[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M6JM4CCDR086YBEFFVPPA2C1":3,"skill-same:01M6JM4CCDR086YBEFFVPPA2C1":78},{"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":36,"linkOnly":37,"markdownContent":38,"markdownBody":39,"frontMatter":40,"refName":41,"commitSha":42,"skillDirectory":43,"forksCount":44,"repositoryHtmlUrl":45,"repositoryHomepageUrl":46,"ownerHtmlUrl":47,"ownerBlogUrl":48,"ownerDescription":6,"updatedAt":49,"install":50,"resources":63},"01M6JM4CCDR086YBEFFVPPA2C1","voice-extractor",null,"Extract and document someone's authentic writing voice from samples. Use when someone needs a \"voice guide,\" wants to capture their writing DNA, or needs to train AI to write in their style. Also useful for ghostwriting, brand voice documentation, or onboarding writers.","LongLeo287\u002FOmniClaw","LongLeo287","https:\u002F\u002Favatars.githubusercontent.com\u002Fu\u002F141803367?v=4","01M6JK75C62VCNZKR5BRZ386YV","LongLeo","01M6JK75GQ78TSP1ZPXNKK3MCH",9,"MIT","https:\u002F\u002Fgithub.com\u002FLongLeo287\u002FOmniClaw\u002Fblob\u002Fmain\u002Fecosystem\u002Fskills\u002Fai_marketing_claude_code_skills\u002Fvoice_extractor\u002FSKILL.md",[],[19,20,21,22,23,24,25,26,27,28,29,30,31,32,33,34,35],"voice extractor","voice","guide","for","style","DNA","train","document","brand voice","use","writing","extract","write","capture","brand","onboarding","documentation","2026-11-10 10:12:30",false,"---\nname: voice-extractor\ndescription: Extract and document someone's authentic writing voice from samples. Use when someone needs a \"voice guide,\" wants to capture their writing DNA, or needs to train AI to write in their style. Also useful for ghostwriting, brand voice documentation, or onboarding writers.\n---\n\n# Voice Extractor\n\nAI-generated content all sounds the same. The fix isn't better prompts — it's teaching the AI how you actually communicate.\n\nThis skill extracts your communication DNA from writing samples and produces a Voice Guide: documented, tested, and ready to use.\n\n---\n\n## Mode\n\nDetect from context or ask: *\"Quick voice snapshot, full Voice Guide, or full guide with examples?\"*\n\n| Mode | What you get | Best for |\n|------|-------------|----------|\n| `quick` | Top 5 voice characteristics + 3 do\u002Fdon't rules | Fast style reference, single piece |\n| `standard` | Full Voice Guide: tone, vocabulary, rhythm, structure | AI training, ghostwriting, brand documentation |\n| `deep` | Full Voice Guide + 10 sample rewrites + writing rules checklist + AI training examples | Onboarding writers, building a brand voice system |\n\n**Default: `standard`** — use `quick` if they just need a fast reference. Use `deep` if they're onboarding a ghostwriter or building a content team.\n\n---\n\n## Context Loading Gates\n\n**Before extracting, collect:**\n\n- [ ] **Writing samples** — minimum 3 samples OR 500 total words (see priority list below)\n- [ ] **Purpose of voice guide** — AI training? Ghostwriter onboarding? Team alignment?\n- [ ] **Confidence zones** — Any topics where they want to sound more\u002Fless authoritative?\n- [ ] **Known anti-patterns** — Any words or phrases they already know they want to avoid?\n\n**Sample priority (most → least authentic):**\n1. Casual Slack or email (raw, unedited voice)\n2. Podcast or call transcript\n3. LinkedIn posts or articles\n4. Website copy (often edited, less authentic)\n\n**Minimum sample gate:** If samples total under 500 words, stop:\n> \"These samples are too short to extract reliable patterns. Please add 2-3 more — emails, Slack messages, or transcripts work best. The messier and more casual, the better.\"\n\nDo not attempt full extraction from under 500 words. Offer quick mode instead.