[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M7BVY93830KDB5AWX3PR0P7K":3,"skill-same:01M7BVY93830KDB5AWX3PR0P7K":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},"01M7BVY93830KDB5AWX3PR0P7K","discover-analytics-patterns",null,"Discovers how analytics tracking calls are actually written in this codebase — the concrete SDK calls, function signatures, and import patterns used to send events. Use this skill whenever you need to understand the existing analytics instrumentation patterns before adding new tracking, when someone asks \"how do we track events here?\", \"show me the analytics setup\", \"what's the analytics pattern in this codebase?\", or any time the instrument-events or discover-event-surfaces skills are about to run and you need to know the correct coding style to follow. Outputs a deduplicated list of patterns with generalized examples and the file paths where each pattern appears, plus the dominant event and property naming conventions inferred from those call sites. Always use this skill before writing any analytics instrumentation code.","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\u002Fdiscover-analytics-patterns\u002FSKILL.md",[],[],"2026-11-15 14:19:17",false,"---\nname: discover-analytics-patterns\ndescription: >\n  Discovers how analytics tracking calls are actually written in this codebase —\n  the concrete SDK calls, function signatures, and import patterns used to send\n  events. Use this skill whenever you need to understand the existing analytics\n  instrumentation patterns before adding new tracking, when someone asks \"how do\n  we track events here?\", \"show me the analytics setup\", \"what's the analytics\n  pattern in this codebase?\", or any time the instrument-events or\n  discover-event-surfaces skills are about to run and you need to know the\n  correct coding style to follow. Outputs a deduplicated list of patterns with\n  generalized examples and the file paths where each pattern appears, plus the\n  dominant event and property naming conventions inferred from those call sites.\n  Always use this skill before writing any analytics instrumentation code.\n---\n\n# discover-analytics-patterns\n\nYour goal is to find out **how** this codebase sends analytics events — not which\nevents exist, but the specific code patterns engineers use to fire a tracking\ncall. This output helps engineers add new events that look consistent with the\nrest of the codebase. It should also tell downstream skills how event names and\nproperty names are typically written in code here.\n\nWhen determining naming conventions in this skill, use the following sources in strict order of preference:\n1. Customer directives in `.amplitude\u002Finstrumentation-agent-context.md` (and any files it references), if present — explicit conventions the customer wants followed, so they override everything below.\n2. Events and properties observed from the Amplitude MCP server\n3. Real tracking call sites in the codebase\n4. The `taxonomy` skill at `..\u002Ftaxonomy\u002FSKILL.md`\n\n---\n\n## Step 0: Read repo instrumentation context\n\nBefore anything else, check for `.amplitude\u002Finstrumentation-agent-context.md`\n(repo root, or the subdirectory you're instrumenting). If it exists, read it and\nany repo-relative files it references. Any naming conventions, property\nstandards, or SDK\u002Fwrapper patterns it states are **customer directives** — they\ntake precedence over everything you infer below; record them and skip inference\nfor whatever they cover. If it's absent, just continue — the `instrument-events`\nskill owns prompting the user to add one.\n\n---\n\n## Step 1: Find tracking calls\n\nUse two approaches based on what's available.\n\n### If the Amplitude MCP is connected\n\nCall `manage_amp_events` with `action: \"get\"` and `kind: \"event\"` to fetch a\nsample of event names from the project. If its input schema accepts `_client`,\nevery `manage_amp_events` call made by this skill MUST include the top-level argument\n`\"_client\": { \"type\": \"skill\", \"skill_name\": \"discover-analytics-patterns\" }`\nin the tool arguments; otherwise, omit `_client`. Use those results to choose a\nfew representative non-system product events, then call `get_properties`\nfor those events to inspect real property names. This is your primary naming\nreference.