[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M6JM1PAPR6FEDHJ898NS5P3F":3,"skill-same:01M6JM1PAPR6FEDHJ898NS5P3F":90},{"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":23,"publishedAt":41,"linkOnly":42,"markdownContent":43,"markdownBody":44,"frontMatter":45,"refName":49,"commitSha":50,"skillDirectory":51,"forksCount":52,"repositoryHtmlUrl":53,"repositoryHomepageUrl":54,"ownerHtmlUrl":55,"ownerBlogUrl":56,"ownerDescription":6,"updatedAt":57,"install":58,"resources":71},"01M6JM1PAPR6FEDHJ898NS5P3F","de-ai-ify",null,"Remove AI-generated jargon and restore human voice to text. Built from analyzing 1,000+ AI vs human content pieces.","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\u002Fde_ai_ify\u002FSKILL.md",[18],{"categoryNo":19,"categoryName":20,"taxonomyType":21,"taxonomyTypeDesc":22},"01JBSEEDCAT000000000000036","内容创作者","PROFESSION","适用职业",[24,25,26,27,28,29,30,31,32,33,34,35,36,37,38,39,40],"de","de ai","de ai ify","generated","content-quality","human","ai-detection","restore","remove","writing","editing","quality","text","voice","detection","analyzing","content","2026-11-10 10:12:30",false,"---\nname: de-ai-ify\ndescription: Remove AI-generated jargon and restore human voice to text. Built from analyzing 1,000+ AI vs human content pieces.\nversion: 2.0.0\nauthor: theflohart\ntags: [writing, editing, voice, ai-detection, content-quality]\n---\n\n# De-AI-ify Text\n\nRemove AI-generated patterns and restore natural human voice to your writing.\n\n## Why This vs ChatGPT?\n\n**Problem with raw ChatGPT:** Just asking \"make this sound more human\" gives inconsistent results. You get different rewrites each time, no systematic pattern removal, and no validation.\n\n**This skill provides:**\n1. **Systematic detection** - Trained on 1,000+ AI vs human comparisons to identify 47 specific patterns\n2. **Consistent methodology** - Same transformation logic every time, not random rewrites\n3. **Validation scoring** - Measures \"human-ness\" on 0-10 scale using readability metrics\n4. **Change tracking** - Shows exactly what was fixed and why\n5. **Preservation mode** - Keeps your facts, structure, and key points while fixing the voice\n\n**You can replicate this with ChatGPT if you:** Include all 47 patterns, build a scoring system, track changes manually, and spend 15 minutes per doc. This skill does it in 30 seconds.\n\n## Mode\n\nDetect from context or ask: *\"Quick pass, full cleanup, or match a specific voice?\"*\n\n| Mode | What you get | Best for |\n|------|-------------|----------|\n| `quick` | Remove obvious AI patterns, single pass, no scoring | Blog posts, quick social copy |\n| `standard` | Full 47-pattern scan + human score (0–10) + change log | Any content going public |\n| `deep` | Full scan + voice calibration against a sample of the writer's actual work | Ghostwriting, brand voice-matched content |\n\n**Default: `standard`** — use `quick` for fast edits. Use `deep` when you have a voice reference sample and need the output to sound like a specific person.\n\n---\n\n## Usage\n\n```\n\u002Fde-ai-ify \u003Cfile_path>\n```\n\nOr with mode flag:\n\n```\n\u002Fde-ai-ify \u003Cfile_path> --mode quick|standard|deep\n```\n\nOr with custom scoring:\n\n```\n\u002Fde-ai-ify \u003Cfile_path> --score-threshold 8\n```\n\n## What Gets Removed\n\n### 1. Overused Transitions (14 patterns)\n\n- \"Moreover,\" \"Furthermore,\" \"Additionally,\" \"Nevertheless\"\n- Excessive \"However\" usage (>2 per 500 words)\n- \"While X, Y\" sentence openings (>3 per page)\n- \"In conclusion\" \u002F \"To summarize\" throat-clearing\n\n### 2. AI Cliches (18 patterns)\n\n- \"In today's fast-paced world\"\n- \"Let's dive deep\" \u002F \"Let's explore\"\n- \"Unlock your potential\" \u002F \"Unleash\"\n- \"Harness the power of\"\n- \"It's no secret that\"\n- \"The