[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M7BWD0V8P9ENJN5E278BYAV0":3,"skill-same:01M7BWD0V8P9ENJN5E278BYAV0":75},{"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":30,"commitSha":31,"skillDirectory":32,"forksCount":33,"repositoryHtmlUrl":34,"repositoryHomepageUrl":6,"ownerHtmlUrl":35,"ownerBlogUrl":36,"ownerDescription":37,"updatedAt":38,"install":39,"resources":52},"01M7BWD0V8P9ENJN5E278BYAV0","diagram",null,"Generates architecture diagrams from code, infrastructure, or descriptions. Use when user asks to visualize, diagram, or document system architecture.","CognitionAI\u002Fdevin-marketplace","CognitionAI","https:\u002F\u002Favatars.githubusercontent.com\u002Fu\u002F163493330?v=4","01M7BVSRD98NC4FG8T3EZS6V5M","Cognition","01M7BVSRDX111C2XPWJ0E6MY26",29,"MIT","https:\u002F\u002Fgithub.com\u002FCognitionAI\u002Fdevin-marketplace\u002Fblob\u002Fmain\u002Fplugins\u002Feraser\u002Fskills\u002Fdiagram\u002FSKILL.md",[],[],"2026-11-15 14:19:17",false,"---\nname: diagram\ndescription: 'Generates architecture diagrams from code, infrastructure, or descriptions. Use when user asks to visualize, diagram, or document system architecture.'\nlicense: MIT\ncompatibility: Requires network access to call Eraser API\nallowed-tools: Read Write Bash(curl:*)\nmetadata:\n  version: \"1.0.0\"\n  author: Eraser Labs\n  tags: diagram, architecture, infrastructure, visualization, terraform, aws, azure, cloud\n---\n\n# Eraser Diagram Generator\n\nGenerates professional architecture diagrams directly from code, infrastructure files, or natural language descriptions using the Eraser API.\n\n## When to Use\n\nActivate this skill when:\n\n- User asks to create, generate, or visualize a diagram\n- User wants to document architecture from code\n- User has Terraform, AWS, Azure, or infrastructure files\n- User describes a system and wants it visualized\n- User mentions \"diagram\", \"architecture\", \"visualize\", or \"draw\"\n\n## How It Works\n\n1. **Analyze the source**: Extract architecture information from code, files, or descriptions\n2. **Generate Eraser DSL**: Create Eraser DSL code that describes the diagram\n3. **Call the Eraser API**: Make an HTTP POST request to render the diagram\n4. **Return the result**: Present the image URL and editor link to the user\n\n## Diagram Types and Syntax\n\nEraser supports five types of diagrams, each optimized for different use cases. For detailed DSL syntax and examples, refer to the appropriate reference file:\n\n### Flow Charts\n\nVisualize process flows, user flows, and logic flows represented as nodes, groups, and relationships. Diagrams are created using simple syntax.\n\n**Use for**: Process flows, user journeys, decision trees, business process documentation\n\n**diagramType**: `\"flowchart-diagram\"`\n\n**Reference**: [Flowchart Syntax](references\u002Fflowchart-syntax.md)\n\n### Entity Relationship Diagrams (ERD)\n\nVisualize data models represented as entities, attributes, and relationships. Diagrams are created using simple syntax.\n\n**Use for**: Database schema design, data modeling, understanding entity relationships, documenting data structures\n\n**diagramType**: `\"entity-relationship-diagram\"`\n\n**Reference**: [ERD Syntax](references\u002Ferd-syntax.md)\n\n### Cloud Architecture Diagrams\n\nVisualize cloud infrastructure represented as nodes, groups, and connections. Diagrams are created using simple syntax.