\n\n---\n\n## Phase 1: Sample Quality Assessment\n\nBefore extracting, reason through:\n\n1. **Sample authenticity:** Are these samples from edited\u002Fpolished contexts (website, press) or raw contexts (Slack, email)? More polish = less authentic voice.\n2. **Sample variety:** Do the samples cover different contexts (professional, casual, educational)? Single-context samples produce single-dimension voice guides.\n3. **Exclusion check:** Identify and flag patterns that are NOT the authentic voice:\n   - Platform formatting tics (LinkedIn line breaks, Twitter brevity forcing)\n   - Typos and autocorrect errors\n   - Phrases borrowed from others (quotes, retweets)\n   - Unusually formal writing (legal docs, press releases)\n4. **Sample size adequacy:** Is there enough material for full mode, or should I use quick mode?\n\nOutput a sample assessment:\n> \"I have [X samples \u002F Y words] to work with. Quality: [high\u002Fmedium — why]. I'll use [full\u002Fquick] mode. Excluding: [any patterns and why].\"\n\n---\n\n## Phase 2: Core Energy Extraction\n\nIdentify the fundamental communication mode:\n\n**Role:**\n- Teacher (breaks things down systematically)\n- Challenger (pushes back on assumptions)\n- Cheerleader (builds confidence and momentum)\n- Straight-shooter (cuts through BS efficiently)\n\n**Default energy:**\n- Calm authority (\"Here's what works.\")\n- High enthusiasm (\"This is exciting — let me show you.\")\n- Understated confidence (\"I've seen this a hundred times.\")\n\n**Recurring themes:** What topics appear unprompted across samples? These are the things they actually care about.\n\n---\n\n## Phase 3: Phrase Extraction (Systematic)\n\nScan all samples and extract:\n\n**Transition phrases** (how they shift topics):\n- Quote exact examples from samples\n- Pattern: \"Here's the thing...\", \"What I've learned...\", \"Let me put it differently...\"\n\n**Emphasis phrases** (how they land a point):\n- Quote exact examples\n- Pattern: \"The reality is...\", \"This is the part people miss...\", \"Here's the actual problem...\"\n\n**Closers** (how they wrap up):\n- Quote exact examples\n- Pattern: \"That's the move.\", \"Start there.\", \"You've got this.\"\n\n---\n\n## Phase 4: Confidence Zone Mapping\n\n| Zone | Description | Language Markers |\n|---|---|---|\n| Full authority | Topics they're an expert in | No hedging, definitive statements, \"here's what works\" |\n| Earned perspective | Topics with experience but not mastery | \"In my experience...\", \"What I've found...\" |\n| Active exploration | Topics they're learning now | \"I'm testing this...\", \"What I'm seeing...\" |\n\nMap their stated expertise areas to each zone. This calibration is what makes the voice feel real vs. one-dimensional.\n\n---\n\n## Phase 5: Anti-Pattern Documentation\n\nExtract what they'd NEVER say:\n- Words that would feel wrong in their voice\n- Phrases that make them cringe\n- Tones they naturally avoid\n- Industry jargon they hate\n\nSource these from sample evidence where possible: \"You never used [word] across [X samples] — it doesn't fit your voice.\"\n\n---\n\n## Phase 6: Validation Test (REQUIRED)\n\nAfter extracting the full profile, generate 2 test sentences on the same topic:\n\n**Version A** (using the extracted voice profile):\n> \"[Sample sentence in their voice]\"\n\n**Version B** (wrong voice — contrasting example):\n> \"[Same content, different voice — shows what to avoid]\"\n\nAsk the user: \"Does Version A actually sound like you when you're not overthinking it? What feels off?\"\n\nThis validation catches extraction errors before the guide is put into production.