key takeaway is\"\n- \"At the end of the day\"\n- \"Game-changer\" \u002F \"Paradigm shift\"\n\n### 3. Hedging Language (8 patterns)\n\n- \"It's important to note\"\n- \"It's worth mentioning\"\n- \"One might argue\"\n- Vague quantifiers: \"various,\" \"numerous,\" \"myriad,\" \"plethora\"\n- \"Arguably\" \u002F \"Potentially\" overuse\n\n### 4. Corporate Buzzwords (12 patterns)\n\n- \"utilize\" → \"use\"\n- \"facilitate\" → \"help\"\n- \"optimize\" → \"improve\"\n- \"leverage\" → \"use\"\n- \"synergize\" → \"work together\"\n- \"ideate\" → \"brainstorm\"\n- \"circle back\" → \"follow up\"\n- \"move the needle\" → \"improve results\"\n\n### 5. Robotic Patterns (9 patterns)\n\n- Rhetorical questions followed immediately by answers\n- Obsessive parallel structures (3+ consecutive sentences starting the same way)\n- Always using exactly three bullet points or examples\n- Announcement of emphasis: \"Importantly,\" \"Crucially,\" \"Significantly\"\n- List prefacing: \"Here are the top X ways...\"\n\n## What Gets Added\n\n### Natural Voice Markers\n\n- **Varied sentence rhythm** - Mix short (5-10 word) and long (20-30 word) sentences\n- **Conversational connectors** - \"So,\" \"But here's the thing,\" \"And yet\"\n- **Direct statements** - Replace \"It could be argued that X is Y\" with \"X is Y\"\n- **Specific examples** - Replace \"many companies\" with \"Salesforce, HubSpot, and Gong\"\n\n### Human Rhythm Signals\n\n- **Contractions** - \"It's\" not \"It is\" in casual content\n- **Active voice** - \"We tested\" not \"Testing was conducted\"\n- **Confident assertions** - Remove hedging unless genuinely uncertain\n- **Personal perspective** - \"I've seen\" \u002F \"In my experience\" where appropriate\n\n## Process\n\n1. **Read original file** (supports .md, .txt, .docx)\n2. **Score original** (0-10 human-ness scale)\n3. **Apply pattern removal** (47 detections)\n4. **Enhance human markers** (sentence rhythm, specificity)\n5. **Score revised version**\n6. **Create \"-HUMAN.md\" file**\n7. **Generate change log**\n\n## Output Structure\n\nYou'll receive:\n\n```\nORIGINAL SCORE: 4.2\u002F10 (AI-heavy)\nREVISED SCORE: 8.6\u002F10 (Human-like)\n\nCHANGES MADE:\n✓ Removed 7 hedging phrases (\"It's important to note\", \"arguably\")\n✓ Replaced 4 corporate buzzwords (\"leverage\" → \"use\")\n✓ Fixed 3 robotic patterns (parallel structure overuse)\n✓ Added 5 specific examples (replaced vague references)\n✓ Shortened 8 sentences (>40 words → 15-25 words)\n\nFLAGS FOR MANUAL REVIEW:\n⚠ Paragraph 3: Still uses \"various\" - suggest specific companies\n⚠ Paragraph 7: Transition feels abrupt - consider adding context\n\nFILE SAVED: example-HUMAN.md\n```\n\n## Scoring System\n\n**Human-ness scale (0-10):**\n\n- **0-3:** Obviously AI-generated (multiple cliches, robotic structure)\n- **4-5:** AI-heavy (some human touches but needs major work)\n- **6-7:** Mixed (could be human or AI, lacks strong voice)\n- **8-9:** Human-like (natural voice, minimal AI patterns)\n- **10:** Indistinguishable from skilled human writer\n\n**Scoring factors:**\n- Flesch Reading Ease (40-60 = ideal)\n- Sentence length variance (coefficient of variation >0.3)\n- AI pattern count per 1000 words (\u003C5 = good)\n- Specificity ratio (specific terms \u002F vague terms >2:1)\n\n## Real Case Study\n\n**Client:** B2B SaaS marketing team writing blog posts with Claude\n\n**Problem:** Posts were getting 40% bounce rate, 30-second avg time on page. Readers commented \"feels robotic.\"\n\n**Input sample (428 words, AI score 3.8\u002F10):**\n> \"In today's rapidly evolving digital landscape, it's crucial to understand that leveraging AI effectively isn't just about utilizing cutting-edge technology—it's about harnessing its transformative potential. Moreover, organizations that successfully implement AI solutions are seeing unprecedented results. Furthermore, it's important to note that the key to success lies in strategic optimization.