[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M7CR104FJ45RRYVXW0SBSHS8":3,"skill-same:01M7CR104FJ45RRYVXW0SBSHS8":101},{"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":28,"commitSha":29,"skillDirectory":30,"forksCount":31,"repositoryHtmlUrl":32,"repositoryHomepageUrl":33,"ownerHtmlUrl":34,"ownerBlogUrl":6,"ownerDescription":35,"updatedAt":36,"install":37,"resources":50},"01M7CR104FJ45RRYVXW0SBSHS8","outbound-engine",null,"Design, analyze, and optimize cold outbound email campaigns for Instantly. Handles end-to-end ICP definition, expert panel scoring (recursive to 90+), sequence copywriting, infrastructure audit, capacity planning, and implementation docs. Use when asked to build cold outbound sequences, optimize cold email, analyze outbound campaigns, build sales sequences, build Instantly sequences, create cold outbound strategies, or design email campaigns. Supports both \"start from scratch\" and \"optimize existing\" modes.","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-Skills-技能包\u002FYYC3-Skills-技能包-code-skills\u002Fskills\u002Foutbound-engine\u002FSKILL.md",[],[],"2026-11-15 14:19:17",false,"---\nname: outbound-engine\ndescription: Design, analyze, and optimize cold outbound email campaigns for Instantly. Handles end-to-end ICP definition, expert panel scoring (recursive to 90+), sequence copywriting, infrastructure audit, capacity planning, and implementation docs. Use when asked to build cold outbound sequences, optimize cold email, analyze outbound campaigns, build sales sequences, build Instantly sequences, create cold outbound strategies, or design email campaigns. Supports both \"start from scratch\" and \"optimize existing\" modes.\ndescription_zh: \"自动化外拓邮件引擎，从 ICP 定义到邮件入站全流程\"\ndescription_en: \"Automated cold outbound engine from ICP definition to inbox delivery\"\nversion: 1.0.0\nhomepage: https:\u002F\u002Fgithub.com\u002Fericosiu\u002Fai-marketing-skills\n---\n\n\n## Preamble (runs on skill start)\n\n```bash\n# Version check (silent if up to date)\npython3 telemetry\u002Fversion_check.py 2>\u002Fdev\u002Fnull || true\n\n# Telemetry opt-in (first run only, then remembers your choice)\npython3 telemetry\u002Ftelemetry_init.py 2>\u002Fdev\u002Fnull || true\n```\n\n> **Privacy:** This skill logs usage locally to `~\u002F.ai-marketing-skills\u002Fanalytics\u002F`. Remote telemetry is opt-in only. No code, file paths, or repo content is ever collected. See `telemetry\u002FREADME.md`.\n\n---\n\n# Cold Outbound Optimizer\n\n---\n\n## Startup: Determine Mode\n\nAsk the user:\n1. Do you have an **existing Instantly account** with campaigns to audit, or are you **starting from scratch**?\n2. Do you have an **Instantly API key**? (Required for audit mode.)\n\nIf API key provided → run `scripts\u002Finstantly-audit.py` to pull campaigns, account inventory, and warmup scores before proceeding.\n\n---\n\n## Phase 1: Discovery & Audit\n\n### 1A — Infrastructure Check (if API key available)\nRun `python3 scripts\u002Finstantly-audit.py --api-key \u003CKEY>` and report:\n- Active campaigns (name, status, reply rate, open rate)\n- Sending accounts (count, warmup score, daily limit)\n- Domain inventory\n- Warmup gaps: any account with score \u003C80 or \u003C14 days warmup → flag as NOT ready\n\n### 1B — Performance Data\n- Pull campaign analytics from Instantly\n- Ask: \"Do you have a spreadsheet with historical outbound data?\" If yes, request link.\n\n### 1C — ICP Definition\nIf no ICP defined, collect:\n- **Titles:** Who are you targeting? (e.g., VP Marketing, Head of Growth)\n- **Industries:** Which verticals?