[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M7F89FFMZVR3JD685P6GG96B":3,"skill-same:01M7F89FFMZVR3JD685P6GG96B":69},{"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":19,"linkOnly":20,"markdownContent":21,"markdownBody":22,"frontMatter":23,"refName":25,"commitSha":26,"skillDirectory":27,"forksCount":28,"repositoryHtmlUrl":29,"repositoryHomepageUrl":6,"ownerHtmlUrl":30,"ownerBlogUrl":6,"ownerDescription":31,"updatedAt":32,"install":33,"resources":46},"01M7F89FFMZVR3JD685P6GG96B","copilotkit-debug",null,"Use when diagnosing CopilotKit issues -- runtime connectivity failures, agent not responding, streaming errors, tool execution problems, transcription failures, version mismatches, and AG-UI event tracing.","lza6\u002FArmor-piercing-system-prompts","lza6","https:\u002F\u002Favatars.githubusercontent.com\u002Fu\u002F128880206?v=4","01M7EB3K7WPX5T28EJ2NVHE6EG","Chinese-tingfeng","01M7EB3K97E1KQ16QWKJMFNGX8",11,"MIT","https:\u002F\u002Fgithub.com\u002Flza6\u002FArmor-piercing-system-prompts\u002Fblob\u002Fmain\u002F06-前端与设计\u002Fcopilotkit-debug\u002FSKILL.md",[],[],"2026-11-16 10:05:34",false,"---\nname: copilotkit-debug\ndescription: \"Use when diagnosing CopilotKit issues -- runtime connectivity failures, agent not responding, streaming errors, tool execution problems, transcription failures, version mismatches, and AG-UI event tracing.\"\nversion: 1.0.1\n---\n\n# CopilotKit Debugging Skill\n\n## When to Use\n\nInvoke this skill when:\n\n- The CopilotKit runtime is unreachable or returning errors\n- Agents fail to connect, respond, or stream events\n- Frontend tools are not executing or returning results\n- Transcription (voice) is failing\n- Version mismatch errors appear between packages\n- AG-UI SSE events are malformed or missing\n- CORS errors block browser requests to the runtime\n\n## Diagnostic Workflow\n\n### Step 1: Gather Information\n\nBefore proposing any fix, collect:\n\n1. **Package versions** -- Run `npm ls @copilotkit\u002Fruntime @copilotkit\u002Freact-core @copilotkit\u002Fcore @ag-ui\u002Fclient` (or the v1 equivalents). Version mismatches between runtime and React packages are a common root cause.\n2. **Runtime mode** -- Is this SSE mode (`CopilotSseRuntime`) or Intelligence mode (`CopilotIntelligenceRuntime`)? Check the runtime constructor.\n3. **Transport configuration** -- What is `runtimeUrl` set to on the `CopilotKit` provider (from `@copilotkit\u002Freact-core\u002Fv2`)? Does it match the `basePath` in `createCopilotRuntimeHandler`?\n4. **Agent type** -- Is the agent a `BuiltInAgent`, `LangGraphAgent`, `A2AAgent`, or custom `AbstractAgent`?\n5. **Error messages** -- Collect the exact error from browser console and server logs. CopilotKit uses structured error codes (see `references\u002Ferror-patterns.md`).\n6. **Browser network tab** -- Check the `\u002Finfo` request (runtime discovery), the `\u002Fagent\u002F:id\u002Frun` SSE stream, and any CORS preflight failures.\n\n### Step 2: Check Logs and Error Codes\n\nCopilotKit has three error code systems:\n\n- **V1 error codes** -- Legacy error codes from the v1 runtime layer (`@copilotkit\u002Fruntime`). Codes like `NETWORK_ERROR`, `AGENT_NOT_FOUND`, `API_NOT_FOUND`. Still surfaced in some contexts since `@copilotkit\u002F*` packages wrap v2 internally.\n- **V2 `CopilotKitCoreErrorCode`** -- Used by `@copilotkit\u002Fcore`. Codes like `runtime_info_fetch_failed`, `agent_connect_failed`, `agent_run_failed`.