[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M6DF3C64PP26PFG9A5P2SNGV":3,"skill-same:01M6DF3C64PP26PFG9A5P2SNGV":71},{"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":29,"linkOnly":30,"markdownContent":31,"markdownBody":32,"frontMatter":33,"refName":40,"commitSha":41,"skillDirectory":42,"forksCount":14,"repositoryHtmlUrl":43,"repositoryHomepageUrl":6,"ownerHtmlUrl":44,"ownerBlogUrl":6,"ownerDescription":6,"updatedAt":45,"install":46,"resources":59},"01M6DF3C64PP26PFG9A5P2SNGV","voice-apply",null,"Applies a voice profile to transform content. Use when asked to write in a specific voice, match a tone, or restyle content. NOT for creating a profile (use voice-create).","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\u002Fskills\u002Fvoice-apply\u002FSKILL.md",[],[19,20,21,22,23,24,25,26,27,28],"voice","voice apply","github","create","content","https","write","profile","use","tone","2026-11-10 10:12:30",false,"---\nname: voice-apply\ndescription: Applies a voice profile to transform content. Use when asked to write in a specific voice, match a tone, or restyle content. NOT for creating a profile (use voice-create).\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 Apply Skill\n\n## Purpose\n\nTransform content to match a specified voice profile. This skill loads voice profiles and applies their characteristics (tone, vocabulary, structure, perspective) to new or existing content.\n\n**Critical rule**: Every piece of output MUST pass the AI writing tells check defined in `references\u002Fai-tells.md`. This is non-negotiable. If the output contains any banned vocabulary, structures, transitions, or punctuation patterns from that reference, rewrite until clean.\n\n## When This Skill Applies\n\n- User asks to \"write in X voice\" or \"use Y tone\"\n- User wants to \"make this sound more [casual\u002Fformal\u002Ftechnical\u002Fetc.]\"\n- User provides content and asks to transform its style\n- User references a voice profile by name\n- User wants content to match a specific audience or context\n\n## Trigger Phrases\n\n| Natural Language | Action |\n|------------------|--------|\n| \"Write this in technical voice\" | Apply technical-authority profile |\n| \"Make it more casual\" | Apply casual-conversational or calibrate toward casual |\n| \"This needs to sound executive\" | Apply executive-brief profile |\n| \"Explain like I'm a beginner\" | Apply friendly-explainer profile |\n| \"Use the [profile-name] voice\" | Load and apply named profile |\n| \"Transform this to match [example]\" | Analyze example, apply derived voice |\n\n## Voice Profile Locations\n\nSkill checks these locations (in order):\n1. Project: `.aiwg\u002Fvoices\u002F`\n2. User: `~\u002F.config\u002Faiwg\u002Fvoices\u002F`\n3. Built-in: `voice-framework\u002Fvoices\u002Ftemplates\u002F`\n\n## Built-in Voice Profiles\n\n| Profile | Description | Best For |\n|---------|-------------|----------|\n| `technical-authority` | Direct, precise, confident | Docs, architecture, engineering |\n| `friendly-explainer` | Approachable, encouraging | Tutorials, onboarding, education |\n| `executive-brief` | Concise, outcome-focused | Business cases, stakeholder comms |\n| `casual-conversational` | Relaxed, personal | Blog posts, social, newsletters |\n\n## Application Process\n\n### 1. Load Voice Profile\n\n```python\n# Load from YAML\nprofile = load_voice_profile(\"technical-authority\")\n```\n\n### 2. Analyze Source Content (if transforming)\n\n- Current tone characteristics\n- Vocabulary patterns\n- Structure patterns\n- Gap analysis vs target voice\n\n### 3. Apply Voice Characteristics\n\n**Tone Calibration**:\n- Adjust formality level (word choice, contractions)\n- Calibrate confidence (hedging vs assertion)\n- Set warmth (clinical vs personable)\n- Tune energy (measured vs enthusiastic)\n\n**Vocabulary Transformation**:\n- Replace words per `prefer`\u002F`avoid` guidance\n- Introduce domain terminology naturally\n- Weave in signature phrases where appropriate\n\n**Structure Adjustment**:\n- Modify sentence length distribution\n- Adjust