\n\n---\n\n## Quick Mode (`--quick`)\n\nWhen samples are thin (300–500 words) or time is short:\n\n1. Read 3 samples fast\n2. Pull 10 signature phrases\n3. Note 3 things they'd never say\n4. Write 1 sentence describing their energy\n\n**Output:** Minimum viable voice guide.\n\n**Difference from full mode:**\n- Quick: ~10 phrases, 3 anti-patterns, 1-sentence energy descriptor\n- Full: Complete profile with confidence calibration, validated test sentences, and source-cited examples\n\n---\n\n## Phase 7: Self-Critique Pass (REQUIRED)\n\nAfter generating the Voice Guide:\n\n- [ ] Are the extracted phrases actually from the samples, or am I inferring them?\n- [ ] Does the anti-pattern list include specific words\u002Fphrases, or just vague categories?\n- [ ] Do the validation test sentences demonstrate a real difference between in-voice and out-of-voice?\n- [ ] Is the confidence zone mapping specific to named topics, or just generic?\n- [ ] Would a ghostwriter be able to use this guide without asking follow-up questions?\n\nFlag any issues: \"The anti-pattern section only has 2 entries — not enough for a usable guide. I need more samples or direct input from the user.\"\n\n---\n\n## Output Structure\n\n```markdown\n## Voice Guide: [Name] — [Date]\n\n### Sample Assessment\n- Samples: [count, types]\n- Total words: [count]\n- Quality: [high\u002Fmedium — reason]\n- Mode: [quick\u002Ffull]\n- Excluded: [patterns excluded + why]\n\n---\n\n### Core Energy\n- Role: [teacher\u002Fchallenger\u002Fcheerleader\u002Fstraight-shooter]\n- Default energy: [description]\n- Recurring themes: [list]\n\n### Signature Phrases\n**Transitions:**\n- \"[Phrase]\" (source: [email\u002Fpost])\n- \"[Phrase]\"\n\n**Emphasis:**\n- \"[Phrase]\" (source: [email\u002Fpost])\n\n**Closers:**\n- \"[Phrase]\"\n\n### Confidence Calibration\n**Full authority (no hedging):**\nTopics: [list]\nSounds like: \"[example sentence]\"\n\n**Earned perspective:**\nTopics: [list]\nSounds like: \"[example sentence]\"\n\n**Active exploration:**\nTopics: [list]\nSounds like: \"[example sentence]\"\n\n### Anti-Patterns (Never Use)\n- [Word\u002Fphrase] — why: [evidence from samples]\n- [Word\u002Fphrase] — why: [evidence]\n\n### Validation Test\n**This sounds like you:**\n\"[Version A]\"\n\n**This doesn't:**\n\"[Version B — contrast]\"\n\n### Self-Critique Notes\n[Any gaps, things to validate with user]\n\n### Usage Instructions\n- For AI: Paste this guide into your system prompt\n- For ghostwriter: Share on day 1 — cuts revision cycles in half\n- For team: This is the benchmark for \"on brand\"\n```\n\n---\n\n*Skill by Brian Wagner | AI Marketing Architect | brianrwagner.com*\n","# Voice Extractor\n\nAI-generated content all sounds the same. The fix isn't better prompts — it's teaching the AI how you actually communicate.\n\nThis skill extracts your communication DNA from writing samples and produces a Voice Guide: documented, tested, and ready to use.\n\n---\n\n## Mode\n\nDetect from context or ask: *\"Quick voice snapshot, full Voice Guide, or full guide with examples?\"*\n\n| Mode | What you get | Best for |\n|------|-------------|----------|\n| `quick` | Top 5 voice characteristics + 3 do\u002Fdon't rules | Fast style reference, single piece |\n| `standard` | Full Voice Guide: tone, vocabulary, rhythm, structure | AI training, ghostwriting, brand documentation |\n| `deep` | Full Voice Guide + 10 sample rewrites + writing rules checklist + AI training examples | Onboarding writers, building a brand voice system |\n\n**Default: `standard`** — use `quick` if they just need a fast reference. Use `deep` if they're onboarding a ghostwriter or building a content team.