[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M6DC4FYX4R4P1PHHE2D5JDV0":3,"skill-same:01M6DC4FYX4R4P1PHHE2D5JDV0":67},{"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":31,"linkOnly":32,"markdownContent":33,"markdownBody":34,"frontMatter":35,"refName":42,"commitSha":43,"skillDirectory":44,"forksCount":14,"repositoryHtmlUrl":45,"repositoryHomepageUrl":6,"ownerHtmlUrl":46,"ownerBlogUrl":6,"ownerDescription":6,"updatedAt":47,"install":48,"resources":61},"01M6DC4FYX4R4P1PHHE2D5JDV0","voice-analyze",null,"Reverse-engineer voice profiles from samples by analyzing writing patterns. Use when the user pastes samples. NOT from a description (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\u002F.agents\u002Fskills\u002Fvoice-analyze\u002FSKILL.md",[],[19,20,21,22,23,24,25,26,27,28,29,30],"voice","analyze","voice analyze","writing","github","create","https","analyzing","user","use","engineer","patterns","2026-11-10 10:12:30",false,"---\nname: voice-analyze\ndescription: Reverse-engineer voice profiles from samples by analyzing writing patterns. Use when the user pastes samples. NOT from a description (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-analyze\n\nReverse-engineer voice profiles from sample content by analyzing writing patterns. Detects and flags AI writing tells so the resulting profile produces human-sounding output.\n\n## Triggers\n\nAlternate expressions and non-obvious activations (primary phrases are matched automatically from the skill description):\n\n- \"voice fingerprint\" -> voice profile extraction\n- \"what's my writing style\" -> voice analysis\n\n## Behavior\n\nWhen triggered, this skill:\n\n1. **Analyzes text samples** for:\n   - Sentence structure and length patterns\n   - Vocabulary sophistication and domain\n   - Tone markers (formality, confidence, warmth)\n   - Structural patterns (lists, examples, questions)\n   - Perspective and voice choices\n\n2. **Extracts measurable features**:\n   - Average sentence length\n   - Vocabulary complexity (syllables, word length)\n   - Contraction usage\n   - Personal pronoun frequency\n   - Question density\n   - List\u002Fbullet usage\n\n3. **Scans for AI writing tells** (see `..\u002Fvoice-apply\u002Freferences\u002Fai-tells.md`):\n   - Flags any banned vocabulary found in the sample (verbs, adjectives, nouns, adverbs from the tells list)\n   - Detects banned sentence structures: \"It's not X, it's Y\" negation patterns, self-posed questions answered immediately, anaphora abuse, present participle trailing clauses\n   - Measures em dash frequency (AI models use ~10x more than human writers)\n   - Checks for uniform sentence length clustering (the \"burstiness problem\": AI clusters at 15-20 words, humans swing from 3-word fragments to 40-word sprawls)\n   - Detects banned transitions and filler phrases (throat-clearing openers, pedagogical openers, fake-suspense transitions, hype phrases)\n   - Flags formatting tells: bold-first bullet points, excessive headers, erratic bolding, emoji decoration\n   - Checks for Rule of Three overuse (back-to-back tricolons are an AI fingerprint)\n   - Detects uniform paragraph length (the most visually obvious tell)\n   - If the sample contains AI tells, the profile's `vocabulary.avoid` list MUST include them and the `ai_tells_report` section must document what was found\n\n4. **Maps features to voice dimensions**:\n   - Statistical analysis -> tone scale values (0-1)\n   - Pattern detection -> structure preferences\n   - Vocabulary extraction -> prefer\u002Favoid lists\n\n5. **Generates voice profile** matching the analyzed style, with AI tells filtered