paragraph breaks\n- Add\u002Fremove lists, examples, analogies as specified\n\n**Perspective Shift**:\n- Adjust narrative person (I, we, you, they)\n- Calibrate opinion expression\n- Set reader relationship tone\n\n### 4. AI Tells Elimination Pass (MANDATORY)\n\nAfter applying the voice profile, run every piece of output through the full AI tells check. This is the most important step. Reference: `references\u002Fai-tells.md`\n\n**Vocabulary check**: Scan output for every word in the banned lists:\n- Banned verbs: delve, leverage, utilize, harness, unlock, unleash, empower, facilitate, foster, bolster, optimize, streamline, navigate, spearhead, underscore, illuminate, elucidate, embark, unravel, elevate, reimagine, revolutionize, transcend, resonate, showcase, craft, embrace, thrive, unveil, champion, and all others on the list\n- Banned adjectives: multifaceted, seamless, robust, comprehensive, cutting-edge, holistic, meticulous, groundbreaking, transformative, innovative, compelling, invaluable, paramount, unprecedented, impactful, game-changing, and all others on the list\n- Banned nouns: tapestry, realm, testament, beacon, myriad, landscape, ecosystem, paradigm, nexus, catalyst, synergy, roadmap, cornerstone, bedrock, pinnacle, plethora, stakeholders, and all others on the list\n- Banned adverbs: furthermore, moreover, additionally, notably, crucially, importantly, consequently, seamlessly, fundamentally, undoubtedly, and all others on the list\n\n**Transition check**: Remove all banned transitions:\n- Throat-clearing: \"in today's digital age\", \"in a world where\", \"when it comes to\"\n- Pedagogical: \"let's dive in\", \"let's unpack this\", \"great question!\"\n- Signposting: \"it's important to note\", \"it's worth noting\", \"this underscores\"\n- Fake-suspense: \"here's the thing\", \"the best part?\", \"here's the kicker\"\n- Hype: \"game-changer\", \"pushing the boundaries\", \"paving the way\"\n- Conclusions: \"in conclusion\", \"to wrap up\", \"at the end of the day\"\n- Bot closers: \"I hope this helps!\", \"feel free to reach out\"\n\n**Structure check**: Eliminate banned patterns:\n- The \"It's not X, it's Y\" negation pattern (the single most prominent AI tell)\n- Self-posed questions answered immediately (\"The best part? It's this.\")\n- Anaphora abuse (same opener 3+ times in a row)\n- Present participle trailing clauses (\"highlighting its importance\", \"reflecting broader trends\")\n- False ranges (\"From innovation to implementation\")\n- Hedge-stacking (multiple qualifiers in one sentence)\n- Consecutive adverbial sentence starters\n\n**Punctuation check**:\n- Remove em dashes. Replace with commas, periods, parentheses, or colons.\n- Remove semicolons (unless user explicitly uses them)\n- Remove Oxford commas (unless user explicitly uses them)\n- Replace Unicode ellipsis with three dots or restructure\n\n**Rhythm check**:\n- Verify sentence length varies (mix 5-word punches with 25-word flows)\n- Verify paragraph length varies (some 1-sentence, some 5-sentence)\n- Break any Rule of Three that appears back-to-back\n- Check for uniform subsection length and vary it\n\n**Formatting check**:\n- No bold-first bullet points (every bullet starting with \"**Word**: explanation\")\n- No excessive headers for content that doesn't need them\n- No erratic bolding of random words\n- No emoji decoration in professional contexts\n\n**Tone check**:\n- No relentless positivity. Include criticism where warranted.\n- No false balance. Make bold claims when the evidence supports them.\n- No emotional flatness. Let genuine reactions show.\n- No elevated register for simple ideas.\n\n**Self-reference check**:\n- No mentions of being an AI or language model\n- No \"as someone who...\"\n- No disclaimers about AI limitations\n- No \"as of my last knowledge update\"\n- No \"Certainly, here are...