[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M6DC4R8YHJ1ZXYN41R1C2AYV":3,"skill-same:01M6DC4R8YHJ1ZXYN41R1C2AYV":66},{"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":30,"linkOnly":31,"markdownContent":32,"markdownBody":33,"frontMatter":34,"refName":41,"commitSha":42,"skillDirectory":43,"forksCount":14,"repositoryHtmlUrl":44,"repositoryHomepageUrl":6,"ownerHtmlUrl":45,"ownerBlogUrl":6,"ownerDescription":6,"updatedAt":46,"install":47,"resources":60},"01M6DC4R8YHJ1ZXYN41R1C2AYV","voice-create",null,"Generate custom voice profiles from natural language descriptions. Use when the user wants a new voice from a description. NOT from samples (use voice-analyze).","Prekzursil\u002Fagent-skills-toolchain","Prekzursil","https:\u002F\u002Favatars.githubusercontent.com\u002Fu\u002F54636077?v=4","01M6DACZ1PCQHD99SCR1YXG28B","Andrei Mihai Visalon","01M6DACZ670WZF535V3WYYSS4Z",0,"MIT","https:\u002F\u002Fgithub.com\u002FPrekzursil\u002Fagent-skills-toolchain\u002Fblob\u002Fmain\u002F.agents\u002Fskills\u002Fvoice-create\u002FSKILL.md",[],[19,20,21,22,23,24,25,26,27,28,29],"create","voice","voice create","github","generate","https","analyze","user","use","language","natural language","2026-11-10 10:12:30",false,"---\nname: voice-create\ndescription: Generate custom voice profiles from natural language descriptions. Use when the user wants a new voice from a description. NOT from samples (use voice-analyze).\nlicense: MIT\nmetadata:\n  version: 1.0.0\n  platforms:\n  - all\n  source: https:\u002F\u002Fgithub.com\u002Fangelarose210\u002Fghostwriter\n  upstream_author: angelarose210\n---\n\n# voice-create\n\nGenerate custom voice profiles from natural language descriptions. Every generated profile includes AI tells avoidance rules by default.\n\n## Triggers\n\nAlternate expressions and non-obvious activations (primary phrases are matched automatically from the skill description):\n\n- \"make me sound like [reference]\" -> reference-based voice creation\n- \"voice fingerprint\" -> voice profile extraction from text\n\n## Behavior\n\nWhen triggered, this skill:\n\n1. **Parses the description** to identify:\n   - Target audience (developers, executives, general public)\n   - Tone characteristics (formal\u002Fcasual, confident\u002Ftentative, warm\u002Fclinical)\n   - Domain context (technical, marketing, academic, conversational)\n   - Any specific constraints or preferences mentioned\n\n2. **Maps description to voice dimensions**:\n   - Formality (0-1): casual \u003C-> formal\n   - Confidence (0-1): hedging \u003C-> assertive\n   - Warmth (0-1): clinical \u003C-> friendly\n   - Energy (0-1): calm \u003C-> enthusiastic\n   - Complexity (0-1): simple \u003C-> sophisticated\n\n3. **Generates vocabulary guidance**:\n   - Preferred terms based on domain\n   - Terms to avoid based on tone\n   - Signature phrases that match the voice\n   - **Always includes AI tells avoidance**: every generated profile's `vocabulary.avoid` list includes the full set of banned AI vocabulary from `..