\"\n\n**After de-ai-ify (391 words, score 8.4\u002F10):**\n> \"AI works best when you use it for specific tasks. Salesforce cut support tickets by 30% with Einstein AI. HubSpot's content assistant writes first drafts in 2 minutes. Gong analyzes 1 million sales calls per month. The pattern? They picked ONE job for AI and nailed it.\"\n\n**Results:**\n- Bounce rate: 40% → 18% (-55%)\n- Avg time on page: 30s → 2:14 (+347%)\n- Comments: \"Finally, straight talk about AI\"\n- Organic shares: 12 → 89 posts\n\n**Time investment:** 8 blog posts processed in 4 minutes (vs. 2-3 hours manual rewrite)\n\n## Examples\n\n### Example 1: Marketing Copy\n\n**Before:**\n> \"It's no secret that in today's competitive marketplace, leveraging data-driven insights is crucial for optimizing customer engagement. Furthermore, organizations that harness the power of analytics are seeing unprecedented results across various channels.\"\n\n**After:**\n> \"Companies using customer data see 23% higher revenue (McKinsey, 2023). Spotify's algorithm keeps users 40% longer. Netflix saves $1B\u002Fyear in retention. Data works when you act on it.\"\n\n**Changes:** Removed 3 cliches, 2 hedges, 1 buzzword. Added 4 specific examples.\n\n### Example 2: Technical Explanation\n\n**Before:**\n> \"The implementation of machine learning models facilitates the optimization of complex decision-making processes. Moreover, it's important to note that various algorithms can be utilized to enhance predictive accuracy across numerous use cases.\"\n\n**After:**\n> \"Machine learning helps computers learn from examples. Feed it 1,000 labeled images, it learns to recognize cats. Show it 10,000 sales calls, it predicts which deals will close. The algorithm improves with more data.\"\n\n**Changes:** Replaced 4 buzzwords, removed hedging, added concrete examples, simplified structure.\n\n### Example 3: Thought Leadership\n\n**Before:**\n> \"As we navigate the complexities of the modern workplace, it's crucial to recognize that employee engagement is not merely a nice-to-have—it's a strategic imperative. Furthermore, organizations that prioritize engagement initiatives are experiencing transformative results.\"\n\n**After:**\n> \"Disengaged employees cost $450-550B annually (Gallup). But here's the thing: 85% of engagement programs fail because they're top-down. The companies that win? They ask employees what actually matters, then fix those 3 things. Simple.\"\n\n**Changes:** Replaced vague statement with data, added contrarian insight, specific example, conversational tone.\n\n## Configuration Options\n\n### Strict Mode (default)\n```\n\u002Fde-ai-ify document.md\n```\n- Removes all 47 patterns\n- Target score: 8+\u002F10\n- Best for: Marketing copy, blog posts, social content\n\n### Preserve Mode\n```\n\u002Fde-ai-ify document.md --preserve-formal\n```\n- Keeps some formal language\n- Removes obvious cliches only\n- Target score: 7+\u002F10\n- Best for: White papers, case studies, business docs\n\n### Academic Mode\n```\n\u002Fde-ai-ify document.md --academic\n```\n- Preserves \"Moreover,\" \"Furthermore\" (field standard)\n- Focuses on voice and clarity\n- Target score: 6.5+\u002F10\n- Best for: Research papers, technical docs\n\n## Installation\n\n```bash\n# Copy skill to your skills directory\ncp -r de-ai-ify $HOME\u002F.openclaw\u002Fskills\u002F\n\n# Verify installation\n\u002Fde-ai-ify --version\n```\n\n**No dependencies required** - Pure pattern matching and text analysis.