\n\nDo not infer naming conventions from bracket-prefixed Amplitude system names\nsuch as `[Amplitude], [Guides-Surveys], [Assistant], [Experiment]` for either events or properties. Exclude those from\npattern detection. If the MCP sample is dominated by Amplitude system names or otherwise does not provide enough evidence, fall back to codebase\ninference for naming.\n\nThen search the codebase for the sampled non-system event names using Grep to\nlocate the actual tracking call sites.\n\n### If the Amplitude MCP is not available (fallback)\n\nSearch the codebase for these signals using Grep. Cast a wide net — you can\nnarrow down after:\n\n| What to search for                                       | Why                                               |\n| -------------------------------------------------------- | ------------------------------------------------- |\n| `\\.track\\(`                                              | Generic `.track()` method calls                   |\n| `ampli\\.`                                                | Ampli typed SDK calls (e.g. `ampli.myEvent(...)`) |\n| `amplitude\\.track\\|amplitude\\.logEvent`                  | Direct Amplitude SDK calls                        |\n| `sendEvent`                                              | Custom wrapper method names                       |\n| `from.*amplitude\\|import.*amplitude\\|require.*amplitude` | Import statements                                 |\n| `https:\u002F\u002Fapi2\\.amplitude\\.com\u002F2\u002Fhttpapi`                 | HTTP API calls                                    |\n\nAlso actively look for custom analytics wrappers — a codebase often wraps the\nraw SDK in a utility like `trackEvent()`, `track()`, or a React hook like\n`useAnalytics()` or `useTracking()`. Search for these by looking for functions\nthat call into Amplitude internally. **Treat each wrapper as its own pattern,\nseparate from the underlying SDK call**, even if it ultimately calls\n`amplitude.track()` underneath. Engineers who encounter the wrapper will use\n*it*, not the raw SDK — so it's the more important pattern to document.\n\nTo find wrappers: search for files that import the Amplitude SDK, then check\nwhether any of those files export a function or hook that other parts of the\ncodebase import and use for tracking.\n\nExclude test files (`.test.`, `.spec.`, `__tests__`) and mock files unless they\nare the *only* place a pattern appears.\n\n---\n\n## Step 2: Group by pattern\n\nTwo call sites use the **same pattern** if they share the same:\n- Library\u002FSDK\u002Ffunction being called\n- Method name\n- Argument structure (even if the event name or properties differ)\n\nFor example, these are the **same** pattern:\n```ts\namplitude.track('Page Viewed', { page: '\u002Fhome' })\namplitude.track('Button Clicked', { label: 'signup' })\n```\n\nBut these are **different** patterns — always keep them separate:\n```ts\namplitude.track('Page Viewed', { page: '\u002Fhome' })   \u002F\u002F direct SDK — one pattern\nampli.pageViewed({ page: '\u002Fhome' })                  \u002F\u002F Ampli typed method — different pattern\ntrackEvent('Page Viewed', { page: '\u002Fhome' })         \u002F\u002F custom wrapper — also a separate pattern\n```\n\nA custom wrapper is always its own pattern, even if it delegates to the SDK\nunderneath. When documenting a wrapper pattern, note what it wraps (e.g.,\n\"Custom hook wrapping `amplitude.track()`\") so engineers understand the layering.\n\n---\n\n## Step 3: Resolve naming conventions\n\nResolve two conventions separately:\n\n- `event_naming_convention` — casing, separators, word order, prefixes, and\n  tense used for event names in instrumentation code. Examples: `Title Case`,\n  `snake_case`, `[Prefix] Action`, object-first vs action-first.\n- `property_naming_convention` — casing, separators, and common suffix\u002Fprefix\n  patterns used for event properties. Examples: `snake_case`, `camelCase`,\n  `*_id`, `is_*`, flat keys vs nested objects.