out\n\n## Usage Examples\n\n### Analyze Existing Documentation\n```\nUser: \"Analyze this writing style\" + [paste technical docs]\n\nAnalysis:\n- Formality: 0.7 (no contractions, structured sentences)\n- Confidence: 0.85 (direct statements, few hedges)\n- Warmth: 0.25 (impersonal, third-person)\n- Complexity: 0.8 (technical vocabulary, long sentences)\n- AI Tells Detected: 3 (2 banned verbs, 1 negation pattern)\n\nOutput: analyzed-technical-docs.yaml\n```\n\n### Match Brand Voice\n```\nUser: \"Extract voice from our marketing copy\" + [paste samples]\n\nAnalysis:\n- Formality: 0.3 (conversational, contractions)\n- Confidence: 0.7 (benefit claims, but some hedging)\n- Warmth: 0.85 (second person, friendly tone)\n- Energy: 0.8 (exclamation points, action verbs)\n- AI Tells Detected: 0\n\nOutput: brand-marketing-voice.yaml\n```\n\n### Capture Personal Style\n```\nUser: \"Create profile from my blog posts\" + [paste samples]\n\nAnalysis:\n- Identifies personal writing quirks\n- Extracts signature phrases\n- Maps to voice dimensions\n- Flags and excludes any AI tells found in samples\n\nOutput: personal-blog-voice.yaml\n```\n\n## Analysis Methodology\n\n### Feature Extraction\n\n| Feature | Measurement | Maps To |\n|---------|-------------|---------|\n| Sentence length | Avg words\u002Fsentence | complexity |\n| Sentence length variance | Std deviation of word count | burstiness (human = high variance) |\n| Contractions | Frequency per 100 words | formality (inverse) |\n| First person (\"I\", \"we\") | Frequency | warmth |\n| Second person (\"you\") | Frequency | warmth |\n| Passive voice | Percentage of sentences | confidence (inverse) |\n| Questions | Per paragraph | warmth, engagement |\n| Hedging words | \"might\", \"perhaps\", \"could\" | confidence (inverse) |\n| Exclamation marks | Frequency | energy |\n| Technical terms | Domain vocabulary density | complexity |\n| Em dash frequency | Per 1000 words | ai_tell_score (high = likely AI) |\n| Banned AI vocabulary | Count from tells list | ai_tell_score |\n| Paragraph length variance | Std deviation of sentence count | ai_tell_score (low variance = likely AI) |\n\n### AI Tells Detection Pass\n\nAfter standard feature extraction, run the AI tells scan. For each category in `..\u002Fvoice-apply\u002Freferences\u002Fai-tells.md`:\n\n1. **Vocabulary scan**: Count occurrences of every word\u002Fphrase in the banned lists (verbs, adjectives, nouns, adverbs, connectors)\n2. **Structure scan**: Detect banned sentence patterns (negation flips, self-posed questions, anaphora, trailing participles, false ranges, hedge-stacking)\n3. **Punctuation scan**: Count em dashes, semicolons, Oxford commas, Unicode ellipsis characters\n4. **Rhythm scan**: Calculate sentence length standard deviation. If std dev \u003C 4 words, flag as AI-like clustering\n5. **Formatting scan**: Check for bold-first bullets, excessive headers, erratic bolding\n6. **Transition scan**: Search for throat-clearing openers, pedagogical openers, fake-suspense phrases, hype phrases, banned conclusion phrases\n\nReport findings in the output profile under `ai_tells_report`. Any banned vocabulary found in the sample goes into `vocabulary.avoid` automatically.