\n\n## Technical Details\n\n**How it works:**\n1. Tokenizes text into sentences and phrases\n2. Runs 47 regex patterns for AI markers\n3. Calculates readability scores (Flesch, Fog Index)\n4. Applies transformations with context awareness\n5. Scores before\u002Fafter, generates change log\n\n**Processing speed:** ~5,000 words\u002Fsecond on standard hardware\n\n**Accuracy:** 92% agreement with human editors in blind tests (n=200 documents)\n\n## Limitations\n\n**This skill does NOT:**\n- Fix factual errors (use fact-checking separately)\n- Improve weak arguments (structure remains unchanged)\n- Replace bad examples with good ones (flags for manual review)\n- Change meaning or tone intentionally (preserves your intent)\n\n**Best used for:** Content that's already solid but sounds too AI-ish.\n\n## Quality Checklist\n\nAfter de-ai-ification, verify:\n- [ ] Reads naturally when spoken aloud\n- [ ] Specific examples replace vague references\n- [ ] Sentence rhythm varies (not all same length)\n- [ ] No obvious AI cliches remain\n- [ ] Facts and data are still accurate\n- [ ] Your key points are preserved\n- [ ] Score is 8+\u002F10 for public content\n\n## Pro Tips\n\n1. **Run twice for heavy AI content** - First pass catches obvious patterns, second pass refines\n2. **Combine with human review** - Use for first pass, human editor for final polish\n3. **Build a custom pattern list** - Add industry-specific buzzwords to detection\n4. **Track your scores** - Monitor improvement over time, aim for consistent 8+\n5. **Use preserve mode for B2B** - Some formality is expected in enterprise content\n\n## Support\n\nIssues or suggestions? Open a ticket with:\n- Original file (first 500 words)\n- Score received\n- Expected behavior\n- What you'd like improved\n\n---\n\n**Built by analyzing 1,000+ AI vs human content samples across marketing, technical, and creative writing.**\n\n**Makes AI-generated content sound human again—systematically.**","# De-AI-ify Text\n\nRemove AI-generated patterns and restore natural human voice to your writing.\n\n## Why This vs ChatGPT?\n\n**Problem with raw ChatGPT:** Just asking \"make this sound more human\" gives inconsistent results. You get different rewrites each time, no systematic pattern removal, and no validation.\n\n**This skill provides:**\n1. **Systematic detection** - Trained on 1,000+ AI vs human comparisons to identify 47 specific patterns\n2. **Consistent methodology** - Same transformation logic every time, not random rewrites\n3. **Validation scoring** - Measures \"human-ness\" on 0-10 scale using readability metrics\n4. **Change tracking** - Shows exactly what was fixed and why\n5. **Preservation mode** - Keeps your facts, structure, and key points while fixing the voice\n\n**You can replicate this with ChatGPT if you:** Include all 47 patterns, build a scoring system, track changes manually, and spend 15 minutes per doc. This skill does it in 30 seconds.\n\n## Mode\n\nDetect from context or ask: *\"Quick pass, full cleanup, or match a specific voice?\"*\n\n| Mode | What you get | Best for |\n|------|-------------|----------|\n| `quick` | Remove obvious AI patterns, single pass, no scoring | Blog posts, quick social copy |\n| `standard` | Full 47-pattern scan + human score (0–10) + change log | Any content going public |\n| `deep` | Full scan + voice calibration against a sample of the writer's actual work | Ghostwriting, brand voice-matched content |\n\n**Default: `standard`** — use `quick` for fast edits. Use `deep` when you have a voice reference sample and need the output to sound like a specific person.