[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M7BVVKSS16WR5KTQ2S9K49AM":3,"skill-same:01M7BVVKSS16WR5KTQ2S9K49AM":47},{"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":24,"commitSha":25,"skillDirectory":26,"forksCount":27,"repositoryHtmlUrl":28,"repositoryHomepageUrl":6,"ownerHtmlUrl":29,"ownerBlogUrl":30,"ownerDescription":31,"updatedAt":32,"install":33,"resources":46},"01M7BVVKSS16WR5KTQ2S9K49AM","analyze-account-health",null,"Summarizes B2B account health by analyzing usage patterns, engagement trends, risk signals, and expansion opportunities. Use for customer success reviews, renewal preparation, QBRs, or account prioritization.","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\u002Famplitude\u002Fskills\u002Fanalyze-account-health\u002FSKILL.md",[],[],"2026-11-15 14:19:17",false,"---\nname: analyze-account-health\ndescription: Summarizes B2B account health by analyzing usage patterns, engagement trends, risk signals, and expansion opportunities. Use for customer success reviews, renewal preparation, QBRs, or account prioritization.\n---\n\n# Analyze Account Health\n\nDeep-dive into a B2B account's product usage to prepare for QBRs, assess renewal risk, identify expansion opportunities, or prioritize CS outreach.\n\n## Instructions\n\n### Step 0: Identify Account & Discover Context\n\n**Get the account identifier:**\n- Company name, org ID, account ID, or group property value\n- Ask user if not provided\n\n**Search for existing work:**\nUse `Amplitude:search_amp_entities` to find existing dashboards, charts, or notebooks for this account. If found, ask user if they want fresh analysis or to review existing.\n\n**Resolve how accounts are modelled — do this before any query.**\nEvery step below breaks down \"by account\", and there are three different ways a\nproject represents one. Check in this order and reuse the answer throughout:\n\n1. `get_group_types` — if the project has a group type (commonly `org id` or\n   `company`), that is the account. Account attributes are **group\n   properties**: `get_properties({propertyType: 'group', groupType: '\u003Ctype>'})`,\n   referenced with `scope: 'group'` plus `group_type`. To count accounts rather\n   than users, set `count_unique_by` to the group type.\n2. If there is no group type, the account is usually a **user property**\n   (`company`, `org_name`) — `scope: 'user'`.\n3. Failing both, an **event property** carrying the org (`org id`, `org url`).\n\nIf a group property comes back as `Invalid group property … for group type …`,\nthe query engine's registry is missing it — that is a platform gap, not a\nnaming mistake. Do not retry spelling variants. Fall back to the user- or\nevent-level equivalent from (2)\u002F(3), and tell the user which representation you\nused, since the numbers are not interchangeable.\n\n---\n\n### Step 1: Quick Health Triage\n\nUse `Amplitude:query_amplitude_data` to run these queries in parallel:\n\n**Usage Trend:**\n- Event: `_active`, Metric: `uniques`, Group by: the account property resolved in Step 0 (with its scope)\n- Time: Last 60 days, daily interval\n- **Shows:** Activity increasing or decreasing?\n\n**Engagement Quality:**\n- Calculate DAU and MAU for account\n- Get DAU\u002FMAU ratio (stickiness)\n- **Shows:** How engaged are active users?\n\n**User Momentum:**\n- Active user count week-over-week\n- **Shows:** Team growing or shrinking?