\n\n### Dimension Calibration\n\n**Formality** (0-1):\n- 0.0-0.3: Contractions frequent, casual language, fragments okay\n- 0.4-0.6: Mixed style, professional but accessible\n- 0.7-1.0: No contractions, complete sentences, formal structure\n\n**Confidence** (0-1):\n- 0.0-0.3: Many hedges (\"might\", \"perhaps\"), questions, qualifiers\n- 0.4-0.6: Balanced certainty, occasional hedges\n- 0.7-1.0: Direct statements, conclusions first, few qualifiers\n\n**Warmth** (0-1):\n- 0.0-0.3: Third person, passive voice, clinical tone\n- 0.4-0.6: Professional but personable\n- 0.7-1.0: Second person, inclusive language, empathetic\n\n**Energy** (0-1):\n- 0.0-0.3: Calm, measured, understated\n- 0.4-0.6: Balanced engagement\n- 0.7-1.0: Exclamation marks, action verbs, dynamic phrasing\n\n**Complexity** (0-1):\n- 0.0-0.3: Short sentences, simple vocabulary, accessible\n- 0.4-0.6: Moderate complexity, clear but nuanced\n- 0.7-1.0: Long sentences, technical vocabulary, layered ideas\n\n### Vocabulary Extraction\n\n**Signature phrases** - Identified by:\n- Repeated patterns across samples\n- Distinctive constructions\n- Opening\u002Fclosing patterns\n\n**Domain vocabulary** - Extracted by:\n- Technical term frequency\n- Specialized jargon\n- Industry-specific language\n\n**Avoid patterns** - Built from two sources:\n1. Conspicuous absence of common phrases in the samples\n2. Any AI writing tells found during the tells detection pass (always include these)\n\n## Output Format\n\n```yaml\nname: analyzed-sample-voice\nversion: 1.0.0\ndescription: Voice profile extracted from sample content\nanalysis_source:\n  sample_size: 1500  # words analyzed\n  sample_count: 3    # number of samples\n  confidence: 0.85   # analysis confidence score\ntone:\n  formality: 0.65\n  confidence: 0.8\n  warmth: 0.4\n  energy: 0.5\n  complexity: 0.7\nvocabulary:\n  prefer:\n    - \"extracted signature phrase 1\"\n    - \"detected domain terminology\"\n  avoid:\n    - \"leverage\"       # AI tell: banned verb\n    - \"delve\"          # AI tell: banned verb\n    - \"comprehensive\"  # AI tell: banned adjective\n    - \"landscape\"      # AI tell: banned noun\n    - \"furthermore\"    # AI tell: banned adverb\n    - \"patterns not found in samples\"\n  signature_phrases:\n    - \"The key point is...\"\n    - \"This demonstrates...\"\nstructure:\n  sentence_length: medium    # avg 15-20 words\n  sentence_length_variance: high  # std dev > 6 words (human-like)\n  paragraph_length: medium   # avg 4-6 sentences\n  paragraph_length_variance: high # varied paragraph sizes (human-like)\n  sentence_variety: high     # varied structure detected\n  use_lists: when-appropriate\n  use_examples: frequently\n  use_questions: rarely\n  em_dash_usage: avoid       # always set to avoid unless user explicitly uses them naturally\nperspective:\n  person: third\n  voice: active\n  tense: present\nextracted_patterns:\n  opening_style: \"context-first\"\n  closing_style: \"conclusion-summary\"\n  transition_style: \"logical-flow\"\nai_tells_report:\n  tells_found: 3\n  em_dash_frequency: 2.1     # per 1000 words (human avg ~0.5, AI avg ~5.0)\n  sentence_length_std_dev: 7.2  # words (human = 6-12, AI = 2-4)\n  paragraph_length_std_dev: 2.8 # sentences (human = 2-5, AI = 0.5-1.5)\n  banned_vocabulary_found:\n    - \"leverage (1x)\"\n    - \"comprehensive (2x)\"\n  banned_structures_found:\n    - \"negation pattern (1x)\"\n  banned_transitions_found: []\n  formatting_tells_found: []\n  overall_human_score: 0.82  # 0 = clearly AI, 1 = clearly human\n```\n\n## Integration\n\n- **Output**: Creates profiles usable by `voice-apply`\n- **Chain**: `voice-analyze` -> `voice-create` (to refine) -> `voice-apply`\n- **Chain**: `voice-analyze` + `voice-analyze` -> `voice-blend` (combine styles)\n\n## Accuracy Considerations\n\n- **Minimum sample**: 500+ words for reliable analysis\n- **Multiple samples**: 3+ samples improve accuracy\n- **Consistent genre**: Mixing genres reduces accuracy\n- **Confidence score**: Output includes analysis confidence (0-1)\n- **AI tells in samples**: If the sample itself contains AI tells (e.g., it was partially AI-generated), the analyzer will flag them and exclude them from the profile's preferred patterns. The `overall_human_score` helps gauge how much of the sample is genuinely the user's voice vs AI artifacts.