[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M7BZ3CVGHTF9X9CDCDQ946VF":3,"skill-same:01M7BZ3CVGHTF9X9CDCDQ946VF":45},{"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":19,"linkOnly":20,"markdownContent":21,"markdownBody":22,"frontMatter":23,"refName":24,"commitSha":25,"skillDirectory":26,"forksCount":27,"repositoryHtmlUrl":28,"repositoryHomepageUrl":6,"ownerHtmlUrl":29,"ownerBlogUrl":6,"ownerDescription":6,"updatedAt":30,"install":31,"resources":44},"01M7BZ3CVGHTF9X9CDCDQ946VF","file-organizer",null,"Intelligently organizes your files and folders across your computer by understanding context, finding duplicates, suggesting better structures, and automating cleanup tasks. Reduces cognitive load and keeps your digital workspace tidy without manual effort.","linyouxue\u002Fskill-repair-benchmark","linyouxue","https:\u002F\u002Favatars.githubusercontent.com\u002Fu\u002F216151464?v=4","01M7BJEVCXKD74KH6FG9CBVSQB","林宥学","01M7BJEVE02NP217V93BKZFC0J",0,"Apache-2.0","https:\u002F\u002Fgithub.com\u002Flinyouxue\u002Fskill-repair-benchmark\u002Fblob\u002Fmain\u002Fevaluation\u002Fresults\u002FSkillAxe\u002Ftasks\u002Forganize-messy-files\u002Frepaired_skill\u002Ffile-organizer\u002FSKILL.md",[],[],"2026-11-15 14:19:17",false,"---\nname: file-organizer\ndescription: Intelligently organizes your files and folders across your computer by understanding context, finding duplicates, suggesting better structures, and automating cleanup tasks. Reduces cognitive load and keeps your digital workspace tidy without manual effort.\n---\n\n# File Organizer\n\nThis skill acts as your personal organization assistant, helping you maintain a clean, logical file structure across your computer without the mental overhead of constant manual organization.\n\n## When to Use This Skill\n\n- Your Downloads folder is a chaotic mess\n- You can't find files because they're scattered everywhere\n- You have duplicate files taking up space\n- You're establishing a new folder structure for a project\n- You're cleaning up before archiving old projects\n\n## What This Skill Does\n\n1. **Analyzes Current Structure**: Reviews your folders and files to understand what you have\n2. **Finds Duplicates**: Identifies duplicate files across your system\n3. **Suggests Organization**: Proposes logical folder structures based on your content\n4. **Automates Cleanup**: Moves, renames, and organizes files with your approval (or by explicit user instruction)\n5. **Maintains Context**: Makes smart decisions based on file types, dates, and content\n6. **Reduces Clutter**: Identifies old files you probably don't need anymore\n\n## How to Use\n\n### From Your Home Directory\n\n```\ncd ~\n```\n\nThen run Claude Code and ask for help:\n\n```\nHelp me organize my Downloads folder\n```\n\n```\nFind duplicate files in my Documents folder\n```\n\n```\nReview my project directories and suggest improvements\n```\n\n### Specific Organization Tasks\n\n```\nOrganize these downloads into proper folders based on what they are\n```\n\n```\nFind duplicate files and help me decide which to keep\n```\n\n```\nClean up old files I haven't touched in 6+ months\n```\n\n```\nCreate a better folder structure for my [work\u002Fprojects\u002Fphotos\u002Fetc]\n```\n\n## Instructions\n\nWhen a user requests file organization help:\n\n### 1. Understand the Scope\n\nAsk clarifying questions **only when needed**:\n- Which directory needs organization?\n- Any files or folders to avoid?\n- Any rules (folder names, mapping rules, “must not rename”, etc.)?\n\n**Non-interactive exception (IMPORTANT)**\nIf the user provides **explicit target folders and rules** (e.g., “sort everything into exactly these 5 folders; don’t rename; nothing left out”), you should **not block on a separate approval loop**. Instead:\n- Restate the rules you will follow.\n- Proceed conservatively.\n- Perform strict post-move verification checks (see §7).