\n\nUse this precedence order:\n\n1. **Repo instrumentation context first.** If\n   `.amplitude\u002Finstrumentation-agent-context.md` (from Step 0) states an explicit\n   event or property naming convention, it wins outright — record it and skip\n   inference for whatever it specifies. Only fall through when the file is absent\n   or silent on naming.\n2. **Amplitude MCP second.** If the observed `eventType` values and\n   property names returned by `get_properties` for a few representative\n   non-system events show a clear dominant convention, use that. Do not use\n   bracket-prefixed Amplitude system names as naming evidence.\n3. **Codebase third.** If the MCP evidence is unavailable, sparse, or\n   inconsistent, infer the dominant convention from nearby, real tracking call\n   sites in the repository. If the codebase shows multiple conventions, call\n   out the dominant one and note meaningful local exceptions.\n4. **Taxonomy fallback last.** If none of the above is\n   clear enough, fall back to the `taxonomy` skill at `..\u002Ftaxonomy\u002FSKILL.md`.\n\nDo not guess. If one or both conventions remain unclear even after checking\nthose sources, say so explicitly.\n\n---\n\n## Step 4: Output\n\nStart with a short conventions section, then list each unique pattern.\n\n```yaml\nevent_naming_convention: \"\u003Cfrom repo context file if it specifies one, else MCP if clear, else codebase, else taxonomy skill, or 'insufficient evidence'>\"\nproperty_naming_convention: \"\u003Cfrom repo context file if it specifies one, else MCP if clear, else codebase, else taxonomy skill, or 'insufficient evidence'>\"\n```\n\nThen, for each unique pattern, output a section in this format:\n\n---\n\n### Pattern: `\u003Cshort descriptive name>`\n\n**Description**: What this pattern does and when it's typically used in this\ncodebase (e.g., \"Used throughout the React frontend for user action tracking\").\n\n**Example** (generalized):\n```\u003Clanguage>\n\u002F\u002F show the import(s) needed\nimport { amplitude } from '@\u002Flib\u002Fanalytics'\n\n\u002F\u002F show a representative tracking call with placeholder names\namplitude.track('Event Name', {\n  propertyOne: value,\n  propertyTwo: value,\n})\n```\n\n**Relevant paths**:\n- `src\u002Fpath\u002Fto\u002Ffile.ts`\n- `src\u002Fanother\u002Ffile.tsx`\n\n---\n\nList patterns from most common (most file paths) to least common.\n\nIf two patterns are always used together (e.g., an import + a call), show them\ntogether in one example.\n\n---\n\n## Step 5: Handle no results\n\nIf no tracking calls are found with any search strategy, say so clearly. Suggest\nthat the user check whether Amplitude (or another analytics library) has been set\nup in the project, and offer to search for other analytics libraries (Segment,\nMixpanel, PostHog, etc.) if relevant.\n","# discover-analytics-patterns\n\nYour goal is to find out **how** this codebase sends analytics events — not which\nevents exist, but the specific code patterns engineers use to fire a tracking\ncall. This output helps engineers add new events that look consistent with the\nrest of the codebase. It should also tell downstream skills how event names and\nproperty names are typically written in code here.\n\nWhen determining naming conventions in this skill, use the following sources in strict order of preference:\n1. Customer directives in `.amplitude\u002Finstrumentation-agent-context.md` (and any files it references), if present — explicit conventions the customer wants followed, so they override everything below.\n2. Events and properties observed from the Amplitude MCP server\n3. Real tracking call sites in the codebase\n4. The `taxonomy` skill at `..\u002Ftaxonomy\u002FSKILL.md`\n\n---\n\n## Step 0: Read repo instrumentation context\n\nBefore anything else, check for `.amplitude\u002Finstrumentation-agent-context.md`\n(repo root, or the subdirectory you're instrumenting). If it exists, read it and\nany repo-relative files it references. Any naming conventions, property\nstandards, or SDK\u002Fwrapper patterns it states are **customer directives** — they\ntake precedence over everything you infer below; record them and skip inference\nfor whatever they cover. If it's absent, just continue — the `instrument-events`\nskill owns prompting the user to add one.