\u002Fvoice-apply\u002Freferences\u002Fai-tells.md`\n\n4. **Creates structure patterns**:\n   - Sentence length preferences\n   - Paragraph structure\n   - Use of lists, examples, analogies\n   - **Always enforces human-like rhythm**: high sentence length variance, varied paragraph lengths, em dash avoidance, no Rule of Three abuse\n\n5. **Adds anti-AI-tells rules**:\n   - `punctuation.em_dashes`: avoid (default for all generated profiles)\n   - `punctuation.semicolons`: avoid (unless user specifies formal\u002Facademic)\n   - `structure.sentence_length_variance`: high (enforces burstiness)\n   - `structure.paragraph_length_variance`: high (prevents uniform blocks)\n   - `structure.rule_of_three`: break-pattern (vary item counts)\n   - `banned_patterns`: negation flips, self-posed questions, anaphora, trailing participles, hedge-stacking\n\n6. **Outputs valid YAML** conforming to voice-profile schema\n\n## Usage Examples\n\n### Technical Documentation Voice\n```\nUser: \"Create a voice for API documentation - precise, no-nonsense, assumes developer knowledge\"\n\nOutput: technical-api-docs.yaml\n- formality: 0.6\n- confidence: 0.9\n- warmth: 0.2\n- energy: 0.3\n- complexity: 0.8\n- vocabulary.prefer: technical terms, code references, precise metrics\n- vocabulary.avoid: [all AI tells] + marketing language\n- structure: varied sentence length, no em dashes\n```\n\n### Friendly Tutorial Voice\n```\nUser: \"Make me a voice for beginner tutorials - encouraging, patient, uses lots of analogies\"\n\nOutput: beginner-tutorial.yaml\n- formality: 0.2\n- confidence: 0.7\n- warmth: 0.9\n- energy: 0.7\n- complexity: 0.3\n- vocabulary.prefer: everyday language, encouraging phrases, analogies\n- vocabulary.avoid: [all AI tells] + jargon\n- structure: short sentences mixed with longer explanations, no \"let's dive in\" openers\n```\n\n### Executive Summary Voice\n```\nUser: \"Generate a voice profile for board presentations - authoritative but accessible\"\n\nOutput: board-presentation.yaml\n- formality: 0.8\n- confidence: 0.9\n- warmth: 0.4\n- energy: 0.5\n- complexity: 0.6\n- vocabulary.prefer: business metrics, strategic language, clear conclusions\n- vocabulary.avoid: [all AI tells] + buzzwords like \"synergy\", \"paradigm\", \"stakeholders\"\n- structure: varied paragraph lengths, direct openers, no \"in conclusion\" closers\n```\n\n## Output Location\n\nGenerated profiles are saved to:\n1. `.aiwg\u002Fvoices\u002F{name}.yaml` (project-specific, default)\n2. `~\u002F.config\u002Faiwg\u002Fvoices\u002F{name}.yaml` (user-wide, with --global flag)\n\n## Voice Generation Process\n\n### Step 1: Dimension Calibration\n\nParse natural language for dimension indicators:\n\n| Description Keywords | Dimension | Value Range |\n|---------------------|-----------|-------------|\n| casual, relaxed, conversational | formality | 0.1-0.3 |\n| professional, business | formality | 0.5-0.7 |\n| formal, academic, official | formality | 0.8-1.0 |\n| tentative, careful, hedging | confidence | 0.2-0.4 |\n| balanced, measured | confidence | 0.5-0.7 |\n| assertive, authoritative, direct | confidence | 0.8-1.0 |\n| clinical, detached, objective | warmth | 0.1-0.3 |\n| neutral, professional | warmth | 0.4-0.6 |\n| friendly, warm, personable | warmth | 0.7-0.9 |\n| calm, measured, understated | energy | 0.1-0.3 |\n| balanced, engaged | energy | 0.4-0.6 |\n| enthusiastic, dynamic, energetic | energy | 0.7-0.9 |\n| simple, accessible, plain | complexity | 0.1-0.3 |\n| clear, moderate | complexity | 0.4-0.6 |\n| sophisticated, detailed, nuanced | complexity | 0.7-0.9 |\n\n### Step 2: Domain Detection\n\nIdentify domain from context:\n- **Technical**: API, code, system, architecture, implementation\n- **Marketing**: brand, campaign, audience, engagement, conversion\n- **Academic**: research, methodology, analysis, findings, literature\n- **Executive**: strategy, ROI, decision, outcome\n- **Support**: help, issue, solution, troubleshoot, resolve\n\n### Step 3: Vocabulary Generation\n\nBased on domain and tone, generate:\n- 5-10 preferred terms\n- 3-5 domain-specific terms to avoid\n- 2-4 signature phrases\n- **Mandatory**: merge the full AI tells banned vocabulary list into `vocabulary.avoid`. This list includes 50+ banned verbs, 40+ banned adjectives, 40+ banned nouns, 30+ banned adverbs, and all banned connectors. See `..