\n\n## References\n\n- AI Writing Tells: `..\u002Fvoice-apply\u002Freferences\u002Fai-tells.md`\n","# voice-analyze\n\nReverse-engineer voice profiles from sample content by analyzing writing patterns. Detects and flags AI writing tells so the resulting profile produces human-sounding output.\n\n## Triggers\n\nAlternate expressions and non-obvious activations (primary phrases are matched automatically from the skill description):\n\n- \"voice fingerprint\" -> voice profile extraction\n- \"what's my writing style\" -> voice analysis\n\n## Behavior\n\nWhen triggered, this skill:\n\n1. **Analyzes text samples** for:\n   - Sentence structure and length patterns\n   - Vocabulary sophistication and domain\n   - Tone markers (formality, confidence, warmth)\n   - Structural patterns (lists, examples, questions)\n   - Perspective and voice choices\n\n2. **Extracts measurable features**:\n   - Average sentence length\n   - Vocabulary complexity (syllables, word length)\n   - Contraction usage\n   - Personal pronoun frequency\n   - Question density\n   - List\u002Fbullet usage\n\n3. **Scans for AI writing tells** (see `..\u002Fvoice-apply\u002Freferences\u002Fai-tells.md`):\n   - Flags any banned vocabulary found in the sample (verbs, adjectives, nouns, adverbs from the tells list)\n   - Detects banned sentence structures: \"It's not X, it's Y\" negation patterns, self-posed questions answered immediately, anaphora abuse, present participle trailing clauses\n   - Measures em dash frequency (AI models use ~10x more than human writers)\n   - Checks for uniform sentence length clustering (the \"burstiness problem\": AI clusters at 15-20 words, humans swing from 3-word fragments to 40-word sprawls)\n   - Detects banned transitions and filler phrases (throat-clearing openers, pedagogical openers, fake-suspense transitions, hype phrases)\n   - Flags formatting tells: bold-first bullet points, excessive headers, erratic bolding, emoji decoration\n   - Checks for Rule of Three overuse (back-to-back tricolons are an AI fingerprint)\n   - Detects uniform paragraph length (the most visually obvious tell)\n   - If the sample contains AI tells, the profile's `vocabulary.avoid` list MUST include them and the `ai_tells_report` section must document what was found\n\n4. **Maps features to voice dimensions**:\n   - Statistical analysis -> tone scale values (0-1)\n   - Pattern detection -> structure preferences\n   - Vocabulary extraction -> prefer\u002Favoid lists\n\n5. **Generates voice profile** matching the analyzed style, with AI tells filtered out\n\n## Usage Examples\n\n### Analyze Existing Documentation\n```\nUser: \"Analyze this writing style\" + [paste technical docs]\n\nAnalysis:\n- Formality: 0.7 (no contractions, structured sentences)\n- Confidence: 0.85 (direct statements, few hedges)\n- Warmth: 0.25 (impersonal, third-person)\n- Complexity: 0.8 (technical vocabulary, long sentences)\n- AI Tells Detected: 3 (2 banned verbs, 1 negation pattern)\n\nOutput: analyzed-technical-docs.yaml\n```\n\n### Match Brand Voice\n```\nUser: \"Extract voice from our marketing copy\" + [paste samples]\n\nAnalysis:\n- Formality: 0.3 (conversational, contractions)\n- Confidence: 0.7 (benefit claims, but some hedging)\n- Warmth: 0.85 (second person, friendly tone)\n- Energy: 0.8 (exclamation points, action verbs)\n- AI Tells