\n- **`TranscriptionErrorCode`** -- Used by both v1 and v2 for voice transcription. Codes like `service_not_configured`, `rate_limited`, `auth_failed`.\n\nMatch the error code to the catalog in `references\u002Ferror-patterns.md` for root cause and resolution.\n\n### Step 3: Trace AG-UI Events\n\nFor streaming\u002Fagent issues, trace the AG-UI event flow:\n\n1. **RunStartedEvent** -- Confirms the agent run was initiated\n2. **TextMessageStartEvent \u002F TextMessageChunkEvent \u002F TextMessageEndEvent** -- Text streaming\n3. **ToolCallStartEvent \u002F ToolCallArgsEvent \u002F ToolCallEndEvent** -- Tool invocations\n4. **ToolCallResultEvent** -- Tool results flowing back\n5. **StateSnapshotEvent \u002F StateDeltaEvent** -- Agent state synchronization\n6. **ReasoningStartEvent \u002F ReasoningMessageContentEvent \u002F ReasoningMessageEndEvent** -- Reasoning tokens (can cause stalls, see issue #3323)\n7. **RunFinishedEvent** -- Successful completion\n8. **RunErrorEvent** -- Agent-level error\n\nEnable the CopilotKit Web Inspector (`@copilotkit\u002Fweb-inspector`) to see events in real time. Or check the SSE stream directly in the browser Network tab -- each event is a `data:` line in the `text\u002Fevent-stream` response.\n\n### Step 4: Identify Root Cause\n\nUse the reference documents to match symptoms to known issues:\n\n- **`references\u002Fruntime-debugging.md`** -- Connectivity, CORS, transport, SSE streaming\n- **`references\u002Fagent-debugging.md`** -- Agent discovery, state sync, tool execution, AG-UI protocol\n- **`references\u002Ferror-patterns.md`** -- Complete error code catalog with resolutions\n- **`references\u002Fquick-workflows.md`** -- Step-by-step diagnostic sequences for common scenarios\n\n### Step 5: Fix and Verify\n\n1. Apply the fix\n2. Verify the `\u002Finfo` endpoint returns the expected agent list\n3. Confirm the SSE stream produces a complete event sequence (RunStarted through RunFinished)\n4. Check the browser console for any remaining structured errors\n\n## Using mcp-docs for Live Documentation Lookups\n\nDuring debugging, use the `copilotkit-docs` MCP server to look up the latest CopilotKit documentation. This server provides two tools: `search-docs` (search documentation) and `search-code` (search source code examples).\n\n### MCP Setup\n\n**Claude Code:** The MCP server is auto-configured by the plugin's `.mcp.json` -- no manual setup needed. The agent can call the `search-docs` and `search-code` tools from the `copilotkit-docs` server directly.\n\n**Codex:** Add the following to your `.codex\u002Fconfig.toml`:\n\n```toml\n[mcp_servers.copilotkit-docs]\ntype = \"http\"\nurl = \"https:\u002F\u002Fmcp.copilotkit.ai\u002Fmcp\"\n```\n\n### Tool Usage\n\nThe `search-docs` and `search-code` tools are invoked as MCP tool calls (not CLI commands). Examples of what to search for during debugging:\n\n```\nsearch-docs(\"AGENT_NOT_FOUND\")\nsearch-docs(\"CopilotRuntime configuration\")\nsearch-docs(\"AG-UI protocol events\")\nsearch-docs(\"troubleshooting common issues\")\nsearch-docs(\"CORS configuration copilotkit\")\nsearch-code(\"CopilotRuntime error handling\")\n```\n\nThe official troubleshooting docs are at:\n\n- `https:\u002F\u002Fdocs.copilotkit.ai\u002Ftroubleshooting\u002Fcommon-issues`\n- `https:\u002F\u002Fdocs.copilotkit.ai\u002Fcoagents\u002Ftroubleshooting\u002Fcommon-issues`\n\n## Key File Locations in the