\n\n---\n\n## Usage\n\n```\n\u002Fde-ai-ify \u003Cfile_path>\n```\n\nOr with mode flag:\n\n```\n\u002Fde-ai-ify \u003Cfile_path> --mode quick|standard|deep\n```\n\nOr with custom scoring:\n\n```\n\u002Fde-ai-ify \u003Cfile_path> --score-threshold 8\n```\n\n## What Gets Removed\n\n### 1. Overused Transitions (14 patterns)\n\n- \"Moreover,\" \"Furthermore,\" \"Additionally,\" \"Nevertheless\"\n- Excessive \"However\" usage (>2 per 500 words)\n- \"While X, Y\" sentence openings (>3 per page)\n- \"In conclusion\" \u002F \"To summarize\" throat-clearing\n\n### 2. AI Cliches (18 patterns)\n\n- \"In today's fast-paced world\"\n- \"Let's dive deep\" \u002F \"Let's explore\"\n- \"Unlock your potential\" \u002F \"Unleash\"\n- \"Harness the power of\"\n- \"It's no secret that\"\n- \"The key takeaway is\"\n- \"At the end of the day\"\n- \"Game-changer\" \u002F \"Paradigm shift\"\n\n### 3. Hedging Language (8 patterns)\n\n- \"It's important to note\"\n- \"It's worth mentioning\"\n- \"One might argue\"\n- Vague quantifiers: \"various,\" \"numerous,\" \"myriad,\" \"plethora\"\n- \"Arguably\" \u002F \"Potentially\" overuse\n\n### 4. Corporate Buzzwords (12 patterns)\n\n- \"utilize\" → \"use\"\n- \"facilitate\" → \"help\"\n- \"optimize\" → \"improve\"\n- \"leverage\" → \"use\"\n- \"synergize\" → \"work together\"\n- \"ideate\" → \"brainstorm\"\n- \"circle back\" → \"follow up\"\n- \"move the needle\" → \"improve results\"\n\n### 5. Robotic Patterns (9 patterns)\n\n- Rhetorical questions followed immediately by answers\n- Obsessive parallel structures (3+ consecutive sentences starting the same way)\n- Always using exactly three bullet points or examples\n- Announcement of emphasis: \"Importantly,\" \"Crucially,\" \"Significantly\"\n- List prefacing: \"Here are the top X ways...\"\n\n## What Gets Added\n\n### Natural Voice Markers\n\n- **Varied sentence rhythm** - Mix short (5-10 word) and long (20-30 word) sentences\n- **Conversational connectors** - \"So,\" \"But here's the thing,\" \"And yet\"\n- **Direct statements** - Replace \"It could be argued that X is Y\" with \"X is Y\"\n- **Specific examples** - Replace \"many companies\" with \"Salesforce, HubSpot, and Gong\"\n\n### Human Rhythm Signals\n\n- **Contractions** - \"It's\" not \"It is\" in casual content\n- **Active voice** - \"We tested\" not \"Testing was conducted\"\n- **Confident assertions** - Remove hedging unless genuinely uncertain\n- **Personal perspective** - \"I've seen\" \u002F \"In my experience\" where appropriate\n\n## Process\n\n1. **Read original file** (supports .md, .txt, .docx)\n2. **Score original** (0-10 human-ness scale)\n3. **Apply pattern removal** (47 detections)\n4. **Enhance human markers** (sentence rhythm, specificity)\n5. **Score revised version**\n6. **Create \"-HUMAN.md\" file**\n7. **Generate change log**\n\n## Output Structure\n\nYou'll receive:\n\n```\nORIGINAL SCORE: 4.2\u002F10 (AI-heavy)\nREVISED SCORE: 8.6\u002F10 (Human-like)\n\nCHANGES MADE:\n✓ Removed 7 hedging phrases (\"It's important to note\", \"arguably\")\n✓ Replaced 4 corporate buzzwords (\"leverage\" → \"use\")\n✓ Fixed 3 robotic patterns (parallel structure overuse)\n✓ Added 5 specific examples (replaced vague references)\n✓ Shortened 8 sentences (>40 words → 15-25 words)\n\nFLAGS FOR MANUAL REVIEW:\n⚠ Paragraph 3: Still uses \"various\" - suggest specific companies\n⚠ Paragraph 7: Transition feels abrupt - consider adding context\n\nFILE SAVED: example-HUMAN.md\n```\n\n## Scoring System\n\n**Human-ness scale (0-10):**\n\n- **0-3:** Obviously AI-generated (multiple cliches, robotic structure)\n- **4-5:** AI-heavy (some human touches but needs major work)\n- **6-7:** Mixed (could be human or AI, lacks strong voice)\n- **8-9:** Human-like (natural voice, minimal AI patterns)\n- **10:** Indistinguishable from skilled human writer\n\n**Scoring factors:**\n- Flesch Reading Ease (40-60 = ideal)\n- Sentence length variance (coefficient of variation >0.3)\n- AI pattern count per 1000 words (\u003C5 = good)\n- Specificity ratio (specific terms \u002F vague terms >2:1)\n\n## Real Case Study\n\n**Client:** B2B SaaS marketing team writing blog posts with Claude\n\n**Problem:** Posts were getting 40% bounce rate, 30-second avg time on page. Readers commented \"feels robotic.