\n\n---\n\n## Context Loading Gates\n\n**Before extracting, collect:**\n\n- [ ] **Writing samples** — minimum 3 samples OR 500 total words (see priority list below)\n- [ ] **Purpose of voice guide** — AI training? Ghostwriter onboarding? Team alignment?\n- [ ] **Confidence zones** — Any topics where they want to sound more\u002Fless authoritative?\n- [ ] **Known anti-patterns** — Any words or phrases they already know they want to avoid?\n\n**Sample priority (most → least authentic):**\n1. Casual Slack or email (raw, unedited voice)\n2. Podcast or call transcript\n3. LinkedIn posts or articles\n4. Website copy (often edited, less authentic)\n\n**Minimum sample gate:** If samples total under 500 words, stop:\n> \"These samples are too short to extract reliable patterns. Please add 2-3 more — emails, Slack messages, or transcripts work best. The messier and more casual, the better.\"\n\nDo not attempt full extraction from under 500 words. Offer quick mode instead.\n\n---\n\n## Phase 1: Sample Quality Assessment\n\nBefore extracting, reason through:\n\n1. **Sample authenticity:** Are these samples from edited\u002Fpolished contexts (website, press) or raw contexts (Slack, email)? More polish = less authentic voice.\n2. **Sample variety:** Do the samples cover different contexts (professional, casual, educational)? Single-context samples produce single-dimension voice guides.\n3. **Exclusion check:** Identify and flag patterns that are NOT the authentic voice:\n   - Platform formatting tics (LinkedIn line breaks, Twitter brevity forcing)\n   - Typos and autocorrect errors\n   - Phrases borrowed from others (quotes, retweets)\n   - Unusually formal writing (legal docs, press releases)\n4. **Sample size adequacy:** Is there enough material for full mode, or should I use quick mode?\n\nOutput a sample assessment:\n> \"I have [X samples \u002F Y words] to work with. Quality: [high\u002Fmedium — why]. I'll use [full\u002Fquick] mode. Excluding: [any patterns and why].\"\n\n---\n\n## Phase 2: Core Energy Extraction\n\nIdentify the fundamental communication mode:\n\n**Role:**\n- Teacher (breaks things down systematically)\n- Challenger (pushes back on assumptions)\n- Cheerleader (builds confidence and momentum)\n- Straight-shooter (cuts through BS efficiently)\n\n**Default energy:**\n- Calm authority (\"Here's what works.\")\n- High enthusiasm (\"This is exciting — let me show you.\")\n- Understated confidence (\"I've seen this a hundred times.\")\n\n**Recurring themes:** What topics appear unprompted across samples? These are the things they actually care about.\n\n---\n\n## Phase 3: Phrase Extraction (Systematic)\n\nScan all samples and extract:\n\n**Transition phrases** (how they shift topics):\n- Quote exact examples from samples\n- Pattern: \"Here's the thing...\", \"What I've learned...\", \"Let me put it differently...\"\n\n**Emphasis phrases** (how they land a point):\n- Quote exact examples\n- Pattern: \"The reality is...\", \"This is the part people miss...\", \"Here's the actual problem...\"\n\n**Closers** (how they wrap up):\n- Quote exact examples\n- Pattern: \"That's the move.\", \"Start there.\", \"You've got this.\"\n\n---\n\n## Phase 4: Confidence Zone Mapping\n\n| Zone | Description | Language Markers |\n|---|---|---|\n| Full authority | Topics they're an expert in | No hedging, definitive statements, \"here's what works\" |\n| Earned perspective | Topics with experience but not mastery | \"In my experience...\", \"What I've found...\" |\n| Active exploration | Topics they're learning now | \"I'm testing this...\", \"What I'm seeing...\" |\n\nMap their stated expertise areas to each zone. This calibration is what makes the voice feel real vs. one-dimensional.