[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M7F4FKA0TSJWB5XENA22WSNE":3,"skill-same:01M7F4FKA0TSJWB5XENA22WSNE":49},{"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":27,"commitSha":28,"skillDirectory":29,"forksCount":30,"repositoryHtmlUrl":31,"repositoryHomepageUrl":6,"ownerHtmlUrl":32,"ownerBlogUrl":6,"ownerDescription":33,"updatedAt":34,"install":35,"resources":48},"01M7F4FKA0TSJWB5XENA22WSNE","segment-automation",null,"Automate Segment tasks via Rube MCP (Composio): track events, identify users, manage groups, page views, aliases, batch operations. Always search tools first for current schemas.","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\u002F05-技能与代理开发\u002Fsegment-automation-antigravity-awesome-skills-main\u002FSKILL.md",[],[],"2026-11-16 10:05:34",false,"---\nname: segment-automation\ndescription: \"Automate Segment tasks via Rube MCP (Composio): track events, identify users, manage groups, page views, aliases, batch operations. Always search tools first for current schemas.\"\nrisk: critical\nsource: community\ndate_added: \"2026-02-27\"\n---\n\n# Segment Automation via Rube MCP\n\nAutomate Segment customer data platform operations through Composio's Segment toolkit via Rube MCP.\n\n## Prerequisites\n\n- Rube MCP must be connected (RUBE_SEARCH_TOOLS available)\n- Active Segment connection via `RUBE_MANAGE_CONNECTIONS` with toolkit `segment`\n- Always call `RUBE_SEARCH_TOOLS` first to get current tool schemas\n\n## Setup\n\n**Get Rube MCP**: Add `https:\u002F\u002Frube.app\u002Fmcp` as an MCP server in your client configuration. No API keys needed — just add the endpoint and it works.\n\n\n1. Verify Rube MCP is available by confirming `RUBE_SEARCH_TOOLS` responds\n2. Call `RUBE_MANAGE_CONNECTIONS` with toolkit `segment`\n3. If connection is not ACTIVE, follow the returned auth link to complete Segment authentication\n4. Confirm connection status shows ACTIVE before running any workflows\n\n## Core Workflows\n\n### 1. Track Events\n\n**When to use**: User wants to send event data to Segment for downstream destinations\n\n**Tool sequence**:\n1. `SEGMENT_TRACK` - Send a single track event [Required]\n\n**Key parameters**:\n- `userId`: User identifier (required if no `anonymousId`)\n- `anonymousId`: Anonymous identifier (required if no `userId`)\n- `event`: Event name (e.g., 'Order Completed', 'Button Clicked')\n- `properties`: Object with event-specific properties\n- `timestamp`: ISO 8601 timestamp (optional; defaults to server time)\n- `context`: Object with contextual metadata (IP, user agent, etc.)\n\n**Pitfalls**:\n- At least one of `userId` or `anonymousId` is required\n- `event` name is required and should follow consistent naming conventions\n- Properties are freeform objects; ensure consistent schema across events\n- Timestamp must be ISO 8601 format (e.g., '2024-01-15T10:30:00Z')\n- Events are processed asynchronously; successful API response means accepted, not delivered\n\n### 2. Identify Users\n\n**When to use**: User wants to associate traits with a user profile in Segment\n\n**Tool sequence**:\n1. `SEGMENT_IDENTIFY` - Set user traits and identity [Required]\n\n**Key parameters**:\n- `userId`: User identifier (required if no `anonymousId`)\n- `anonymousId`: Anonymous identifier\n- `traits`: Object with user properties (email, name, plan, etc.)\n- `timestamp`: ISO 8601 timestamp\n- `context`: Contextual metadata\n\n**Pitfalls**:\n- At least one of `userId` or `anonymousId` is required\n- Traits are merged with existing traits, not replaced\n- To remove a trait, set it to `null`\n- Identify calls should be made before track calls for new users\n- Avoid sending PII in traits unless destinations are configured for it\n\n### 3. Batch Operations\n\n**When to use**: User wants to send multiple events, identifies, or other calls in a single request\n\n**Tool sequence**:\n1. `SEGMENT_BATCH` - Send multiple Segment calls in one request [Required]\n\n**Key parameters**:\n- `batch`: Array of message objects, each with:\n  - `type`: Message type ('track', 'identify', 'group', 'page', 'alias')\n  - `userId` \u002F `anonymousId`: User identifier\n  - Additional fields based on type (event, properties, traits, etc.)