CopilotKit Codebase\n\n| Component                      | Path                                                              |\n| ------------------------------ | ----------------------------------------------------------------- |\n| Legacy error classes & codes   | `packages\u002Fshared\u002Fsrc\u002Futils\u002Ferrors.ts`                             |\n| V2 Core error codes            | `packages\u002Fcore\u002Fsrc\u002Fcore\u002Fcore.ts` (`CopilotKitCoreErrorCode` enum) |\n| V2 Transcription errors        | `packages\u002Fshared\u002Fsrc\u002Ftranscription-errors.ts`                     |\n| Runtime SSE response           | `packages\u002Fruntime\u002Fsrc\u002Fv2\u002Fruntime\u002Fhandlers\u002Fshared\u002Fsse-response.ts` |\n| Runtime info endpoint          | `packages\u002Fruntime\u002Fsrc\u002Fv2\u002Fruntime\u002Fhandlers\u002Fget-runtime-info.ts`    |\n| Runtime CORS config            | `packages\u002Fruntime\u002Fsrc\u002Fv2\u002Fruntime\u002Fcore\u002Ffetch-cors.ts`              |\n| CopilotKit Intelligence client | `packages\u002Fruntime\u002Fsrc\u002Fv2\u002Fruntime\u002Fintelligence-platform\u002Fclient.ts` |\n| BuiltInAgent                   | `packages\u002Fruntime\u002Fsrc\u002Fagent\u002Findex.ts`                             |\n| Web Inspector                  | `packages\u002Fweb-inspector\u002Fsrc\u002Findex.ts`                             |\n","# CopilotKit Debugging Skill\n\n## When to Use\n\nInvoke this skill when:\n\n- The CopilotKit runtime is unreachable or returning errors\n- Agents fail to connect, respond, or stream events\n- Frontend tools are not executing or returning results\n- Transcription (voice) is failing\n- Version mismatch errors appear between packages\n- AG-UI SSE events are malformed or missing\n- CORS errors block browser requests to the runtime\n\n## Diagnostic Workflow\n\n### Step 1: Gather Information\n\nBefore proposing any fix, collect:\n\n1. **Package versions** -- Run `npm ls @copilotkit\u002Fruntime @copilotkit\u002Freact-core @copilotkit\u002Fcore @ag-ui\u002Fclient` (or the v1 equivalents). Version mismatches between runtime and React packages are a common root cause.\n2. **Runtime mode** -- Is this SSE mode (`CopilotSseRuntime`) or Intelligence mode (`CopilotIntelligenceRuntime`)? Check the runtime constructor.\n3. **Transport configuration** -- What is `runtimeUrl` set to on the `CopilotKit` provider (from `@copilotkit\u002Freact-core\u002Fv2`)? Does it match the `basePath` in `createCopilotRuntimeHandler`?\n4. **Agent type** -- Is the agent a `BuiltInAgent`, `LangGraphAgent`, `A2AAgent`, or custom `AbstractAgent`?\n5. **Error messages** -- Collect the exact error from browser console and server logs. CopilotKit uses structured error codes (see `references\u002Ferror-patterns.md`).\n6. **Browser network tab** -- Check the `\u002Finfo` request (runtime discovery), the `\u002Fagent\u002F:id\u002Frun` SSE stream, and any CORS preflight failures.\n\n### Step 2: Check Logs and Error Codes\n\nCopilotKit has three error code systems:\n\n- **V1 error codes** -- Legacy error codes from the v1 runtime layer (`@copilotkit\u002Fruntime`). Codes like `NETWORK_ERROR`, `AGENT_NOT_FOUND`, `API_NOT_FOUND`. Still surfaced in some contexts since `@copilotkit\u002F*` packages wrap v2 internally.\n- **V2 `CopilotKitCoreErrorCode`** -- Used by `@copilotkit\u002Fcore`. Codes like `runtime_info_fetch_failed`, `agent_connect_failed`, `agent_run_failed`.