflow/SKILL.md`                                        |\n| Add a feature to a package under `sdk/`                                 | `.github/skills/find-package-skill/SKILL.md` (check the registry FIRST)       |\n| Generate or regenerate SDK code from TypeSpec                           | `.github/skills/azsdk-common-generate-sdk-locally/SKILL.md`                   |\n| Release / publish a package                                             | `.github/skills/azsdk-common-sdk-release/SKILL.md`                            |\n| Management SDK release rotation / PR approval                           | `documentation/mgmt-release-rotation-runbook.md`                             |\n| Resolve APIView feedback                                                | `.github/skills/azsdk-common-apiview-feedback-resolution/SKILL.md`            |\n| Troubleshoot a CI / pipeline failure                                    | `.github/skills/azsdk-common-pipeline-troubleshooting/SKILL.md`               |\n| Audit or register ADO pipelines for `ci.yml` files                      | `.github/skills/ado-pipeline-audit/SKILL.md`                                  |\n| Create a new package-specific skill                                     | `.github/skills/create-package-skill/SKILL.md`                                |\n| Copilot code review (CCR)                                               | `.github/skills/code-review/SKILL.md` (routes to canonical reviewer guidance) |\n| Review criteria (architecture, perf, security, deps, tests, docs, mgmt) | `.github/instructions/reviewer/*.instructions.md`                             |\n| Test framework, recorder lifecycle, asset-sync                          | `documentation/Quickstart-on-how-to-write-tests.md`                           |\n| TypeSpec / codegen workflow                                             | `documentation/Generate-code-from-TypeSpec.md`                                |\n| Linting rules and troubleshooting                                       | `documentation/linting.md`                                                    |\n| Dependency management                                                   | `documentation/dependency-management.md`                                      |\n| Authoritative API design guidelines                                     | https://azure.github.io/azure-sdk/typescript_design.html                      |\n| Other deep dives                                                        | `documentation/` (browse the directory)                                       |\n\n> **Before pushing any code change** — including changes outside `sdk/` — run\n> the checks defined by CI for the affected package locally. Package managers\n> and scripts vary for non-workspace `eng/*` tools. See\n> `.github/skills/sdk-workflow/SKILL.md` § \"Before you push\".\n\nThe skills above carry workflow guidance the rest of this repo's\ncontributor docs assume agents will find. Read them on demand — don't\nload them all up front.\n\n## Hard rules\n\nRules agents have violated in the past and which the eval suite at\n`eng/agent-evals/` actively regression-tests. Each one is here because\nit has no static-analysis enforcement today (otherwise it would be a\nlint rule or CI check, not an eval).\n\n- Build a single package with `pnpm turbo build --filter=<pkg>... --token 1`.\n  Do **not** use `npm run build` at the package level — turbo workspace\n  linking breaks it.\n- Do **not** edit files under `<package>/generated/`. Those are\n  regenerated on every `tsp-client` run. Customizations go in `src/`\n  or via TypeSpec decorators. See `documentation/modular-customization.md`.\n- `snippets.spec.ts` files are documentation source, **not** real tests.\n  Don't refactor, delete, or \"fix\" them as part of test cleanup. They're\n  consumed by `dev-tool run update-snippets` to keep README code blocks\n  in sync.\n- Options bags on client methods extend `OperationOptions` from a core\n  package (`@azure-rest/core-client`, `@azure/core-client`, or\n  `@azure/core-rest-pipeline` depending on the package lineage).\n- Do **not** disable `@azure/eslint-plugin-azure-sdk` rules with\n  `eslint-disable` directives. Fix the underlying issue.\n- Do **not** hand-roll long-running operations. Use the LRO primitives\n  in `@azure/core-lro` and `@azure/core-client`. Review\n  `sdk/core/core-lro` for the latest patterns.