[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M7BGGXB5KJ80GMWFZP4PMK0M":3,"skill-same:01M7BGGXB5KJ80GMWFZP4PMK0M":52},{"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":30,"commitSha":31,"skillDirectory":32,"forksCount":33,"repositoryHtmlUrl":34,"repositoryHomepageUrl":35,"ownerHtmlUrl":36,"ownerBlogUrl":6,"ownerDescription":37,"updatedAt":38,"install":39,"resources":51},"01M7BGGXB5KJ80GMWFZP4PMK0M","agent-analytics",null,"Analytics your AI agent can actually use. Track, analyze, run A\u002FB experiments, and optimize across all your projects via CLI. Includes a growth playbook so your agent knows HOW to grow, not just what to track.","YYC-Cube\u002FYYC3-Knowledge-Base","YYC-Cube","https:\u002F\u002Favatars.githubusercontent.com\u002Fu\u002F235006543?v=4","01M79J2PH4SWD2X0825X6PN748","yyc3","01M79J2PHVK3F6ZBYT8K2SCZCW",1,"MIT","https:\u002F\u002Fgithub.com\u002FYYC-Cube\u002FYYC3-Knowledge-Base\u002Fblob\u002Fmain\u002FYYC3-AI-应用工具\u002FYYC3-AI-应用工具-buildwithclaude\u002Fplugins\u002Fall-skills\u002Fskills\u002Fagent-analytics\u002FSKILL.md",[],[],"2026-11-15 14:19:17",false,"---\nname: agent-analytics\ndescription: \"Analytics your AI agent can actually use. Track, analyze, run A\u002FB experiments, and optimize across all your projects via CLI. Includes a growth playbook so your agent knows HOW to grow, not just what to track.\"\ncategory: analytics\nrequires:\n  env: [AGENT_ANALYTICS_API_KEY]\n  bins: [npx]\n---\n\n# Agent Analytics — Analytics your agent can actually use\n\nYou are adding analytics tracking using Agent Analytics — the analytics platform your AI agent can actually use. Built for developers who ship lots of projects and want their AI agent to track, analyze, experiment, and optimize across all of them.\n\n**Website:** [agentanalytics.sh](https:\u002F\u002Fagentanalytics.sh)\n**GitHub:** [Agent-Analytics\u002Fagent-analytics](https:\u002F\u002Fgithub.com\u002FAgent-Analytics\u002Fagent-analytics)\n**Docs:** [docs.agentanalytics.sh](https:\u002F\u002Fdocs.agentanalytics.sh)\n\n## When to Use This Skill\n\n- User wants to add analytics tracking to a website or app\n- User wants to check how their projects are doing (traffic, conversions, engagement)\n- User wants to run A\u002FB experiments on headlines, CTAs, or flows\n- User wants funnel analysis, retention cohorts, or traffic breakdowns\n- User asks \"how's my site doing?\" or \"are people visiting?\"\n\n## Philosophy\n\nYou are NOT Mixpanel. Don't track everything. Track only what answers: **\"Is this project alive and growing?\"**\n\nFor a typical site, that's 3-5 custom events max on top of automatic page views.\n\n## First-time setup\n\n**Get an API key:** Sign up at [agentanalytics.sh](https:\u002F\u002Fagentanalytics.sh) and generate a key from the dashboard. Alternatively, self-host the open-source version from [GitHub](https:\u002F\u002Fgithub.com\u002FAgent-Analytics\u002Fagent-analytics).\n\nIf the project doesn't have tracking yet:\n\n```bash\n# 1. Login (one time — uses your API key)\nnpx @agent-analytics\u002Fcli login --token aak_YOUR_API_KEY\n\n# 2. Create the project (returns a project write token)\nnpx @agent-analytics\u002Fcli create my-site --domain https:\u002F\u002Fmysite.com\n\n# 3. Add the snippet using the returned token\n# 4. Deploy, click around, verify:\nnpx @agent-analytics\u002Fcli events my-site\n```\n\nThe `create` command returns a **project write token** — use it as `data-token` in the snippet. This is separate from your API key (which is for reading\u002Fquerying).\n\n## Step 1: Add the tracking snippet\n\nThe `create` command returns a tracking snippet with your project token — add it before `\u003C\u002Fbody>`. It auto-tracks `page_view` events with path, referrer, browser, OS, device, screen size, and UTM params. You do NOT need to add custom page_view events.