\u002Fvoice-apply\u002Freferences\u002Fai-tells.md` for the complete lists.\n\n### Step 4: Structure Selection\n\nMap tone to structure patterns:\n- High formality -> longer sentences, structured paragraphs\n- Low formality -> shorter sentences, varied structure\n- High confidence -> direct statements, conclusions first\n- High warmth -> questions, inclusive language (\"we\", \"let's\")\n\n**Always enforce**:\n- `sentence_length_variance: high` (mix 5-word punches with 30-word flows)\n- `paragraph_length_variance: high` (mix 1-sentence paragraphs with 5-sentence paragraphs)\n- `em_dash_usage: avoid` (use commas, periods, parentheses, colons instead)\n- `rule_of_three: break-pattern` (use 2 items or 4 items to break the AI fingerprint)\n\n### Step 5: Anti-Pattern Rules\n\nEvery generated profile includes these structure rules:\n\n```yaml\nanti_ai_tells:\n  # Sentence patterns to never use\n  banned_patterns:\n    - negation_flip          # \"It's not X, it's Y\"\n    - self_posed_questions   # \"The best part? It's this.\"\n    - anaphora_abuse         # Same opener 3+ times\n    - trailing_participles   # \"highlighting its importance\"\n    - false_ranges           # \"From innovation to implementation\"\n    - hedge_stacking         # Multiple qualifiers per sentence\n    - consecutive_adverbials # Starting sentences with \"Furthermore,\" \"Moreover,\" etc.\n  # Punctuation rules\n  punctuation:\n    em_dashes: avoid\n    semicolons: avoid\n    oxford_commas: avoid\n    unicode_ellipsis: never\n  # Formatting rules\n  formatting:\n    bold_first_bullets: never\n    excessive_headers: avoid\n    erratic_bolding: never\n    emoji_in_professional: never\n  # Rhythm rules\n  rhythm:\n    sentence_length_variance: high    # std dev > 6 words\n    paragraph_length_variance: high   # mix short and long\n    uniform_subsections: never        # vary section lengths\n  # Tone rules\n  tone_guards:\n    relentless_positivity: avoid      # be critical when warranted\n    false_balance: avoid              # make bold claims\n    emotional_flatness: avoid         # show genuine reactions\n    elevated_register_for_simple: avoid  # match register to content\n```\n\n## Integration\n\nWorks with other voice-framework skills:\n- Created voices can be applied via `voice-apply`\n- Created voices can be inputs to `voice-blend`\n- `voice-analyze` can create base profiles that `voice-create` refines\n- All created voices automatically include AI tells avoidance\n\n## References\n\n- AI Writing Tells: `..\u002Fvoice-apply\u002Freferences\u002Fai-tells.md`\n","# voice-create\n\nGenerate custom voice profiles from natural language descriptions. Every generated profile includes AI tells avoidance rules by default.