[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M7CQ6FS7HACAMECF2M9YGCW3":3,"skill-same:01M7CQ6FS7HACAMECF2M9YGCW3":63},{"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},"01M7CQ6FS7HACAMECF2M9YGCW3","autoresearch",null,"Run Karpathy-style autoresearch optimization on any content. Generates 50+ variants, scores with a 5-expert simulated panel, evolves winners through multiple rounds, outputs optimized version + full experiment log. Use when optimizing landing pages, email sequences, ad copy, headlines, form pages, CTA text, or any conversion-focused content. Triggers on \"optimize this page\", \"run autoresearch\", \"score these variants\", \"A\u002FB test this copy\".","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\u002Fautoresearch\u002FSKILL.md",[],[],"2026-11-15 14:19:17",false,"---\nname: autoresearch\ndescription: Run Karpathy-style autoresearch optimization on any content. Generates 50+ variants, scores with a 5-expert simulated panel, evolves winners through multiple rounds, outputs optimized version + full experiment log. Use when optimizing landing pages, email sequences, ad copy, headlines, form pages, CTA text, or any conversion-focused content. Triggers on \"optimize this page\", \"run autoresearch\", \"score these variants\", \"A\u002FB test this copy\".\ndescription_zh: \"Karpathy 风格内容优化，50+ 变体 + 专家评分 + 进化迭代\"\ndescription_en: \"Karpathy-style content optimization with 50+ variants, expert scoring, and evolution\"\nversion: 1.0.0\nhomepage: https:\u002F\u002Fgithub.com\u002Fericosiu\u002Fai-marketing-skills\n---\n\n# Autoresearch Skill\n\nKarpathy-style optimization loops for any conversion-focused content. No traffic needed. Simulated expert panel. Minutes, not weeks.\n\n**When to use this:** Pre-launch content optimization. Generate 50+ variants, score with 5 simulated experts, evolve winners, output the best version + full experiment log.\n\n**When NOT to use this:** Post-launch real-traffic A\u002FB testing — that requires real analytics, not simulated scoring.\n\n> **The sequence:** Run autoresearch FIRST to hit 85+ simulated score. Then deploy. Then validate with real traffic.\n\n---\n\n## What You'll Produce\n\nEvery run outputs 3 files:\n\n| File | Purpose |\n|------|---------|\n| `{name}-optimized.{ext}` | The winning optimized content |\n| `data\u002F{name}-experiments.json` | Full experiment log — all variants + all scores |\n| `data\u002F{name}-optimization-report.md` | Human-readable summary with winner rationale |\n\n---\n\n## Expert Panel (5 Personas)\n\nScore every variant against all 5. Batch all variants into a **single API call** per round.\n\n| # | Persona | Scoring Lens |\n|---|---------|-------------|\n| 1 | **CMO at a mid-market B2B company (50M+ revenue)** | \"Would this make me stop and engage?\" |\n| 2 | **Skeptical founder** | \"Do I believe this? Would I trust this company?\" |\n| 3 | **Conversion rate optimizer** | \"Is this clear, specific, and action-driving?\" |\n| 4 | **Senior copywriter** | \"Is this compelling, differentiated, and well-crafted?\" |\n| 5 | **Your CEO\u002Ffounder** | \"Direct, ROI-obsessed, no BS. Would I put this on my site?\" |\n\n> **Customization:** Replace persona #5 with your own CEO\u002Ffounder voice. Define their priorities and communication style in a `references\u002Ffounder-voice.md` file.\n\nEach judge scores 0–100. **Final score = average across all 5 judges.**\n\n---\n\n## Round Structure (Per Content Element)\n\n```\nRound 1:\n  → Generate 10 variants of the element\n  → Batch-score all 10 with the 5-expert panel (1 API call)\n  → Rank by average score\n  → Keep top 3\n\nRound 2 (Evolution):\n  → Analyze what the top 3 did right\n  → Generate 10 new variants that push those winning patterns further\n  → Batch-score all 10 (1 API call)\n  → Keep top 3\n\nRound 3 (If score \u003C threshold):\n  → Identify weakest scoring dimension\n  → Generate 10 variants optimized for that dimension\n  → Batch-score → keep top 1\n\nMulti-element cross-breeding:\n  → Take top 1 winner from each element\n  → Generate 5 combinations that mix winning elements\n  → Score holistically as complete units\n  → Output the single best combination\n```\n\n**Stop condition:** Top variant hits minimum score threshold (default: 80) OR 3 rounds complete.