\n- **Company size:** Employee count or revenue range?\n- **Revenue floor:** Minimum ARR\u002Frevenue to qualify?\n- **Anti-ICP:** Who to explicitly exclude?\n\nUse `references\u002Ficp-template.md` as the collection template.\n\n### 1D — Business Context\nCollect:\n- What do you sell? (One sentence, no jargon)\n- What's the primary offer? (Free trial, audit, demo, consultation)\n- Real URLs to reference (pricing page, case studies, relevant content)\n- Any proof points? (Client results, stats, social proof)\n\n### 1E — Expert Panel Config\nDefault: 10 experts (see `references\u002Fexpert-panel.md`).\nAsk: \"Any industry-specific experts to add, or panelists to swap?\" Confirm roster before scoring.\n\n---\n\n## Phase 2: Expert Panel Recursive Scoring\n\n**Target: 90\u002F100. Non-negotiable. Iterate until reached.**\n\n### Round Structure\nEach round produces:\n1. **Score table** — all 10 panelists, individual score (0-100), one-line rationale\n2. **Aggregate score** — average of all 10\n3. **Top weaknesses** — ranked list of what's holding the copy back\n4. **Changes made** — specific edits addressing each weakness\n5. **Updated copy** — full revised sequence after changes\n\n### Scoring Criteria (per panelist's lens — see `references\u002Fexpert-panel.md`)\n- Subject line curiosity \u002F open rate potential\n- First sentence pattern interrupt\n- Body clarity and brevity\n- CTA softness and specificity\n- Sequence flow and follow-up logic\n- Deliverability risk signals (spam words, link density)\n- Personalization believability\n\n### Rules\n- Scores must be brutally honest. No padding to 90 without earning it.\n- If round score \u003C 90: identify top 3 weaknesses, revise copy, run next round.\n- If round score ≥ 90: finalize copy and proceed to deliverables.\n- Show every round in the final doc — the iteration trail is part of the value.\n\n---\n\n## Phase 3: Deliverables\n\n### Strategy Doc\nCreate a document (Google Doc, Notion, or markdown) with:\n\n1. **Pre-Analysis \u002F Brutal Truth** — what the existing campaigns are doing wrong (or baseline if starting from scratch)\n2. **ICP Summary** — confirmed targeting parameters\n3. **Infrastructure Status** — account inventory, warmup readiness, capacity math\n4. **Scoring Rounds** — full panel vote tables for every round\n5. **Final Email Copy** — all steps for all campaigns, Instantly-ready format\n6. **Implementation Plan** — step-by-step setup instructions\n7. **Capacity Math** — accounts × daily send rate = pipeline projections\n8. **Weekly Metrics Targets** — open rate, reply rate, positive reply rate, meetings booked\n9. **STOP List** — what to kill immediately\n10. **START List** — what to launch first\n\n### Format Rules for Final Copy\nFollow all rules in `references\u002Finstantly-rules.md` and `references\u002Fcopy-rules.md`.\n\n### Human Review Gate\n**Do NOT push anything to Instantly automatically.** The doc is for human review. Get explicit approval before any API writes.\n\n### Iteration\nAfter review, collect feedback and re-run scoring on revised copy if needed.\n\n---\n\n## Capacity Math Formula\n\n```\nAccounts ready (score ≥80, ≥14 days warmup) × 30 emails\u002Fday = conservative daily volume\nAccounts ready × 50 emails\u002Fday = aggressive daily volume\nDaily volume × 22 working days = monthly send capacity\nMonthly sends × expected reply rate = expected replies\nExpected replies × qualification rate = pipeline opportunities\n```\n\n---\n\n## Weekly Metrics Targets (Baselines)\n\n| Metric | Good | Great |\n|--------|------|-------|\n| Open rate | 40%+ | 60%+ |\n| Reply rate | 3%+ | 7%+ |\n| Positive reply rate | 1%+ | 3%+ |\n| Meeting rate | 0.5%+ | 1.5%+ |\n\nAdjust targets based on niche and offer. Cold traffic to a free audit converts differently than a paid trial.