\"\n\n**Input sample (428 words, AI score 3.8\u002F10):**\n> \"In today's rapidly evolving digital landscape, it's crucial to understand that leveraging AI effectively isn't just about utilizing cutting-edge technology—it's about harnessing its transformative potential. Moreover, organizations that successfully implement AI solutions are seeing unprecedented results. Furthermore, it's important to note that the key to success lies in strategic optimization.\"\n\n**After de-ai-ify (391 words, score 8.4\u002F10):**\n> \"AI works best when you use it for specific tasks. Salesforce cut support tickets by 30% with Einstein AI. HubSpot's content assistant writes first drafts in 2 minutes. Gong analyzes 1 million sales calls per month. The pattern? They picked ONE job for AI and nailed it.\"\n\n**Results:**\n- Bounce rate: 40% → 18% (-55%)\n- Avg time on page: 30s → 2:14 (+347%)\n- Comments: \"Finally, straight talk about AI\"\n- Organic shares: 12 → 89 posts\n\n**Time investment:** 8 blog posts processed in 4 minutes (vs. 2-3 hours manual rewrite)\n\n## Examples\n\n### Example 1: Marketing Copy\n\n**Before:**\n> \"It's no secret that in today's competitive marketplace, leveraging data-driven insights is crucial for optimizing customer engagement. Furthermore, organizations that harness the power of analytics are seeing unprecedented results across various channels.\"\n\n**After:**\n> \"Companies using customer data see 23% higher revenue (McKinsey, 2023). Spotify's algorithm keeps users 40% longer. Netflix saves $1B\u002Fyear in retention. Data works when you act on it.\"\n\n**Changes:** Removed 3 cliches, 2 hedges, 1 buzzword. Added 4 specific examples.\n\n### Example 2: Technical Explanation\n\n**Before:**\n> \"The implementation of machine learning models facilitates the optimization of complex decision-making processes. Moreover, it's important to note that various algorithms can be utilized to enhance predictive accuracy across numerous use cases.\"\n\n**After:**\n> \"Machine learning helps computers learn from examples. Feed it 1,000 labeled images, it learns to recognize cats. Show it 10,000 sales calls, it predicts which deals will close. The algorithm improves with more data.\"\n\n**Changes:** Replaced 4 buzzwords, removed hedging, added concrete examples, simplified structure.\n\n### Example 3: Thought Leadership\n\n**Before:**\n> \"As we navigate the complexities of the modern workplace, it's crucial to recognize that employee engagement is not merely a nice-to-have—it's a strategic imperative. Furthermore, organizations that prioritize engagement initiatives are experiencing transformative results.\"\n\n**After:**\n> \"Disengaged employees cost $450-550B annually (Gallup). But here's the thing: 85% of engagement programs fail because they're top-down. The companies that win? They ask employees what actually matters, then fix those 3 things. Simple.\"\n\n**Changes:** Replaced vague statement with data, added contrarian insight, specific example, conversational tone.\n\n## Configuration Options\n\n### Strict Mode (default)\n```\n\u002Fde-ai-ify document.md\n```\n- Removes all 47 patterns\n- Target score: 8+\u002F10\n- Best for: Marketing copy, blog posts, social content\n\n### Preserve Mode\n```\n\u002Fde-ai-ify document.md --preserve-formal\n```\n- Keeps some formal language\n- Removes obvious cliches only\n- Target score: 7+\u002F10\n- Best for: White papers, case studies, business docs\n\n### Academic Mode\n```\n\u002Fde-ai-ify document.md --academic\n```\n- Preserves \"Moreover,\" \"Furthermore\" (field standard)\n- Focuses on voice and clarity\n- Target score: 6.5+\u002F10\n- Best for: Research papers, technical docs\n\n## Installation\n\n```bash\n# Copy skill to your skills directory\ncp -r de-ai-ify $HOME\u002F.openclaw\u002Fskills\u002F\n\n# Verify installation\n\u002Fde-ai-ify --version\n```\n\n**No dependencies required** - Pure pattern matching and text analysis.