[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill-e9556a01-8aad-4e74-8d93-3a53eced128a":3,"$fE-14RNGoDVBYo9KwqhbcnqW6PRPnl8sqqtjAttpsOSQ":43},{"id":4,"title":5,"description":6,"categoryId":7,"moduleId":8,"tags":9,"prompt":10,"icon":11,"source":12,"sourceUrl":13,"authorId":14,"authorName":15,"isPublic":16,"stars":17,"runs":18,"createdAt":19,"updatedAt":19,"module":20,"category":27,"packages":34},"e9556a01-8aad-4e74-8d93-3a53eced128a","mixpanel-automation","通过Rube MCP（Composio）自动化Mixpanel任务：事件、细分、漏斗、群体、用户档案、JQL查询。始终首先搜索工具以查找当前模式。","cat_prod_automation","mod_productivity","sickn33,productivity","---\nname: mixpanel-automation\ndescription: \"Automate Mixpanel tasks via Rube MCP (Composio): events, segmentation, funnels, cohorts, user profiles, JQL queries. Always search tools first for current schemas.\"\nrisk: critical\nsource: community\ndate_added: \"2026-02-27\"\n---\n\n# Mixpanel Automation via Rube MCP\n\nAutomate Mixpanel product analytics through Composio's Mixpanel toolkit via Rube MCP.\n\n## Prerequisites\n\n- Rube MCP must be connected (RUBE_SEARCH_TOOLS available)\n- Active Mixpanel connection via `RUBE_MANAGE_CONNECTIONS` with toolkit `mixpanel`\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 `mixpanel`\n3. If connection is not ACTIVE, follow the returned auth link to complete Mixpanel authentication\n4. Confirm connection status shows ACTIVE before running any workflows\n\n## Core Workflows\n\n### 1. Aggregate Event Data\n\n**When to use**: User wants to count events, get totals, or track event trends over time\n\n**Tool sequence**:\n1. `MIXPANEL_GET_ALL_PROJECTS` - List projects to get project ID [Prerequisite]\n2. `MIXPANEL_AGGREGATE_EVENT_COUNTS` - Get event counts and aggregations [Required]\n\n**Key parameters**:\n- `event`: Event name or array of event names to aggregate\n- `from_date` \u002F `to_date`: Date range in 'YYYY-MM-DD' format\n- `unit`: Time granularity ('minute', 'hour', 'day', 'week', 'month')\n- `type`: Aggregation type ('general', 'unique', 'average')\n- `where`: Filter expression for event properties\n\n**Pitfalls**:\n- Date format must be 'YYYY-MM-DD'; other formats cause errors\n- Event names are case-sensitive; use exact names from your Mixpanel project\n- `where` filter uses Mixpanel expression syntax (e.g., `properties[\"country\"] == \"US\"`)\n- Maximum date range may be limited depending on your Mixpanel plan\n\n### 2. Run Segmentation Queries\n\n**When to use**: User wants to break down events by properties for detailed analysis\n\n**Tool sequence**:\n1. `MIXPANEL_QUERY_SEGMENTATION` - Run segmentation analysis [Required]\n\n**Key parameters**:\n- `event`: Event name to segment\n- `from_date` \u002F `to_date`: Date range in 'YYYY-MM-DD' format\n- `on`: Property to segment by (e.g., `properties[\"country\"]`)\n- `unit`: Time granularity\n- `type`: Count type ('general', 'unique', 'average')\n- `where`: Filter expression\n- `limit`: Maximum number of segments to return\n\n**Pitfalls**:\n- The `on` parameter uses Mixpanel property expression syntax\n- Property references must use `properties[\"prop_name\"]` format\n- Segmentation on high-cardinality properties returns capped results; use `limit`\n- Results are grouped by the segmentation property and time unit\n\n### 3. Analyze Funnels\n\n**When to use**: User wants to track conversion funnels and identify drop-off points\n\n**Tool sequence**:\n1. `MIXPANEL_LIST_FUNNELS` - List saved funnels to find funnel ID [Prerequisite]\n2. `MIXPANEL_QUERY_FUNNEL` - Execute funnel analysis [Required]\n\n**Key parameters**:\n- `funnel_id`: ID of the