\n\n### 2. Analyze Current State\n\nReview the target directory:\n```bash\n# Get overview of current structure\nls -la [target_directory]\n\n# Check file types and sizes\nfind [target_directory] -type f -exec file {} \\; | head -20\n\n# Identify largest files\ndu -sh [target_directory]\u002F* | sort -rh | head -20\n\n# Count file types\nfind [target_directory] -type f | sed 's\u002F.*\\.\u002F\u002F' | sort | uniq -c | sort -rn\n```\n\nSummarize findings:\n- Total files and folders\n- File type breakdown\n- Size distribution\n- Date ranges\n- Obvious organization issues\n\n### 3. Identify Organization Patterns\n\nDefault groupings:\n\n**By Type**:\n- Documents (PDFs, DOCX, TXT)\n- Images (JPG, PNG, SVG)\n- Videos (MP4, MOV)\n- Archives (ZIP, TAR, DMG)\n- Code\u002FProjects (directories with code)\n- Spreadsheets (XLSX, CSV)\n- Presentations (PPTX, KEY)\n\n**By Purpose**:\n- Work vs. Personal\n- Active vs. Archive\n- Project-specific\n- Reference materials\n- Temporary\u002Fscratch files\n\n**By Date**:\n- Current year\u002Fmonth\n- Previous years\n- Very old (archive candidates)\n\n**By Content \u002F Subject (for strict topic sorting tasks)**\nWhen the user asks for subject\u002Ftopic grouping (e.g., “put each document into exactly one of these subject folders based on content”), you must do **content-aware classification** instead of relying on extensions or filenames.\n\nRecommended approach:\n- **Extract a small, high-signal snippet** per file (title + abstract \u002F first 1–2 pages for PDFs; first few slides for PPTX; main body for DOCX).\n- **Score subjects with positive and negative keywords**, and include “tie-break” rules.\n- **Avoid a “catch-all by default” too early**. Use catch-all (the last category) only after checking the others.\n- **Flag low-confidence cases** for a second-pass deeper extraction.\n\nPractical extraction tools (no installs required):\n```bash\n# PDFs\npdftotext -f 1 -l 2 \"file.pdf\" -\n\n# DOCX\u002FPPTX: treat as zip and extract XML text (works without pandoc)\npython3 - \u003C\u003C'PY'\nimport zipfile, sys, re\nfrom xml.etree import ElementTree as ET\np=sys.argv[1]\nwith zipfile.ZipFile(p) as z:\n    if p.lower().endswith('.docx'):\n        xml=z.read('word\u002Fdocument.xml')\n        root=ET.fromstring(xml)\n        txt='\\n'.join(el.text for el in root.iter() if el.tag.endswith('}t') and el.text)\n    else:\n        slides=sorted(n for n in z.namelist() if n.startswith('ppt\u002Fslides\u002Fslide') and n.endswith('.xml'))\n        parts=[]\n        for n in slides[:3]:\n            root=ET.fromstring(z.read(n))\n            parts += [el.text for el in root.iter() if el.tag.endswith('}t') and el.text]\n        txt='\\n'.join(parts)\nprint(re.sub(r'\\s+',' ',txt)[:2000])\nPY file.docx\n```\n\n### 4. Find Duplicates\n\nWhen requested, search for duplicates:\n```bash\n# Find exact duplicates by hash\nfind [directory] -type f -exec md5 {} \\; | sort | uniq -d\n\n# Find files with same name\nfind [directory] -type f -printf '%f\\n' | sort | uniq -d\n\n# Find similar-sized files\nfind [directory] -type f -printf '%s %p\\n' | sort -n\n```\n\nFor each set of duplicates:\n- Show all file paths\n- Display sizes and modification dates\n- Recommend which to keep\n- **Always ask for confirmation before deleting**\n\n### 5. Propose Organization Plan\n\nPresent a clear plan before making changes **unless** the user has already provided an explicit deterministic mapping\u002Fruleset.\n\n```markdown\n# Organization Plan for [Directory]\n\n## Current State\n- X files across Y folders\n- [Size] total\n- File types: [breakdown]\n- Issues: [list problems]\n\n## Proposed Structure\n\n[Directory]\u002F\n├── ...\n\n## Changes I'll Make\n1. Create new folders: ...\n2. Move files: ...\n\n## Files Needing Your Decision\n- ...