\n\n**Use for**: Cloud infrastructure visualization, AWS\u002FAzure\u002FGCP architectures, system architecture documentation, data flow visualization\n\n**diagramType**: `\"cloud-architecture-diagram\"`\n\n**Reference**: [Architecture Syntax](references\u002Farchitecture-syntax.md)\n\n### Sequence Diagrams\n\nVisualize system flows using sequence diagrams. Each vertical column represents an entity (e.g. user, server, DB) and arrows between the columns represent the flow of information or requests. Diagrams are created using simple syntax.\n\n**Use for**: API request\u002Fresponse flows, system interactions, user workflows, message passing between services, process flows over time\n\n**diagramType**: `\"sequence-diagram\"`\n\n**Reference**: [Sequence Syntax](references\u002Fsequence-syntax.md)\n\n### BPMN Diagrams (Swimlane Diagrams)\n\nVisualize business processes represented as pools, lanes, and flow objects such as tasks, events, and gateways. Diagrams are created using simple syntax.\n\n**Use for**: Business process documentation, workflow visualization, process improvement, cross-functional processes, swimlane diagrams showing roles\u002Fresponsibilities\n\n**diagramType**: `\"bpmn-diagram\"`\n\n**Reference**: [BPMN Syntax](references\u002Fbpmn-syntax.md)\n\nEach reference file contains complete syntax documentation, property references, and practical examples.\n\n## API Integration\n\n### Endpoint\n\n```\nPOST https:\u002F\u002Fapp.eraser.io\u002Fapi\u002Frender\u002Felements\nContent-Type: application\u002Fjson\nAuthorization: Bearer ${ERASER_API_TOKEN}\nX-Skill-Source: eraser-skill\n```\n\n**Note**: The `X-Skill-Source` header identifies the AI agent. You MUST replace `eraser-skill` with your actual agent name:\n- If you are Claude (Anthropic), use: `claude`\n- If you are running in Cursor, use: `cursor`\n- If you are ChatGPT (OpenAI), use: `chatgpt`\n- If you are Gemini (Google), use: `gemini`\n- Otherwise, use your model\u002Fagent name in lowercase\n\n### Response Format\n\n```json\n{\n  \"imageUrl\": \"https:\u002F\u002Fstorage.googleapis.com\u002Feraser-images\u002F...\",\n  \"createEraserFileUrl\": \"https:\u002F\u002Fapp.eraser.io\u002Fnew?requestId=abc123&state=xyz789\",\n  \"renderedElements\": [...]\n}\n```\n\n### Error Responses\n\n| Status | Error | Cause | Solution |\n| --- | --- | --- | --- |\n| 400 | `Diagram element has no code` | Missing `code` field in element | Ensure element has valid DSL code |\n| 400 | `Diagram element has no diagramType` | Missing `diagramType` field | Add valid diagramType to element |\n| 400 | `Invalid diagramType` | Unsupported diagram type | Use one of the supported types listed above |\n| 401 | `Unauthorized` | Invalid or expired API token | Check `ERASER_API_TOKEN` is valid |\n| 500 | `Internal server error` | Server-side issue | Retry the request; if persistent, contact support |\n\n**Error Response Format:**\n\n```json\n{\n  \"error\": {\n    \"message\": \"Diagram element has no code\",\n    \"status\": 400\n  }\n}\n```\n\n**Troubleshooting Tips:**\n\n- Verify DSL syntax is correct before making the API call\n- Ensure `diagramType` matches the DSL content (e.g., sequence DSL with `sequence-diagram`)\n- For auth errors, verify the API key is set correctly as an environment variable\n\n## Instructions\n\nWhen the user requests a diagram:\n\n1. **Extract Information**\n\n   - If code\u002Ffiles are provided, analyze the structure, resources, and relationships\n   - If description is provided, identify key components and connections\n   - Determine the appropriate diagram type\n\n2. **Generate Eraser DSL**\n\n   - Create Eraser DSL code that represents the architecture\n   - **CRITICAL: Label Formatting Rules**\n     - Labels MUST be on a single line - NEVER use newlines inside label attributes\n     - Keep labels simple and readable - prefer separate labels over concatenating too much metadata\n     - Format DSL with proper line breaks (one node\u002Fgroup per line, but labels stay on single lines)\n   - For detailed DSL syntax and examples, see the [Diagram Types and Syntax](#diagram-types-and-syntax) section above for links to reference files\n\n3. **Create Element Definition**\n\n   - Create an element object with:\n     - `type: \"diagram\"`\n     - `id: \"diagram-1\"` (or generate a unique ID)\n     - `code: \"\u003Cyour generated DSL code>\"`\n     - `diagramType: \"\u003Cappropriate type>\"`\n\n4. **Make the HTTP Request**\n\n   **IMPORTANT**: You MUST execute this curl command after generating the DSL. Never stop after generating DSL without making the API call.\n\n   **CRITICAL**: Replace `eraser-skill` in the `X-Skill-Source` header with your actual AI agent name (see API Integration section above for values).\n\n   ```bash\n   curl -X POST https:\u002F\u002Fapp.eraser.io\u002Fapi\u002Frender\u002Felements \\\n     -H \"Content-Type: application\u002Fjson\" \\\n     -H \"X-Skill-Source: eraser-skill\" \\\n     -H \"Authorization: Bearer ${ERASER_API_TOKEN}\" \\\n     -d '{\n       \"elements\": [{\n         \"type\": \"diagram\",\n         \"id\": \"diagram-1\",\n         \"code\": \"\u003Cyour generated DSL>\",\n         \"diagramType\": \"cloud-architecture-diagram\"\n       }],\n       \"scale\": 2,\n       \"theme\": \"${ERASER_THEME:-dark}\",\n       \"background\": true\n     }'\n   ```\n\n5. **Track Sources During Analysis**\n\n   As you analyze files and resources to generate the diagram, track:\n\n   - **Internal files**: Record each file path you read and what information was extracted (e.g., `infra\u002Fmain.tf` - VPC and subnet definitions)\n   - **External references**: Note any documentation, examples, or URLs consulted (e.g., AWS VPC best practices documentation)\n   - **Annotations**: For each source, note what it contributed to the diagram\n\n6. **Handle the Response**\n\n   **CRITICAL: Minimal Output Format**\n\n   Your response MUST always include these elements with clear headers:\n\n   1. **Diagram Preview**: Display with a header\n      ```\n      ## Diagram\n      ![{Title}]({imageUrl})\n      ```\n      Use the ACTUAL `imageUrl` from the API response.\n\n   2. **Editor Link**: Display with a header\n      ```\n      ## Open in Eraser\n      [Edit this diagram in the Eraser editor]({createEraserFileUrl})\n      ```\n      Use the ACTUAL URL from the API response.\n\n   3. **Sources section**: Brief list of files\u002Fresources analyzed (if applicable)\n      ```\n      ## Sources\n      - `path\u002Fto\u002Ffile` - What was extracted\n      ```\n\n   4. **Diagram Code section**: The Eraser DSL in a code block with `eraser` language tag\n      ```\n      ## Diagram Code\n      ```eraser\n      {DSL code here}\n      ```\n      ```\n\n   5. **Learn More link**: `You can learn more about Eraser at https:\u002F\u002Fdocs.eraser.io\u002Fdocs\u002Fusing-ai-agent-integrations`\n\n   **Additional content rules:**\n   - If the user ONLY asked for a diagram, include NOTHING beyond the 5 elements above\n   - If the user explicitly asked for more (e.g., \"explain the architecture\", \"suggest improvements\"), you may include that additional content\n   - Never add unrequested sections like Overview, Security Considerations, Testing, etc.\n\n   The default output should be SHORT. The diagram image speaks for itself.