\"\n- Use contractions naturally unless context is genuinely formal\n\n### 5. Verify Authenticity Markers\n\nEnsure output includes profile's authenticity characteristics:\n- Acknowledges uncertainty (if specified)\n- Shows tradeoffs (if specified)\n- Uses specific numbers (if specified)\n- References constraints (if specified)\n\n### 6. Final Read-Aloud Test\n\nRead the output in your head. If any sentence sounds like it could appear in any other AI-generated text, rewrite it until it sounds like a specific person said it.\n\n## Usage Examples\n\n### Apply Named Voice\n\n```\nUser: \"Write release notes in technical-authority voice\"\n\nProcess:\n1. Load technical-authority.yaml\n2. Generate release notes with:\n   - Precise technical terminology\n   - Specific version numbers\n   - Direct, confident statements\n   - Tradeoff acknowledgments where relevant\n3. AI tells elimination pass\n4. Final read-aloud test\n```\n\n### Transform Existing Content\n\n```\nUser: \"Make this documentation more friendly for beginners\"\n\nInput: \"The API endpoint accepts a JSON payload containing the requisite parameters...\"\n\nProcess:\n1. Load friendly-explainer.yaml\n2. Analyze: formal, technical, passive\n3. Transform to: casual, accessible, active\n4. AI tells elimination pass\n\nOutput: \"To use this endpoint, send it some JSON with the info it needs...\"\n```\n\n### Calibrate Voice\n\n```\nUser: \"This is too formal, dial it back 30%\"\n\nProcess:\n1. Identify current formality (~0.8)\n2. Calculate target (0.8 - 0.3 = 0.5)\n3. Adjust vocabulary and structure for medium formality\n4. AI tells elimination pass\n```\n\n## Voice Blending\n\nCombine multiple profiles:\n\n```\nUser: \"Write this with 70% technical-authority and 30% friendly-explainer\"\n\nProcess:\n1. Load both profiles\n2. Weighted merge:\n   - tone.formality: 0.7 * 0.7 + 0.3 * 0.3 = 0.58\n   - tone.warmth: 0.7 * 0.3 + 0.3 * 0.8 = 0.45\n   - etc.\n3. Apply merged profile\n4. AI tells elimination pass (always runs last)\n```\n\n## Output Format\n\nWhen reporting voice application:\n\n```\nVoice Applied: technical-authority\n\nTransformations:\n- Formality: 0.4 -> 0.7 (increased)\n- Confidence: 0.5 -> 0.9 (increased)\n- Vocabulary: 12 replacements\n- Structure: Added 2 examples, removed 1 rhetorical question\n\nAI Tells Check:\n- Banned vocabulary removed: 3 instances\n- Em dashes replaced: 2 instances\n- Banned structures fixed: 1 negation pattern\n- Sentence length variance: OK (std dev 7.4)\n- Paragraph length variance: OK (varied)\n\nAuthenticity Check:\n- Acknowledges tradeoffs\n- Uses specific numbers\n- References constraints\n```\n\n## References\n\n- AI Writing Tells (MANDATORY): `references\u002Fai-tells.md`\n","# Voice Apply Skill\n\n## Purpose\n\nTransform content to match a specified voice profile. This skill loads voice profiles and applies their characteristics (tone, vocabulary, structure, perspective) to new or existing content.\n\n**Critical rule**: Every piece of output MUST pass the AI writing tells check defined in `references\u002Fai-tells.md`. This is non-negotiable. If the output contains any banned vocabulary, structures, transitions, or punctuation patterns from that reference, rewrite until clean.\n\n## When This Skill Applies\n\n- User asks to \"write in X voice\" or \"use Y tone\"\n- User wants to \"make this sound more [casual\u002Fformal\u002Ftechnical\u002Fetc.]\"\n- User provides content and asks to transform its style\n- User references a voice profile by name\n- User wants content to match a specific audience or context\n\n## Trigger Phrases\n\n| Natural Language | Action |\n|------------------|--------|\n| \"Write this in technical voice\" | Apply technical-authority profile |\n| \"Make it more casual\" | Apply casual-conversational or calibrate toward casual |\n| \"This needs to sound executive\" | Apply executive-brief profile |\n| \"Explain like I'm a beginner\" | Apply friendly-explainer profile |\n| \"Use the [profile-name] voice\" | Load and apply named profile |\n| \"Transform this to match [example]\" | Analyze example, apply derived voice |\n\n## Voice Profile Locations\n\nSkill checks these locations (in order):\n1. Project: `.aiwg\u002Fvoices\u002F`\n2. User: `~\u002F.config\u002Faiwg\u002Fvoices\u002F`\n3. Built-in: `voice-framework\u002Fvoices\u002Ftemplates\u002F`\n\n## Built-in Voice Profiles\n\n| Profile | Description | Best For |\n|---------|-------------|----------|\n| `technical-authority` | Direct, precise, confident | Docs, architecture, engineering |\n| `friendly-explainer` | Approachable, encouraging | Tutorials, onboarding, education |\n| `executive-brief` | Concise, outcome-focused | Business cases, stakeholder comms |\n| `casual-conversational` | Relaxed, personal | Blog posts, social, newsletters |\n\n## Application Process\n\n### 1. Load Voice Profile\n\n```python\n# Load from YAML\nprofile = load_voice_profile(\"technical-authority\")\n```\n\n### 2. Analyze Source Content (if transforming)\n\n- Current tone characteristics\n- Vocabulary patterns\n- Structure patterns\n- Gap analysis vs target voice\n\n### 3. Apply Voice Characteristics\n\n**Tone Calibration**:\n- Adjust formality level (word choice, contractions)\n- Calibrate confidence (hedging vs assertion)\n- Set warmth (clinical vs personable)\n- Tune energy (measured vs enthusiastic)\n\n**Vocabulary Transformation**:\n- Replace words per `prefer`\u002F`avoid` guidance\n- Introduce domain terminology naturally\n- Weave in signature phrases where appropriate\n\n**Structure Adjustment**:\n- Modify sentence length distribution\n- Adjust paragraph breaks\n- Add\u002Fremove lists, examples, analogies as specified\n\n**Perspective Shift**:\n- Adjust narrative person (I, we, you, they)\n- Calibrate opinion expression\n- Set reader relationship tone\n\n### 4. AI Tells Elimination Pass (MANDATORY)\n\nAfter applying the voice profile, run every piece of output through the full AI tells check. This is the most important step. Reference: `references\u002Fai-tells.md`\n\n**Vocabulary check**: Scan output for every word in the banned lists:\n- Banned verbs: delve, leverage, utilize, harness, unlock, unleash, empower, facilitate, foster, bolster, optimize, streamline, navigate, spearhead, underscore, illuminate, elucidate, embark, unravel, elevate, reimagine, revolutionize, transcend, resonate, showcase, craft, embrace, thrive, unveil, champion, and all others on the list\n- Banned adjectives: multifaceted, seamless, robust, comprehensive, cutting-edge, holistic, meticulous, groundbreaking, transformative, innovative, compelling, invaluable, paramount, unprecedented, impactful, game-changing, and all others on the list\n- Banned nouns: tapestry, realm, testament, beacon, myriad, landscape, ecosystem, paradigm, nexus, catalyst, synergy, roadmap, cornerstone, bedrock, pinnacle, plethora, stakeholders, and all others on the list\n- Banned adverbs: furthermore, moreover, additionally, notably, crucially, importantly, consequently, seamlessly, fundamentally, undoubtedly, and all others on the list\n\n**Transition check**: Remove all banned transitions:\n- Throat-clearing: \"in today's digital age\", \"in a world where\", \"when it comes to\"\n- Pedagogical: \"let's dive in\", \"let's unpack this\", \"great question!\"\n- Signposting: \"it's important to note\", \"it's worth noting\", \"this underscores\"\n- Fake-suspense: \"here's the thing\", \"the best part?\", \"here's the kicker\"\n- Hype: \"game-changer\", \"pushing the boundaries\", \"paving the way\"\n- Conclusions: \"in conclusion\", \"to wrap up\", \"at the end of the day\"\n- Bot closers: \"I hope this helps!\", \"feel free to reach out\"\n\n**Structure check**: Eliminate banned patterns:\n- The \"It's not X, it's Y\" negation pattern (the single most prominent AI tell)\n- Self-posed questions answered immediately (\"The best part? It's this.\")\n- Anaphora abuse (same opener 3+ times in a row)\n- Present participle trailing clauses (\"highlighting its importance\", \"reflecting broader trends\")\n- False ranges (\"From innovation to implementation\")\n- Hedge-stacking (multiple qualifiers in one sentence)\n- Consecutive adverbial sentence starters\n\n**Punctuation check**:\n- Remove em dashes. Replace with commas, periods, parentheses, or colons.