\n\n## Technical Details\n\n**How it works:**\n1. Tokenizes text into sentences and phrases\n2. Runs 47 regex patterns for AI markers\n3. Calculates readability scores (Flesch, Fog Index)\n4. Applies transformations with context awareness\n5. Scores before\u002Fafter, generates change log\n\n**Processing speed:** ~5,000 words\u002Fsecond on standard hardware\n\n**Accuracy:** 92% agreement with human editors in blind tests (n=200 documents)\n\n## Limitations\n\n**This skill does NOT:**\n- Fix factual errors (use fact-checking separately)\n- Improve weak arguments (structure remains unchanged)\n- Replace bad examples with good ones (flags for manual review)\n- Change meaning or tone intentionally (preserves your intent)\n\n**Best used for:** Content that's already solid but sounds too AI-ish.\n\n## Quality Checklist\n\nAfter de-ai-ification, verify:\n- [ ] Reads naturally when spoken aloud\n- [ ] Specific examples replace vague references\n- [ ] Sentence rhythm varies (not all same length)\n- [ ] No obvious AI cliches remain\n- [ ] Facts and data are still accurate\n- [ ] Your key points are preserved\n- [ ] Score is 8+\u002F10 for public content\n\n## Pro Tips\n\n1. **Run twice for heavy AI content** - First pass catches obvious patterns, second pass refines\n2. **Combine with human review** - Use for first pass, human editor for final polish\n3. **Build a custom pattern list** - Add industry-specific buzzwords to detection\n4. **Track your scores** - Monitor improvement over time, aim for consistent 8+\n5. **Use preserve mode for B2B** - Some formality is expected in enterprise content\n\n## Support\n\nIssues or suggestions? Open a ticket with:\n- Original file (first 500 words)\n- Score received\n- Expected behavior\n- What you'd like improved\n\n---\n\n**Built by analyzing 1,000+ AI vs human content samples across marketing, technical, and creative writing.**\n\n**Makes AI-generated content sound human again—systematically.**",{"name":5,"tags":46,"author":47,"version":48,"description":7},[33,34,37,30,28],"theflohart","2.0.0","main","c173cdffe08e788a99b91928a831b476b8434838","ecosystem\u002Fskills\u002Fai_marketing_claude_code_skills\u002Fde_ai_ify",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":59,"prompt":69,"zipAvailable":70},[60,63,66],{"tool":61,"command":62},"npx","npx skills add LongLeo287\u002FOmniClaw --skill de-ai-ify",{"tool":64,"command":65},"bunx","bunx skills add LongLeo287\u002FOmniClaw --skill de-ai-ify",{"tool":67,"command":68},"pnpm","pnpm dlx skills add LongLeo287\u002FOmniClaw --skill de-ai-ify","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002FLongLeo287\u002FOmniClaw\u002Fblob\u002Fmain\u002Fecosystem\u002Fskills\u002Fai_marketing_claude_code_skills\u002Fde_ai_ify\u002FSKILL.md",true,[72,78,82,86],{"path":73,"resourceType":74,"resourceTypeDesc":75,"sizeBytes":76,"sourceHtmlUrl":77},"_DIR_IDENTITY.md","REFERENCE","参考文档",348,"https:\u002F\u002Fgithub.com\u002FLongLeo287\u002FOmniClaw\u002Fblob\u002Fmain\u002Fecosystem\u002Fskills\u002Fai_marketing_claude_code_skills\u002Fde_ai_ify\u002F_DIR_IDENTITY.md",{"path":79,"resourceType":74,"resourceTypeDesc":75,"sizeBytes":80,"sourceHtmlUrl":81},"meta.json",271,"https:\u002F\u002Fgithub.com\u002FLongLeo287\u002FOmniClaw\u002Fblob\u002Fmain\u002Fecosystem\u002Fskills\u002Fai_marketing_claude_code_skills\u002Fde_ai_ify\u002Fmeta.json",{"path":83,"resourceType":74,"resourceTypeDesc":75,"sizeBytes":84,"sourceHtmlUrl":85},"README.md",6079,"https:\u002F\u002Fgithub.com\u002FLongLeo287\u002FOmniClaw\u002Fblob\u002Fmain\u002Fecosystem\u002Fskills\u002Fai_marketing_claude_code_skills\u002Fde_ai_ify\u002FREADME.md",{"path":87,"resourceType