\n\n7. **Error Handling**\n   - If API call fails, explain the error\n   - Suggest checking API key if authentication fails\n   - Offer to regenerate DSL code as fallback\n\n## Best Practices\n\n- **Generate Valid DSL**: Ensure the DSL syntax is correct before calling the API\n- **Quote Labels Properly**: Always quote labels that contain spaces, special characters, or numbers\n- **Single-Line Labels**: Labels MUST be on a single line - never use newlines inside label attributes\n- **Format for Readability**: Put each node, group, and connection on its own line (but keep labels single-line)\n- **Include Metadata**: If including CIDR blocks, instance types, etc., put them in the same quoted label string: `[label: \"VPC 10.0.0.0\u002F16\"]`\n- **Use Appropriate Diagram Type**: Choose the right `diagramType` for the content\n- **Group Related Items**: Use containers (VPCs, modules) to group related components\n- **Specify Connections**: Show data flows, dependencies, and relationships\n- **Handle Large Systems**: Break down very large systems into focused diagrams\n- **Include Source Header**: Always include `X-Skill-Source` header with your AI agent name (claude, cursor, chatgpt, etc.)\n\n## Notes\n\n- Free tier diagrams include a watermark but are fully functional\n- The `createEraserFileUrl` is always returned (works for both free and paid tiers) and allows users to edit diagrams in the Eraser web editor\n- The DSL code can be used to regenerate or modify diagrams\n- API responses are cached, so identical requests return quickly\n","# Eraser Diagram Generator\n\nGenerates professional architecture diagrams directly from code, infrastructure files, or natural language descriptions using the Eraser API.\n\n## When to Use\n\nActivate this skill when:\n\n- User asks to create, generate, or visualize a diagram\n- User wants to document architecture from code\n- User has Terraform, AWS, Azure, or infrastructure files\n- User describes a system and wants it visualized\n- User mentions \"diagram\", \"architecture\", \"visualize\", or \"draw\"\n\n## How It Works\n\n1. **Analyze the source**: Extract architecture information from code, files, or descriptions\n2. **Generate Eraser DSL**: Create Eraser DSL code that describes the diagram\n3. **Call the Eraser API**: Make an HTTP POST request to render the diagram\n4. **Return the result**: Present the image URL and editor link to the user\n\n## Diagram Types and Syntax\n\nEraser supports five types of diagrams, each optimized for different use cases. For detailed DSL syntax and examples, refer to the appropriate reference file:\n\n### Flow Charts\n\nVisualize process flows, user flows, and logic flows represented as nodes, groups, and relationships. Diagrams are created using simple syntax.\n\n**Use for**: Process flows, user journeys, decision trees, business process documentation\n\n**diagramType**: `\"flowchart-diagram\"`\n\n**Reference**: [Flowchart Syntax](references\u002Fflowchart-syntax.md)\n\n### Entity Relationship Diagrams (ERD)\n\nVisualize data models represented as entities, attributes, and relationships. Diagrams are created using simple syntax.\n\n**Use for**: Database schema design, data modeling, understanding entity relationships, documenting data structures\n\n**diagramType**: `\"entity-relationship-diagram\"`\n\n**Reference**: [ERD Syntax](references\u002Ferd-syntax.md)\n\n### Cloud Architecture Diagrams\n\nVisualize cloud infrastructure represented as nodes, groups, and connections. Diagrams are created using simple syntax.\n\n**Use for**: Cloud infrastructure visualization, AWS\u002FAzure\u002FGCP architectures, system architecture documentation, data flow visualization\n\n**diagramType**: `\"cloud-architecture-diagram\"`\n\n**Reference**: [Architecture Syntax](references\u002Farchitecture-syntax.md)\n\n### Sequence Diagrams\n\nVisualize system flows using sequence diagrams. Each vertical column represents an entity (e.g. user, server, DB) and arrows between the columns represent the flow of information or requests. Diagrams are created using simple syntax.