\n\n**Classify Health:**\n- **Healthy**: Growing MAU, DAU\u002FMAU >40%, positive WoW\n- **At-Risk**: Flat\u002Fdeclining MAU, DAU\u002FMAU 20-40%, negative WoW\n- **Critical**: Steep decline, DAU\u002FMAU \u003C20%, sustained negative WoW\n\n---\n\n### Step 2: User-Level Analysis\n\nUse `Amplitude:query_amplitude_data` with user-level groupBy:\n\n**Power Users:**\n- Top 3-5 users by event volume (champions to leverage)\n\n**Churned Users:**\n- Users active in previous period but not current (retention risks)\n\n**License Utilization:**\n- Active users in last 30 days vs total seats\n\n---\n\n### Step 3: Feature Usage Analysis\n\nUse `Amplitude:query_amplitude_data` grouped by events\u002Ffeatures:\n\n**Feature Breadth:**\n- Which core features are being used (ask user for 5-10 key features)\n- Adoption rate per feature\n\n**Feature Trends:**\n- Usage over last 90 days per feature\n- Identify growing vs declining features\n\n**Focus based on health:**\n- **If At-Risk\u002FCritical:** Find abandoned features (used 60-90 days ago, not in last 30)\n- **If Healthy:** Find expansion opportunities (premium features not yet tried)\n\n---\n\n### Step 4: Account Feedback Analysis\n\n**Get feedback sources:**\nUse `Amplitude:use_amplitude_ai_feedback` with `facet: \"sources\"` to see what's available.\n\n**Get feedback insights:**\nUse `Amplitude:use_amplitude_ai_feedback` with `facet: \"insights\"` filtered by:\n- ampId for each user in the account\n- dateStart\u002FdateEnd: Last 90 days\n- types: `bug`, `painPoint`, `complaint`, `request`, `lovedFeature`\n\n**Get specific mentions:**\nFor top 3-5 insights, use `Amplitude:use_amplitude_ai_feedback` with `facet: \"mentions\"` to get quotes.\n\n**Correlate with behavior:**\n- Complaint about Feature X? Query their usage of Feature X\n- Request for Feature Y? Check if they hit limits Y would solve\n- Praise for Feature Z? Validate they're heavy users of Z\n\n---\n\n### Step 5: Present Account Health Report\n\nStructure output as follows:\n\n# Account Health Report: [Account Name]\n\n## Executive Summary\n[2-3 sentences: Health score, key trend, primary recommendation]\n\n## Health Score: [🟢 Healthy | 🟡 At-Risk | 🔴 Critical]\n[One sentence rationale with key metric]\n\n---\n\n## Key Metrics\n| Metric | Current | Trend | Status |\n|--------|---------|-------|--------|\n| MAU | X | ↑↓→ Y% | 🟢🟡🔴 |\n| DAU\u002FMAU | X% | ↑↓→ Y% | 🟢🟡🔴 |\n| License Utilization | X% | ↑↓→ | 🟢🟡🔴 |\n| Features Adopted | X\u002FY | ↑↓→ | 🟢🟡🔴 |\n\n---\n\n## 🚨 Risk Factors (if any)\n1. **[Issue]** - [Impact]\n   - Usage data: [metric\u002Ftrend]\n   - Customer feedback: [theme with X mentions] - [representative quote]\n\n## ✅ Positive Signals\n1. **[What's working]** - [Evidence from usage + feedback]\n\n---\n\n## 👥 User Intelligence\n\n### Champions (Leverage)\n- **[User ID\u002FName]**: [Activity summary] - *Action: [Specific CS recommendation]*\n\n### At Risk (Engage)\n- **[User ID\u002FName]**: [Last active date \u002F declining pattern] - *Action: [Check-in recommendation]*\n\n### Inactive (>30 days)\n- [Count] users ([X]% of licenses)\n\n---\n\n## 💡 Top Pain Points & Requests\n\n### Pain Points\n1. **[Theme]** (X mentions)\n   - [Concise description]\n   - Evidence: [Behavioral data] + \"[Quote]\" - [Source, Date]\n   - *Action: [What to do]*\n\n### Feature Requests\n1. **[Theme]** (X mentions)\n   - [What they want]\n   - Evidence: \"[Quote]\" - [Source, Date]\n   - *Roadmap status: [On roadmap\u002FNot planned\u002FConsidering]*\n\n### What They Love ❤️\n1. **[Feature]**: \"[Quote]\"\n\n---\n\n## 📊 Feature Adoption\n\n**High Usage:** [Feature] - [X users] (↑Y%)\n**Declining:** [Feature] - [X users] (↓Y%) - *Investigate*\n**Untapped (Upsell):** [Premium feature] - Could solve [pain point]\n\n---\n\n## 🎯 Recommendations\n\n### 🔥 This Week\n1. [Specific action with user\u002Fcontact name]\n\n### 📅 This Month\n1. [Strategic action with context]\n\n### 💰 Expansion Opportunities\n1. [Upsell signal with evidence]\n\n---\n\n## 📎 Details\n- **Analysis Date:** [Date]\n- **Timeframe:** [Last X days]\n- **Confidence:** [High\u002FMedium\u002FLow based on data volume]\n\n---\n\n## Best Practices\n\n- **Always name users** - CS needs who to contact, not aggregates\n- **Connect feedback to behavior** - Validate complaints with usage data\n- **Be specific in recommendations** - \"Call Sarah about Feature X\" not \"improve engagement\"\n- **Show trends, not snapshots** - Direction matters more than point-in-time\n- **Flag data gaps** - Note low volume, missing properties, or incomplete data\n- **Prioritize by impact** - Focus on issues affecting multiple users or champions\n\n## Common Patterns\n\n**Churn Risks:**\n- Champion churned + declining overall usage\n- Multiple complaints about same issue + behavioral evidence of friction\n- License utilization declining + negative feedback\n\n**Expansion Signals:**\n- Hitting plan limits (users, API, storage)\n- Requests for premium features + high engagement\n- New users being added + positive feedback\n","# Analyze Account Health\n\nDeep-dive into a B2B account's product usage to prepare for QBRs, assess renewal risk, identify expansion opportunities, or prioritize CS outreach.\n\n## Instructions\n\n### Step 0: Identify Account & Discover Context\n\n**Get the account identifier:**\n- Company name, org ID, account ID, or group property value\n- Ask user if not provided\n\n**Search for existing work:**\nUse `Amplitude:search_amp_entities` to find existing dashboards, charts, or notebooks for this account. If found, ask user if they want fresh analysis or to review existing.\n\n**Resolve how accounts are modelled — do this before any query.**\nEvery step below breaks down \"by account\", and there are three different ways a\nproject represents one. Check in this order and reuse the answer throughout:\n\n1. `get_group_types` — if the project has a group type (commonly `org id` or\n   `company`), that is the account. Account attributes are **group\n   properties**: `get_properties({propertyType: 'group', groupType: '\u003Ctype>'})`,\n   referenced with `scope: 'group'` plus `group_type`. To count accounts rather\n   than users, set `count_unique_by` to the group type.\n2. If there is no group type, the account is usually a **user property**\n   (`company`, `org_name`) — `scope: 'user'`.\n3. Failing both, an **event property** carrying the org (`org id`, `org url`).\n\nIf a group property comes back as `Invalid group property … for group type …`,\nthe query engine's registry is missing it — that is a platform gap, not a\nnaming mistake. Do not retry spelling variants. Fall back to the user- or\nevent-level equivalent from (2)\u002F(3), and tell the user which representation you\nused, since the numbers are not interchangeable.\n\n---\n\n### Step 1: Quick Health Triage\n\nUse `Amplitude:query_amplitude_data` to run these queries in parallel:\n\n**Usage Trend:**\n- Event: `_active`, Metric: `uniques`, Group by: the account property resolved in Step 0 (with its scope)\n- Time: Last 60 days, daily interval\n- **Shows:** Activity increasing or decreasing?\n\n**Engagement Quality:**\n- Calculate DAU and MAU for account\n- Get DAU\u002FMAU ratio (stickiness)\n- **Shows:** How engaged are active users?\n\n**User Momentum:**\n- Active user count week-over-week\n- **Shows:** Team growing or shrinking?