Detected: 0\n\nOutput: brand-marketing-voice.yaml\n```\n\n### Capture Personal Style\n```\nUser: \"Create profile from my blog posts\" + [paste samples]\n\nAnalysis:\n- Identifies personal writing quirks\n- Extracts signature phrases\n- Maps to voice dimensions\n- Flags and excludes any AI tells found in samples\n\nOutput: personal-blog-voice.yaml\n```\n\n## Analysis Methodology\n\n### Feature Extraction\n\n| Feature | Measurement | Maps To |\n|---------|-------------|---------|\n| Sentence length | Avg words\u002Fsentence | complexity |\n| Sentence length variance | Std deviation of word count | burstiness (human = high variance) |\n| Contractions | Frequency per 100 words | formality (inverse) |\n| First person (\"I\", \"we\") | Frequency | warmth |\n| Second person (\"you\") | Frequency | warmth |\n| Passive voice | Percentage of sentences | confidence (inverse) |\n| Questions | Per paragraph | warmth, engagement |\n| Hedging words | \"might\", \"perhaps\", \"could\" | confidence (inverse) |\n| Exclamation marks | Frequency | energy |\n| Technical terms | Domain vocabulary density | complexity |\n| Em dash frequency | Per 1000 words | ai_tell_score (high = likely AI) |\n| Banned AI vocabulary | Count from tells list | ai_tell_score |\n| Paragraph length variance | Std deviation of sentence count | ai_tell_score (low variance = likely AI) |\n\n### AI Tells Detection Pass\n\nAfter standard feature extraction, run the AI tells scan. For each category in `..\u002Fvoice-apply\u002Freferences\u002Fai-tells.md`:\n\n1. **Vocabulary scan**: Count occurrences of every word\u002Fphrase in the banned lists (verbs, adjectives, nouns, adverbs, connectors)\n2. **Structure scan**: Detect banned sentence patterns (negation flips, self-posed questions, anaphora, trailing participles, false ranges, hedge-stacking)\n3. **Punctuation scan**: Count em dashes, semicolons, Oxford commas, Unicode ellipsis characters\n4. **Rhythm scan**: Calculate sentence length standard deviation. If std dev \u003C 4 words, flag as AI-like clustering\n5. **Formatting scan**: Check for bold-first bullets, excessive headers, erratic bolding\n6. **Transition scan**: Search for throat-clearing openers, pedagogical openers, fake-suspense phrases, hype phrases, banned conclusion phrases\n\nReport findings in the output profile under `ai_tells_report`. Any banned vocabulary found in the sample goes into `vocabulary.avoid` automatically.\n\n### Dimension Calibration\n\n**Formality** (0-1):\n- 0.0-0.3: Contractions frequent, casual language, fragments okay\n- 0.4-0.6: Mixed style, professional but accessible\n- 0.7-1.0: No contractions, complete sentences, formal structure\n\n**Confidence** (0-1):\n- 0.0-0.3: Many hedges (\"might\", \"perhaps\"), questions, qualifiers\n- 0.4-0.6: Balanced certainty, occasional hedges\n- 0.7-1.0: Direct statements, conclusions first, few qualifiers\n\n**Warmth** (0-1):\n- 0.0-0.3: Third person, passive voice, clinical tone\n- 0.4-0.6: Professional but personable\n- 0.7-1.0: Second person, inclusive language, empathetic\n\n**Energy** (0-1):\n- 0.0-0.3: Calm, measured, understated\n- 0.4-0.6: Balanced engagement\n- 0.7-1.0: Exclamation marks, action verbs, dynamic phrasing\n\n**Complexity** (0-1):\n- 0.0-0.3: Short sentences, simple vocabulary, accessible\n- 0.4-0.6: Moderate complexity, clear but nuanced\n- 0.7-1.0: Long sentences, technical vocabulary, layered ideas\n\n### Vocabulary Extraction\n\n**Signature phrases** - Identified by:\n- Repeated patterns across samples\n- Distinctive constructions\n- Opening\u002Fclosing patterns\n\n**Domain vocabulary** - Extracted by:\n- Technical