\n- Always consult `.github/skills/find-package-skill/SKILL.md` (and the\n  relevant package-specific `SKILL.md` if one is registered there)\n  **before** modifying a package under `sdk/`.\n- When pushing new commits to an **existing** pull request, re-check that\n  the PR description still matches the current changes. If iterating has\n  made it inaccurate or incomplete, update the description in the same\n  step — don't leave a stale description behind.\n\n## Where new guidance belongs\n\nRules for the agent that maintains this file:\n\n- A rule that applies to **all** package work → here, \"Hard rules\"\n  section, **only if** it's eval-covered. Don't add hard rules without\n  a corresponding eval in `eng/agent-evals/` — the eval is what\n  prevents the rule from silently drifting.\n- A workflow that's specific to one task type (build, generate,\n  release, ...) → a new or existing skill in `.github/skills/`.\n- Reviewer-only behavior → `.github/instructions/reviewer/`.\n- Deep-dive how-to or tutorial → a new file under `documentation/`,\n  then a row in the \"Where to find guidance\" table above pointing at\n  it.\n- Package-specific tribal knowledge → a package-owned skill at\n  `sdk/<svc>/<pkg>/.github/skills/<name>/SKILL.md`.\n- Contributor-facing prose (workflows, prerequisites, setup) →\n  `CONTRIBUTING.md`, not here. AGENTS.md is for agent-routing only.\n\nIf a fact would belong in two places, pick the more-specific one. Link\nfrom the less-specific to the more-specific, don't copy.\n\n<!-- BEGIN:turborepo-agent-rules -->\n\n# This is NOT the Turborepo you know\n\nTurborepo configuration, task behavior, and CLI commands can vary between installed versions and may differ from your training data. Resolve the `turbo` package from this file's directory or relevant workspace; in monorepos, it may not be visible from the repository root. For example, run `node -p \"require.resolve('turbo/package.json')\"` from a workspace that depends on `turbo`.\n\nRead `docs/README.md` inside that installed package first, then read the relevant pages from its `docs/` directory before changing Turborepo configuration or commands. Heed deprecation notices. These bundled docs match the installed package version and are available without network access.\n\nThis block is written and re-added by `turbo` before repository-scoped commands when an AI agent is detected. In the Turborepo source repository, its template is defined in `crates/turborepo-cli/src/cli/agent_guidance.rs`. Removing the managed block while updates are enabled means a later qualifying invocation will add it again. Set `\"agentGuidance\": false` in the root `turbo.json` or `turbo.jsonc` to opt out; this does not remove an existing block. Keep the block committed with your work to avoid an uncommitted change on the next agent invocation.\n<!-- END:turborepo-agent-rules -->\n\n<!-- File: .github/copilot-instructions.md (Tokens: ~126 | Category: copilot-instructions) -->\n# Repository guidance has moved\n\nAgent-facing guidance for this repository now lives in\n[`AGENTS.md`](../AGENTS.md) at the repository root. It acts as a\n**resolver**: each topic points at its canonical home (skills under\n`.github/skills/`, reviewer instructions under\n`.github/instructions/reviewer/`, and deep-dive docs under\n`documentation/`) so the same rule isn't duplicated across files.\n\nStart there. This file is intentionally kept as a lightweight redirect\nso tooling and pipelines that reference `.github/copilot-instructions.md`\nby path continue to resolve during the transition.\n\n<!-- File: .claude-plugin/marketplace.json (Tokens: ~300 | Category: marketplace) -->\n# Claude Plugin Marketplace Catalog\n\nPath: `.claude-plugin/marketplace.json`\n\n[View Raw Content on GitHub](https://raw.githubusercontent.com/Azure/azure-sdk-for-js/HEAD/.claude-plugin/marketplace.json)\n\n<!-- File: .claude-plugin/plugin.json (Tokens: ~300 | Category: plugin-manifest) -->\n# claude-plugin Plugin Manifest\n\nPath: `.claude-plugin/plugin.json`\n\n[View Raw Content on GitHub](https://raw.githubusercontent.com/Azure/azure-sdk-for-js/HEAD/.claude-plugin/plugin.json)\n\n<!-- File: .cursor/mcp.json (Tokens: ~300 | Category: mcp-config) -->\n# Model Context Protocol (MCP) Configuration\n\nPath: `.cursor/mcp.json`\n\n[View Raw Content on GitHub](https://raw.githubusercontent.com/Azure/azure-sdk-for-js/HEAD/.cursor/mcp.json)\n</yakaai_skills>"}