\n\n---\n\n## Add-On Recommendations (mention but don't build)\n\n- **LinkedIn automation:** HeyReach or similar for multi-channel sequences. Separate workflow.\n- **Lead enrichment:** Clay or Apollo for personalization data before upload.\n- **Lead pipeline:** Use `scripts\u002Flead-pipeline.py` for Apollo → LeadMagic → Instantly automation.\n\n---\n\n## Reference Files\n\n| File | Purpose |\n|------|---------|\n| `references\u002Finstantly-rules.md` | Variable syntax, sequence structure, deliverability rules |\n| `references\u002Fexpert-panel.md` | Default 10-expert roster with scoring lenses |\n| `references\u002Fcopy-rules.md` | Email copy rules (first sentence, CTA, stats framing) |\n| `references\u002Ficp-template.md` | ICP data collection template |\n| `scripts\u002Finstantly-audit.py` | Pulls campaigns, accounts, warmup scores via Instantly v2 API |\n| `scripts\u002Flead-pipeline.py` | End-to-end lead sourcing pipeline |\n| `scripts\u002Fcompetitive-monitor.py` | Competitor tracking and intelligence |\n| `scripts\u002Fcross-signal-detector.py` | Multi-source signal detection |\n| `scripts\u002Fcold-outbound-sender.py` | Send approved outbound emails |\n","## Preamble (runs on skill start)\n\n```bash\n# Version check (silent if up to date)\npython3 telemetry\u002Fversion_check.py 2>\u002Fdev\u002Fnull || true\n\n# Telemetry opt-in (first run only, then remembers your choice)\npython3 telemetry\u002Ftelemetry_init.py 2>\u002Fdev\u002Fnull || true\n```\n\n> **Privacy:** This skill logs usage locally to `~\u002F.ai-marketing-skills\u002Fanalytics\u002F`. Remote telemetry is opt-in only. No code, file paths, or repo content is ever collected. See `telemetry\u002FREADME.md`.\n\n---\n\n# Cold Outbound Optimizer\n\n---\n\n## Startup: Determine Mode\n\nAsk the user:\n1. Do you have an **existing Instantly account** with campaigns to audit, or are you **starting from scratch**?\n2. Do you have an **Instantly API key**? (Required for audit mode.)\n\nIf API key provided → run `scripts\u002Finstantly-audit.py` to pull campaigns, account inventory, and warmup scores before proceeding.\n\n---\n\n## Phase 1: Discovery & Audit\n\n### 1A — Infrastructure Check (if API key available)\nRun `python3 scripts\u002Finstantly-audit.py --api-key \u003CKEY>` and report:\n- Active campaigns (name, status, reply rate, open rate)\n- Sending accounts (count, warmup score, daily limit)\n- Domain inventory\n- Warmup gaps: any account with score \u003C80 or \u003C14 days warmup → flag as NOT ready\n\n### 1B — Performance Data\n- Pull campaign analytics from Instantly\n- Ask: \"Do you have a spreadsheet with historical outbound data?\" If yes, request link.\n\n### 1C — ICP Definition\nIf no ICP defined, collect:\n- **Titles:** Who are you targeting? (e.g., VP Marketing, Head of Growth)\n- **Industries:** Which verticals?\n- **Company size:** Employee count or revenue range?\n- **Revenue floor:** Minimum ARR\u002Frevenue to qualify?\n- **Anti-ICP:** Who to explicitly exclude?\n\nUse `references\u002Ficp-template.md` as the collection template.