\n\n---\n\n## Content Types & Score Dimensions\n\n### Landing Pages\n**Elements to optimize:** Hero headline, subheadline, CTA text, problem section, social proof\n\n**Score dimensions:**\n- `first_impression` — Does it grab immediately?\n- `clarity` — Is the offer instantly understood?\n- `trust` — Does it feel credible?\n- `urgency` — Is there a reason to act now?\n- `would_convert` — Would the judge actually click?\n\n### Email Sequences\n**Elements to optimize:** Subject line, opening line, body copy, CTA, PS line\n\n**Score dimensions:**\n- `would_open` — Subject line pass rate\n- `would_read` — Does the opening hook?\n- `would_click` — Is the CTA compelling?\n- `would_reply` — Does it feel personal enough to respond to?\n- `spam_risk` — Does it feel spammy? (lower = better; invert for final score)\n\n### Ad Copy\n**Elements to optimize:** Headline, description, CTA\n\n**Score dimensions:**\n- `scroll_stopping` — Does it interrupt the scroll?\n- `clarity` — Is the value prop clear in 3 seconds?\n- `click_worthiness` — Does the judge want to click?\n- `relevance` — Does it match likely audience intent?\n- `differentiation` — Does it stand out from competitors?\n\n### Form Pages\n**Elements to optimize:** Headline, subtext, value prop bullets, button text, field order, thank-you copy\n\n**Score dimensions:**\n- `first_impression` — Does it feel worth filling out?\n- `trust` — Do they believe their info is safe and the offer is real?\n- `completion_likelihood` — Would the judge start filling it out?\n- `lead_quality` — Would this attract serious prospects (not tire-kickers)?\n- `would_fill_out` — Final gut check: would they submit?\n\n---\n\n## Step-by-Step Execution Protocol\n\n### Step 1: Intake & Parse\n\nRead the source content. Identify content type automatically or confirm with user:\n- HTML file → landing page or form page\n- Markdown \u002F plain text → email or ad copy\n- If ambiguous, ask: \"Is this a landing page, email sequence, ad copy, or form page?\"\n\nExtract all optimizable elements. List them back to user:\n```\nFound 5 elements to optimize:\n1. Hero headline: \"We help B2B companies grow\"\n2. Subheadline: \"Full-service digital marketing...\"\n3. CTA: \"Get Started\"\n4. Problem statement: [excerpt]\n5. Social proof: [excerpt]\n\nOptimizing: all | Variants per round: 10 | Min score: 80\n```\n\n### Step 2: Get API Key\n\nCheck for Anthropic API key: `$ANTHROPIC_API_KEY` environment variable.\n\n```bash\nexport ANTHROPIC_API_KEY=\"your-api-key-here\"\n```\n\n### Step 3: Run Optimization Rounds\n\nFor each element, run the round structure above.\n\n**Critical API efficiency rule:** ALWAYS batch all variants into a single prompt. Never call the API once per variant. A round with 10 variants = 1 API call.\n\nModel preference (in order):\n1. `claude-sonnet-4-5` (preferred — fast + smart)\n2. `claude-opus-4` (if highest quality needed)\n3. Any claude-3.5+ model if the above aren't available\n\n### Step 4: Cross-Breed (Multi-Element)\n\nAfter all elements have winners:\n1. Assemble the top winner from each element into a complete unit\n2. Generate 5 holistic variants that naturally combine the winning elements\n3. Score the complete units (not just individual parts)\n4. Pick the winner with the highest holistic score\n\n### Step 5: Write Output Files\n\n```bash\n# Create output directory\nmkdir -p data\n\n# Write optimized content\n# Write experiments JSON\n# Write optimization report\n```\n\n**Experiments JSON structure:**\n```json\n{\n  \"run_id\": \"autoresearch-{name}-{timestamp}\",\n  \"content_type\": \"landing_page\",\n  \"source_file\": \"path\u002Fto\u002Foriginal\",\n  \"min_score_threshold\": 80,\n  \"rounds\": [\n    {\n      \"round\": 1,\n      \"element\": \"hero_headline\",\n      \"variants\": [\n        {\n          \"id\": 1,\n          \"text\": \"...\",\n          \"scores\": {\n            \"cmo\": 72,\n            \"skeptical_founder\": 68,\n            \"cro\": 75,\n            \"copywriter\": 70,\n            \"founder\": 65\n          },\n          \"avg_score\": 70\n        }\n      ],\n      \"top_3\": [1, 4, 7],\n      \"winner_score\": 82\n    }\n  ],\n  \"final_winner\": {\n    \"hero_headline\": \"...