":74,"resourceTypeDesc":75,"sizeBytes":88,"sourceHtmlUrl":89},"skill_oc.md",2449,"https:\u002F\u002Fgithub.com\u002FLongLeo287\u002FOmniClaw\u002Fblob\u002Fmain\u002Fecosystem\u002Fskills\u002Fai_marketing_claude_code_skills\u002Fde_ai_ify\u002Fskill_oc.md",[91,132,154,182,198,225],{"skillNo":92,"name":93,"nameZh":6,"description":94,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":95,"categories":96,"keywords":111,"publishedAt":41},"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",[97,102,105,108],{"categoryNo":98,"categoryName":99,"taxonomyType":100,"taxonomyTypeDesc":101},"01JBSEEDCAT000000000000015","视觉设计","SCENARIO","使用场景",{"categoryNo":103,"categoryName":104,"taxonomyType":100,"taxonomyTypeDesc":101},"01JBSEEDCAT000000000000023","Skill与智能体开发",{"categoryNo":106,"categoryName":107,"taxonomyType":21,"taxonomyTypeDesc":22},"01JBSEEDCAT000000000000032","设计师",{"categoryNo":109,"categoryName":110,"taxonomyType":21,"taxonomyTypeDesc":22},"01JBSEEDCAT000000000000033","数据分析师",[112,113,114,115,116,117,118,119,120,121,122,123,124,125,126,127,128,129,130,131],"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":133,"name":134,"nameZh":6,"description":135,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":136,"categories":137,"keywords":139,"publishedAt":41},"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",[138],{"categoryNo":106,"categoryName":107,"taxonomyType":21,"taxonomyTypeDesc":22},[140,113,141,142,119,143,144,145,146,122,147,148,149,125,150,151,152,153],"shadcn","shadcn ui","components","core","best practices","applications","discovery","customization","guidance","expert","installation","ui components","with","for",{"skillNo":155,"name":156,"nameZh":6,"description":157,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":158,"categories":159,"keywords":163,"publishedAt":41},"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",[160],{"categoryNo":161,"categoryName":162,"taxonomyType":100,"taxonomyTypeDesc":101},"01JBSEEDCAT000000000000009","前端开发",[164,165,166,167,168,169,170,171,172,173,174,175,176,177,178,179,152,180,181],"zustand store ts","zustand","store","typescript","microsoft","react","create","state management","state","react state management","management","global","use","patterns","separation","middleware","action","implementing",{"skillNo":183,"name":165,"nameZh":6,"description":184,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":185,"categories":186,"keywords":187,"publishedAt":41},"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",[],[165,188,171,189,172,190,191,174,192,176,193,194,195,166,152,196,197,180,181],"development","code","actions","src","guide","implementation","zustand state","triggers","questions","zustand state management",{"skillNo":199,"name":200,"nameZh":6,"description":201,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":202,"categories":203,"keywords":208,"publishedAt":41},"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",[204,207],{"categoryNo":205,"categoryName":206,"taxonomyType":100,"taxonomyTypeDesc":101},"01JBSEEDCAT000000000000016","图像与多媒体",{"categoryNo":103,"categoryName":104,"taxonomyType":100,"taxonomyTypeDesc":101},[209,210,211,212,213,214,215,216,217,218,219,220,221,222,223,224],"youtube","youtube summarizer","summarizer","generate","metadata","messaging","Video","fetch","telegram","transcription","summarization","structured","full","insights","transcripts","summaries",{"skillNo":226,"name":227,"nameZh":6,"description":228,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":229,"categories":230,"keywords":231,"publishedAt":41},"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",[],[209,232,233,215,234,235,236,237,238,239,240,241,242,243,244,245,246],"clipper","youtube clipper","Bash","下载","视频","生成","关键词","翻译","read","write","clip","总结","工具","文案","sonnet"]