\n```\n\n### 6. Execute Organization\n\nOrganize systematically:\n\n```bash\nmkdir -p \"path\u002Fto\u002Fnew\u002Ffolders\"\n\n# Move files with clear logging\nmv \"old\u002Fpath\u002Ffile.pdf\" \"new\u002Fpath\u002Ffile.pdf\"\n```\n\n**Important Rules**:\n- Do not rename or modify files unless explicitly requested\n- Handle filename conflicts gracefully (stop and ask; never overwrite silently)\n- Log all moves for potential undo\n\n### 7. Post-move Verification (MANDATORY for strict sorting tasks)\n\nWhen the task has hard constraints (e.g., “every document must be in exactly one of N subject folders; nothing left out; no renames”), run checks that match those constraints.\n\n**A. Completeness & uniqueness**\n- Count source files before.\n- Count files across destination folders after.\n- Ensure each original basename appears exactly once.\n\n**B. No leftovers in source**\n- Ensure the staging folder (e.g., `papers\u002Fall`) contains none of the allowed file types.\n\n**C. No stray allowed files elsewhere (IMPORTANT)**\nIn strict benchmarks, the evaluator may treat *any* allowed extension anywhere under the working root as “unsorted\u002Fstray” (including files created by tool installs or caches).\n\nSo, avoid creating new `.pdf\u002F.docx\u002F.pptx` outside the target subject folders, and verify:\n```bash\n# Example pattern: search for allowed extensions under \u002Froot (or project root)\n# excluding the known source folder if applicable.\nfind \u002Froot -type f \\( -iname '*.pdf' -o -iname '*.docx' -o -iname '*.pptx' \\) \\\n  ! -path '\u002Froot\u002Fpapers\u002FLLM\u002F*' \\\n  ! -path '\u002Froot\u002Fpapers\u002Ftrapped_ion_and_qc\u002F*' \\\n  ! -path '\u002Froot\u002Fpapers\u002Fblack_hole\u002F*' \\\n  ! -path '\u002Froot\u002Fpapers\u002FDNA\u002F*' \\\n  ! -path '\u002Froot\u002Fpapers\u002Fmusic_history\u002F*'\n```\nIf this finds cache\u002Ftool\u002Ftemplate artifacts, remove them **only if they were created during your run and are not part of the user’s files** (or avoid the install step that created them).\n\n**D. Classification QA (spot-check + low-confidence pass)**\n- Re-extract text for borderline\u002Fshort documents and re-score.\n- For each folder, spot-check a few files to confirm topical alignment.\n\n### 8. Provide Summary and Maintenance Tips\n\nAfter organizing, report:\n- Folder counts\n- Any ambiguous files and how they were resolved\n- Verification results (what checks you ran)\n\n```markdown\n## What Changed\n- Created ...\n- Organized ...\n\n## Verification\n- Total moved: ...\n- No leftovers: ...\n- No stray allowed files elsewhere: ...\n```\n\n## Examples\n\n### Example 1: Organizing Downloads (From Justin Dielmann)\n\n**User**: \"My Downloads folder is a mess with 500+ files. Help me organize it.\"\n\n**Process**:\n1. Analyzes Downloads folder\n2. Finds patterns: work docs, personal photos, installers, random PDFs\n3. Proposes structure\n4. Asks for confirmation\n5. Moves files intelligently\n\n### Example 2: Finding and Removing Duplicates\n\n**User**: \"Find duplicate files in my Documents and help me decide which to keep.\"\n\n(…)\n\n## Pro Tips\n\n1. **Start Small**: Begin with one messy folder to build trust\n2. **Regular Maintenance**: Run weekly cleanup\n3. **Consistent Naming**: Use consistent naming where appropriate\n4. **Archive Aggressively**: Move old projects to Archive instead of deleting\n\n## Best Practices\n\n### Folder Naming\n- Use clear, descriptive names\n- Avoid spaces (use hyphens or underscores)\n\n### File Naming\n- Be descriptive\n- Avoid version clutter\n\n### When to Archive\n- Projects not touched in 6+ months\n- Completed work that might be referenced later\n","# File Organizer\n\nThis skill acts as your personal organization assistant, helping you maintain a clean, logical file structure across your computer without the mental overhead of constant manual organization.