\n\n## Step 1b: Discover existing events (existing projects)\n\nIf tracking is already set up, check what events and property keys are already in use so you match the naming:\n\n```bash\nnpx @agent-analytics\u002Fcli properties-received PROJECT_NAME\n```\n\n## Step 2: Add custom events to important actions\n\nUse `onclick` handlers on the elements that matter:\n\n```html\n\u003Ca href=\"...\" onclick=\"window.aa?.track('EVENT_NAME', {id: 'ELEMENT_ID'})\">\n```\n\n### Standard events for 80% of SaaS sites\n\nPick the ones that apply. Most sites need 2-4:\n\n| Event | When to fire | Properties |\n|-------|-------------|------------|\n| `cta_click` | User clicks a call-to-action button | `id` (which button) |\n| `signup` | User creates an account | `method` (github\u002Fgoogle\u002Femail) |\n| `login` | User returns and logs in | `method` |\n| `feature_used` | User engages with a core feature | `feature` (which one) |\n| `checkout` | User starts a payment flow | `plan` (free\u002Fpro\u002Fetc) |\n| `error` | Something went wrong visibly | `message`, `page` |\n\n### What NOT to track\n- Every link or button (too noisy)\n- Scroll depth (not actionable)\n- Form field interactions (too granular)\n- Footer links (low signal)\n\n### Property naming rules\n\n- Use `snake_case`: `hero_get_started` not `heroGetStarted`\n- The `id` property identifies WHICH element: short, descriptive\n- Name IDs as `section_action`: `hero_signup`, `pricing_pro`, `nav_dashboard`\n\n## Step 2b: Run A\u002FB experiments\n\nExperiments let you test which variant of a page element converts better. The full lifecycle is API-driven — no dashboard UI needed.\n\n### Creating an experiment\n\n```bash\nnpx @agent-analytics\u002Fcli experiments create my-site \\\n  --name signup_cta --variants control,new_cta --goal signup\n```\n\n### Implementing variants\n\n**Declarative (recommended):** Use `data-aa-experiment` and `data-aa-variant-{key}` HTML attributes. Original content is the control. The tracker swaps text for assigned variants automatically.\n\n```html\n\u003Ch1 data-aa-experiment=\"signup_cta\" data-aa-variant-new_cta=\"Start Free Trial\">Sign Up\u003C\u002Fh1>\n```\n\n**Programmatic (complex cases):** Use `window.aa?.experiment(name, variants)` — deterministic, same user always gets same variant.\n\n### Checking results\n\n```bash\nnpx @agent-analytics\u002Fcli experiments get exp_abc123\n```\n\nReturns Bayesian `probability_best`, `lift`, and a `recommendation`. The system needs ~100 exposures per variant before results are significant.\n\n## Step 3: Test immediately\n\nAfter adding tracking, verify it works:\n\n```bash\n# Click around, then check:\nnpx @agent-analytics\u002Fcli events PROJECT_NAME\n# Events appear within seconds.\n```\n\n## CLI Reference\n\nAll commands use `npx @agent-analytics\u002Fcli`:\n\n```bash\n# Setup\nlogin --token aak_YOUR_KEY           # Save API key (one time)\nprojects                              # List all projects\ncreate my-site --domain https:\u002F\u002F...   # Create project\n\n# Real-time\nlive                                  # Live TUI dashboard across ALL projects\nlive my-site                          # Live view for one project\n\n# Analytics\nstats my-site --days 7                # Overview: events, users, daily trends\ninsights my-site --period 7d          # Period-over-period comparison\nbreakdown my-site --property path --event page_view --limit 10  # Top pages\u002Freferrers\u002FUTM\npages my-site --type entry            # Landing page performance & bounce rates\nsessions-dist my-site                 # Session engagement histogram\nheatmap my-site                       # Peak hours & busiest days\nevents my-site --days 30              # Raw event log\nsessions my-site                      # Individual session records\nproperties my-site                    # Discover event names & property keys\nfunnel my-site --steps \"page_view,signup,purchase\"  # Funnel drop-off\nretention my-site --period week --cohorts 8         # Cohort retention\n\n# A\u002FB experiments\nexperiments list my-site\nexperiments create my-site --name signup_cta --variants control,new_cta --goal signup\nexperiments get exp_abc123\nexperiments complete exp_abc123 --winner new_cta\n```\n\n## Which endpoint for which question\n\n| User asks | Call | Why |\n|-----------|------|-----|\n| \"How's my site doing?