\n\n**Pitfalls**:\n- Each message in the batch must have a valid `type` field\n- Maximum batch size limit applies; check schema for current limit\n- All messages in a batch are processed independently; one failure does not affect others\n- Each message must independently satisfy its type's requirements (e.g., track needs event name)\n- Batch is the most efficient way to send multiple calls; prefer over individual calls\n\n### 4. Group Users\n\n**When to use**: User wants to associate a user with a company, team, or organization\n\n**Tool sequence**:\n1. `SEGMENT_GROUP` - Associate user with a group [Required]\n\n**Key parameters**:\n- `userId`: User identifier (required if no `anonymousId`)\n- `anonymousId`: Anonymous identifier\n- `groupId`: Group\u002Forganization identifier (required)\n- `traits`: Object with group properties (name, industry, size, plan)\n- `timestamp`: ISO 8601 timestamp\n\n**Pitfalls**:\n- `groupId` is required; it identifies the company or organization\n- Group traits are merged with existing traits for that group\n- A user can belong to multiple groups\n- Group traits update the group profile, not the user profile\n\n### 5. Track Page Views\n\n**When to use**: User wants to record page view events in Segment\n\n**Tool sequence**:\n1. `SEGMENT_PAGE` - Send a page view event [Required]\n\n**Key parameters**:\n- `userId`: User identifier (required if no `anonymousId`)\n- `anonymousId`: Anonymous identifier\n- `name`: Page name (e.g., 'Home', 'Pricing', 'Dashboard')\n- `category`: Page category (e.g., 'Docs', 'Marketing')\n- `properties`: Object with page-specific properties (url, title, referrer)\n\n**Pitfalls**:\n- At least one of `userId` or `anonymousId` is required\n- `name` and `category` are optional but recommended for proper analytics\n- Standard properties include `url`, `title`, `referrer`, `path`, `search`\n- Page calls are often automated; manual use is for server-side page tracking\n\n### 6. Alias Users and Manage Sources\n\n**When to use**: User wants to merge anonymous and identified users, or manage source configuration\n\n**Tool sequence**:\n1. `SEGMENT_ALIAS` - Link two user identities together [Optional]\n2. `SEGMENT_LIST_SCHEMA_SETTINGS_IN_SOURCE` - View source schema settings [Optional]\n3. `SEGMENT_UPDATE_SOURCE` - Update source configuration [Optional]\n\n**Key parameters**:\n- For ALIAS:\n  - `userId`: New user identifier (the identified ID)\n  - `previousId`: Old user identifier (the anonymous ID)\n- For source operations:\n  - `sourceId`: Source identifier\n\n**Pitfalls**:\n- ALIAS is a one-way operation; cannot be undone\n- `previousId` is the anonymous\u002Fold ID, `userId` is the new\u002Fidentified ID\n- Not all destinations support alias calls; check destination documentation\n- ALIAS should be called once when a user first identifies (e.g., signs up)\n- Source updates may affect data collection; review changes carefully\n\n## Common Patterns\n\n### User Lifecycle\n\nStandard Segment user lifecycle:\n```\n1. Anonymous user visits -> PAGE call with anonymousId\n2. User interacts -> TRACK call with anonymousId\n3. User signs up -> ALIAS (anonymousId -> userId), then IDENTIFY with traits\n4. User takes action -> TRACK call with userId\n5. User joins org -> GROUP call linking userId to groupId\n```\n\n### Batch Optimization\n\nFor bulk data ingestion:\n```\n1. Collect events in memory (array of message objects)\n2. Each message includes type, userId\u002FanonymousId, and type-specific fields\n3. Call SEGMENT_BATCH with the collected messages\n4. Check response for any individual message errors\n```\n\n### Naming Conventions\n\nSegment recommends consistent event naming:\n- **Events**: Use \"Object Action\" format (e.g., 'Order Completed', 'Article Viewed')\n- **Properties**: Use snake_case (e.g., 'order_total', 'product_name')\n- **Traits**: Use snake_case (e.g., 'first_name', 'plan_type')\n\n## Known Pitfalls\n\n**Identity Resolution**:\n- Always include `userId` or `anonymousId` on every call\n- Use ALIAS only once per user identity merge\n- Identify before tracking to ensure