\n\n**Classify Health:**\n- **Healthy**: Growing MAU, DAU\u002FMAU >40%, positive WoW\n- **At-Risk**: Flat\u002Fdeclining MAU, DAU\u002FMAU 20-40%, negative WoW\n- **Critical**: Steep decline, DAU\u002FMAU \u003C20%, sustained negative WoW\n\n---\n\n### Step 2: User-Level Analysis\n\nUse `Amplitude:query_amplitude_data` with user-level groupBy:\n\n**Power Users:**\n- Top 3-5 users by event volume (champions to leverage)\n\n**Churned Users:**\n- Users active in previous period but not current (retention risks)\n\n**License Utilization:**\n- Active users in last 30 days vs total seats\n\n---\n\n### Step 3: Feature Usage Analysis\n\nUse `Amplitude:query_amplitude_data` grouped by events\u002Ffeatures:\n\n**Feature Breadth:**\n- Which core features are being used (ask user for 5-10 key features)\n- Adoption rate per feature\n\n**Feature Trends:**\n- Usage over last 90 days per feature\n- Identify growing vs declining features\n\n**Focus based on health:**\n- **If At-Risk\u002FCritical:** Find abandoned features (used 60-90 days ago, not in last 30)\n- **If Healthy:** Find expansion opportunities (premium features not yet tried)\n\n---\n\n### Step 4: Account Feedback Analysis\n\n**Get feedback sources:**\nUse `Amplitude:use_amplitude_ai_feedback` with `facet: \"sources\"` to see what's available.\n\n**Get feedback insights:**\nUse `Amplitude:use_amplitude_ai_feedback` with `facet: \"insights\"` filtered by:\n- ampId for each user in the account\n- dateStart\u002FdateEnd: Last 90 days\n- types: `bug`, `painPoint`, `complaint`, `request`, `lovedFeature`\n\n**Get specific mentions:**\nFor top 3-5 insights, use `Amplitude:use_amplitude_ai_feedback` with `facet: \"mentions\"` to get quotes.\n\n**Correlate with behavior:**\n- Complaint about Feature X? Query their usage of Feature X\n- Request for Feature Y? Check if they hit limits Y would solve\n- Praise for Feature Z? Validate they're heavy users of Z\n\n---\n\n### Step 5: Present Account Health Report\n\nStructure output as follows:\n\n# Account Health Report: [Account Name]\n\n## Executive Summary\n[2-3 sentences: Health score, key trend, primary recommendation]\n\n## Health Score: [🟢 Healthy | 🟡 At-Risk | 🔴 Critical]\n[One sentence rationale with key metric]\n\n---\n\n## Key Metrics\n| Metric | Current | Trend | Status |\n|--------|---------|-------|--------|\n| MAU | X | ↑↓→ Y% | 🟢🟡🔴 |\n| DAU\u002FMAU | X% | ↑↓→ Y% | 🟢🟡🔴 |\n| License Utilization | X% | ↑↓→ | 🟢🟡🔴 |\n| Features Adopted | X\u002FY | ↑↓→ | 🟢🟡🔴 |\n\n---\n\n## 🚨 Risk Factors (if any)\n1. **[Issue]** - [Impact]\n   - Usage data: [metric\u002Ftrend]\n   - Customer feedback: [theme with X mentions] - [representative quote]\n\n## ✅ Positive Signals\n1. **[What's working]** - [Evidence from usage + feedback]\n\n---\n\n## 👥 User Intelligence\n\n### Champions (Leverage)\n- **[User ID\u002FName]**: [Activity summary] - *Action: [Specific CS recommendation]*\n\n### At Risk (Engage)\n- **[User ID\u002FName]**: [Last active date \u002F declining pattern] - *Action: [Check-in recommendation]*\n\n### Inactive (>30 days)\n- [Count] users ([X]% of licenses)\n\n---\n\n## 💡 Top Pain Points & Requests\n\n### Pain Points\n1. **[Theme]** (X mentions)\n   - [Concise description]\n   - Evidence: [Behavioral data] + \"[Quote]\" - [Source, Date]\n   - *Action: [What to do]*\n\n### Feature Requests\n1. **[Theme]** (X mentions)\n   - [What they want]\n   - Evidence: \"[Quote]\" - [Source, Date]\n   - *Roadmap status: [On roadmap\u002FNot planned\u002FConsidering]*\n\n### What They Love ❤️\n1. **[Feature]**: \"[Quote]\"\n\n---\n\n## 📊 Feature Adoption\n\n**High Usage:** [Feature] - [X users] (↑Y%)\n**Declining:** [Feature] - [X users] (↓Y%) - *Investigate*\n**Untapped (Upsell):** [Premium feature] - Could solve [pain point]\n\n---\n\n## 🎯 Recommendations\n\n### 🔥 This Week\n1. [Specific action with user\u002Fcontact name]\n\n### 📅 This Month\n1. [Strategic action with context]\n\n### 💰 Expansion Opportunities\n1. [Upsell signal with evidence]\n\n---\n\n## 📎 Details\n- **Analysis Date:** [Date]\n- **Timeframe:** [Last X days]\n- **Confidence:** [High\u002FMedium\u002FLow based on data volume]\n\n---\n\n## Best Practices\n\n- **Always name users** - CS needs who to contact, not aggregates\n- **Connect feedback to behavior** - Validate complaints with usage data\n- **Be specific in recommendations** - \"Call Sarah about Feature X\" not \"improve engagement\"\n- **Show trends, not snapshots** - Direction matters more than point-in-time\n- **Flag data gaps** - Note low volume, missing properties, or incomplete data\n- **Prioritize by impact** - Focus on issues affecting multiple users or champions\n\n## Common Patterns\n\n**Churn Risks:**\n- Champion churned + declining overall usage\n- Multiple complaints about same issue + behavioral evidence of friction\n- License utilization declining + negative feedback\n\n**Expansion Signals:**\n- Hitting plan limits (users, API, storage)\n- Requests for premium features + high engagement\n- New users being added + positive feedback\n",{"name":5,"description":7},"main","9836d94e88404aabb682086405c2aa9cba7657ac","plugins\u002Famplitude\u002Fskills\u002Fanalyze-account-health",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":34,"prompt":44,"zipAvailable":45},[35,38,41],{"tool":36,"command":37},"npx","npx skills add CognitionAI\u002Fdevin-marketplace --skill analyze-account-health",{"tool":39,"command":40},"bunx","bunx skills add CognitionAI\u002Fdevin-marketplace --skill analyze-account-health",{"tool":42,"command":43},"pnpm","pnpm dlx skills add CognitionAI\u002Fdevin-marketplace --skill analyze-account-health","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002FCognitionAI\u002Fdevin-marketplace\u002Fblob\u002Fmain\u002Fplugins\u002Famplitude\u002Fskills\u002Fanalyze-account-health\u002FSKILL.md",true,[],[48,54,61,67,74,81],{"skillNo":49,"name":50,"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":51,"categories":52,"keywords":53,"publishedAt":19},"01M7BYC4AJGM98P2G9JH7QS24Z","business-data","https:\u002F\u002Fgithub.com\u002FCognitionAI\u002Fdevin-marketplace\u002Fblob\u002Fmain\u002Fplugins\u002Fwindsor-ai\u002Fskills\u002Fbusiness-data\u002FSKILL.md",[],[],{"skillNo":55,"name":56,"nameZh":6,"description":57,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":58,"categories":59,"keywords":60,"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":62,"name":56,"nameZh":6,"description":63,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":64,"categories":65,"keywords":66,"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":68,"name":69,"nameZh":6,"description":70,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":71,"categories":72,"keywords":73,"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":75,"name":76,"nameZh":6,"description":77,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":78,"categories":79,"keywords":80,"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":82,"name":83,"nameZh":6,"description":84,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":85,"categories":86,"keywords":87,"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",[],[]]