\n\n---\n\n## Phase 5: Anti-Pattern Documentation\n\nExtract what they'd NEVER say:\n- Words that would feel wrong in their voice\n- Phrases that make them cringe\n- Tones they naturally avoid\n- Industry jargon they hate\n\nSource these from sample evidence where possible: \"You never used [word] across [X samples] — it doesn't fit your voice.\"\n\n---\n\n## Phase 6: Validation Test (REQUIRED)\n\nAfter extracting the full profile, generate 2 test sentences on the same topic:\n\n**Version A** (using the extracted voice profile):\n> \"[Sample sentence in their voice]\"\n\n**Version B** (wrong voice — contrasting example):\n> \"[Same content, different voice — shows what to avoid]\"\n\nAsk the user: \"Does Version A actually sound like you when you're not overthinking it? What feels off?\"\n\nThis validation catches extraction errors before the guide is put into production.\n\n---\n\n## Quick Mode (`--quick`)\n\nWhen samples are thin (300–500 words) or time is short:\n\n1. Read 3 samples fast\n2. Pull 10 signature phrases\n3. Note 3 things they'd never say\n4. Write 1 sentence describing their energy\n\n**Output:** Minimum viable voice guide.\n\n**Difference from full mode:**\n- Quick: ~10 phrases, 3 anti-patterns, 1-sentence energy descriptor\n- Full: Complete profile with confidence calibration, validated test sentences, and source-cited examples\n\n---\n\n## Phase 7: Self-Critique Pass (REQUIRED)\n\nAfter generating the Voice Guide:\n\n- [ ] Are the extracted phrases actually from the samples, or am I inferring them?\n- [ ] Does the anti-pattern list include specific words\u002Fphrases, or just vague categories?\n- [ ] Do the validation test sentences demonstrate a real difference between in-voice and out-of-voice?\n- [ ] Is the confidence zone mapping specific to named topics, or just generic?\n- [ ] Would a ghostwriter be able to use this guide without asking follow-up questions?\n\nFlag any issues: \"The anti-pattern section only has 2 entries — not enough for a usable guide. I need more samples or direct input from the user.\"\n\n---\n\n## Output Structure\n\n```markdown\n## Voice Guide: [Name] — [Date]\n\n### Sample Assessment\n- Samples: [count, types]\n- Total words: [count]\n- Quality: [high\u002Fmedium — reason]\n- Mode: [quick\u002Ffull]\n- Excluded: [patterns excluded + why]\n\n---\n\n### Core Energy\n- Role: [teacher\u002Fchallenger\u002Fcheerleader\u002Fstraight-shooter]\n- Default energy: [description]\n- Recurring themes: [list]\n\n### Signature Phrases\n**Transitions:**\n- \"[Phrase]\" (source: [email\u002Fpost])\n- \"[Phrase]\"\n\n**Emphasis:**\n- \"[Phrase]\" (source: [email\u002Fpost])\n\n**Closers:**\n- \"[Phrase]\"\n\n### Confidence Calibration\n**Full authority (no hedging):**\nTopics: [list]\nSounds like: \"[example sentence]\"\n\n**Earned perspective:**\nTopics: [list]\nSounds like: \"[example sentence]\"\n\n**Active exploration:**\nTopics: [list]\nSounds like: \"[example sentence]\"\n\n### Anti-Patterns (Never Use)\n- [Word\u002Fphrase] — why: [evidence from samples]\n- [Word\u002Fphrase] — why: [evidence]\n\n### Validation Test\n**This sounds like you:**\n\"[Version A]\"\n\n**This doesn't:**\n\"[Version B — contrast]\"\n\n### Self-Critique Notes\n[Any gaps, things to validate with user]\n\n### Usage Instructions\n- For AI: Paste this guide into your system prompt\n- For ghostwriter: Share on day 1 — cuts revision cycles in half\n- For team: This is the benchmark for \"on brand\"\n```\n\n---\n\n*Skill by Brian Wagner | AI Marketing Architect | brianrwagner.com*\n",{"name":5,"description":7},"main","c173cdffe08e788a99b91928a831b476b8434838","ecosystem\u002Fskills\u002Fai_marketing_claude_code_skills\u002Fvoice_extractor",0,"https:\u002F\u002Fgithub.com\u002FLongLeo287\u002FOmniClaw","https:\u002F\u002Fportfolio-longleo.vercel.app\u002Flabs\u002Fomniclaw.html","https:\u002F\u002Fgithub.com\u002FLongLeo287","https:\u002F\u002Fwww.facebook.com\u002FResourceRookie2023","2026-09-30 