\n- **`TranscriptionErrorCode`** -- Used by both v1 and v2 for voice transcription. Codes like `service_not_configured`, `rate_limited`, `auth_failed`.\n\nMatch the error code to the catalog in `references\u002Ferror-patterns.md` for root cause and resolution.\n\n### Step 3: Trace AG-UI Events\n\nFor streaming\u002Fagent issues, trace the AG-UI event flow:\n\n1. **RunStartedEvent** -- Confirms the agent run was initiated\n2. **TextMessageStartEvent \u002F TextMessageChunkEvent \u002F TextMessageEndEvent** -- Text streaming\n3. **ToolCallStartEvent \u002F ToolCallArgsEvent \u002F ToolCallEndEvent** -- Tool invocations\n4. **ToolCallResultEvent** -- Tool results flowing back\n5. **StateSnapshotEvent \u002F StateDeltaEvent** -- Agent state synchronization\n6. **ReasoningStartEvent \u002F ReasoningMessageContentEvent \u002F ReasoningMessageEndEvent** -- Reasoning tokens (can cause stalls, see issue #3323)\n7. **RunFinishedEvent** -- Successful completion\n8. **RunErrorEvent** -- Agent-level error\n\nEnable the CopilotKit Web Inspector (`@copilotkit\u002Fweb-inspector`) to see events in real time. Or check the SSE stream directly in the browser Network tab -- each event is a `data:` line in the `text\u002Fevent-stream` response.\n\n### Step 4: Identify Root Cause\n\nUse the reference documents to match symptoms to known issues:\n\n- **`references\u002Fruntime-debugging.md`** -- Connectivity, CORS, transport, SSE streaming\n- **`references\u002Fagent-debugging.md`** -- Agent discovery, state sync, tool execution, AG-UI protocol\n- **`references\u002Ferror-patterns.md`** -- Complete error code catalog with resolutions\n- **`references\u002Fquick-workflows.md`** -- Step-by-step diagnostic sequences for common scenarios\n\n### Step 5: Fix and Verify\n\n1. Apply the fix\n2. Verify the `\u002Finfo` endpoint returns the expected agent list\n3. Confirm the SSE stream produces a complete event sequence (RunStarted through RunFinished)\n4. Check the browser console for any remaining structured errors\n\n## Using mcp-docs for Live Documentation Lookups\n\nDuring debugging, use the `copilotkit-docs` MCP server to look up the latest CopilotKit documentation. This server provides two tools: `search-docs` (search documentation) and `search-code` (search source code examples).\n\n### MCP Setup\n\n**Claude Code:** The MCP server is auto-configured by the plugin's `.mcp.json` -- no manual setup needed. The agent can call the `search-docs` and `search-code` tools from the `copilotkit-docs` server directly.\n\n**Codex:** Add the following to your `.codex\u002Fconfig.toml`:\n\n```toml\n[mcp_servers.copilotkit-docs]\ntype = \"http\"\nurl = \"https:\u002F\u002Fmcp.copilotkit.ai\u002Fmcp\"\n```\n\n### Tool Usage\n\nThe `search-docs` and `search-code` tools are invoked as MCP tool calls (not CLI commands). Examples of what to search for during debugging:\n\n```\nsearch-docs(\"AGENT_NOT_FOUND\")\nsearch-docs(\"CopilotRuntime configuration\")\nsearch-docs(\"AG-UI protocol events\")\nsearch-docs(\"troubleshooting common issues\")\nsearch-docs(\"CORS configuration copilotkit\")\nsearch-code(\"CopilotRuntime error handling\")\n```\n\nThe official troubleshooting docs are at:\n\n- `https:\u002F\u002Fdocs.copilotkit.ai\u002Ftroubleshooting\u002Fcommon-issues`\n- `https:\u002F\u002Fdocs.copilotkit.ai\u002Fcoagents\u002Ftroubleshooting\u002Fcommon-issues`\n\n## Key File Locations in the CopilotKit