\n- Remove semicolons (unless user explicitly uses them)\n- Remove Oxford commas (unless user explicitly uses them)\n- Replace Unicode ellipsis with three dots or restructure\n\n**Rhythm check**:\n- Verify sentence length varies (mix 5-word punches with 25-word flows)\n- Verify paragraph length varies (some 1-sentence, some 5-sentence)\n- Break any Rule of Three that appears back-to-back\n- Check for uniform subsection length and vary it\n\n**Formatting check**:\n- No bold-first bullet points (every bullet starting with \"**Word**: explanation\")\n- No excessive headers for content that doesn't need them\n- No erratic bolding of random words\n- No emoji decoration in professional contexts\n\n**Tone check**:\n- No relentless positivity. Include criticism where warranted.\n- No false balance. Make bold claims when the evidence supports them.\n- No emotional flatness. Let genuine reactions show.\n- No elevated register for simple ideas.\n\n**Self-reference check**:\n- No mentions of being an AI or language model\n- No \"as someone who...\"\n- No disclaimers about AI limitations\n- No \"as of my last knowledge update\"\n- No \"Certainly, here are...\"\n- Use contractions naturally unless context is genuinely formal\n\n### 5. Verify Authenticity Markers\n\nEnsure output includes profile's authenticity characteristics:\n- Acknowledges uncertainty (if specified)\n- Shows tradeoffs (if specified)\n- Uses specific numbers (if specified)\n- References constraints (if specified)\n\n### 6. Final Read-Aloud Test\n\nRead the output in your head. If any sentence sounds like it could appear in any other AI-generated text, rewrite it until it sounds like a specific person said it.\n\n## Usage Examples\n\n### Apply Named Voice\n\n```\nUser: \"Write release notes in technical-authority voice\"\n\nProcess:\n1. Load technical-authority.yaml\n2. Generate release notes with:\n   - Precise technical terminology\n   - Specific version numbers\n   - Direct, confident statements\n   - Tradeoff acknowledgments where relevant\n3. AI tells elimination pass\n4. Final read-aloud test\n```\n\n### Transform Existing Content\n\n```\nUser: \"Make this documentation more friendly for beginners\"\n\nInput: \"The API endpoint accepts a JSON payload containing the requisite parameters...\"\n\nProcess:\n1. Load friendly-explainer.yaml\n2. Analyze: formal, technical, passive\n3. Transform to: casual, accessible, active\n4. AI tells elimination pass\n\nOutput: \"To use this endpoint, send it some JSON with the info it needs...\"\n```\n\n### Calibrate Voice\n\n```\nUser: \"This is too formal, dial it back 30%\"\n\nProcess:\n1. Identify current formality (~0.8)\n2. Calculate target (0.8 - 0.3 = 0.5)\n3. Adjust vocabulary and structure for medium formality\n4. AI tells elimination pass\n```\n\n## Voice Blending\n\nCombine multiple profiles:\n\n```\nUser: \"Write this with 70% technical-authority and 30% friendly-explainer\"\n\nProcess:\n1. Load both profiles\n2. Weighted merge:\n   - tone.formality: 0.7 * 0.7 + 0.3 * 0.3 = 0.58\n   - tone.warmth: 0.7 * 0.3 + 0.3 * 0.8 = 0.45\n   - etc.\n3. Apply merged profile\n4. AI tells elimination pass (always runs last)\n```\n\n## Output Format\n\nWhen reporting voice application:\n\n```\nVoice Applied: technical-authority\n\nTransformations:\n- Formality: 0.4 -> 0.7 (increased)\n- Confidence: 0.5 -> 0.9 (increased)\n- Vocabulary: 12 replacements\n- Structure: Added 2 examples, removed 1 rhetorical question\n\nAI Tells Check:\n- Banned vocabulary removed: 3 instances\n- Em dashes replaced: 2 instances\n- Banned structures fixed: 1 negation pattern\n- Sentence length variance: OK (std dev 7.4)\n- Paragraph length variance: OK (varied)\n\nAuthenticity Check:\n- Acknowledges tradeoffs\n- Uses specific numbers\n- References constraints\n```\n\n## References\n\n- AI Writing Tells (MANDATORY): `references\u002Fai-tells.md`\n",{"name":5,"license":15,"metadata":34,"description":7},{"source":35,"version":36,"platforms":37,"upstream_author":39},"https:\u002F\u002Fgithub.com\u002Fangelarose210\u002Fghostwriter","1.0.0",[38],"all","angelarose210","main","a298c929b6cbd662e1fce54302ce520d5ceea1a5","skills\u002Fvoice-apply","https:\u002F\u002Fgithub.com\u002FPrekzursil\u002Fagent-skills-toolchain","https:\u002F\u002Fgithub.com\u002FPrekzursil","2026-11-02 