\n\n## Triggers\n\nAlternate expressions and non-obvious activations (primary phrases are matched automatically from the skill description):\n\n- \"make me sound like [reference]\" -> reference-based voice creation\n- \"voice fingerprint\" -> voice profile extraction from text\n\n## Behavior\n\nWhen triggered, this skill:\n\n1. **Parses the description** to identify:\n   - Target audience (developers, executives, general public)\n   - Tone characteristics (formal\u002Fcasual, confident\u002Ftentative, warm\u002Fclinical)\n   - Domain context (technical, marketing, academic, conversational)\n   - Any specific constraints or preferences mentioned\n\n2. **Maps description to voice dimensions**:\n   - Formality (0-1): casual \u003C-> formal\n   - Confidence (0-1): hedging \u003C-> assertive\n   - Warmth (0-1): clinical \u003C-> friendly\n   - Energy (0-1): calm \u003C-> enthusiastic\n   - Complexity (0-1): simple \u003C-> sophisticated\n\n3. **Generates vocabulary guidance**:\n   - Preferred terms based on domain\n   - Terms to avoid based on tone\n   - Signature phrases that match the voice\n   - **Always includes AI tells avoidance**: every generated profile's `vocabulary.avoid` list includes the full set of banned AI vocabulary from `..\u002Fvoice-apply\u002Freferences\u002Fai-tells.md`\n\n4. **Creates structure patterns**:\n   - Sentence length preferences\n   - Paragraph structure\n   - Use of lists, examples, analogies\n   - **Always enforces human-like rhythm**: high sentence length variance, varied paragraph lengths, em dash avoidance, no Rule of Three abuse\n\n5. **Adds anti-AI-tells rules**:\n   - `punctuation.em_dashes`: avoid (default for all generated profiles)\n   - `punctuation.semicolons`: avoid (unless user specifies formal\u002Facademic)\n   - `structure.sentence_length_variance`: high (enforces burstiness)\n   - `structure.paragraph_length_variance`: high (prevents uniform blocks)\n   - `structure.rule_of_three`: break-pattern (vary item counts)\n   - `banned_patterns`: negation flips, self-posed questions, anaphora, trailing participles, hedge-stacking\n\n6. **Outputs valid YAML** conforming to voice-profile schema\n\n## Usage Examples\n\n### Technical Documentation Voice\n```\nUser: \"Create a voice for API documentation - precise, no-nonsense, assumes developer knowledge\"\n\nOutput: technical-api-docs.yaml\n- formality: 0.6\n- confidence: 0.9\n- warmth: 0.2\n- energy: 0.3\n- complexity: 0.8\n- vocabulary.prefer: technical terms, code references, precise metrics\n- vocabulary.avoid: [all AI tells] + marketing language\n- structure: varied sentence length, no em dashes\n```\n\n### Friendly Tutorial Voice\n```\nUser: \"Make me a voice for beginner tutorials - encouraging, patient, uses lots of analogies\"\n\nOutput: beginner-tutorial.yaml\n- formality: 0.2\n- confidence: 0.7\n- warmth: 0.9\n- energy: 0.7\n- complexity: 0.3\n- vocabulary.prefer: everyday language, encouraging phrases, analogies\n- vocabulary.avoid: [all AI tells] + jargon\n- structure: short sentences mixed with longer explanations, no \"let's dive in\" openers\n```\n\n### Executive Summary Voice\n```\nUser: \"Generate a voice profile for board presentations - authoritative but accessible\"\n\nOutput: board-presentation.yaml\n- formality: 0.8\n- confidence: 0.9\n- warmth: 0.4\n- energy: 0.5\n- complexity: 0.6\n- vocabulary.prefer: business metrics, strategic language, clear conclusions\n- vocabulary.avoid: [all AI tells] + buzzwords like \"synergy\", \"paradigm\", \"stakeholders\"\n- structure: varied paragraph lengths, direct openers, no \"in conclusion\" closers\n```\n\n## Output Location\n\nGenerated profiles are saved to:\n1. `.aiwg\u002Fvoices\u002F{name}.yaml` (project-specific, default)\n2. `~\u002F.config\u002Faiwg\u002Fvoices\u002F{name}.yaml` (user-wide, with --global flag)\n\n## Voice Generation Process\n\n### Step 1: Dimension