\n\n### 1D — Business Context\nCollect:\n- What do you sell? (One sentence, no jargon)\n- What's the primary offer? (Free trial, audit, demo, consultation)\n- Real URLs to reference (pricing page, case studies, relevant content)\n- Any proof points? (Client results, stats, social proof)\n\n### 1E — Expert Panel Config\nDefault: 10 experts (see `references\u002Fexpert-panel.md`).\nAsk: \"Any industry-specific experts to add, or panelists to swap?\" Confirm roster before scoring.\n\n---\n\n## Phase 2: Expert Panel Recursive Scoring\n\n**Target: 90\u002F100. Non-negotiable. Iterate until reached.**\n\n### Round Structure\nEach round produces:\n1. **Score table** — all 10 panelists, individual score (0-100), one-line rationale\n2. **Aggregate score** — average of all 10\n3. **Top weaknesses** — ranked list of what's holding the copy back\n4. **Changes made** — specific edits addressing each weakness\n5. **Updated copy** — full revised sequence after changes\n\n### Scoring Criteria (per panelist's lens — see `references\u002Fexpert-panel.md`)\n- Subject line curiosity \u002F open rate potential\n- First sentence pattern interrupt\n- Body clarity and brevity\n- CTA softness and specificity\n- Sequence flow and follow-up logic\n- Deliverability risk signals (spam words, link density)\n- Personalization believability\n\n### Rules\n- Scores must be brutally honest. No padding to 90 without earning it.\n- If round score \u003C 90: identify top 3 weaknesses, revise copy, run next round.\n- If round score ≥ 90: finalize copy and proceed to deliverables.\n- Show every round in the final doc — the iteration trail is part of the value.\n\n---\n\n## Phase 3: Deliverables\n\n### Strategy Doc\nCreate a document (Google Doc, Notion, or markdown) with:\n\n1. **Pre-Analysis \u002F Brutal Truth** — what the existing campaigns are doing wrong (or baseline if starting from scratch)\n2. **ICP Summary** — confirmed targeting parameters\n3. **Infrastructure Status** — account inventory, warmup readiness, capacity math\n4. **Scoring Rounds** — full panel vote tables for every round\n5. **Final Email Copy** — all steps for all campaigns, Instantly-ready format\n6. **Implementation Plan** — step-by-step setup instructions\n7. **Capacity Math** — accounts × daily send rate = pipeline projections\n8. **Weekly Metrics Targets** — open rate, reply rate, positive reply rate, meetings booked\n9. **STOP List** — what to kill immediately\n10. **START List** — what to launch first\n\n### Format Rules for Final Copy\nFollow all rules in `references\u002Finstantly-rules.md` and `references\u002Fcopy-rules.md`.\n\n### Human Review Gate\n**Do NOT push anything to Instantly automatically.** The doc is for human review. Get explicit approval before any API writes.\n\n### Iteration\nAfter review, collect feedback and re-run scoring on revised copy if needed.\n\n---\n\n## Capacity Math Formula\n\n```\nAccounts ready (score ≥80, ≥14 days warmup) × 30 emails\u002Fday = conservative daily volume\nAccounts ready × 50 emails\u002Fday = aggressive daily volume\nDaily volume × 22 working days = monthly send capacity\nMonthly sends × expected reply rate = expected replies\nExpected replies × qualification rate = pipeline opportunities\n```\n\n---\n\n## Weekly Metrics Targets (Baselines)\n\n| Metric | Good | Great |\n|--------|------|-------|\n| Open rate | 40%+ | 60%+ |\n| Reply rate | 3%+ | 7%+ |\n| Positive reply rate | 1%+ | 3%+ |\n| Meeting rate | 0.5%+ | 1.5%+ |\n\nAdjust targets based on niche and offer. Cold traffic to a free audit converts differently than a paid trial.\n\n---\n\n## Add-On Recommendations (mention but don't build)\n\n- **LinkedIn automation:** HeyReach or similar for multi-channel sequences. Separate workflow.