\n\n**Use for**: API request\u002Fresponse flows, system interactions, user workflows, message passing between services, process flows over time\n\n**diagramType**: `\"sequence-diagram\"`\n\n**Reference**: [Sequence Syntax](references\u002Fsequence-syntax.md)\n\n### BPMN Diagrams (Swimlane Diagrams)\n\nVisualize business processes represented as pools, lanes, and flow objects such as tasks, events, and gateways. Diagrams are created using simple syntax.\n\n**Use for**: Business process documentation, workflow visualization, process improvement, cross-functional processes, swimlane diagrams showing roles\u002Fresponsibilities\n\n**diagramType**: `\"bpmn-diagram\"`\n\n**Reference**: [BPMN Syntax](references\u002Fbpmn-syntax.md)\n\nEach reference file contains complete syntax documentation, property references, and practical examples.\n\n## API Integration\n\n### Endpoint\n\n```\nPOST https:\u002F\u002Fapp.eraser.io\u002Fapi\u002Frender\u002Felements\nContent-Type: application\u002Fjson\nAuthorization: Bearer ${ERASER_API_TOKEN}\nX-Skill-Source: eraser-skill\n```\n\n**Note**: The `X-Skill-Source` header identifies the AI agent. You MUST replace `eraser-skill` with your actual agent name:\n- If you are Claude (Anthropic), use: `claude`\n- If you are running in Cursor, use: `cursor`\n- If you are ChatGPT (OpenAI), use: `chatgpt`\n- If you are Gemini (Google), use: `gemini`\n- Otherwise, use your model\u002Fagent name in lowercase\n\n### Response Format\n\n```json\n{\n  \"imageUrl\": \"https:\u002F\u002Fstorage.googleapis.com\u002Feraser-images\u002F...\",\n  \"createEraserFileUrl\": \"https:\u002F\u002Fapp.eraser.io\u002Fnew?requestId=abc123&state=xyz789\",\n  \"renderedElements\": [...]\n}\n```\n\n### Error Responses\n\n| Status | Error | Cause | Solution |\n| --- | --- | --- | --- |\n| 400 | `Diagram element has no code` | Missing `code` field in element | Ensure element has valid DSL code |\n| 400 | `Diagram element has no diagramType` | Missing `diagramType` field | Add valid diagramType to element |\n| 400 | `Invalid diagramType` | Unsupported diagram type | Use one of the supported types listed above |\n| 401 | `Unauthorized` | Invalid or expired API token | Check `ERASER_API_TOKEN` is valid |\n| 500 | `Internal server error` | Server-side issue | Retry the request; if persistent, contact support |\n\n**Error Response Format:**\n\n```json\n{\n  \"error\": {\n    \"message\": \"Diagram element has no code\",\n    \"status\": 400\n  }\n}\n```\n\n**Troubleshooting Tips:**\n\n- Verify DSL syntax is correct before making the API call\n- Ensure `diagramType` matches the DSL content (e.g., sequence DSL with `sequence-diagram`)\n- For auth errors, verify the API key is set correctly as an environment variable\n\n## Instructions\n\nWhen the user requests a diagram:\n\n1. **Extract Information**\n\n   - If code\u002Ffiles are provided, analyze the structure, resources, and relationships\n   - If description is provided, identify key components and connections\n   - Determine the appropriate diagram type\n\n2. **Generate Eraser DSL**\n\n   - Create Eraser DSL code that represents the architecture\n   - **CRITICAL: Label Formatting Rules**\n     - Labels MUST be on a single line - NEVER use newlines inside label attributes\n     - Keep labels simple and readable - prefer separate labels over concatenating too much metadata\n     - Format DSL with proper line breaks (one node\u002Fgroup per line, but labels stay on single lines)\n   - For detailed DSL syntax and examples, see the [Diagram Types and Syntax](#diagram-types-and-syntax) section above for links to reference files\n\n3. **Create Element Definition**\n\n   - Create an element object with:\n     - `type: \"diagram\"`\n     - `id: \"diagram-1\"` (or generate a unique ID)\n     - `code: \"\u003Cyour generated DSL code>\"`\n     - `diagramType: \"\u003Cappropriate type>\"`\n\n4. **Make the HTTP Request**\n\n   **IMPORTANT**: You MUST execute this curl command after generating the DSL. Never stop after generating DSL without making the API call.