\" | `insights` + `breakdown` + `pages` (parallel) | Full weekly picture |\n| \"Is anyone visiting right now?\" | `live` | Real-time visitors across all projects |\n| \"What are my top pages?\" | `breakdown --property path --event page_view` | Ranked page list |\n| \"Where's my traffic coming from?\" | `breakdown --property referrer --event page_view` | Referrer sources |\n| \"Are people actually engaging?\" | `sessions-dist` | Bounce vs engaged split |\n| \"When should I deploy?\" | `heatmap` | Find low-traffic windows |\n| \"Where do users drop off?\" | `funnel --steps \"page_view,signup,purchase\"` | Step-by-step conversion |\n| \"Are users coming back?\" | `retention --period week --cohorts 8` | Cohort retention |\n| \"Which CTA converts better?\" | `experiments create` + `experiments get` | A\u002FB test lifecycle |\n\nFor any \"how is X doing\" question, **always call `insights` first** — it's the single most useful endpoint.\n\n## Examples\n\nTrack custom events via `window.aa?.track()`:\n\n```js\nwindow.aa?.track('cta_click', {id: 'hero_get_started'});\nwindow.aa?.track('signup', {method: 'github'});\nwindow.aa?.track('feature_used', {feature: 'create_project'});\nwindow.aa?.track('checkout', {plan: 'pro'});\n```\n\n## What this skill does NOT do\n\n- No GUI dashboards — your agent IS the dashboard (or use `live` for a real-time TUI)\n- No user management or billing\n- No PII stored — IP addresses are not logged or retained. Privacy-first by design\n","# Agent Analytics — Analytics your agent can actually use\n\nYou are adding analytics tracking using Agent Analytics — the analytics platform your AI agent can actually use. Built for developers who ship lots of projects and want their AI agent to track, analyze, experiment, and optimize across all of them.\n\n**Website:** [agentanalytics.sh](https:\u002F\u002Fagentanalytics.sh)\n**GitHub:** [Agent-Analytics\u002Fagent-analytics](https:\u002F\u002Fgithub.com\u002FAgent-Analytics\u002Fagent-analytics)\n**Docs:** [docs.agentanalytics.sh](https:\u002F\u002Fdocs.agentanalytics.sh)\n\n## When to Use This Skill\n\n- User wants to add analytics tracking to a website or app\n- User wants to check how their projects are doing (traffic, conversions, engagement)\n- User wants to run A\u002FB experiments on headlines, CTAs, or flows\n- User wants funnel analysis, retention cohorts, or traffic breakdowns\n- User asks \"how's my site doing?\" or \"are people visiting?\"\n\n## Philosophy\n\nYou are NOT Mixpanel. Don't track everything. Track only what answers: **\"Is this project alive and growing?\"**\n\nFor a typical site, that's 3-5 custom events max on top of automatic page views.\n\n## First-time setup\n\n**Get an API key:** Sign up at [agentanalytics.sh](https:\u002F\u002Fagentanalytics.sh) and generate a key from the dashboard. Alternatively, self-host the open-source version from [GitHub](https:\u002F\u002Fgithub.com\u002FAgent-Analytics\u002Fagent-analytics).\n\nIf the project doesn't have tracking yet:\n\n```bash\n# 1. Login (one time — uses your API key)\nnpx @agent-analytics\u002Fcli login --token aak_YOUR_API_KEY\n\n# 2. Create the project (returns a project write token)\nnpx @agent-analytics\u002Fcli create my-site --domain https:\u002F\u002Fmysite.com\n\n# 3. Add the snippet using the returned token\n# 4. Deploy, click around, verify:\nnpx @agent-analytics\u002Fcli events my-site\n```\n\nThe `create` command returns a **project write token** — use it as `data-token` in the snippet. This is separate from your API key (which is for reading\u002Fquerying).\n\n## Step 1: Add the tracking snippet\n\nThe `create` command returns a tracking snippet with your project token — add it before `\u003C\u002Fbody>`. It auto-tracks `page_view` events with path, referrer, browser, OS, device, screen size, and UTM params. You do NOT need to add custom page_view events.