Calibration\n\nParse natural language for dimension indicators:\n\n| Description Keywords | Dimension | Value Range |\n|---------------------|-----------|-------------|\n| casual, relaxed, conversational | formality | 0.1-0.3 |\n| professional, business | formality | 0.5-0.7 |\n| formal, academic, official | formality | 0.8-1.0 |\n| tentative, careful, hedging | confidence | 0.2-0.4 |\n| balanced, measured | confidence | 0.5-0.7 |\n| assertive, authoritative, direct | confidence | 0.8-1.0 |\n| clinical, detached, objective | warmth | 0.1-0.3 |\n| neutral, professional | warmth | 0.4-0.6 |\n| friendly, warm, personable | warmth | 0.7-0.9 |\n| calm, measured, understated | energy | 0.1-0.3 |\n| balanced, engaged | energy | 0.4-0.6 |\n| enthusiastic, dynamic, energetic | energy | 0.7-0.9 |\n| simple, accessible, plain | complexity | 0.1-0.3 |\n| clear, moderate | complexity | 0.4-0.6 |\n| sophisticated, detailed, nuanced | complexity | 0.7-0.9 |\n\n### Step 2: Domain Detection\n\nIdentify domain from context:\n- **Technical**: API, code, system, architecture, implementation\n- **Marketing**: brand, campaign, audience, engagement, conversion\n- **Academic**: research, methodology, analysis, findings, literature\n- **Executive**: strategy, ROI, decision, outcome\n- **Support**: help, issue, solution, troubleshoot, resolve\n\n### Step 3: Vocabulary Generation\n\nBased on domain and tone, generate:\n- 5-10 preferred terms\n- 3-5 domain-specific terms to avoid\n- 2-4 signature phrases\n- **Mandatory**: merge the full AI tells banned vocabulary list into `vocabulary.avoid`. This list includes 50+ banned verbs, 40+ banned adjectives, 40+ banned nouns, 30+ banned adverbs, and all banned connectors. See `..\u002Fvoice-apply\u002Freferences\u002Fai-tells.md` for the complete lists.\n\n### Step 4: Structure Selection\n\nMap tone to structure patterns:\n- High formality -> longer sentences, structured paragraphs\n- Low formality -> shorter sentences, varied structure\n- High confidence -> direct statements, conclusions first\n- High warmth -> questions, inclusive language (\"we\", \"let's\")\n\n**Always enforce**:\n- `sentence_length_variance: high` (mix 5-word punches with 30-word flows)\n- `paragraph_length_variance: high` (mix 1-sentence paragraphs with 5-sentence paragraphs)\n- `em_dash_usage: avoid` (use commas, periods, parentheses, colons instead)\n- `rule_of_three: break-pattern` (use 2 items or 4 items to break the AI fingerprint)\n\n### Step 5: Anti-Pattern Rules\n\nEvery generated profile includes these structure rules:\n\n```yaml\nanti_ai_tells:\n  # Sentence patterns to never use\n  banned_patterns:\n    - negation_flip          # \"It's not X, it's Y\"\n    - self_posed_questions   # \"The best part? It's this.\"\n    - anaphora_abuse         # Same opener 3+ times\n    - trailing_participles   # \"highlighting its importance\"\n    - false_ranges           # \"From innovation to implementation\"\n    - hedge_stacking         # Multiple qualifiers per sentence\n    - consecutive_adverbials # Starting sentences with \"Furthermore,\" \"Moreover,\" etc.