[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M7BVVYKVZ5B12XWSQEYP84HC":3,"skill-same:01M7BVVYKVZ5B12XWSQEYP84HC":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":26,"commitSha":27,"skillDirectory":28,"forksCount":29,"repositoryHtmlUrl":30,"repositoryHomepageUrl":6,"ownerHtmlUrl":31,"ownerBlogUrl":32,"ownerDescription":33,"updatedAt":34,"install":35,"resources":48},"01M7BVVYKVZ5B12XWSQEYP84HC","analyze-chart",null,"Performs deep analysis of a specific Amplitude chart to explain trends, anomalies, and likely drivers. Use when a metric looks unusual, investigating a spike or drop, or understanding the \"why\" behind numbers.","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-chart\u002FSKILL.md",[],[],"2026-11-15 14:19:17",false,"---\nname: analyze-chart\ndescription: Performs deep analysis of a specific Amplitude chart to explain trends, anomalies, and likely drivers. Use when a metric looks unusual, investigating a spike or drop, or understanding the \"why\" behind numbers.\nx-amp-exclude-when-flags: [mcp-consolidate-charts]\n---\n\n# Chart Deep Dive\n\n## When to Use\n\n- A metric spiked or dropped unexpectedly\n- You need to understand what’s driving a trend\n- Preparing a detailed, evidence-backed analysis for stakeholders\n- Investigating differences between user or event segments\n\n## Instructions\n\n### Step 0: Identify the Chart\n\n- Accept a chart **URL or chart ID**\n- If the user provides a URL, use `Amplitude:get_from_url` to extract the chart ID\n- If no chart identifier is provided, ask explicitly for the chart URL or ID and stop\n\n---\n\n### Step 1: Retrieve and Validate Chart Data (Mandatory)\n\n- Use **Reading chart data** to retrieve the chart definition and data\n- If chart data cannot be retrieved or is empty, **do not proceed**\n  - Explain what’s missing (time range, event, filters, permissions)\n  - Ask the user to correct the chart or provide a valid chart\n\nCapture and restate:\n- Metric being measured\n- Time range and granularity\n- Chart type (e.g. time series, funnel, retention)\n- Existing filters, segments, or breakdowns\n\n---\n\n### Step 2: Identify the Pattern and Change Window\n\nUse **Analyzing chart** to characterize what’s happening:\n\n- **Spike \u002F Drop**: Sudden change on specific date(s)\n- **Trend**: Gradual increase or decrease over time\n- **Seasonality**: Recurring weekly or monthly patterns\n- **Anomaly**: Deviation from recent baseline or historical behavior\n\nExplicitly identify:\n- The **window of change** (start\u002Fend)\n- Direction and magnitude of the change\n- Baseline period used for comparison (default: previous equal-length period)\n\n---\n\n### Step 3: Investigate Likely Drivers (Bounded)\n\nInstead of broad slicing, use **guided segmentation**:\n\n1. Use **Finding the right event properties** to identify the most relevant properties for explaining the change\n2. Select **up to 9 high-signal properties** (e.g. platform, country, plan, version)\n3. Re-run **Analyzing chart** with these properties in mind to determine:\n   - Which segments contribute most to the change\n   - Whether the pattern is localized or broad-based\n   - Only fetch up to 3 charts at a time when using `Amplitude:query_charts`\n\nAvoid testing more than 9 properties in aggregate unless the user explicitly asks for deeper exploration.\n\n---\n\n### Step 4: Correlate with Context (Required for Anomalies)\n\nFor spikes, drops, or unexpected shifts, gather contextual signals in the same timeframe:\n\n- Use **Getting experiments** to identify active experiments or flags\n- Use **Getting deployments** to identify releases or rollouts\n- Use **Searching for content** to surface annotations or relevant documentation\n- Use `Amplitude:get_feedback_insights` to search customer feedback trends that might explain the change\n- Use `Amplitude:get_feedback_mentions` to pull in specific customer mentions if there's a likely feedback trend tied to what's being explained.\n\nDetermine whether any contextual changes align temporally with the chart pattern.\n\n---\n\n### Step 5: Synthesize Findings\n\nPresent a structured, decision-ready analysis:\n\n1. **What Happened**  \n   Clear description of the observed pattern and magnitude\n\n2. **When**  \n   Exact timeframe and comparison baseline\n\n3. **Primary Hypothesis**  \n   Most likely explanation based on chart data and contextual signals\n\n4. **Supporting Evidence**  \n   - Key metrics\n   - Segment contributions\n   - Relevant experiments, deployments, or annotations\n\n5. **Alternative Explanations**  \n   1–3 plausible alternatives and why they are less likely\n\n6. **Impact**  \n   Quantify impact where possible (users, events, conversion, revenue proxy)\n\n7. **Recommended Next Step**  \n   One clear follow-up action (e.g. deeper segment, experiment review, instrumentation check)\n\nAlways include:\n- Chart name\n- Chart ID\n- Link back to the chart\n- Coverage (e.g. properties tested, segments analyzed)\n\n---\n\n## Best Practices\n\n- Always compare against a clear baseline period\n- Distinguish **observations** from **hypotheses**\n- Prefer high-signal segmentation over exhaustive slicing\n- Note data quality issues (low volume, incomplete periods, heavy “(none)” values)\n- Do **not** create or edit charts unless the user explicitly asks\n","# Chart Deep Dive\n\n## When to Use\n\n- A metric spiked or dropped unexpectedly\n- You need to understand what’s driving a trend\n- Preparing a detailed, evidence-backed analysis for stakeholders\n- Investigating differences between user or event segments\n\n## Instructions\n\n### Step 0: Identify the Chart\n\n- Accept a chart **URL or chart ID**\n- If the user provides a URL, use `Amplitude:get_from_url` to extract the chart ID\n- If no chart identifier is provided, ask explicitly for the chart URL or ID and stop\n\n---\n\n### Step 1: Retrieve and Validate Chart Data (Mandatory)\n\n- Use **Reading chart data** to retrieve the chart definition and data\n- If chart data cannot be retrieved or is empty, **do not proceed**\n  - Explain what’s missing (time range, event, filters, permissions)\n  - Ask the user to correct the chart or provide a valid chart\n\nCapture and restate:\n- Metric being measured\n- Time range and granularity\n- Chart type (e.g. time series, funnel, retention)\n- Existing filters, segments, or breakdowns\n\n---\n\n### Step 2: Identify the Pattern and Change Window\n\nUse **Analyzing chart** to characterize what’s happening:\n\n- **Spike \u002F Drop**: Sudden change on specific date(s)\n- **Trend**: Gradual increase or decrease over time\n- **Seasonality**: Recurring weekly or monthly patterns\n- **Anomaly**: Deviation from recent baseline or historical behavior\n\nExplicitly identify:\n- The **window of change** (start\u002Fend)\n- Direction and magnitude of the change\n- Baseline period used for comparison (default: previous equal-length period)\n\n---\n\n### Step 3: Investigate Likely Drivers (Bounded)\n\nInstead of broad slicing, use **guided segmentation**:\n\n1. Use **Finding the right event properties** to identify the most relevant properties for explaining the change\n2. Select **up to 9 high-signal properties** (e.g. platform, country, plan, version)\n3. Re-run **Analyzing chart** with these properties in mind to determine:\n   - Which segments contribute most to the change\n   - Whether the pattern is localized or broad-based\n   - Only fetch up to 3 charts at a time when using `Amplitude:query_charts`\n\nAvoid testing more than 9 properties in aggregate unless the user explicitly asks for deeper exploration.\n\n---\n\n### Step 4: Correlate with Context (Required for Anomalies)\n\nFor spikes, drops, or unexpected shifts, gather contextual signals in the same timeframe:\n\n- Use **Getting experiments** to identify active experiments or flags\n- Use **Getting deployments** to identify releases or rollouts\n- Use **Searching for content** to surface annotations or relevant documentation\n- Use `Amplitude:get_feedback_insights` to search customer feedback trends that might explain the change\n- Use `Amplitude:get_feedback_mentions` to pull in specific customer mentions if there's a likely feedback trend tied to what's being explained.\n\nDetermine whether any contextual changes align temporally with the chart pattern.\n\n---\n\n### Step 5: Synthesize Findings\n\nPresent a structured, decision-ready analysis:\n\n1. **What Happened**  \n   Clear description of the observed pattern and magnitude\n\n2. **When**  \n   Exact timeframe and comparison baseline\n\n3. **Primary Hypothesis**  \n   Most likely explanation based on chart data and contextual signals\n\n4. **Supporting Evidence**  \n   - Key metrics\n   - Segment contributions\n   - Relevant experiments, deployments, or annotations\n\n5. **Alternative Explanations**  \n   1–3 plausible alternatives and why they are less likely\n\n6. **Impact**  \n   Quantify impact where possible (users, events, conversion, revenue proxy)\n\n7. **Recommended Next Step**  \n   One clear follow-up action (e.g. deeper segment, experiment review, instrumentation check)\n\nAlways include:\n- Chart name\n- Chart ID\n- Link back to the chart\n- Coverage (e.g. properties tested, segments analyzed)\n\n---\n\n## Best Practices\n\n- Always compare against a clear baseline period\n- Distinguish **observations** from **hypotheses**\n- Prefer high-signal segmentation over exhaustive slicing\n- Note data quality issues (low volume, incomplete periods, heavy “(none)” values)\n- Do **not** create or edit charts unless the user explicitly asks\n",{"name":5,"description":7,"x-amp-exclude-when-flags":24},[25],"mcp-consolidate-charts","main","9836d94e88404aabb682086405c2aa9cba7657ac","plugins\u002Famplitude\u002Fskills\u002Fanalyze-chart",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":36,"prompt":46,"zipAvailable":47},[37,40,43],{"tool":38,"command":39},"npx","npx skills add CognitionAI\u002Fdevin-marketplace --skill analyze-chart",{"tool":41,"command":42},"bunx","bunx skills add CognitionAI\u002Fdevin-marketplace --skill analyze-chart",{"tool":44,"command":45},"pnpm","pnpm dlx skills add CognitionAI\u002Fdevin-marketplace --skill analyze-chart","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002FCognitionAI\u002Fdevin-marketplace\u002Fblob\u002Fmain\u002Fplugins\u002Famplitude\u002Fskills\u002Fanalyze-chart\u002FSKILL.md",true,[],[50,56,63,69,76,83],{"skillNo":51,"name":52,"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":53,"categories":54,"keywords":55,"publishedAt":19},"01M7BYC4AJGM98P2G9JH7QS24Z","business-data","https:\u002F\u002Fgithub.com\u002FCognitionAI\u002Fdevin-marketplace\u002Fblob\u002Fmain\u002Fplugins\u002Fwindsor-ai\u002Fskills\u002Fbusiness-data\u002FSKILL.md",[],[],{"skillNo":57,"name":58,"nameZh":6,"description":59,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":60,"categories":61,"keywords":62,"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":64,"name":58,"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},"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":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},"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":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},"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":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},"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",[],[]]