\n\n   **CRITICAL**: Replace `eraser-skill` in the `X-Skill-Source` header with your actual AI agent name (see API Integration section above for values).\n\n   ```bash\n   curl -X POST https:\u002F\u002Fapp.eraser.io\u002Fapi\u002Frender\u002Felements \\\n     -H \"Content-Type: application\u002Fjson\" \\\n     -H \"X-Skill-Source: eraser-skill\" \\\n     -H \"Authorization: Bearer ${ERASER_API_TOKEN}\" \\\n     -d '{\n       \"elements\": [{\n         \"type\": \"diagram\",\n         \"id\": \"diagram-1\",\n         \"code\": \"\u003Cyour generated DSL>\",\n         \"diagramType\": \"cloud-architecture-diagram\"\n       }],\n       \"scale\": 2,\n       \"theme\": \"${ERASER_THEME:-dark}\",\n       \"background\": true\n     }'\n   ```\n\n5. **Track Sources During Analysis**\n\n   As you analyze files and resources to generate the diagram, track:\n\n   - **Internal files**: Record each file path you read and what information was extracted (e.g., `infra\u002Fmain.tf` - VPC and subnet definitions)\n   - **External references**: Note any documentation, examples, or URLs consulted (e.g., AWS VPC best practices documentation)\n   - **Annotations**: For each source, note what it contributed to the diagram\n\n6. **Handle the Response**\n\n   **CRITICAL: Minimal Output Format**\n\n   Your response MUST always include these elements with clear headers:\n\n   1. **Diagram Preview**: Display with a header\n      ```\n      ## Diagram\n      ![{Title}]({imageUrl})\n      ```\n      Use the ACTUAL `imageUrl` from the API response.\n\n   2. **Editor Link**: Display with a header\n      ```\n      ## Open in Eraser\n      [Edit this diagram in the Eraser editor]({createEraserFileUrl})\n      ```\n      Use the ACTUAL URL from the API response.\n\n   3. **Sources section**: Brief list of files\u002Fresources analyzed (if applicable)\n      ```\n      ## Sources\n      - `path\u002Fto\u002Ffile` - What was extracted\n      ```\n\n   4. **Diagram Code section**: The Eraser DSL in a code block with `eraser` language tag\n      ```\n      ## Diagram Code\n      ```eraser\n      {DSL code here}\n      ```\n      ```\n\n   5. **Learn More link**: `You can learn more about Eraser at https:\u002F\u002Fdocs.eraser.io\u002Fdocs\u002Fusing-ai-agent-integrations`\n\n   **Additional content rules:**\n   - If the user ONLY asked for a diagram, include NOTHING beyond the 5 elements above\n   - If the user explicitly asked for more (e.g., \"explain the architecture\", \"suggest improvements\"), you may include that additional content\n   - Never add unrequested sections like Overview, Security Considerations, Testing, etc.\n\n   The default output should be SHORT. The diagram image speaks for itself.