\n  # Punctuation rules\n  punctuation:\n    em_dashes: avoid\n    semicolons: avoid\n    oxford_commas: avoid\n    unicode_ellipsis: never\n  # Formatting rules\n  formatting:\n    bold_first_bullets: never\n    excessive_headers: avoid\n    erratic_bolding: never\n    emoji_in_professional: never\n  # Rhythm rules\n  rhythm:\n    sentence_length_variance: high    # std dev > 6 words\n    paragraph_length_variance: high   # mix short and long\n    uniform_subsections: never        # vary section lengths\n  # Tone rules\n  tone_guards:\n    relentless_positivity: avoid      # be critical when warranted\n    false_balance: avoid              # make bold claims\n    emotional_flatness: avoid         # show genuine reactions\n    elevated_register_for_simple: avoid  # match register to content\n```\n\n## Integration\n\nWorks with other voice-framework skills:\n- Created voices can be applied via `voice-apply`\n- Created voices can be inputs to `voice-blend`\n- `voice-analyze` can create base profiles that `voice-create` refines\n- All created voices automatically include AI tells avoidance\n\n## References\n\n- AI Writing Tells: `..\u002Fvoice-apply\u002Freferences\u002Fai-tells.md`\n",{"name":5,"license":15,"metadata":35,"description":7},{"source":36,"version":37,"platforms":38,"upstream_author":40},"https:\u002F\u002Fgithub.com\u002Fangelarose210\u002Fghostwriter","1.0.0",[39],"all","angelarose210","main","a298c929b6cbd662e1fce54302ce520d5ceea1a5",".agents\u002Fskills\u002Fvoice-create","https:\u002F\u002Fgithub.com\u002FPrekzursil\u002Fagent-skills-toolchain","https:\u002F\u002Fgithub.com\u002FPrekzursil","2026-11-02 14:30:57",{"source":8,"skillName":5,"commands":48,"prompt":58,"zipAvailable":59},[49,52,55],{"tool":50,"command":51},"npx","npx skills add Prekzursil\u002Fagent-skills-toolchain --skill voice-create",{"tool":53,"command":54},"bunx","bunx skills add Prekzursil\u002Fagent-skills-toolchain --skill voice-create",{"tool":56,"command":57},"pnpm","pnpm dlx skills add Prekzursil\u002Fagent-skills-toolchain --skill voice-create","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002FPrekzursil\u002Fagent-skills-toolchain\u002Fblob\u002Fmain\u002F.agents\u002Fskills\u002Fvoice-create\u002FSKILL.md",true,[61],{"path":62,"resourceType":62,"resourceTypeDesc":63,"sizeBytes":64,"sourceHtmlUrl":65},"LICENSE","许可证",1056,"https:\u002F\u002Fgithub.com\u002FPrekzursil\u002Fagent-skills-toolchain\u002Fblob\u002Fmain\u002F.agents\u002Fskills\u002Fvoice-create\u002FLICENSE",[67,88,118,145,159,174],{"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":30},"01M6DF7D7478R55P46REYH4QAC","clarify-requirements","Resolve genuine pre-execution ambiguity by scanning repo context, generating 1-6 grounded options, and asking 1-3 focused questions via AskUserQuestion. NOT for mid-task use (injection risk); NOT when the goal is already unambiguous; use to disambiguate vague prompts before any file edits.","https:\u002F\u002Fgithub.com\u002FPrekzursil\u002Fagent-skills-toolchain\u002Fblob\u002Fmain\u002Ftools\u002Fworkspace-hooks\u002Fskills\u002Fclarify-requirements\u002FSKILL.md",[],[74,75,76,77,78,79,80,81,82,27,83,84,85,86,87],"clarify requirements","clarify","requirements","risk","options","task","prompts","goal","scanning","context","repo","injection","execution","file",{"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":99,"publishedAt":30},"01M6DF79CA4BHJS66J8EZDBPWJ","openmm-md","Run FREE, open-source, Windows-native GPU molecular dynamics via the openmm-md MCP (OpenMM + CUDA on the local NVIDIA GPU). Use for protein \u002F protein-ligand MD when you want a free stack or are on Windows without a Schrodinger license. Covers the full workflow (prepare, solvate, minimize, equilibrate, production, analyze, mmgbsa) AND an honest decision guide vs Schrodinger Desmond, including how to run Desmond legitimately on Linux or a cloud GPU with