\n\n## Step 1b: Discover existing events (existing projects)\n\nIf tracking is already set up, check what events and property keys are already in use so you match the naming:\n\n```bash\nnpx @agent-analytics\u002Fcli properties-received PROJECT_NAME\n```\n\n## Step 2: Add custom events to important actions\n\nUse `onclick` handlers on the elements that matter:\n\n```html\n\u003Ca href=\"...\" onclick=\"window.aa?.track('EVENT_NAME', {id: 'ELEMENT_ID'})\">\n```\n\n### Standard events for 80% of SaaS sites\n\nPick the ones that apply. Most sites need 2-4:\n\n| Event | When to fire | Properties |\n|-------|-------------|------------|\n| `cta_click` | User clicks a call-to-action button | `id` (which button) |\n| `signup` | User creates an account | `method` (github\u002Fgoogle\u002Femail) |\n| `login` | User returns and logs in | `method` |\n| `feature_used` | User engages with a core feature | `feature` (which one) |\n| `checkout` | User starts a payment flow | `plan` (free\u002Fpro\u002Fetc) |\n| `error` | Something went wrong visibly | `message`, `page` |\n\n### What NOT to track\n- Every link or button (too noisy)\n- Scroll depth (not actionable)\n- Form field interactions (too granular)\n- Footer links (low signal)\n\n### Property naming rules\n\n- Use `snake_case`: `hero_get_started` not `heroGetStarted`\n- The `id` property identifies WHICH element: short, descriptive\n- Name IDs as `section_action`: `hero_signup`, `pricing_pro`, `nav_dashboard`\n\n## Step 2b: Run A\u002FB experiments\n\nExperiments let you test which variant of a page element converts better. The full lifecycle is API-driven — no dashboard UI needed.\n\n### Creating an experiment\n\n```bash\nnpx @agent-analytics\u002Fcli experiments create my-site \\\n  --name signup_cta --variants control,new_cta --goal signup\n```\n\n### Implementing variants\n\n**Declarative (recommended):** Use `data-aa-experiment` and `data-aa-variant-{key}` HTML attributes. Original content is the control. The tracker swaps text for assigned variants automatically.\n\n```html\n\u003Ch1 data-aa-experiment=\"signup_cta\" data-aa-variant-new_cta=\"Start Free Trial\">Sign Up\u003C\u002Fh1>\n```\n\n**Programmatic (complex cases):** Use `window.aa?.experiment(name, variants)` — deterministic, same user always gets same variant.\n\n### Checking results\n\n```bash\nnpx @agent-analytics\u002Fcli experiments get exp_abc123\n```\n\nReturns Bayesian `probability_best`, `lift`, and a `recommendation`. The system needs ~100 exposures per variant before results are significant.\n\n## Step 3: Test immediately\n\nAfter adding tracking, verify it works:\n\n```bash\n# Click around, then check:\nnpx @agent-analytics\u002Fcli events PROJECT_NAME\n# Events appear within seconds.\n```\n\n## CLI Reference\n\nAll commands use `npx @agent-analytics\u002Fcli`:\n\n```bash\n# Setup\nlogin --token aak_YOUR_KEY           # Save API key (one time)\nprojects                              # List all projects\ncreate my-site --domain https:\u002F\u002F...   # Create project\n\n# Real-time\nlive                                  # Live TUI dashboard across ALL projects\nlive my-site                          # Live view for one project\n\n# Analytics\nstats my-site --days 7                # Overview: events, users, daily trends\ninsights my-site --period 7d          # Period-over-period comparison\nbreakdown my-site --property path --event page_view --limit 10  # Top pages\u002Freferrers\u002FUTM\npages my-site --type entry            # Landing page performance & bounce rates\nsessions-dist my-site                 # Session engagement histogram\nheatmap my-site                       # Peak hours & busiest days\nevents my-site --days 30              # Raw event log\nsessions my-site                      # Individual session records\nproperties my-site                    # Discover event names & property keys\nfunnel my-site --steps \"page_view,signup,purchase\"  # Funnel drop-off\nretention my-site --period week --cohorts 8         # Cohort retention\n\n# A\u002FB experiments\nexperiments list my-site\nexperiments create my-site --name signup_cta --variants control,new_cta --goal signup\nexperiments get exp_abc123\nexperiments complete exp_abc123 --winner new_cta\n```\n\n## Which endpoint for which question\n\n| User asks | Call | Why |\n|-----------|------|-----|\n| \"How's my site doing?