\n\n7. **Error Handling**\n   - If API call fails, explain the error\n   - Suggest checking API key if authentication fails\n   - Offer to regenerate DSL code as fallback\n\n## Best Practices\n\n- **Generate Valid DSL**: Ensure the DSL syntax is correct before calling the API\n- **Quote Labels Properly**: Always quote labels that contain spaces, special characters, or numbers\n- **Single-Line Labels**: Labels MUST be on a single line - never use newlines inside label attributes\n- **Format for Readability**: Put each node, group, and connection on its own line (but keep labels single-line)\n- **Include Metadata**: If including CIDR blocks, instance types, etc., put them in the same quoted label string: `[label: \"VPC 10.0.0.0\u002F16\"]`\n- **Use Appropriate Diagram Type**: Choose the right `diagramType` for the content\n- **Group Related Items**: Use containers (VPCs, modules) to group related components\n- **Specify Connections**: Show data flows, dependencies, and relationships\n- **Handle Large Systems**: Break down very large systems into focused diagrams\n- **Include Source Header**: Always include `X-Skill-Source` header with your AI agent name (claude, cursor, chatgpt, etc.)\n\n## Notes\n\n- Free tier diagrams include a watermark but are fully functional\n- The `createEraserFileUrl` is always returned (works for both free and paid tiers) and allows users to edit diagrams in the Eraser web editor\n- The DSL code can be used to regenerate or modify diagrams\n- API responses are cached, so identical requests return quickly\n",{"name":5,"license":15,"metadata":24,"description":7,"allowed-tools":28,"compatibility":29},{"tags":25,"author":26,"version":27},"diagram, architecture, infrastructure, visualization, terraform, aws, azure, cloud","Eraser Labs","1.0.0","Read Write Bash(curl:*)","Requires network access to call Eraser API","main","9836d94e88404aabb682086405c2aa9cba7657ac","plugins\u002Feraser\u002Fskills\u002Fdiagram",156,"https:\u002F\u002Fgithub.com\u002FCognitionAI\u002Fdevin-marketplace","https:\u002F\u002Fgithub.com\u002FCognitionAI","https:\u002F\u002Fcognition.ai\u002F","Makers of Devin, the AI software engineer.","2026-11-13 07:08:23",{"source":8,"skillName":5,"commands":40,"prompt":50,"zipAvailable":51},[41,44,47],{"tool":42,"command":43},"npx","npx skills add CognitionAI\u002Fdevin-marketplace --skill diagram",{"tool":45,"command":46},"bunx","bunx skills add CognitionAI\u002Fdevin-marketplace --skill diagram",{"tool":48,"command":49},"pnpm","pnpm dlx skills add CognitionAI\u002Fdevin-marketplace --skill diagram","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002FCognitionAI\u002Fdevin-marketplace\u002Fblob\u002Fmain\u002Fplugins\u002Feraser\u002Fskills\u002Fdiagram\u002FSKILL.md",true,[53,59,63,67,71],{"path":54,"resourceType":55,"resourceTypeDesc":56,"sizeBytes":57,"sourceHtmlUrl":58},"references\u002Farchitecture-syntax.md","REFERENCE","参考文档",8358,"https:\u002F\u002Fgithub.com\u002FCognitionAI\u002Fdevin-marketplace\u002Fblob\u002Fmain\u002Fplugins\u002Feraser\u002Fskills\u002Fdiagram\u002Freferences\u002Farchitecture-syntax.md",{"path":60,"resourceType":55,"resourceTypeDesc":56,"sizeBytes":61,"sourceHtmlUrl":62},"references\u002Fbpmn-syntax.md",8425,"https:\u002F\u002Fgithub.com\u002FCognitionAI\u002Fdevin-marketplace\u002Fblob\u002Fmain\u002Fplugins\u002Feraser\u002Fskills\u002Fdiagram\u002Freferences\u002Fbpmn-syntax.md",{"path":64,"resourceType":55,"resourceTypeDesc":56,"sizeBytes":65,"sourceHtmlUrl":66},"references\u002Ferd-syntax.md",6197,"https:\u002F\u002Fgithub.com\u002FCognitionAI\u002Fdevin-marketplace\u002Fblob\u002Fmain\u002Fplugins\u002Feraser\u002Fskills\u002Fdiagram\u002Freferences\u002Ferd-syntax.md",{"path":68,"resourceType":55,"resourceTypeDesc":56,"sizeBytes":69,"sourceHtmlUrl":70},"references\u002Fflowchart-syntax.md",7162,"https:\u002F\u002Fgithub.com\u002FCognitionAI\u002Fdevin-marketplace\u002Fblob\u002Fmain\u002Fplugins\u002Feraser\u002Fskills\u002Fdiagram\u002Freferences\u002Fflowchart-syntax.md",{"path":72,"resourceType":55,"resourceTypeDesc":56,"sizeBytes":73