[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M7BVVC3W232NKV6997X2V33B":3,"skill-same:01M7BVVC3W232NKV6997X2V33B":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},"01M7BVVC3W232NKV6997X2V33B","add-analytics-instrumentation",null,"End-to-end analytics instrumentation workflow for a PR, branch, file, directory, or feature. Reads the code, discovers what events should be tracked, and produces a concrete instrumentation plan — all in one shot. Use this skill whenever a user wants to add analytics to a PR, asks \"instrument this PR\", \"add tracking to this branch\", \"what analytics does this file need\", \"instrument the checkout flow\", \"run the full instrumentation workflow\", or any request that implies going from code changes to a tracking plan. Also trigger when the user gives you a PR link, branch name, file path, or feature description and mentions analytics, events, or instrumentation. This is the main entry point for the analytics workflow — prefer it over calling the individual steps (diff-intake, discover-event-surfaces, instrument-events) separately.","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\u002Fadd-analytics-instrumentation\u002FSKILL.md",[],[],"2026-11-15 14:19:17",false,"---\nname: add-analytics-instrumentation\ndescription: >\n  End-to-end analytics instrumentation workflow for a PR, branch, file,\n  directory, or feature. Reads the code, discovers what events should be\n  tracked, and produces a concrete instrumentation plan — all in one shot. Use\n  this skill whenever a user wants to add analytics to a PR, asks \"instrument\n  this PR\", \"add tracking to this branch\", \"what analytics does this file need\",\n  \"instrument the checkout flow\", \"run the full instrumentation workflow\", or any\n  request that implies going from code changes to a tracking plan. Also trigger\n  when the user gives you a PR link, branch name, file path, or feature\n  description and mentions analytics, events, or instrumentation. This is the\n  main entry point for the analytics workflow — prefer it over calling the\n  individual steps (diff-intake, discover-event-surfaces, instrument-events)\n  separately.\n---\n\n# add-analytics-instrumentation\n\nYou are the orchestrator for the analytics instrumentation pipeline. Your job is\nto figure out what the user wants to instrument, gather the relevant code, and\nrun the pipeline to produce a tracking plan.\n\n## Pipeline\n\n### Step 0: Capture intent\n\nBefore running anything, determine **what** the user wants to instrument. There\nare four input types — infer the type from what the user has already provided in\nthe conversation. Only ask if it's genuinely ambiguous.\n\n| Input type           | How to recognize it                                                            | Example                                                                     |\n| -------------------- | ------------------------------------------------------------------------------ | --------------------------------------------------------------------------- |\n| **PR**               | A PR URL, PR number, or phrases like \"this PR\", \"my PR\"                        | `instrument PR #42`, `https:\u002F\u002Fgithub.com\u002Forg\u002Frepo\u002Fpull\u002F42`                  |\n| **Branch**           | A branch name or \"this branch\", \"my branch\", \"current branch\"                  | `instrument feature\u002Fcheckout`, `add tracking to this branch`                |\n| **File \u002F Directory** | A file path, directory path, or glob pattern                                   | `instrument src\u002Fcomponents\u002FCheckout.tsx`, `add analytics to src\u002Fpayments\u002F`  |\n| **Feature**          | A natural-language description of functionality, not a specific code reference | `instrument the onboarding flow`, `add tracking to the checkout experience` |\n\n**Inference rules:**\n- If the user provided a URL or `#number` → **PR**\n- If the user provided something that looks like a branch name (contains `\u002F`, no file extension, matches a git branch) → **Branch**\n- If the user provided a path that exists on disk (file or directory) → **File \u002F Directory**\n- If none of the above match and the input is descriptive → **Feature**\n- If the conversation already contains a PR link, branch name, or file path from earlier messages, use that instead of asking again\n\n**If ambiguous**, ask the user:\n\n> What would you like to instrument?\n> 1. A specific file or directory\n> 2. A PR\n> 3. A branch\n> 4. A feature (describe it and I'll find the relevant code)\n\nOnce you know the input type, proceed to the appropriate step:\n\n- **PR or Branch** → go to Step 1 (diff-intake)\n- **File \u002F Directory** → go to Step 1a (direct file read)\n- **Feature** → go to Step 1b (feature search)\n\n### Step 1: diff-intake skill (PR or Branch)\n\nInvoke the `diff-intake` skill with the user's PR or branch reference.\n\nIt produces a `change_brief` YAML block.\n\nCapture the full YAML output — step 2 consumes it verbatim. Skip to Step 2.\n\n### Step 1a: Direct file read (File \u002F Directory)\n\nSkip diff-intake entirely — there's no diff to analyze. Instead, build the\n`change_brief` YAML yourself by reading the files directly.