\n\n## When to Use This Skill\n\n- Your Downloads folder is a chaotic mess\n- You can't find files because they're scattered everywhere\n- You have duplicate files taking up space\n- You're establishing a new folder structure for a project\n- You're cleaning up before archiving old projects\n\n## What This Skill Does\n\n1. **Analyzes Current Structure**: Reviews your folders and files to understand what you have\n2. **Finds Duplicates**: Identifies duplicate files across your system\n3. **Suggests Organization**: Proposes logical folder structures based on your content\n4. **Automates Cleanup**: Moves, renames, and organizes files with your approval (or by explicit user instruction)\n5. **Maintains Context**: Makes smart decisions based on file types, dates, and content\n6. **Reduces Clutter**: Identifies old files you probably don't need anymore\n\n## How to Use\n\n### From Your Home Directory\n\n```\ncd ~\n```\n\nThen run Claude Code and ask for help:\n\n```\nHelp me organize my Downloads folder\n```\n\n```\nFind duplicate files in my Documents folder\n```\n\n```\nReview my project directories and suggest improvements\n```\n\n### Specific Organization Tasks\n\n```\nOrganize these downloads into proper folders based on what they are\n```\n\n```\nFind duplicate files and help me decide which to keep\n```\n\n```\nClean up old files I haven't touched in 6+ months\n```\n\n```\nCreate a better folder structure for my [work\u002Fprojects\u002Fphotos\u002Fetc]\n```\n\n## Instructions\n\nWhen a user requests file organization help:\n\n### 1. Understand the Scope\n\nAsk clarifying questions **only when needed**:\n- Which directory needs organization?\n- Any files or folders to avoid?\n- Any rules (folder names, mapping rules, “must not rename”, etc.)?\n\n**Non-interactive exception (IMPORTANT)**\nIf the user provides **explicit target folders and rules** (e.g., “sort everything into exactly these 5 folders; don’t rename; nothing left out”), you should **not block on a separate approval loop**. Instead:\n- Restate the rules you will follow.\n- Proceed conservatively.\n- Perform strict post-move verification checks (see §7).\n\n### 2. Analyze Current State\n\nReview the target directory:\n```bash\n# Get overview of current structure\nls -la [target_directory]\n\n# Check file types and sizes\nfind [target_directory] -type f -exec file {} \\; | head -20\n\n# Identify largest files\ndu -sh [target_directory]\u002F* | sort -rh | head -20\n\n# Count file types\nfind [target_directory] -type f | sed 's\u002F.*\\.\u002F\u002F' | sort | uniq -c | sort -rn\n```\n\nSummarize findings:\n- Total files and folders\n- File type breakdown\n- Size distribution\n- Date ranges\n- Obvious organization issues\n\n### 3. Identify Organization Patterns\n\nDefault groupings:\n\n**By Type**:\n- Documents (PDFs, DOCX, TXT)\n- Images (JPG, PNG, SVG)\n- Videos (MP4, MOV)\n- Archives (ZIP, TAR, DMG)\n- Code\u002FProjects (directories with code)\n- Spreadsheets (XLSX, CSV)\n- Presentations (PPTX, KEY)\n\n**By Purpose**:\n- Work vs. Personal\n- Active vs. Archive\n- Project-specific\n- Reference materials\n- Temporary\u002Fscratch files\n\n**By Date**:\n- Current year\u002Fmonth\n- Previous years\n- Very old (archive candidates)\n\n**By Content \u002F Subject (for strict topic sorting tasks)**\nWhen the user asks for subject\u002Ftopic grouping (e.g., “put each document into exactly one of these subject folders based on content”), you must do **content-aware classification** instead of relying on extensions or filenames.\n\nRecommended approach:\n- **Extract a small, high-signal snippet** per file (title + abstract \u002F first 1–2 pages for PDFs; first few slides for PPTX; main body for DOCX).\n- **Score subjects with positive and negative keywords**, and include “tie-break” rules.\n- **Avoid a “catch-all by default” too early**. Use catch-all (the last category) only after checking the others.\n- **Flag low-confidence cases** for a second-pass deeper extraction.