\n\n---\n\n## Step 1: Find tracking calls\n\nUse two approaches based on what's available.\n\n### If the Amplitude MCP is connected\n\nCall `manage_amp_events` with `action: \"get\"` and `kind: \"event\"` to fetch a\nsample of event names from the project. If its input schema accepts `_client`,\nevery `manage_amp_events` call made by this skill MUST include the top-level argument\n`\"_client\": { \"type\": \"skill\", \"skill_name\": \"discover-analytics-patterns\" }`\nin the tool arguments; otherwise, omit `_client`. Use those results to choose a\nfew representative non-system product events, then call `get_properties`\nfor those events to inspect real property names. This is your primary naming\nreference.\n\nDo not infer naming conventions from bracket-prefixed Amplitude system names\nsuch as `[Amplitude], [Guides-Surveys], [Assistant], [Experiment]` for either events or properties. Exclude those from\npattern detection. If the MCP sample is dominated by Amplitude system names or otherwise does not provide enough evidence, fall back to codebase\ninference for naming.\n\nThen search the codebase for the sampled non-system event names using Grep to\nlocate the actual tracking call sites.\n\n### If the Amplitude MCP is not available (fallback)\n\nSearch the codebase for these signals using Grep. Cast a wide net — you can\nnarrow down after:\n\n| What to search for                                       | Why                                               |\n| -------------------------------------------------------- | ------------------------------------------------- |\n| `\\.track\\(`                                              | Generic `.track()` method calls                   |\n| `ampli\\.`                                                | Ampli typed SDK calls (e.g. `ampli.myEvent(...)`) |\n| `amplitude\\.track\\|amplitude\\.logEvent`                  | Direct Amplitude SDK calls                        |\n| `sendEvent`                                              | Custom wrapper method names                       |\n| `from.*amplitude\\|import.*amplitude\\|require.*amplitude` | Import statements                                 |\n| `https:\u002F\u002Fapi2\\.amplitude\\.com\u002F2\u002Fhttpapi`                 | HTTP API calls                                    |\n\nAlso actively look for custom analytics wrappers — a codebase often wraps the\nraw SDK in a utility like `trackEvent()`, `track()`, or a React hook like\n`useAnalytics()` or `useTracking()`. Search for these by looking for functions\nthat call into Amplitude internally. **Treat each wrapper as its own pattern,\nseparate from the underlying SDK call**, even if it ultimately calls\n`amplitude.track()` underneath. Engineers who encounter the wrapper will use\n*it*, not the raw SDK — so it's the more important pattern to document.\n\nTo find wrappers: search for files that import the Amplitude SDK, then check\nwhether any of those files export a function or hook that other parts of the\ncodebase import and use for tracking.\n\nExclude test files (`.test.`, `.spec.`, `__tests__`) and mock files unless they\nare the *only* place a pattern appears.\n\n---\n\n## Step 2: Group by pattern\n\nTwo call sites use the **same pattern** if they share the same:\n- Library\u002FSDK\u002Ffunction being called\n- Method name\n- Argument structure (even if the event name or properties differ)\n\nFor example, these are the **same** pattern:\n```ts\namplitude.track('Page Viewed', { page: '\u002Fhome' })\namplitude.track('Button Clicked', { label: 'signup' })\n```\n\nBut these are **different** patterns — always keep them separate:\n```ts\namplitude.track('Page Viewed', { page: '\u002Fhome' })   \u002F\u002F direct SDK — one pattern\nampli.pageViewed({ page: '\u002Fhome' })                  \u002F\u002F Ampli typed method — different pattern\ntrackEvent('Page Viewed', { page: '\u002Fhome' })         \u002F\u002F custom wrapper — also a separate pattern\n```\n\nA custom wrapper is always its own pattern, even if it delegates to the SDK\nunderneath. When documenting a wrapper pattern, note what it wraps (e.g.,\n\"Custom hook wrapping `amplitude.track()`\") so engineers understand the layering.