00:58:05",{"source":8,"skillName":5,"commands":51,"prompt":61,"zipAvailable":62},[52,55,58],{"tool":53,"command":54},"npx","npx skills add LongLeo287\u002FOmniClaw --skill voice-extractor",{"tool":56,"command":57},"bunx","bunx skills add LongLeo287\u002FOmniClaw --skill voice-extractor",{"tool":59,"command":60},"pnpm","pnpm dlx skills add LongLeo287\u002FOmniClaw --skill voice-extractor","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002FLongLeo287\u002FOmniClaw\u002Fblob\u002Fmain\u002Fecosystem\u002Fskills\u002Fai_marketing_claude_code_skills\u002Fvoice_extractor\u002FSKILL.md",true,[64,70,74],{"path":65,"resourceType":66,"resourceTypeDesc":67,"sizeBytes":68,"sourceHtmlUrl":69},"_DIR_IDENTITY.md","REFERENCE","参考文档",378,"https:\u002F\u002Fgithub.com\u002FLongLeo287\u002FOmniClaw\u002Fblob\u002Fmain\u002Fecosystem\u002Fskills\u002Fai_marketing_claude_code_skills\u002Fvoice_extractor\u002F_DIR_IDENTITY.md",{"path":71,"resourceType":66,"resourceTypeDesc":67,"sizeBytes":72,"sourceHtmlUrl":73},"skill_oc.md",3561,"https:\u002F\u002Fgithub.com\u002FLongLeo287\u002FOmniClaw\u002Fblob\u002Fmain\u002Fecosystem\u002Fskills\u002Fai_marketing_claude_code_skills\u002Fvoice_extractor\u002Fskill_oc.md",{"path":75,"resourceType":66,"resourceTypeDesc":67,"sizeBytes":76,"sourceHtmlUrl":77},"voice_guide_template.md",3719,"https:\u002F\u002Fgithub.com\u002FLongLeo287\u002FOmniClaw\u002Fblob\u002Fmain\u002Fecosystem\u002Fskills\u002Fai_marketing_claude_code_skills\u002Fvoice_extractor\u002Fvoice_guide_template.md",[79,122,143,170,185,212],{"skillNo":80,"name":81,"nameZh":6,"description":82,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":83,"categories":84,"keywords":101,"publishedAt":36},"01M6JR0KQP4MHT32TN40D9CBFX","UI-UX Pro Max","Advanced UI\u002FUX analysis and generation skills with data-driven patterns. Python scripts (core.py, search.py) for systematic UI pattern extraction, design system generation, and component search from curated data sources.","https:\u002F\u002Fgithub.com\u002FLongLeo287\u002FOmniClaw\u002Fblob\u002Fmain\u002Fecosystem\u002Fui_components\u002Fui_ux_pro_max\u002FSKILL.md",[85,90,93,98],{"categoryNo":86,"categoryName":87,"taxonomyType":88,"taxonomyTypeDesc":89},"01JBSEEDCAT000000000000015","视觉设计","SCENARIO","使用场景",{"categoryNo":91,"categoryName":92,"taxonomyType":88,"taxonomyTypeDesc":89},"01JBSEEDCAT000000000000023","Skill与智能体开发",{"categoryNo":94,"categoryName":95,"taxonomyType":96,"taxonomyTypeDesc":97},"01JBSEEDCAT000000000000032","设计师","PROFESSION","适用职业",{"categoryNo":99,"categoryName":100,"taxonomyType":96,"taxonomyTypeDesc":97},"01JBSEEDCAT000000000000033","数据分析师",[102,103,104,105,106,107,108,109,110,111,112,113,114,115,116,117,118,119,120,121],"ux","ui","ui ux pro max","max","pro","ui ux","design","component","search","analysis","team","rd","ui-ux","active","systematic","scripts","pattern extraction","sources","advanced","data-driven",{"skillNo":123,"name":124,"nameZh":6,"description":125,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":126,"categories":127,"keywords":129,"publishedAt":36},"01M6JR0EF5AEQHP2FSTB57H05P","shadcn-ui","Expert guidance for integrating and building applications with shadcn\u002Fui components, including component discovery, installation, customization, and best practices.","https:\u002F\u002Fgithub.com\u002FLongLeo287\u002FOmniClaw\u002Fblob\u002Fmain\u002Fecosystem\u002Fui_components\u002Fshadcn_ui\u002FSKILL.md",[128],{"categoryNo":94,"categoryName":95,"taxonomyType":96,"taxonomyTypeDesc":97},[130,103,131,132,109,133,134,135,136,112,137,138,139,115,140,141,142,22],"shadcn","shadcn