\" | `insights` + `breakdown` + `pages` (parallel) | Full weekly picture |\n| \"Is anyone visiting right now?\" | `live` | Real-time visitors across all projects |\n| \"What are my top pages?\" | `breakdown --property path --event page_view` | Ranked page list |\n| \"Where's my traffic coming from?\" | `breakdown --property referrer --event page_view` | Referrer sources |\n| \"Are people actually engaging?\" | `sessions-dist` | Bounce vs engaged split |\n| \"When should I deploy?\" | `heatmap` | Find low-traffic windows |\n| \"Where do users drop off?\" | `funnel --steps \"page_view,signup,purchase\"` | Step-by-step conversion |\n| \"Are users coming back?\" | `retention --period week --cohorts 8` | Cohort retention |\n| \"Which CTA converts better?\" | `experiments create` + `experiments get` | A\u002FB test lifecycle |\n\nFor any \"how is X doing\" question, **always call `insights` first** — it's the single most useful endpoint.\n\n## Examples\n\nTrack custom events via `window.aa?.track()`:\n\n```js\nwindow.aa?.track('cta_click', {id: 'hero_get_started'});\nwindow.aa?.track('signup', {method: 'github'});\nwindow.aa?.track('feature_used', {feature: 'create_project'});\nwindow.aa?.track('checkout', {plan: 'pro'});\n```\n\n## What this skill does NOT do\n\n- No GUI dashboards — your agent IS the dashboard (or use `live` for a real-time TUI)\n- No user management or billing\n- No PII stored — IP addresses are not logged or retained. Privacy-first by design\n",{"name":5,"category":24,"requires":25,"description":7},"analytics",{"env":26,"bins":28},[27],"AGENT_ANALYTICS_API_KEY",[29],"npx","main","87afe6ce96220accf50a345dea46784c8c9f210e","YYC3-AI-应用工具\u002FYYC3-AI-应用工具-buildwithclaude\u002Fplugins\u002Fall-skills\u002Fskills\u002Fagent-analytics",0,"https:\u002F\u002Fgithub.com\u002FYYC-Cube\u002FYYC3-Knowledge-Base","https:\u002F\u002Fkb.yyc3.top\u002F","https:\u002F\u002Fgithub.com\u002FYYC-Cube","万象归元于云枢 | 深栈智启新纪元","2026-11-10 10:37:32",{"source":8,"skillName":5,"commands":40,"prompt":49,"zipAvailable":50},[41,43,46],{"tool":29,"command":42},"npx skills add YYC-Cube\u002FYYC3-Knowledge-Base --skill agent-analytics",{"tool":44,"command":45},"bunx","bunx skills add YYC-Cube\u002FYYC3-Knowledge-Base --skill agent-analytics",{"tool":47,"command":48},"pnpm","pnpm dlx skills add YYC-Cube\u002FYYC3-Knowledge-Base --skill agent-analytics","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002FYYC-Cube\u002FYYC3-Knowledge-Base\u002Fblob\u002Fmain\u002FYYC3-AI-应用工具\u002FYYC3-AI-应用工具-buildwithclaude\u002Fplugins\u002Fall-skills\u002Fskills\u002Fagent-analytics\u002FSKILL.md",true,[],[53,60,67,74,81,88],{"skillNo":54,"name":55,"nameZh":6,"description":56,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":57,"categories":58,"keywords":59,"publishedAt":19},"01M7CTDWHERCXPQCP0K03A86AS","vercel-sandbox","Run agent-browser + Chrome inside Vercel Sandbox microVMs for browser automation from any Vercel-deployed app. Use when the user needs browser automation in a Vercel app (Next.js, SvelteKit, Nuxt, Remix, Astro, etc.), wants to run headless Chrome without binary size limits, needs persistent browser sessions across commands, or wants ephemeral isolated browser environments. Triggers include \"Vercel Sandbox browser\", \"microVM Chrome\", \"agent-browser in sandbox\", \"browser automation on Vercel\", or any task requiring Chrome in a Vercel Sandbox.","https:\u002F\u002Fgithub.com\u002FYYC-Cube\u002FYYC3-Knowledge-Base\u002Fblob\u002Fmain\u002FYYC3-WebSpec-Web标准\u002FYYC3-WebSpec-Web标准-standards\u002Fbrowser-agent\u002Fskills\u002Fvercel-sandbox\u002FSKILL.md",[],[],{"skillNo":61,"name":62,"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},"01M7CTD8D2BNJY54S65M47HEJA","slack","Interact