\",\n    \"subheadline\": \"...\",\n    \"cta\": \"...\",\n    \"holistic_score\": 87\n  }\n}\n```\n\n### Step 6: Report Back\n\nSummarize results to user:\n- Final winning score\n- Biggest score jump (which element improved most)\n- Top 2 runner-up alternatives (in case winner doesn't feel right)\n- Path to all 3 output files\n- Clear next step\n\n---\n\n## User Options\n\n| Option | Default | Description |\n|--------|---------|-------------|\n| `elements` | all | Which elements to optimize |\n| `variants_per_round` | 10 | How many variants to generate per round |\n| `min_score` | 80 | Stop when this score is hit |\n| `rounds` | 3 | Max rounds before stopping |\n| `auto_apply` | false | Whether to overwrite the source file with winners |\n| `content_type` | auto-detect | Force a content type if auto-detect is wrong |\n\n---\n\n## Quality Gates\n\n- **\u003C 70:** Don't ship. Something fundamental is broken.\n- **70-79:** Marginal. One more round targeting the lowest-scoring dimension.\n- **80-84:** Good. Shippable. Validate with real traffic.\n- **85-89:** Strong. Ship with confidence.\n- **90+:** Rare. Ship immediately.\n\n---\n\n## Anti-Patterns to Avoid\n\n- **Never call the API once per variant.** Always batch. A 10-variant round = 1 call.\n- **Don't over-optimize for one dimension.** If you're hitting 95 on clarity but 45 on trust, the overall score is misleading.\n- **Don't run more than 5 rounds.** If you're not hitting 80 after 3 rounds, the problem is strategic (wrong positioning), not tactical (wrong words).\n- **Don't cross-breed until each element has its own winner.** Premature cross-breeding creates incoherent combinations.\n","# Autoresearch Skill\n\nKarpathy-style optimization loops for any conversion-focused content. No traffic needed. Simulated expert panel. Minutes, not weeks.\n\n**When to use this:** Pre-launch content optimization. Generate 50+ variants, score with 5 simulated experts, evolve winners, output the best version + full experiment log.\n\n**When NOT to use this:** Post-launch real-traffic A\u002FB testing — that requires real analytics, not simulated scoring.\n\n> **The sequence:** Run autoresearch FIRST to hit 85+ simulated score. Then deploy. Then validate with real traffic.\n\n---\n\n## What You'll Produce\n\nEvery run outputs 3 files:\n\n| File | Purpose |\n|------|---------|\n| `{name}-optimized.{ext}` | The winning optimized content |\n| `data\u002F{name}-experiments.json` | Full experiment log — all variants + all scores |\n| `data\u002F{name}-optimization-report.md` | Human-readable summary with winner rationale |\n\n---\n\n## Expert Panel (5 Personas)\n\nScore every variant against all 5. Batch all variants into a **single API call** per round.\n\n| # | Persona | Scoring Lens |\n|---|---------|-------------|\n| 1 | **CMO at a mid-market B2B company (50M+ revenue)** | \"Would this make me stop and engage?\" |\n| 2 | **Skeptical founder** | \"Do I believe this? Would I trust this company?\" |\n| 3 | **Conversion rate optimizer** | \"Is this clear, specific, and action-driving?\" |\n| 4 | **Senior copywriter** | \"Is this compelling, differentiated, and well-crafted?\" |\n| 5 | **Your CEO\u002Ffounder** | \"Direct, ROI-obsessed, no BS. Would I put this on my site?\" |\n\n> **Customization:** Replace persona #5 with your own CEO\u002Ffounder voice. Define their priorities and communication style in a `references\u002Ffounder-voice.md` file.\n\nEach judge scores 0–100. **Final score = average across all 5 judges.**\n\n---\n\n## Round Structure (Per Content Element)\n\n```\nRound 1:\n  → Generate 10 variants of the element\n  → Batch-score all 10 with the 5-expert panel (1 API call)\n  → Rank by average score\n  → Keep top 3\n\nRound 2 (Evolution):\n  → Analyze what the top 3 did right\n  → Generate 10 new variants that push those winning patterns further\n  → Batch-score all 10 (1 API call)\n  → Keep top 3\n\nRound 3 (If score \u003C threshold):\n  → Identify weakest scoring dimension\n  → Generate 10 variants optimized for that dimension\n  → Batch-score → keep top 1\n\nMulti-element cross-breeding:\n  → Take top 1 winner from each element\n  → Generate 5 combinations that mix winning elements\n  → Score holistically as complete units\n  → Output the single best combination\n```\n\n**Stop condition:** Top variant hits minimum score threshold (default: 80) OR 3 rounds complete.