ui","components","core","best practices","applications","discovery","customization","guidance","expert","installation","ui components","with",{"skillNo":144,"name":145,"nameZh":6,"description":146,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":147,"categories":148,"keywords":152,"publishedAt":36},"01M6JR08F51BEN17RHFYX65WVE","zustand_store_ts","Create Zustand stores with TypeScript, subscribeWithSelector middleware, and proper state\u002Faction separation. Use when building React state management, creating global stores, or implementing reactive state patterns with Zustand.","https:\u002F\u002Fgithub.com\u002FLongLeo287\u002FOmniClaw\u002Fblob\u002Fmain\u002Fecosystem\u002Fskills\u002Fzustand_store_ts\u002FSKILL.md",[149],{"categoryNo":150,"categoryName":151,"taxonomyType":88,"taxonomyTypeDesc":89},"01JBSEEDCAT000000000000009","前端开发",[153,154,155,156,157,158,159,160,161,162,163,164,28,165,166,167,142,168,169],"zustand store ts","zustand","store","typescript","microsoft","react","create","state management","state","react state management","management","global","patterns","separation","middleware","action","implementing",{"skillNo":171,"name":154,"nameZh":6,"description":172,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":173,"categories":174,"keywords":175,"publishedAt":36},"01M6JR00TDMVAFFCZXZ04AN7Q7","Zustand state management guide. Use when working with store code (src\u002Fstore\u002F**), implementing actions, managing state, or creating slices. Triggers on Zustand store development, state management questions, or action implementation.","https:\u002F\u002Fgithub.com\u002FLongLeo287\u002FOmniClaw\u002Fblob\u002Fmain\u002Fecosystem\u002Fskills\u002Fzustand\u002FSKILL.md",[],[154,176,160,177,161,178,179,163,21,28,180,181,182,155,142,183,184,168,169],"development","code","actions","src","implementation","zustand state","triggers","questions","zustand state management",{"skillNo":186,"name":187,"nameZh":6,"description":188,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":189,"categories":190,"keywords":195,"publishedAt":36},"01M6JQZSWV4KWJP112G6XHEP44","youtube_summarizer","Automatically fetch YouTube video transcripts, generate structured summaries, and send full transcripts to messaging platforms. Detects YouTube URLs and provides metadata, key insights, and downloadable transcripts.","https:\u002F\u002Fgithub.com\u002FLongLeo287\u002FOmniClaw\u002Fblob\u002Fmain\u002Fecosystem\u002Fskills\u002Fyoutube_summarizer\u002FSKILL.md",[191,194],{"categoryNo":192,"categoryName":193,"taxonomyType":88,"taxonomyTypeDesc":89},"01JBSEEDCAT000000000000016","图像与多媒体",{"categoryNo":91,"categoryName":92,"taxonomyType":88,"taxonomyTypeDesc":89},[196,197,198,199,200,201,202,203,204,205,206,207,208,209,210,211],"youtube","youtube summarizer","summarizer","generate","metadata","messaging","Video","fetch","telegram","transcription","summarization","structured","full","insights","transcripts","summaries",{"skillNo":213,"name":214,"nameZh":6,"description":215,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":216,"categories":217,"keywords":218,"publishedAt":36},"01M6JQZN3QJB6B77JGKJD62DQT","youtube_clipper","YouTube 视频智能剪辑工具。下载视频和字幕，AI 分析生成精细章节（几分钟级别）， 用户选择片段后自动剪辑、翻译字幕为中英双语、烧录字幕到视频，并生成总结文案。 使用场景：当用户需要剪辑 YouTube 视频、生成短视频片段、制作双语字幕版本时。 关键词：视频剪辑、YouTube、字幕翻译、双语字幕、视频下载、clip video","https:\u002F\u002Fgithub.com\u002FLongLeo287\u002FOmniClaw\u002Fblob\u002Fmain\u002Fecosystem\u002Fskills\u002Fyoutube_clipper\u002FSKILL.md",[],[196,219,220,202,221,222,223,224,225,226,227,31,228,229,230,231,232],"clipper","youtube clipper","Bash","下载","视频","生成","关键词","翻译","read","clip","总结","工具","文案","sonnet"]