proper user association\n\n**Data Quality**:\n- Event names should be consistent across all sources\n- Properties should follow a defined schema for downstream compatibility\n- Avoid sending sensitive PII unless destinations are configured for it\n\n**Rate Limits**:\n- Use BATCH for bulk operations to stay within rate limits\n- Individual calls are rate-limited per source\n- Batch calls are more efficient and less likely to be throttled\n\n**Response Parsing**:\n- Successful responses indicate acceptance, not delivery to destinations\n- Response data may be nested under `data` key\n- Check for error fields in batch responses for individual message failures\n\n**Timestamps**:\n- Must be ISO 8601 format with timezone (e.g., '2024-01-15T10:30:00Z')\n- Omitting timestamp uses server receive time\n- Historical data imports should include explicit timestamps\n\n## Quick Reference\n\n| Task | Tool Slug | Key Params |\n|------|-----------|------------|\n| Track event | SEGMENT_TRACK | userId, event, properties |\n| Identify user | SEGMENT_IDENTIFY | userId, traits |\n| Batch calls | SEGMENT_BATCH | batch (array of messages) |\n| Group user | SEGMENT_GROUP | userId, groupId, traits |\n| Page view | SEGMENT_PAGE | userId, name, properties |\n| Alias identity | SEGMENT_ALIAS | userId, previousId |\n| Source schema | SEGMENT_LIST_SCHEMA_SETTINGS_IN_SOURCE | sourceId |\n| Update source | SEGMENT_UPDATE_SOURCE | sourceId |\n| Warehouses | SEGMENT_LIST_CONNECTED_WAREHOUSES_FROM_SOURCE | sourceId |\n\n## When to Use\nThis skill is applicable to execute the workflow or actions described in the overview.\n","# Segment Automation via Rube MCP\n\nAutomate Segment customer data platform operations through Composio's Segment toolkit via Rube MCP.\n\n## Prerequisites\n\n- Rube MCP must be connected (RUBE_SEARCH_TOOLS available)\n- Active Segment connection via `RUBE_MANAGE_CONNECTIONS` with toolkit `segment`\n- Always call `RUBE_SEARCH_TOOLS` first to get current tool schemas\n\n## Setup\n\n**Get Rube MCP**: Add `https:\u002F\u002Frube.app\u002Fmcp` as an MCP server in your client configuration. No API keys needed — just add the endpoint and it works.\n\n\n1. Verify Rube MCP is available by confirming `RUBE_SEARCH_TOOLS` responds\n2. Call `RUBE_MANAGE_CONNECTIONS` with toolkit `segment`\n3. If connection is not ACTIVE, follow the returned auth link to complete Segment authentication\n4. Confirm connection status shows ACTIVE before running any workflows\n\n## Core Workflows\n\n### 1. Track Events\n\n**When to use**: User wants to send event data to Segment for downstream destinations\n\n**Tool sequence**:\n1. `SEGMENT_TRACK` - Send a single track event [Required]\n\n**Key parameters**:\n- `userId`: User identifier (required if no `anonymousId`)\n- `anonymousId`: Anonymous identifier (required if no `userId`)\n- `event`: Event name (e.g., 'Order Completed', 'Button Clicked')\n- `properties`: Object with event-specific properties\n- `timestamp`: ISO 8601 timestamp (optional; defaults to server time)\n- `context`: Object with contextual metadata (IP, user agent, etc.)\n\n**Pitfalls**:\n- At least one of `userId` or `anonymousId` is required\n- `event` name is required and should follow consistent naming conventions\n- Properties are freeform objects; ensure consistent schema across events\n- Timestamp must be ISO 8601 format (e.g., '2024-01-15T10:30:00Z')\n- Events are processed asynchronously; successful API response means accepted, not delivered\n\n### 2. Identify Users\n\n**When to use**: User wants to associate traits with a user profile in Segment\n\n**Tool sequence**:\n1. `SEGMENT_IDENTIFY` - Set user traits and identity [Required]\n\n**Key parameters**:\n- `userId`: User identifier (required if no `anonymousId`)\n- `anonymousId`: Anonymous identifier\n- `traits`: Object with user properties (email, name, plan, etc.)