,"sourceHtmlUrl":74},"references\u002Fsequence-syntax.md",5816,"https:\u002F\u002Fgithub.com\u002FCognitionAI\u002Fdevin-marketplace\u002Fblob\u002Fmain\u002Fplugins\u002Feraser\u002Fskills\u002Fdiagram\u002Freferences\u002Fsequence-syntax.md",[76,82,89,95,102,109],{"skillNo":77,"name":78,"nameZh":6,"description":6,"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},"01M7BYC4AJGM98P2G9JH7QS24Z","business-data","https:\u002F\u002Fgithub.com\u002FCognitionAI\u002Fdevin-marketplace\u002Fblob\u002Fmain\u002Fplugins\u002Fwindsor-ai\u002Fskills\u002Fbusiness-data\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},"01M7BYBZ0CD4CBCPZHRZ551BNK","workflow","Creates durable, resumable workflows using Vercel's Workflow SDK. Use when building workflows that need to survive restarts, pause for external events, retry on failure, or coordinate multi-step operations over time. Triggers on mentions of \"workflow\", \"durable functions\", \"resumable\", \"workflow sdk\", \"queue\", \"event\", \"push\", \"subscribe\", or step-based orchestration.","https:\u002F\u002Fgithub.com\u002FCognitionAI\u002Fdevin-marketplace\u002Fblob\u002Fmain\u002Fplugins\u002Fvercel\u002Fskills\u002Fworkflow\u002Fupstream\u002FSKILL.md",[],[],{"skillNo":90,"name":84,"nameZh":6,"description":91,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":92,"categories":93,"keywords":94,"publishedAt":19},"01M7BYB1XSZHKHD8JZTQJ62JN0","Vercel Workflow SDK expert guidance. Use when building durable workflows, long-running tasks, API routes or agents that need pause\u002Fresume, retries, step-based execution, or crash-safe orchestration with Vercel Workflow.","https:\u002F\u002Fgithub.com\u002FCognitionAI\u002Fdevin-marketplace\u002Fblob\u002Fmain\u002Fplugins\u002Fvercel\u002Fskills\u002Fworkflow\u002FSKILL.md",[],[],{"skillNo":96,"name":97,"nameZh":6,"description":98,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":99,"categories":100,"keywords":101,"publishedAt":19},"01M7BYASGMK935J33E21N5WTW0","verification","Full-story verification — infers what the user is building, then verifies the complete flow end-to-end: browser → API → data → response. Triggers on dev server start and 'why isn't this working' signals.","https:\u002F\u002Fgithub.com\u002FCognitionAI\u002Fdevin-marketplace\u002Fblob\u002Fmain\u002Fplugins\u002Fvercel\u002Fskills\u002Fverification\u002FSKILL.md",[],[],{"skillNo":103,"name":104,"nameZh":6,"description":105,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":106,"categories":107,"keywords":108,"publishedAt":19},"01M7BY9WJERKSKEH9HK6E71GW2","vercel-storage","Vercel storage expert guidance — Blob, Global Config (formerly Edge Config), and Marketplace storage (Neon Postgres, Upstash Redis). Use when choosing, configuring, or using data storage with Vercel applications.","https:\u002F\u002Fgithub.com\u002FCognitionAI\u002Fdevin-marketplace\u002Fblob\u002Fmain\u002Fplugins\u002Fvercel\u002Fskills\u002Fvercel-storage\u002FSKILL.md",[],[],{"skillNo":110,"name":111,"nameZh":6,"description":112,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":113,"categories":114,"keywords":115,"publishedAt":19},"01M7BY9N034894YV2J9DCRZHYS","vercel-services","Configure and troubleshoot Vercel Services for multiple frontends and backends in one project. Use when composing a polyglot or multi-service application on one Vercel deployment; defining the `services` key, service-targeted rewrites, or service bindings in `vercel.json`; or running all services with `vercel dev`.","https:\u002F\u002Fgithub.com\u002FCognitionAI\u002Fdevin-marketplace\u002Fblob\u002Fmain\u002Fplugins\u002Fvercel\u002Fskills\u002Fvercel-services\u002FSKILL.md",[],[]]