a real license. This is a deliberately LESSER free alternative and does NOT replace the schrodinger MCP tools. Do NOT use it to pick a free tool when a validated FEP+, WaterMap, IFD-MD, or Prime MM-GBSA result is actually required.","https:\u002F\u002Fgithub.com\u002FPrekzursil\u002Fagent-skills-toolchain\u002Fblob\u002Fmain\u002Ftools\u002Fmcp\u002Fopenmm-md-mcp\u002Fskill\u002Fopenmm-md\u002FSKILL.md",[94],{"categoryNo":95,"categoryName":96,"taxonomyType":97,"taxonomyTypeDesc":98},"01JBSEEDCAT000000000000023","Skill与智能体开发","SCENARIO","使用场景",[100,101,102,103,104,25,105,106,107,108,109,110,111,112,27,113,114,115,116,117],"openmm md","how","decision","pick","linux","tool","stack","open","NVIDIA","gpu","license","workflow","windows","free","molecular dynamics","local","do","MCP",{"skillNo":119,"name":120,"nameZh":6,"description":121,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":122,"categories":123,"keywords":130,"publishedAt":30},"01M6DF76C1MG85VEWP8VZCBNMN","visual-review","Take screenshots of web pages and UI using Playwright for visual review and iteration","https:\u002F\u002Fgithub.com\u002FPrekzursil\u002Fagent-skills-toolchain\u002Fblob\u002Fmain\u002Ftools\u002Feditor\u002Fmetaswarm\u002Fskills\u002Fvisual-review\u002FSKILL.md",[124,127],{"categoryNo":125,"categoryName":126,"taxonomyType":97,"taxonomyTypeDesc":98},"01JBSEEDCAT000000000000003","演示文稿",{"categoryNo":128,"categoryName":129,"taxonomyType":97,"taxonomyTypeDesc":98},"01JBSEEDCAT000000000000008","测试与质量",[131,132,133,134,135,136,137,138,139,140,101,141,142,143,144],"review","visual","visual review","pages","web","false","iteration","take","check","slides","ui","screenshot","playwright","screenshots",{"skillNo":146,"name":147,"nameZh":6,"description":148,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":149,"categories":150,"keywords":151,"publishedAt":30},"01M6DF73AQVCBZKEN0YXEX9FXP","status","Diagnostic status report — shows metaswarm installation state, project setup, and potential issues","https:\u002F\u002Fgithub.com\u002FPrekzursil\u002Fagent-skills-toolchain\u002Fblob\u002Fmain\u002Ftools\u002Feditor\u002Fmetaswarm\u002Fskills\u002Fstatus\u002FSKILL.md",[],[147,152,153,154,155,156,157,158],"setup","report","project","installation","project setup","issues","state",{"skillNo":160,"name":161,"nameZh":6,"description":162,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":163,"categories":164,"keywords":166,"publishedAt":30},"01M6DF6X6C2XB0P6GX76P7TTYV","start","Use when starting work on any task, when the user mentions metaswarm, or when the user wants to begin tracked development work","https:\u002F\u002Fgithub.com\u002FPrekzursil\u002Fagent-skills-toolchain\u002Fblob\u002Fmain\u002Ftools\u002Feditor\u002Fmetaswarm\u002Fskills\u002Fstart\u002FSKILL.md",[165],{"categoryNo":95,"categoryName":96,"taxonomyType":97,"taxonomyTypeDesc":98},[161,167,79,168,169,170,27,26,171,172,173],"start issue","issue","ready","work on issue","work","work on","development",{"skillNo":175,"name":152,"nameZh":6,"description":176,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":177,"categories":178,"keywords":179,"publishedAt":30},"01M6DF6QMJ9AJKFKHHKRT005PQ","Interactive project setup — detects your project, configures metaswarm, writes project-local files","https:\u002F\u002Fgithub.com\u002FPrekzursil\u002Fagent-skills-toolchain\u002Fblob\u002Fmain\u002Ftools\u002Feditor\u002Fmetaswarm\u002Fskills\u002Fsetup\u002FSKILL.md",[],[152,154,115,180,156,181],"files","interactive"]