with Slack workspaces using browser automation. Use when the user needs to check unread channels, navigate Slack, send messages, extract data, find information, search conversations, or automate any Slack task. Triggers include \"check my Slack\", \"what channels have unreads\", \"send a message to\", \"search Slack for\", \"extract from Slack\", \"find who said\", or any task requiring programmatic Slack interaction.","https:\u002F\u002Fgithub.com\u002FYYC-Cube\u002FYYC3-Knowledge-Base\u002Fblob\u002Fmain\u002FYYC3-WebSpec-Web标准\u002FYYC3-WebSpec-Web标准-standards\u002Fbrowser-agent\u002Fskills\u002Fslack\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},"01M7CTCSSB8ZP3Q58C3YZDZK1W","electron","Automate Electron desktop apps (VS Code, Slack, Discord, Figma, Notion, Spotify, etc.) using agent-browser via Chrome DevTools Protocol. Use when the user needs to interact with an Electron app, automate a desktop app, connect to a running app, control a native app, or test an Electron application. Triggers include \"automate Slack app\", \"control VS Code\", \"interact with Discord app\", \"test this Electron app\", \"connect to desktop app\", or any task requiring automation of a native Electron application.","https:\u002F\u002Fgithub.com\u002FYYC-Cube\u002FYYC3-Knowledge-Base\u002Fblob\u002Fmain\u002FYYC3-WebSpec-Web标准\u002FYYC3-WebSpec-Web标准-standards\u002Fbrowser-agent\u002Fskills\u002Felectron\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},"01M7CTCBJY76688V4DCZGWFHGQ","dogfood","Systematically explore and test a web application to find bugs, UX issues, and other problems. Use when asked to \"dogfood\", \"QA\", \"exploratory test\", \"find issues\", \"bug hunt\", \"test this app\u002Fsite\u002Fplatform\", or review the quality of a web application. Produces a structured report with full reproduction evidence -- step-by-step screenshots, repro videos, and detailed repro steps for every issue -- so findings can be handed directly to the responsible teams.","https:\u002F\u002Fgithub.com\u002FYYC-Cube\u002FYYC3-Knowledge-Base\u002Fblob\u002Fmain\u002FYYC3-WebSpec-Web标准\u002FYYC3-WebSpec-Web标准-standards\u002Fbrowser-agent\u002Fskills\u002Fdogfood\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},"01M7CTC4H0FFGVEAQR9PA4GA1A","agent-browser","Browser automation CLI for AI agents. Use when the user needs to interact with websites, including navigating pages, filling forms, clicking buttons, taking screenshots, extracting data, testing web apps, or automating any browser task. Triggers include requests to \"open a website\", \"fill out a form\", \"click a button\", \"take a screenshot\", \"scrape data from a page\", \"test this web app\", \"login to a site\", \"automate browser actions\", or any task requiring programmatic web interaction.","https:\u002F\u002Fgithub.com\u002FYYC-Cube\u002FYYC3-Knowledge-Base\u002Fblob\u002Fmain\u002FYYC3-WebSpec-Web标准\u002FYYC3-WebSpec-Web标准-standards\u002Fbrowser-agent\u002Fskills\u002Fagent-browser\u002FSKILL.md",[],[],{"skillNo":89,"name":90,"nameZh":6,"description":91,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":92,"categories":93,"keywords":94,"publishedAt":19},"01M7CTBKVFYBG78FDSABSDJTTQ","shadcn","Manages shadcn components and projects — adding, searching, fixing, debugging, styling, and composing UI, including chat interfaces. Provides project context, component docs, and usage examples. Applies when working with shadcn\u002Fui, component registries, presets, --preset codes, or any project with a components.json file. Also triggers for \"shadcn init\", \"create an app with --preset\", \"switch to --preset\", and for building a design system or applying a DESIGN.md or brand spec to shadcn\u002Fui.","https:\u002F\u002Fgithub.com\u002FYYC-Cube\u002FYYC3-Knowledge-Base\u002Fblob\u002Fmain\u002FYYC3-UI-界面组件\u002FYYC3-UI-界面组件-ui\u002Fskills\u002Fshadcn\u002FSKILL.md",[],[]]