\n- **Lead enrichment:** Clay or Apollo for personalization data before upload.\n- **Lead pipeline:** Use `scripts\u002Flead-pipeline.py` for Apollo → LeadMagic → Instantly automation.\n\n---\n\n## Reference Files\n\n| File | Purpose |\n|------|---------|\n| `references\u002Finstantly-rules.md` | Variable syntax, sequence structure, deliverability rules |\n| `references\u002Fexpert-panel.md` | Default 10-expert roster with scoring lenses |\n| `references\u002Fcopy-rules.md` | Email copy rules (first sentence, CTA, stats framing) |\n| `references\u002Ficp-template.md` | ICP data collection template |\n| `scripts\u002Finstantly-audit.py` | Pulls campaigns, accounts, warmup scores via Instantly v2 API |\n| `scripts\u002Flead-pipeline.py` | End-to-end lead sourcing pipeline |\n| `scripts\u002Fcompetitive-monitor.py` | Competitor tracking and intelligence |\n| `scripts\u002Fcross-signal-detector.py` | Multi-source signal detection |\n| `scripts\u002Fcold-outbound-sender.py` | Send approved outbound emails |\n",{"name":5,"version":24,"homepage":25,"description":7,"description_en":26,"description_zh":27},"1.0.0","https:\u002F\u002Fgithub.com\u002Fericosiu\u002Fai-marketing-skills","Automated cold outbound engine from ICP definition to inbox delivery","自动化外拓邮件引擎，从 ICP 定义到邮件入站全流程","main","87afe6ce96220accf50a345dea46784c8c9f210e","YYC3-Skills-技能包\u002FYYC3-Skills-技能包-code-skills\u002Fskills\u002Foutbound-engine",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":38,"prompt":48,"zipAvailable":49},[39,42,45],{"tool":40,"command":41},"npx","npx skills add YYC-Cube\u002FYYC3-Knowledge-Base --skill outbound-engine",{"tool":43,"command":44},"bunx","bunx skills add YYC-Cube\u002FYYC3-Knowledge-Base --skill outbound-engine",{"tool":46,"command":47},"pnpm","pnpm dlx skills add YYC-Cube\u002FYYC3-Knowledge-Base --skill outbound-engine","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002FYYC-Cube\u002FYYC3-Knowledge-Base\u002Fblob\u002Fmain\u002FYYC3-Skills-技能包\u002FYYC3-Skills-技能包-code-skills\u002Fskills\u002Foutbound-engine\u002FSKILL.md",true,[51,57,63,67,71,75,79,85,89,93,97],{"path":52,"resourceType":53,"resourceTypeDesc":54,"sizeBytes":55,"sourceHtmlUrl":56},".env.example","OTHER","其他",854,"https:\u002F\u002Fgithub.com\u002FYYC-Cube\u002FYYC3-Knowledge-Base\u002Fblob\u002Fmain\u002FYYC3-Skills-技能包\u002FYYC3-Skills-技能包-code-skills\u002Fskills\u002Foutbound-engine\u002F.env.example",{"path":58,"resourceType":59,"resourceTypeDesc":60,"sizeBytes":61,"sourceHtmlUrl":62},"references\u002Fcopy-rules.md","REFERENCE","参考文档",4772,"https:\u002F\u002Fgithub.com\u002FYYC-Cube\u002FYYC3-Knowledge-Base\u002Fblob\u002Fmain\u002FYYC3-Skills-技能包\u002FYYC3-Skills-技能包-code-skills\u002Fskills\u002Foutbound-engine\u002Freferences\u002Fcopy-rules.md",{"path":64,"resourceType":59,"resourceTypeDesc":60,"sizeBytes":65,"sourceHtmlUrl":66},"references\u002Fexpert-panel.md",4795,"https:\u002F\u002Fgithub.com\u002FYYC-Cube\u002FYYC3-Knowledge-Base\u002Fblob\u002Fmain\u002FYYC3-Skills-技能包\u002FYYC3-Skills-技能包-code-skills\u002Fskills\u002Foutbound-engine\u002Freferences\u002Fexpert-panel.md",{"path":68,"resourceType":59,"resourceTypeDesc":60,"sizeBytes":69,"sourceHtmlUrl":70},"references\u002Ficp-template.md",3238,"https:\u002F\u002Fgithub.com\u002FYYC-Cube\u002FYYC3-Knowledge-Base\u002Fblob\u002Fmain\u002FYYC3-Skills-技能包\u002FYYC3-Skills-技能包-code-skills\u002Fskills\u002Foutbound-engine\u002Freferences\u002Ficp-template.md",{"path":72,"resourceType":59,"resourceTypeDesc":60,"sizeBytes":73,"sourceHtmlUrl":74},"references\u002Finstantly-rules.md",2930,"https:\u002F\u002Fgithub.com\u002FYYC-Cube\u002FYYC3-Knowledge-Base\u002Fblob\u002Fmain\u002FYYC3-Skills-技能包\u002FYYC3-Skills-技能包-code-skills\u002Fskills\u002Foutbound-engine\u002Freferences\u002Finstantly-rules.md",{"path":76,"resourceType":59,"resourceTypeDesc":60,"sizeBytes":77,"sourceHtmlUrl":78},"requirements.txt",17,"https:\u002F\u002Fgithub.com\u002FYYC-Cube\u002FYYC3-Knowledge-Base\u002Fblob\u002Fmain\u002FYYC3-Skills-技能包\u002FYYC3-Skills-技能包-code-skills\u002Fskills\u002Foutbound-engine\u002Frequirements.txt",{"path":80,"resourceType":81,"resourceTypeDesc":82,"sizeBytes":83,"sourceHtmlUrl":84},"scripts\u002Fcold-outbound-sender.py","SCRIPT","脚本",8485,"https:\u002F\u002Fgithub.com\u002FYYC-Cube\u002FYYC3-Knowledge-Base\u002Fblob\u002Fmain\u002FYYC3-Skills-技能包\u002FYYC3-Skills-技能包-code-skills\u002Fskills\u002Foutbound-engine\u002Fscripts\u002Fcold-outbound-sender.py",{"path":86,"resourceType":81,"resourceTypeDesc":82,"sizeBytes":87,"sourceHtmlUrl":88},"scripts\u002Fcompetitive-monitor.py",17209,"https:\u002F\u002Fgithub.com\u002FYYC-Cube\u002FYYC3-Knowledge-Base\u002Fblob\u002Fmain\u002FYYC3-Skills-技能包\u002FYYC3-Skills-技能包-code-skills\u002Fskills\u002Foutbound-engine\u002Fscripts\u002Fcompetitive-monitor.py",{"path":90,"resourceType":81,"resourceTypeDesc":82,"sizeBytes":91,"sourceHtmlUrl":92},"scripts\u002Fcross-signal-detector.py",10804,"https:\u002F\u002Fgithub.com\u002FYYC-Cube\u002FYYC3-Knowledge-Base\u002Fblob\u002Fmain\u002FYYC3-Skills-技能包\u002FYYC3-Skills-技能包-code-skills\u002Fskills\u002Foutbound-engine\u002Fscripts\u002Fcross-signal-detector.py",{"path":94,"resourceType":81,"resourceTypeDesc":82,"sizeBytes":95,"sourceHtmlUrl":96},"scripts\u002Finstantly-audit.py",13179,"https:\u002F\u002Fgithub.com\u002FYYC-Cube\u002FYYC3-Knowledge-Base\u002Fblob\u002Fmain\u002FYYC3-Skills-技能包\u002FYYC3-Skills-技能包-code-skills\u002Fskills\u002Foutbound-engine\u002Fscripts\u002Finstantly-audit.py",{"path":98,"resourceType":81,"resourceTypeDesc":82,"sizeBytes":99,"sourceHtmlUrl":100},"scripts\u002Flead-pipeline.py",21591,"https:\u002F\u002Fgithub.com\u002FYYC-Cube\u002FYYC3-Knowledge-Base\u002Fblob\u002Fmain\u002FYYC3-Skills-技能包\u002FYYC3-Skills-技能包-code-skills\u002Fskills\u002Foutbound-engine\u002Fscripts\u002Flead-pipeline.py",[102,109,116,123,130,137],{"skillNo":103,"name":104,"nameZh":6,"description":105,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":106,"categories":107,"keywords":108,"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":110,"name":111,"nameZh":6,"description":112,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":113,"categories":114,"keywords":115,"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":117,"name":118,"nameZh":6,"description":119,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":120,"categories":121,"keywords":122,"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":124,"name":125,"nameZh":6,"description":126,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":127,"categories":128,"keywords":129,"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":131,"name":132,"nameZh":6,"description":133,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":134,"categories":135,"keywords":136,"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":138,"name":139,"nameZh":6,"description":140,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":141,"categories":142,"keywords":143,"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",[],[]]