Codebase\n\n| Component                      | Path                                                              |\n| ------------------------------ | ----------------------------------------------------------------- |\n| Legacy error classes & codes   | `packages\u002Fshared\u002Fsrc\u002Futils\u002Ferrors.ts`                             |\n| V2 Core error codes            | `packages\u002Fcore\u002Fsrc\u002Fcore\u002Fcore.ts` (`CopilotKitCoreErrorCode` enum) |\n| V2 Transcription errors        | `packages\u002Fshared\u002Fsrc\u002Ftranscription-errors.ts`                     |\n| Runtime SSE response           | `packages\u002Fruntime\u002Fsrc\u002Fv2\u002Fruntime\u002Fhandlers\u002Fshared\u002Fsse-response.ts` |\n| Runtime info endpoint          | `packages\u002Fruntime\u002Fsrc\u002Fv2\u002Fruntime\u002Fhandlers\u002Fget-runtime-info.ts`    |\n| Runtime CORS config            | `packages\u002Fruntime\u002Fsrc\u002Fv2\u002Fruntime\u002Fcore\u002Ffetch-cors.ts`              |\n| CopilotKit Intelligence client | `packages\u002Fruntime\u002Fsrc\u002Fv2\u002Fruntime\u002Fintelligence-platform\u002Fclient.ts` |\n| BuiltInAgent                   | `packages\u002Fruntime\u002Fsrc\u002Fagent\u002Findex.ts`                             |\n| Web Inspector                  | `packages\u002Fweb-inspector\u002Fsrc\u002Findex.ts`                             |\n",{"name":5,"version":24,"description":7},"1.0.1","main","d69096e239f2a89aabc2cd078c47664a9d3b1e11","06-前端与设计\u002Fcopilotkit-debug",3,"https:\u002F\u002Fgithub.com\u002Flza6\u002FArmor-piercing-system-prompts","https:\u002F\u002Fgithub.com\u002Flza6","个人vx：Tf00798\r\n个人✈：@TFGY999","2026-10-08 14:29:22",{"source":8,"skillName":5,"commands":34,"prompt":44,"zipAvailable":45},[35,38,41],{"tool":36,"command":37},"npx","npx skills add lza6\u002FArmor-piercing-system-prompts --skill copilotkit-debug",{"tool":39,"command":40},"bunx","bunx skills add lza6\u002FArmor-piercing-system-prompts --skill copilotkit-debug",{"tool":42,"command":43},"pnpm","pnpm dlx skills add lza6\u002FArmor-piercing-system-prompts --skill copilotkit-debug","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002Flza6\u002FArmor-piercing-system-prompts\u002Fblob\u002Fmain\u002F06-前端与设计\u002Fcopilotkit-debug\u002FSKILL.md",true,[47,53,57,61,65],{"path":48,"resourceType":49,"resourceTypeDesc":50,"sizeBytes":51,"sourceHtmlUrl":52},"references\u002Fagent-debugging.md","REFERENCE","参考文档",10908,"https:\u002F\u002Fgithub.com\u002Flza6\u002FArmor-piercing-system-prompts\u002Fblob\u002Fmain\u002F06-前端与设计\u002Fcopilotkit-debug\u002Freferences\u002Fagent-debugging.md",{"path":54,"resourceType":49,"resourceTypeDesc":50,"sizeBytes":55,"sourceHtmlUrl":56},"references\u002Ferror-patterns.md",15187,"https:\u002F\u002Fgithub.com\u002Flza6\u002FArmor-piercing-system-prompts\u002Fblob\u002Fmain\u002F06-前端与设计\u002Fcopilotkit-debug\u002Freferences\u002Ferror-patterns.md",{"path":58,"resourceType":49,"resourceTypeDesc":50,"sizeBytes":59,"sourceHtmlUrl":60},"references\u002Fquick-workflows.md",9871,"https:\u002F\u002Fgithub.com\u002Flza6\u002FArmor-piercing-system-prompts\u002Fblob\u002Fmain\u002F06-前端与设计\u002Fcopilotkit-debug\u002Freferences\u002Fquick-workflows.md",{"path":62,"resourceType":49,"resourceTypeDesc":50,"sizeBytes":63,"sourceHtmlUrl":64},"references\u002Fruntime-debugging.md",10067,"https:\u002F\u002Fgithub.com\u002Flza6\u002FArmor-piercing-system-prompts\u002Fblob\u002Fmain\u002F06-前端与设计\u002Fcopilotkit-debug\u002Freferences\u002Fruntime-debugging.md",{"path":66,"resourceType":49,"resourceTypeDesc":50,"sizeBytes":67,"sourceHtmlUrl":68},"sources.md",2749,"https:\u002F\u002Fgithub.com\u002Flza6\u002FArmor-piercing-system-prompts\u002Fblob\u002Fmain\u002F06-前端与设计\u002Fcopilotkit-debug\u002Fsources.md",[70,77,82,89,96,103],{"skillNo":71,"name":72,"nameZh":6,"description":73,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":74,"categories":75,"keywords":76,"publishedAt":19},"01M7FFG485KY83TD6HSC4YPCMC","obsidian-clipper-template-creator","Guide for creating templates for the Obsidian Web Clipper. Use when you want to create a new clipping template, understand available variables, or format clipped content.","https:\u002F\u002Fgithub.com\u002Flza6\u002FArmor-piercing-system-prompts\u002Fblob\u002Fmain\u002F07-后端与架构\u002Fobsidian-clipper-template-creator\u002FSKILL.md",[],[],{"skillNo":78,"name":72,"nameZh":6,"description":73,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":79,"categories":80,"keywords":81,"publishedAt":19},"01M7FFG0T6AZ0STEJPSB3CX84K","https:\u002F\u002Fgithub.com\u002Flza6\u002FArmor-piercing-system-prompts\u002Fblob\u002Fmain\u002F07-后端与架构\u002Fobsidian-clipper-template-creator-antigravity-awesome-skills-main\u002FSKILL.md",[],[],{"skillNo":83,"name":84,"nameZh":6,"description":85,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":86,"categories":87,"keywords":88,"publishedAt":19},"01M7FFFY0QEM14SKWPDYGMXM2P","python-api","Programmatic Object-Detection-Metrics API guidance for BoundingBox, BoundingBoxes, Evaluator, enums, coordinate conversion, AP\u002FmAP semantics, and source-style import diagnostics.","https:\u002F\u002Fgithub.com\u002Flza6\u002FArmor-piercing-system-prompts\u002Fblob\u002Fmain\u002F07-后端与架构\u002Fobject-detection-metrics\u002Fsub-skills\u002Fpython-api\u002FSKILL.md",[],[],{"skillNo":90,"name":91,"nameZh":6,"description":92,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":93,"categories":94,"keywords":95,"publishedAt":19},"01M7FFFVZQZ2GJ0C0TGP7JHD20","file-evaluation","Folder-based PASCAL VOC AP\u002FmAP evaluation from ground-truth and detection text files.","https:\u002F\u002Fgithub.com\u002Flza6\u002FArmor-piercing-system-prompts\u002Fblob\u002Fmain\u002F07-后端与架构\u002Fobject-detection-metrics\u002Fsub-skills\u002Ffile-evaluation\u002FSKILL.md",[],[],{"skillNo":97,"name":98,"nameZh":6,"description":99,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":100,"categories":101,"keywords":102,"publishedAt":19},"01M7FFFSFNYSE77SJ6PE1CK2DA","object-detection-metrics","Guides legacy Object-Detection-Metrics PASCAL VOC AP\u002FmAP evaluation from detection text folders and direct Python API classes.","https:\u002F\u002Fgithub.com\u002Flza6\u002FArmor-piercing-system-prompts\u002Fblob\u002Fmain\u002F07-后端与架构\u002Fobject-detection-metrics\u002FSKILL.md",[],[],{"skillNo":104,"name":105,"nameZh":6,"description":106,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":107,"categories":108,"keywords":109,"publishedAt":19},"01M7FFFP0GCK1RVXBCPQ8APBMT","nx-workspace-patterns","Configure and optimize Nx monorepo workspaces. Use when setting up Nx, configuring project boundaries, optimizing build caching, or implementing affected commands.","https:\u002F\u002Fgithub.com\u002Flza6\u002FArmor-piercing-system-prompts\u002Fblob\u002Fmain\u002F07-后端与架构\u002Fnx-workspace-patterns\u002FSKILL.md",[],[]]