\n\n---\n\n## Step 3: Resolve naming conventions\n\nResolve two conventions separately:\n\n- `event_naming_convention` — casing, separators, word order, prefixes, and\n  tense used for event names in instrumentation code. Examples: `Title Case`,\n  `snake_case`, `[Prefix] Action`, object-first vs action-first.\n- `property_naming_convention` — casing, separators, and common suffix\u002Fprefix\n  patterns used for event properties. Examples: `snake_case`, `camelCase`,\n  `*_id`, `is_*`, flat keys vs nested objects.\n\nUse this precedence order:\n\n1. **Repo instrumentation context first.** If\n   `.amplitude\u002Finstrumentation-agent-context.md` (from Step 0) states an explicit\n   event or property naming convention, it wins outright — record it and skip\n   inference for whatever it specifies. Only fall through when the file is absent\n   or silent on naming.\n2. **Amplitude MCP second.** If the observed `eventType` values and\n   property names returned by `get_properties` for a few representative\n   non-system events show a clear dominant convention, use that. Do not use\n   bracket-prefixed Amplitude system names as naming evidence.\n3. **Codebase third.** If the MCP evidence is unavailable, sparse, or\n   inconsistent, infer the dominant convention from nearby, real tracking call\n   sites in the repository. If the codebase shows multiple conventions, call\n   out the dominant one and note meaningful local exceptions.\n4. **Taxonomy fallback last.** If none of the above is\n   clear enough, fall back to the `taxonomy` skill at `..\u002Ftaxonomy\u002FSKILL.md`.\n\nDo not guess. If one or both conventions remain unclear even after checking\nthose sources, say so explicitly.\n\n---\n\n## Step 4: Output\n\nStart with a short conventions section, then list each unique pattern.\n\n```yaml\nevent_naming_convention: \"\u003Cfrom repo context file if it specifies one, else MCP if clear, else codebase, else taxonomy skill, or 'insufficient evidence'>\"\nproperty_naming_convention: \"\u003Cfrom repo context file if it specifies one, else MCP if clear, else codebase, else taxonomy skill, or 'insufficient evidence'>\"\n```\n\nThen, for each unique pattern, output a section in this format:\n\n---\n\n### Pattern: `\u003Cshort descriptive name>`\n\n**Description**: What this pattern does and when it's typically used in this\ncodebase (e.g., \"Used throughout the React frontend for user action tracking\").\n\n**Example** (generalized):\n```\u003Clanguage>\n\u002F\u002F show the import(s) needed\nimport { amplitude } from '@\u002Flib\u002Fanalytics'\n\n\u002F\u002F show a representative tracking call with placeholder names\namplitude.track('Event Name', {\n  propertyOne: value,\n  propertyTwo: value,\n})\n```\n\n**Relevant paths**:\n- `src\u002Fpath\u002Fto\u002Ffile.ts`\n- `src\u002Fanother\u002Ffile.tsx`\n\n---\n\nList patterns from most common (most file paths) to least common.\n\nIf two patterns are always used together (e.g., an import + a call), show them\ntogether in one example.\n\n---\n\n## Step 5: Handle no results\n\nIf no tracking calls are found with any search strategy, say so clearly. Suggest\nthat the user check whether Amplitude (or another analytics library) has been set\nup in the project, and offer to search for other analytics libraries (Segment,\nMixpanel, PostHog, etc.) if relevant.\n",{"name":5,"description":7},"main","9836d94e88404aabb682086405c2aa9cba7657ac","plugins\u002Famplitude\u002Fskills\u002Fdiscover-analytics-patterns",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 discover-analytics-patterns",{"tool":39,"command":40},"bunx","bunx skills add CognitionAI\u002Fdevin-marketplace --skill discover-analytics-patterns",{"tool":42,"command":43},"pnpm","pnpm dlx skills add CognitionAI\u002Fdevin-marketplace --skill discover-analytics-patterns","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002FCognitionAI\u002Fdevin-marketplace\u002Fblob\u002Fmain\u002Fplugins\u002Famplitude\u002Fskills\u002Fdiscover-analytics-patterns\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",[],[]]