14:30:57",{"source":8,"skillName":5,"commands":47,"prompt":57,"zipAvailable":58},[48,51,54],{"tool":49,"command":50},"npx","npx skills add Prekzursil\u002Fagent-skills-toolchain --skill voice-apply",{"tool":52,"command":53},"bunx","bunx skills add Prekzursil\u002Fagent-skills-toolchain --skill voice-apply",{"tool":55,"command":56},"pnpm","pnpm dlx skills add Prekzursil\u002Fagent-skills-toolchain --skill voice-apply","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002FPrekzursil\u002Fagent-skills-toolchain\u002Fblob\u002Fmain\u002Fskills\u002Fvoice-apply\u002FSKILL.md",true,[60,65],{"path":61,"resourceType":61,"resourceTypeDesc":62,"sizeBytes":63,"sourceHtmlUrl":64},"LICENSE","许可证",1056,"https:\u002F\u002Fgithub.com\u002FPrekzursil\u002Fagent-skills-toolchain\u002Fblob\u002Fmain\u002Fskills\u002Fvoice-apply\u002FLICENSE",{"path":66,"resourceType":67,"resourceTypeDesc":68,"sizeBytes":69,"sourceHtmlUrl":70},"references\u002Fai-tells.md","REFERENCE","参考文档",10706,"https:\u002F\u002Fgithub.com\u002FPrekzursil\u002Fagent-skills-toolchain\u002Fblob\u002Fmain\u002Fskills\u002Fvoice-apply\u002Freferences\u002Fai-tells.md",[72,93,124,151,165,181],{"skillNo":73,"name":74,"nameZh":6,"description":75,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":76,"categories":77,"keywords":78,"publishedAt":29},"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",[],[79,80,81,82,83,84,85,86,87,27,88,89,90,91,92],"clarify requirements","clarify","requirements","risk","options","task","prompts","goal","scanning","context","repo","injection","execution","file",{"skillNo":94,"name":95,"nameZh":6,"description":96,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":97,"categories":98,"keywords":104,"publishedAt":29},"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",[99],{"categoryNo":100,"categoryName":101,"taxonomyType":102,"taxonomyTypeDesc":103},"01JBSEEDCAT000000000000023","Skill与智能体开发","SCENARIO","使用场景",[105,106,107,108,109,110,111,112,113,114,115,116,117,118,27,119,120,121,122,123],"openmm md","how","decision","pick","linux","analyze","tool","stack","open","NVIDIA","gpu","license","workflow","windows","free","molecular dynamics","local","do","MCP",{"skillNo":125,"name":126,"nameZh":6,"description":127,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":128,"categories":129,"keywords":136,"publishedAt":29},"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",[130,133],{"categoryNo":131,"categoryName":132,"taxonomyType":102,"taxonomyTypeDesc":103},"01JBSEEDCAT000000000000003","演示文稿",{"categoryNo":134,"categoryName":135,"taxonomyType":102,"taxonomyTypeDesc":103},"01JBSEEDCAT000000000000008","测试与质量",[137,138,139,140,141,142,143,144,145,146,106,147,148,149,150],"review","visual","visual review","pages","web","false","iteration","take","check","slides","ui","screenshot","playwright","screenshots",{"skillNo":152,"name":153,"nameZh":6,"description":154,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":155,"categories":156,"keywords":157,"publishedAt":29},"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",[],[153,158,159,160,161,162,163,164],"setup","report","project","installation","project setup","issues","state",{"skillNo":166,"name":167,"nameZh":6,"description":168,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":169,"categories":170,"keywords":172,"publishedAt":29},"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",[171],{"categoryNo":100,"categoryName":101,"taxonomyType":102,"taxonomyTypeDesc":103},[167,173,84,174,175,176,27,177,178,179,180],"start issue","issue","ready","work on issue","user","work","work on","development",{"skillNo":182,"name":158,"nameZh":6,"description":183,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":184,"categories":185,"keywords":186,"publishedAt":29},"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",[],[158,160,121,187,162,188],"files","interactive"]