\n\n---\n\n## Content Types & Score Dimensions\n\n### Landing Pages\n**Elements to optimize:** Hero headline, subheadline, CTA text, problem section, social proof\n\n**Score dimensions:**\n- `first_impression` — Does it grab immediately?\n- `clarity` — Is the offer instantly understood?\n- `trust` — Does it feel credible?\n- `urgency` — Is there a reason to act now?\n- `would_convert` — Would the judge actually click?\n\n### Email Sequences\n**Elements to optimize:** Subject line, opening line, body copy, CTA, PS line\n\n**Score dimensions:**\n- `would_open` — Subject line pass rate\n- `would_read` — Does the opening hook?\n- `would_click` — Is the CTA compelling?\n- `would_reply` — Does it feel personal enough to respond to?\n- `spam_risk` — Does it feel spammy? (lower = better; invert for final score)\n\n### Ad Copy\n**Elements to optimize:** Headline, description, CTA\n\n**Score dimensions:**\n- `scroll_stopping` — Does it interrupt the scroll?\n- `clarity` — Is the value prop clear in 3 seconds?\n- `click_worthiness` — Does the judge want to click?\n- `relevance` — Does it match likely audience intent?\n- `differentiation` — Does it stand out from competitors?\n\n### Form Pages\n**Elements to optimize:** Headline, subtext, value prop bullets, button text, field order, thank-you copy\n\n**Score dimensions:**\n- `first_impression` — Does it feel worth filling out?\n- `trust` — Do they believe their info is safe and the offer is real?\n- `completion_likelihood` — Would the judge start filling it out?\n- `lead_quality` — Would this attract serious prospects (not tire-kickers)?\n- `would_fill_out` — Final gut check: would they submit?\n\n---\n\n## Step-by-Step Execution Protocol\n\n### Step 1: Intake & Parse\n\nRead the source content. Identify content type automatically or confirm with user:\n- HTML file → landing page or form page\n- Markdown \u002F plain text → email or ad copy\n- If ambiguous, ask: \"Is this a landing page, email sequence, ad copy, or form page?\"\n\nExtract all optimizable elements. List them back to user:\n```\nFound 5 elements to optimize:\n1. Hero headline: \"We help B2B companies grow\"\n2. Subheadline: \"Full-service digital marketing...\"\n3. CTA: \"Get Started\"\n4. Problem statement: [excerpt]\n5. Social proof: [excerpt]\n\nOptimizing: all | Variants per round: 10 | Min score: 80\n```\n\n### Step 2: Get API Key\n\nCheck for Anthropic API key: `$ANTHROPIC_API_KEY` environment variable.\n\n```bash\nexport ANTHROPIC_API_KEY=\"your-api-key-here\"\n```\n\n### Step 3: Run Optimization Rounds\n\nFor each element, run the round structure above.\n\n**Critical API efficiency rule:** ALWAYS batch all variants into a single prompt. Never call the API once per variant. A round with 10 variants = 1 API call.\n\nModel preference (in order):\n1. `claude-sonnet-4-5` (preferred — fast + smart)\n2. `claude-opus-4` (if highest quality needed)\n3. Any claude-3.5+ model if the above aren't available\n\n### Step 4: Cross-Breed (Multi-Element)\n\nAfter all elements have winners:\n1. Assemble the top winner from each element into a complete unit\n2. Generate 5 holistic variants that naturally combine the winning elements\n3. Score the complete units (not just individual parts)\n4. Pick the winner with the highest holistic score\n\n### Step 5: Write Output Files\n\n```bash\n# Create output directory\nmkdir -p data\n\n# Write optimized content\n# Write experiments JSON\n# Write optimization report\n```\n\n**Experiments JSON structure:**\n```json\n{\n  \"run_id\": \"autoresearch-{name}-{timestamp}\",\n  \"content_type\": \"landing_page\",\n  \"source_file\": \"path\u002Fto\u002Foriginal\",\n  \"min_score_threshold\": 80,\n  \"rounds\": [\n    {\n      \"round\": 1,\n      \"element\": \"hero_headline\",\n      \"variants\": [\n        {\n          \"id\": 1,\n          \"text\": \"...\",\n          \"scores\": {\n            \"cmo\": 72,\n            \"skeptical_founder\": 68,\n            \"cro\": 75,\n            \"copywriter\": 70,\n            \"founder\": 65\n          },\n          \"avg_score\": 70\n        }\n      ],\n      \"top_3\": [1, 4, 7],\n      \"winner_score\": 82\n    }\n  ],\n  \"final_winner\": {\n    \"hero_headline\": \"...