\n\n1. **Resolve the input.** If a directory, find all source files in it (skip\n   tests, config, lock files, generated code). If a single file, just use that.\n2. **Read each file** and summarize what it does — focus on user-facing behavior,\n   not implementation details.\n3. **Scan for existing instrumentation** using the same patterns as diff-intake:\n   `track(`, `trackEvent(`, `logEvent(`, `amplitude.track(`, `ampli.`, and\n   analytics-related imports.\n4. **Build the `change_brief` YAML** with `analytics_scope: high` (the user\n   explicitly asked to instrument these files, so assume they want tracking).\n   Set `primary: feat` and `classification.types: [feat]`. Populate\n   `file_summary_map` with each file's summary, layer, and existing\n   instrumentation.\n\nProceed to Step 2 with the YAML you built.\n\n### Step 1b: Feature search (Feature)\n\nThe user described a feature in natural language. Your job is to find the\nrelevant code, then build a `change_brief`.\n\n1. **Search git commit history** to find related commits. Use `git log --all --grep=\"\u003Cpatterns>\"`. This will find relevant commits. Then read the git commit body to understand the feature and relevant files. If the results are good, then proceed to generating the `change_brief` YAML\n2. **Search the codebase** for files related to the described feature. Use a\n   combination of:\n   - Grep for keywords from the feature description (component names, route\n     paths, function names, domain terms)\n   - Glob for likely file paths (e.g., `**\u002Fcheckout\u002F**`, `**\u002Fonboarding\u002F**`)\n   - Read route definitions, navigation configs, or index files to find entry\n     points\n3. Build the `change_brief` YAML.\n\nProceed to Step 2 with the YAML you built.\n\n### Step 2: discover-event-surfaces\n\nInvoke the `discover-event-surfaces` skill, passing the `change_brief` YAML\nfrom step 1.\n\nIt produces an `event_candidates` YAML block. If there are zero candidates,\nstop and tell the user the change has user-facing impact but no events worth\ninstrumenting were identified.\n\nIf event_candidates is empty, stop here and tell the user there's nothing to\ninstrument.\n\nCapture the full YAML output — step 3 consumes it.\n\n### Step 3: instrument-events\n\nInvoke the `instrument-events` skill, passing the `event_candidates` YAML from\nstep 2.\n\nIt produces a `trackingPlan` JSON with exact file locations, tracking code, and\nproperty definitions for every critical (priority 3) event.\n\n## Presenting the result\n\nAfter step 3 completes, present the tracking plan to the user. Walk through each\nevent briefly:\n\n- What it tracks and why it matters\n- Which Amplitude project(s) it routes to (`appId`\u002F`appIds`) — call this out when\n  the repo has an `.amplitude\u002Finstrumentation-agent.yaml` and events span more\n  than one project\n- Where the tracking call goes (file + function)\n- What properties it sends\n\nThen ask if they want to adjust anything or proceed to implementation.\n\n## Error handling\n\nIf any step fails (e.g., the PR doesn't exist, git commands error, no files to\nanalyze), surface the error clearly and stop. Don't try to continue with\nincomplete data.\n","# add-analytics-instrumentation\n\nYou are the orchestrator for the analytics instrumentation pipeline. Your job is\nto figure out what the user wants to instrument, gather the relevant code, and\nrun the pipeline to produce a tracking plan.\n\n## Pipeline\n\n### Step 0: Capture intent\n\nBefore running anything, determine **what** the user wants to instrument. There\nare four input types — infer the type from what the user has already provided in\nthe conversation. Only ask if it's genuinely ambiguous.\n\n| Input type           | How to recognize it                                                            | Example                                                                     |\n| -------------------- | ------------------------------------------------------------------------------ | --------------------------------------------------------------------------- |\n| **PR**               | A PR URL, PR number, or phrases like \"this PR\", \"my PR\"                        | `instrument PR #42`, `https:\u002F\u002Fgithub.com\u002Forg\u002Frepo\u002Fpull\u002F42`                  |\n| **Branch**           | A branch name or \"this branch\", \"my branch\", \"current branch\"                  | `instrument feature\u002Fcheckout`, `add tracking to this branch`                |\n| **File \u002F Directory** | A file path, directory path, or glob pattern                                   | `instrument src\u002Fcomponents\u002FCheckout.tsx`, `add analytics to src\u002Fpayments\u002F`  |\n| **Feature**          | A natural-language description of functionality, not a specific code reference | `instrument the onboarding flow`, `add tracking to the checkout experience` |\n\n**Inference rules:**\n- If the user provided a URL or `#number` → **PR**\n- If the user provided something that looks like a branch name (contains `\u002F`, no file extension, matches a git branch) → **Branch**\n- If the user provided a path that exists on disk (file or directory) → **File \u002F Directory**\n- If none of the above match and the input is descriptive → **Feature**\n- If the conversation already contains a PR link, branch name, or file path from earlier messages, use that instead of asking again\n\n**If ambiguous**, ask the user:\n\n> What would you like to instrument?