saved funnel to query\n- `from_date` \u002F `to_date`: Date range\n- `unit`: Time granularity\n- `where`: Filter expression\n- `on`: Property to segment funnel by\n- `length`: Conversion window in days\n\n**Pitfalls**:\n- `funnel_id` is required; resolve via LIST_FUNNELS first\n- Funnels must be created in Mixpanel UI first; API only queries existing funnels\n- Conversion window (`length`) defaults vary; set explicitly for accuracy\n- Large date ranges with segmentation can produce very large responses\n\n### 4. Manage User Profiles\n\n**When to use**: User wants to query or update user profiles in Mixpanel\n\n**Tool sequence**:\n1. `MIXPANEL_QUERY_PROFILES` - Search and filter user profiles [Required]\n2. `MIXPANEL_PROFILE_BATCH_UPDATE` - Update multiple user profiles [Optional]\n\n**Key parameters**:\n- `where`: Filter expression for profile properties (e.g., `properties[\"plan\"] == \"premium\"`)\n- `output_properties`: Array of property names to include in results\n- `page`: Page number for pagination\n- `session_id`: Session ID for consistent pagination (from first response)\n- For batch update: array of profile updates with `$distinct_id` and property operations\n\n**Pitfalls**:\n- Profile queries return paginated results; use `session_id` from first response for consistent paging\n- `where` uses Mixpanel expression syntax for profile properties\n- BATCH_UPDATE applies operations (`$set`, `$unset`, `$add`, `$append`) to profiles\n- Batch update has a maximum number of profiles per request; chunk larger updates\n- Profile property names are case-sensitive\n\n### 5. Manage Cohorts\n\n**When to use**: User wants to list or analyze user cohorts\n\n**Tool sequence**:\n1. `MIXPANEL_COHORTS_LIST` - List all saved cohorts [Required]\n\n**Key parameters**:\n- No required parameters; returns all accessible cohorts\n- Response includes cohort `id`, `name`, `description`, `count`\n\n**Pitfalls**:\n- Cohorts are created and managed in Mixpanel UI; API provides read access\n- Cohort IDs are numeric; use exact ID from list results\n- Cohort counts may be approximate for very large cohorts\n- Cohorts can be used as filters in other queries via `where` expressions\n\n### 6. Run JQL and Insight Queries\n\n**When to use**: User wants to run custom JQL queries or insight analyses\n\n**Tool sequence**:\n1. `MIXPANEL_JQL_QUERY` - Execute a custom JQL (JavaScript Query Language) query [Optional]\n2. `MIXPANEL_QUERY_INSIGHT` - Run a saved insight query [Optional]\n\n**Key parameters**:\n- For JQL: `script` containing the JQL JavaScript code\n- For Insight: `bookmark_id` of the saved insight\n- `project_id`: Project context for the query\n\n**Pitfalls**:\n- JQL uses JavaScript-like syntax specific to Mixpanel\n- JQL queries have execution time limits; optimize for efficiency\n- Insight `bookmark_id` must reference an existing saved insight\n- JQL is a legacy feature; check Mixpanel documentation for current availability\n\n## Common Patterns\n\n### ID Resolution\n\n**Project name -> Project ID**:\n```\n1. Call MIXPANEL_GET_ALL_PROJECTS\n2. Find project by name in results\n3. Extract project id\n```\n\n**Funnel name -> Funnel ID**:\n```\n1. Call MIXPANEL_LIST_FUNNELS\n2. Find funnel by name\n3. Extract funnel_id\n```\n\n### Mixpanel Expression Syntax\n\nUsed in `where` and `on` parameters:\n- Property reference: `properties[\"property_name\"]`\n- Equality: `properties[\"country\"] == \"US\"`\n- Comparison: `properties[\"age\"] > 25`\n- Boolean: `properties[\"is_premium\"] == true`\n- Contains: `\"search_term\" in properties[\"name\"]`\n- AND\u002FOR: `properties[\"country\"] == \"US\" and properties[\"plan\"] == \"pro\"`\n\n### Pagination\n\n- Event queries: Follow date-based pagination by adjusting date ranges\n- Profile queries: Use `page` number and `session_id` for consistent results\n- Funnel\u002Fcohort lists: Typically return complete results without pagination\n\n## Known Pitfalls\n\n**Date Formats**:\n- Always use 'YYYY-MM-DD' format\n- Date ranges are inclusive on both ends\n- Data freshness depends on Mixpanel ingestion delay (typically minutes)\n\n**Expression Syntax**:\n- Property references always use `properties[\"name\"]` format\n- String values must be quoted: `properties[\"status\"] == \"active\"`\n- Numeric values are unquoted: `properties[\"count\"] > 10`\n- Boolean values: `true` \u002F `false` (lowercase)\n\n**Rate Limits**:\n- Mixpanel API has rate limits per project\n- Large segmentation queries may time out; reduce date range or segments\n- Use batch operations where available to minimize API calls\n\n**Response Parsing**:\n- Response data may be nested under `data` key\n- Event data is typically grouped by date and segment\n- Numeric values may be returned as strings; parse explicitly\n- Empty date ranges return empty objects, not empty arrays\n\n## Quick Reference\n\n| Task | Tool Slug | Key Params |\n|------|-----------|------------|\n| List projects | MIXPANEL_GET_ALL_PROJECTS | (none) |\n| Aggregate events | MIXPANEL_AGGREGATE_EVENT_COUNTS | event, from_date, to_date, unit |\n| Segmentation | MIXPANEL_QUERY_SEGMENTATION | event, on, from_date, to_date |\n| List funnels | MIXPANEL_LIST_FUNNELS | (none) |\n| Query funnel | MIXPANEL_QUERY_FUNNEL | funnel_id, from_date, to_date |\n| Query profiles | MIXPANEL_QUERY_PROFILES | where, output_properties, page |\n| Batch update profiles | MIXPANEL_PROFILE_BATCH_UPDATE | (profile update objects) |\n| List cohorts | MIXPANEL_COHORTS_LIST | (none) |\n| JQL query | MIXPANEL_JQL_QUERY | script |\n| Query insight | MIXPANEL_QUERY_INSIGHT | bookmark_id |\n\n## When to Use\nThis skill is applicable to execute the workflow or actions described in the overview.\n\n## Limitations\n- Use this skill only when the task clearly matches the scope described above.\n- Do not treat the output as a substitute for environment-specific validation, testing, or expert review.\n- Stop and ask for clarification if required inputs, permissions, safety boundaries, or success criteria are missing.\n","","imported","https:\u002F\u002Fgithub.com\u002Fsickn33\u002Fantigravity-awesome-skills","user_system_seed","SkillOPIC",true,234,277,"2026-05-16 13:28:54",{"id":8,"name":21,"slug":22,"icon":23,"description":24,"sort":25,"createdAt":26},"效率工具","productivity","mdi-lightning-bolt-outline","文档处理、数据分析、自动化工作流",4,"2026-05-16 12:53:40",{"id":7,"name":28,"slug":29,"icon":30,"description":31,"moduleId":8,"sort":32,"skillCount":33,"createdAt":26},"自动化","automation","mdi-robot-outline","工作流自动化、批处理",3,101,[35],{"id":36,"skillId":4,"version":37,"fileName":38,"fileSize":39,"filePath":40,"fileHash":41,"manifest":42,"createdAt":19},"0578a9ee-4af0-45e8-a2f3-8eb9cce38d25","1.0.0","mixpanel-automation.zip",3536,"uploads\u002Fskills\u002Fe9556a01-8aad-4e74-8d93-3a53eced128a\u002Fmixpanel-automation.zip","a3c871c0fdf93c9b1e1b3136008adab3439f4fe20c84d264dbeb79f95a53b0ca","[{\"path\":\"SKILL.md\",\"isDirectory\":false,\"size\":9030}]",{"code":44,"message":45,"data":46},200,"success",{"items":47,"stats":48,"page":51},[],{"averageRating":49,"totalRatings":49,"ratingCounts":50},0,[49,49,49,49,49],{"limit":52,"offset":49,"hasMore":53,"nextOffset":52,"ratedOnly":16},15,false]