\n- `timestamp`: ISO 8601 timestamp\n- `context`: Contextual metadata\n\n**Pitfalls**:\n- At least one of `userId` or `anonymousId` is required\n- Traits are merged with existing traits, not replaced\n- To remove a trait, set it to `null`\n- Identify calls should be made before track calls for new users\n- Avoid sending PII in traits unless destinations are configured for it\n\n### 3. Batch Operations\n\n**When to use**: User wants to send multiple events, identifies, or other calls in a single request\n\n**Tool sequence**:\n1. `SEGMENT_BATCH` - Send multiple Segment calls in one request [Required]\n\n**Key parameters**:\n- `batch`: Array of message objects, each with:\n  - `type`: Message type ('track', 'identify', 'group', 'page', 'alias')\n  - `userId` \u002F `anonymousId`: User identifier\n  - Additional fields based on type (event, properties, traits, etc.)\n\n**Pitfalls**:\n- Each message in the batch must have a valid `type` field\n- Maximum batch size limit applies; check schema for current limit\n- All messages in a batch are processed independently; one failure does not affect others\n- Each message must independently satisfy its type's requirements (e.g., track needs event name)\n- Batch is the most efficient way to send multiple calls; prefer over individual calls\n\n### 4. Group Users\n\n**When to use**: User wants to associate a user with a company, team, or organization\n\n**Tool sequence**:\n1. `SEGMENT_GROUP` - Associate user with a group [Required]\n\n**Key parameters**:\n- `userId`: User identifier (required if no `anonymousId`)\n- `anonymousId`: Anonymous identifier\n- `groupId`: Group\u002Forganization identifier (required)\n- `traits`: Object with group properties (name, industry, size, plan)\n- `timestamp`: ISO 8601 timestamp\n\n**Pitfalls**:\n- `groupId` is required; it identifies the company or organization\n- Group traits are merged with existing traits for that group\n- A user can belong to multiple groups\n- Group traits update the group profile, not the user profile\n\n### 5. Track Page Views\n\n**When to use**: User wants to record page view events in Segment\n\n**Tool sequence**:\n1. `SEGMENT_PAGE` - Send a page view event [Required]\n\n**Key parameters**:\n- `userId`: User identifier (required if no `anonymousId`)\n- `anonymousId`: Anonymous identifier\n- `name`: Page name (e.g., 'Home', 'Pricing', 'Dashboard')\n- `category`: Page category (e.g., 'Docs', 'Marketing')\n- `properties`: Object with page-specific properties (url, title, referrer)\n\n**Pitfalls**:\n- At least one of `userId` or `anonymousId` is required\n- `name` and `category` are optional but recommended for proper analytics\n- Standard properties include `url`, `title`, `referrer`, `path`, `search`\n- Page calls are often automated; manual use is for server-side page tracking\n\n### 6. Alias Users and Manage Sources\n\n**When to use**: User wants to merge anonymous and identified users, or manage source configuration\n\n**Tool sequence**:\n1. `SEGMENT_ALIAS` - Link two user identities together [Optional]\n2. `SEGMENT_LIST_SCHEMA_SETTINGS_IN_SOURCE` - View source schema settings [Optional]\n3. `SEGMENT_UPDATE_SOURCE` - Update source configuration [Optional]\n\n**Key parameters**:\n- For ALIAS:\n  - `userId`: New user identifier (the identified ID)\n  - `previousId`: Old user identifier (the anonymous ID)\n- For source operations:\n  - `sourceId`: Source identifier\n\n**Pitfalls**:\n- ALIAS is a one-way operation; cannot be undone\n- `previousId` is the anonymous\u002Fold ID, `userId` is the new\u002Fidentified ID\n- Not all destinations support alias calls; check destination documentation\n- ALIAS should be called once when a user first identifies (e.g., signs up)\n- Source updates may affect data collection; review changes carefully\n\n## Common Patterns\n\n### User Lifecycle\n\nStandard Segment user lifecycle:\n```\n1. Anonymous user visits -> PAGE call with anonymousId\n2. User interacts -> TRACK call with anonymousId\n3. User signs up -> ALIAS (anonymousId -> userId), then IDENTIFY with traits\n4. User takes action -> TRACK call with userId\n5. User joins org -> GROUP call linking userId to groupId\n```\n\n### Batch Optimization\n\nFor bulk data ingestion:\n```\n1. Collect events in memory (array of message objects)\n2. Each message includes type, userId\u002FanonymousId, and type-specific fields\n3. Call SEGMENT_BATCH with the collected messages\n4. Check response for any individual