term frequency\n- Specialized jargon\n- Industry-specific language\n\n**Avoid patterns** - Built from two sources:\n1. Conspicuous absence of common phrases in the samples\n2. Any AI writing tells found during the tells detection pass (always include these)\n\n## Output Format\n\n```yaml\nname: analyzed-sample-voice\nversion: 1.0.0\ndescription: Voice profile extracted from sample content\nanalysis_source:\n  sample_size: 1500  # words analyzed\n  sample_count: 3    # number of samples\n  confidence: 0.85   # analysis confidence score\ntone:\n  formality: 0.65\n  confidence: 0.8\n  warmth: 0.4\n  energy: 0.5\n  complexity: 0.7\nvocabulary:\n  prefer:\n    - \"extracted signature phrase 1\"\n    - \"detected domain terminology\"\n  avoid:\n    - \"leverage\"       # AI tell: banned verb\n    - \"delve\"          # AI tell: banned verb\n    - \"comprehensive\"  # AI tell: banned adjective\n    - \"landscape\"      # AI tell: banned noun\n    - \"furthermore\"    # AI tell: banned adverb\n    - \"patterns not found in samples\"\n  signature_phrases:\n    - \"The key point is...\"\n    - \"This demonstrates...\"\nstructure:\n  sentence_length: medium    # avg 15-20 words\n  sentence_length_variance: high  # std dev > 6 words (human-like)\n  paragraph_length: medium   # avg 4-6 sentences\n  paragraph_length_variance: high # varied paragraph sizes (human-like)\n  sentence_variety: high     # varied structure detected\n  use_lists: when-appropriate\n  use_examples: frequently\n  use_questions: rarely\n  em_dash_usage: avoid       # always set to avoid unless user explicitly uses them naturally\nperspective:\n  person: third\n  voice: active\n  tense: present\nextracted_patterns:\n  opening_style: \"context-first\"\n  closing_style: \"conclusion-summary\"\n  transition_style: \"logical-flow\"\nai_tells_report:\n  tells_found: 3\n  em_dash_frequency: 2.1     # per 1000 words (human avg ~0.5, AI avg ~5.0)\n  sentence_length_std_dev: 7.2  # words (human = 6-12, AI = 2-4)\n  paragraph_length_std_dev: 2.8 # sentences (human = 2-5, AI = 0.5-1.5)\n  banned_vocabulary_found:\n    - \"leverage (1x)\"\n    - \"comprehensive (2x)\"\n  banned_structures_found:\n    - \"negation pattern (1x)\"\n  banned_transitions_found: []\n  formatting_tells_found: []\n  overall_human_score: 0.82  # 0 = clearly AI, 1 = clearly human\n```\n\n## Integration\n\n- **Output**: Creates profiles usable by `voice-apply`\n- **Chain**: `voice-analyze` -> `voice-create` (to refine) -> `voice-apply`\n- **Chain**: `voice-analyze` + `voice-analyze` -> `voice-blend` (combine styles)\n\n## Accuracy Considerations\n\n- **Minimum sample**: 500+ words for reliable analysis\n- **Multiple samples**: 3+ samples improve accuracy\n- **Consistent genre**: Mixing genres reduces accuracy\n- **Confidence score**: Output includes analysis confidence (0-1)\n- **AI tells in samples**: If the sample itself contains AI tells (e.g., it was partially AI-generated), the analyzer will flag them and exclude them from the profile's preferred patterns. The `overall_human_score` helps gauge how much of the sample is genuinely the user's voice vs AI artifacts.\n\n## References\n\n- AI Writing Tells: `..