\",\n    \"subheadline\": \"...\",\n    \"cta\": \"...\",\n    \"holistic_score\": 87\n  }\n}\n```\n\n### Step 6: Report Back\n\nSummarize results to user:\n- Final winning score\n- Biggest score jump (which element improved most)\n- Top 2 runner-up alternatives (in case winner doesn't feel right)\n- Path to all 3 output files\n- Clear next step\n\n---\n\n## User Options\n\n| Option | Default | Description |\n|--------|---------|-------------|\n| `elements` | all | Which elements to optimize |\n| `variants_per_round` | 10 | How many variants to generate per round |\n| `min_score` | 80 | Stop when this score is hit |\n| `rounds` | 3 | Max rounds before stopping |\n| `auto_apply` | false | Whether to overwrite the source file with winners |\n| `content_type` | auto-detect | Force a content type if auto-detect is wrong |\n\n---\n\n## Quality Gates\n\n- **\u003C 70:** Don't ship. Something fundamental is broken.\n- **70-79:** Marginal. One more round targeting the lowest-scoring dimension.\n- **80-84:** Good. Shippable. Validate with real traffic.\n- **85-89:** Strong. Ship with confidence.\n- **90+:** Rare. Ship immediately.\n\n---\n\n## Anti-Patterns to Avoid\n\n- **Never call the API once per variant.** Always batch. A 10-variant round = 1 call.\n- **Don't over-optimize for one dimension.** If you're hitting 95 on clarity but 45 on trust, the overall score is misleading.\n- **Don't run more than 5 rounds.** If you're not hitting 80 after 3 rounds, the problem is strategic (wrong positioning), not tactical (wrong words).\n- **Don't cross-breed until each element has its own winner.** Premature cross-breeding creates incoherent combinations.\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","Karpathy-style content optimization with 50+ variants, expert scoring, and evolution","Karpathy 风格内容优化，50+ 变体 + 专家评分 + 进化迭代","main","87afe6ce96220accf50a345dea46784c8c9f210e","YYC3-Skills-技能包\u002FYYC3-Skills-技能包-code-skills\u002Fskills\u002Fautoresearch",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 autoresearch",{"tool":43,"command":44},"bunx","bunx skills add YYC-Cube\u002FYYC3-Knowledge-Base --skill autoresearch",{"tool":46,"command":47},"pnpm","pnpm dlx skills add YYC-Cube\u002FYYC3-Knowledge-Base --skill autoresearch","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\u002Fautoresearch\u002FSKILL.md",true,[51,57],{"path":52,"resourceType":53,"resourceTypeDesc":54,"sizeBytes":55,"sourceHtmlUrl":56},"autoresearch.py","SCRIPT","脚本",16825,"https:\u002F\u002Fgithub.com\u002FYYC-Cube\u002FYYC3-Knowledge-Base\u002Fblob\u002Fmain\u002FYYC3-Skills-技能包\u002FYYC3-Skills-技能包-code-skills\u002Fskills\u002Fautoresearch\u002Fautoresearch.py",{"path":58,"resourceType":59,"resourceTypeDesc":60,"sizeBytes":61,"sourceHtmlUrl":62},"requirements.txt","REFERENCE","参考文档",18,"https:\u002F\u002Fgithub.com\u002FYYC-Cube\u002FYYC3-Knowledge-Base\u002Fblob\u002Fmain\u002FYYC3-Skills-技能包\u002FYYC3-Skills-技能包-code-skills\u002Fskills\u002Fautoresearch\u002Frequirements.txt",[64,71,78,85,92,99],{"skillNo":65,"name":66,"nameZh":6,"description":67,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":68,"categories":69,"keywords":70,"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":72,"name":73,"nameZh":6,"description":74,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":75,"categories":76,"keywords":77,"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":79,"name":80,"nameZh":6,"description":81,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":82,"categories":83,"keywords":84,"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":86,"name":87,"nameZh":6,"description":88,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":89,"categories":90,"keywords":91,"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":93,"name":94,"nameZh":6,"description":95,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":96,"categories":97,"keywords":98,"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":100,"name":101,"nameZh":6,"description":102,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":103,"categories":104,"keywords":105,"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",[],[]]