message errors\n```\n\n### Naming Conventions\n\nSegment recommends consistent event naming:\n- **Events**: Use \"Object Action\" format (e.g., 'Order Completed', 'Article Viewed')\n- **Properties**: Use snake_case (e.g., 'order_total', 'product_name')\n- **Traits**: Use snake_case (e.g., 'first_name', 'plan_type')\n\n## Known Pitfalls\n\n**Identity Resolution**:\n- Always include `userId` or `anonymousId` on every call\n- Use ALIAS only once per user identity merge\n- Identify before tracking to ensure proper user association\n\n**Data Quality**:\n- Event names should be consistent across all sources\n- Properties should follow a defined schema for downstream compatibility\n- Avoid sending sensitive PII unless destinations are configured for it\n\n**Rate Limits**:\n- Use BATCH for bulk operations to stay within rate limits\n- Individual calls are rate-limited per source\n- Batch calls are more efficient and less likely to be throttled\n\n**Response Parsing**:\n- Successful responses indicate acceptance, not delivery to destinations\n- Response data may be nested under `data` key\n- Check for error fields in batch responses for individual message failures\n\n**Timestamps**:\n- Must be ISO 8601 format with timezone (e.g., '2024-01-15T10:30:00Z')\n- Omitting timestamp uses server receive time\n- Historical data imports should include explicit timestamps\n\n## Quick Reference\n\n| Task | Tool Slug | Key Params |\n|------|-----------|------------|\n| Track event | SEGMENT_TRACK | userId, event, properties |\n| Identify user | SEGMENT_IDENTIFY | userId, traits |\n| Batch calls | SEGMENT_BATCH | batch (array of messages) |\n| Group user | SEGMENT_GROUP | userId, groupId, traits |\n| Page view | SEGMENT_PAGE | userId, name, properties |\n| Alias identity | SEGMENT_ALIAS | userId, previousId |\n| Source schema | SEGMENT_LIST_SCHEMA_SETTINGS_IN_SOURCE | sourceId |\n| Update source | SEGMENT_UPDATE_SOURCE | sourceId |\n| Warehouses | SEGMENT_LIST_CONNECTED_WAREHOUSES_FROM_SOURCE | sourceId |\n\n## When to Use\nThis skill is applicable to execute the workflow or actions described in the overview.\n",{"name":5,"risk":24,"source":25,"date_added":26,"description":7},"critical","community","2026-02-27","main","d69096e239f2a89aabc2cd078c47664a9d3b1e11","05-技能与代理开发\u002Fsegment-automation-antigravity-awesome-skills-main",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":36,"prompt":46,"zipAvailable":47},[37,40,43],{"tool":38,"command":39},"npx","npx skills add lza6\u002FArmor-piercing-system-prompts --skill segment-automation",{"tool":41,"command":42},"bunx","bunx skills add lza6\u002FArmor-piercing-system-prompts --skill segment-automation",{"tool":44,"command":45},"pnpm","pnpm dlx skills add lza6\u002FArmor-piercing-system-prompts --skill segment-automation","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002Flza6\u002FArmor-piercing-system-prompts\u002Fblob\u002Fmain\u002F05-技能与代理开发\u002Fsegment-automation-antigravity-awesome-skills-main\u002FSKILL.md",true,[],[50,57,62,69,76,83],{"skillNo":51,"name":52,"nameZh":6,"description":53,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":54,"categories":55,"keywords":56,"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":58,"name":52,"nameZh":6,"description":53,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":59,"categories":60,"keywords":61,"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":63,"name":64,"nameZh":6,"description":65,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":66,"categories":67,"keywords":68,"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":70,"name":71,"nameZh":6,"description":72,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":73,"categories":74,"keywords":75,"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":77,"name":78,"nameZh":6,"description":79,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":80,"categories":81,"keywords":82,"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":84,"name":85,"nameZh":6,"description":86,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":87,"categories":88,"keywords":89,"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",[],[]]