\u002Fvoice-apply\u002Freferences\u002Fai-tells.md`\n",{"name":5,"license":15,"metadata":36,"description":7},{"source":37,"version":38,"platforms":39,"upstream_author":41},"https:\u002F\u002Fgithub.com\u002Fangelarose210\u002Fghostwriter","1.0.0",[40],"all","angelarose210","main","a298c929b6cbd662e1fce54302ce520d5ceea1a5",".agents\u002Fskills\u002Fvoice-analyze","https:\u002F\u002Fgithub.com\u002FPrekzursil\u002Fagent-skills-toolchain","https:\u002F\u002Fgithub.com\u002FPrekzursil","2026-11-02 14:30:57",{"source":8,"skillName":5,"commands":49,"prompt":59,"zipAvailable":60},[50,53,56],{"tool":51,"command":52},"npx","npx skills add Prekzursil\u002Fagent-skills-toolchain --skill voice-analyze",{"tool":54,"command":55},"bunx","bunx skills add Prekzursil\u002Fagent-skills-toolchain --skill voice-analyze",{"tool":57,"command":58},"pnpm","pnpm dlx skills add Prekzursil\u002Fagent-skills-toolchain --skill voice-analyze","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002FPrekzursil\u002Fagent-skills-toolchain\u002Fblob\u002Fmain\u002F.agents\u002Fskills\u002Fvoice-analyze\u002FSKILL.md",true,[62],{"path":63,"resourceType":63,"resourceTypeDesc":64,"sizeBytes":65,"sourceHtmlUrl":66},"LICENSE","许可证",1056,"https:\u002F\u002Fgithub.com\u002FPrekzursil\u002Fagent-skills-toolchain\u002Fblob\u002Fmain\u002F.agents\u002Fskills\u002Fvoice-analyze\u002FLICENSE",[68,89,119,146,160,175],{"skillNo":69,"name":70,"nameZh":6,"description":71,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":72,"categories":73,"keywords":74,"publishedAt":31},"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",[],[75,76,77,78,79,80,81,82,83,28,84,85,86,87,88],"clarify requirements","clarify","requirements","risk","options","task","prompts","goal","scanning","context","repo","injection","execution","file",{"skillNo":90,"name":91,"nameZh":6,"description":92,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":93,"categories":94,"keywords":100,"publishedAt":31},"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",[95],{"categoryNo":96,"categoryName":97,"taxonomyType":98,"taxonomyTypeDesc":99},"01JBSEEDCAT000000000000023","Skill与智能体开发","SCENARIO","使用场景",[101,102,103,104,105,20,106,107,108,109,110,111,112,113,28,114,115,116,117,118],"openmm md","how","decision","pick","linux","tool","stack","open","NVIDIA","gpu","license","workflow","windows","free","molecular dynamics","local","do","MCP",{"skillNo":120,"name":121,"nameZh":6,"description":122,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":123,"categories":124,"keywords":131,"publishedAt":31},"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",[125,128],{"categoryNo":126,"categoryName":127,"taxonomyType":98,"taxonomyTypeDesc":99},"01JBSEEDCAT000000000000003","演示文稿",{"categoryNo":129,"categoryName":130,"taxonomyType":98,"taxonomyTypeDesc":99},"01JBSEEDCAT000000000000008","测试与质量",[132,133,134,135,136,137,138,139,140,141,102,142,143,144,145],"review","visual","visual review","pages","web","false","iteration","take","check","slides","ui","screenshot","playwright","screenshots",{"skillNo":147,"name":148,"nameZh":6,"description":149,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":150,"categories":151,"keywords":152,"publishedAt":31},"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",[],[148,153,154,155,156,157,158,159],"setup","report","project","installation","project setup","issues","state",{"skillNo":161,"name":162,"nameZh":6,"description":163,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":164,"categories":165,"keywords":167,"publishedAt":31},"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",[166],{"categoryNo":96,"categoryName":97,"taxonomyType":98,"taxonomyTypeDesc":99},[162,168,80,169,170,171,28,27,172,173,174],"start issue","issue","ready","work on issue","work","work on","development",{"skillNo":176,"name":153,"nameZh":6,"description":177,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":178,"categories":179,"keywords":180,"publishedAt":31},"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",[],[153,155,116,181,157,182],"files","interactive"]