\n> 1. A specific file or directory\n> 2. A PR\n> 3. A branch\n> 4. A feature (describe it and I'll find the relevant code)\n\nOnce you know the input type, proceed to the appropriate step:\n\n- **PR or Branch** → go to Step 1 (diff-intake)\n- **File \u002F Directory** → go to Step 1a (direct file read)\n- **Feature** → go to Step 1b (feature search)\n\n### Step 1: diff-intake skill (PR or Branch)\n\nInvoke the `diff-intake` skill with the user's PR or branch reference.\n\nIt produces a `change_brief` YAML block.\n\nCapture the full YAML output — step 2 consumes it verbatim. Skip to Step 2.\n\n### Step 1a: Direct file read (File \u002F Directory)\n\nSkip diff-intake entirely — there's no diff to analyze. Instead, build the\n`change_brief` YAML yourself by reading the files directly.\n\n1. **Resolve the input.** If a directory, find all source files in it (skip\n   tests, config, lock files, generated code). If a single file, just use that.\n2. **Read each file** and summarize what it does — focus on user-facing behavior,\n   not implementation details.\n3. **Scan for existing instrumentation** using the same patterns as diff-intake:\n   `track(`, `trackEvent(`, `logEvent(`, `amplitude.track(`, `ampli.`, and\n   analytics-related imports.\n4. **Build the `change_brief` YAML** with `analytics_scope: high` (the user\n   explicitly asked to instrument these files, so assume they want tracking).\n   Set `primary: feat` and `classification.types: [feat]`. Populate\n   `file_summary_map` with each file's summary, layer, and existing\n   instrumentation.\n\nProceed to Step 2 with the YAML you built.\n\n### Step 1b: Feature search (Feature)\n\nThe user described a feature in natural language. Your job is to find the\nrelevant code, then build a `change_brief`.\n\n1. **Search git commit history** to find related commits. Use `git log --all --grep=\"\u003Cpatterns>\"`. This will find relevant commits. Then read the git commit body to understand the feature and relevant files. If the results are good, then proceed to generating the `change_brief` YAML\n2. **Search the codebase** for files related to the described feature. Use a\n   combination of:\n   - Grep for keywords from the feature description (component names, route\n     paths, function names, domain terms)\n   - Glob for likely file paths (e.g., `**\u002Fcheckout\u002F**`, `**\u002Fonboarding\u002F**`)\n   - Read route definitions, navigation configs, or index files to find entry\n     points\n3. Build the `change_brief` YAML.\n\nProceed to Step 2 with the YAML you built.\n\n### Step 2: discover-event-surfaces\n\nInvoke the `discover-event-surfaces` skill, passing the `change_brief` YAML\nfrom step 1.\n\nIt produces an `event_candidates` YAML block. If there are zero candidates,\nstop and tell the user the change has user-facing impact but no events worth\ninstrumenting were identified.\n\nIf event_candidates is empty, stop here and tell the user there's nothing to\ninstrument.\n\nCapture the full YAML output — step 3 consumes it.\n\n### Step 3: instrument-events\n\nInvoke the `instrument-events` skill, passing the `event_candidates` YAML from\nstep 2.\n\nIt produces a `trackingPlan` JSON with exact file locations, tracking code, and\nproperty definitions for every critical (priority 3) event.\n\n## Presenting the result\n\nAfter step 3 completes, present the tracking plan to the user. Walk through each\nevent briefly:\n\n- What it tracks and why it matters\n- Which Amplitude project(s) it routes to (`appId`\u002F`appIds`) — call this out when\n  the repo has an `.amplitude\u002Finstrumentation-agent.yaml` and events span more\n  than one project\n- Where the tracking call goes (file + function)\n- What properties it sends\n\nThen ask if they want to adjust anything or proceed to implementation.\n\n## Error handling\n\nIf any step fails (e.g., the PR doesn't exist, git commands error, no files to\nanalyze), surface the error clearly and stop. Don't try to continue with\nincomplete data.\n",{"name":5,"description":7},"main","9836d94e88404aabb682086405c2aa9cba7657ac","plugins\u002Famplitude\u002Fskills\u002Fadd-analytics-instrumentation",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 add-analytics-instrumentation",{"tool":39,"command":40},"bunx","bunx skills add CognitionAI\u002Fdevin-marketplace --skill add-analytics-instrumentation",{"tool":42,"command":43},"pnpm","pnpm dlx skills add CognitionAI\u002Fdevin-marketplace --skill add-analytics-instrumentation","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002FCognitionAI\u002Fdevin-marketplace\u002Fblob\u002Fmain\u002Fplugins\u002Famplitude\u002Fskills\u002Fadd-analytics-instrumentation\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",[],[]]