\n\nPractical extraction tools (no installs required):\n```bash\n# PDFs\npdftotext -f 1 -l 2 \"file.pdf\" -\n\n# DOCX\u002FPPTX: treat as zip and extract XML text (works without pandoc)\npython3 - \u003C\u003C'PY'\nimport zipfile, sys, re\nfrom xml.etree import ElementTree as ET\np=sys.argv[1]\nwith zipfile.ZipFile(p) as z:\n    if p.lower().endswith('.docx'):\n        xml=z.read('word\u002Fdocument.xml')\n        root=ET.fromstring(xml)\n        txt='\\n'.join(el.text for el in root.iter() if el.tag.endswith('}t') and el.text)\n    else:\n        slides=sorted(n for n in z.namelist() if n.startswith('ppt\u002Fslides\u002Fslide') and n.endswith('.xml'))\n        parts=[]\n        for n in slides[:3]:\n            root=ET.fromstring(z.read(n))\n            parts += [el.text for el in root.iter() if el.tag.endswith('}t') and el.text]\n        txt='\\n'.join(parts)\nprint(re.sub(r'\\s+',' ',txt)[:2000])\nPY file.docx\n```\n\n### 4. Find Duplicates\n\nWhen requested, search for duplicates:\n```bash\n# Find exact duplicates by hash\nfind [directory] -type f -exec md5 {} \\; | sort | uniq -d\n\n# Find files with same name\nfind [directory] -type f -printf '%f\\n' | sort | uniq -d\n\n# Find similar-sized files\nfind [directory] -type f -printf '%s %p\\n' | sort -n\n```\n\nFor each set of duplicates:\n- Show all file paths\n- Display sizes and modification dates\n- Recommend which to keep\n- **Always ask for confirmation before deleting**\n\n### 5. Propose Organization Plan\n\nPresent a clear plan before making changes **unless** the user has already provided an explicit deterministic mapping\u002Fruleset.\n\n```markdown\n# Organization Plan for [Directory]\n\n## Current State\n- X files across Y folders\n- [Size] total\n- File types: [breakdown]\n- Issues: [list problems]\n\n## Proposed Structure\n\n[Directory]\u002F\n├── ...\n\n## Changes I'll Make\n1. Create new folders: ...\n2. Move files: ...\n\n## Files Needing Your Decision\n- ...\n```\n\n### 6. Execute Organization\n\nOrganize systematically:\n\n```bash\nmkdir -p \"path\u002Fto\u002Fnew\u002Ffolders\"\n\n# Move files with clear logging\nmv \"old\u002Fpath\u002Ffile.pdf\" \"new\u002Fpath\u002Ffile.pdf\"\n```\n\n**Important Rules**:\n- Do not rename or modify files unless explicitly requested\n- Handle filename conflicts gracefully (stop and ask; never overwrite silently)\n- Log all moves for potential undo\n\n### 7. Post-move Verification (MANDATORY for strict sorting tasks)\n\nWhen the task has hard constraints (e.g., “every document must be in exactly one of N subject folders; nothing left out; no renames”), run checks that match those constraints.\n\n**A. Completeness & uniqueness**\n- Count source files before.\n- Count files across destination folders after.\n- Ensure each original basename appears exactly once.\n\n**B. No leftovers in source**\n- Ensure the staging folder (e.g., `papers\u002Fall`) contains none of the allowed file types.\n\n**C. No stray allowed files elsewhere (IMPORTANT)**\nIn strict benchmarks, the evaluator may treat *any* allowed extension anywhere under the working root as “unsorted\u002Fstray” (including files created by tool installs or caches).\n\nSo, avoid creating new `.pdf\u002F.docx\u002F.pptx` outside the target subject folders, and verify:\n```bash\n# Example pattern: search for allowed extensions under \u002Froot (or project root)\n# excluding the known source folder if applicable.\nfind \u002Froot -type f \\( -iname '*.pdf' -o -iname '*.docx' -o -iname '*.pptx' \\) \\\n  ! -path '\u002Froot\u002Fpapers\u002FLLM\u002F*' \\\n  ! -path '\u002Froot\u002Fpapers\u002Ftrapped_ion_and_qc\u002F*' \\\n  ! -path '\u002Froot\u002Fpapers\u002Fblack_hole\u002F*' \\\n  ! -path '\u002Froot\u002Fpapers\u002FDNA\u002F*' \\\n  ! -path '\u002Froot\u002Fpapers\u002Fmusic_history\u002F*'\n```\nIf this finds cache\u002Ftool\u002Ftemplate artifacts, remove them **only if they were created during your run and are not part of the user’s files** (or avoid the install step that created them).\n\n**D. Classification QA (spot-check + low-confidence pass)**\n- Re-extract text for borderline\u002Fshort documents and re-score.\n- For each folder, spot-check a few files to confirm topical alignment.\n\n### 8. Provide Summary and Maintenance Tips\n\nAfter organizing, report:\n- Folder counts\n- Any ambiguous files and how they were resolved\n- Verification results (what checks you ran)\n\n```markdown\n## What Changed\n- Created ...\n- Organized ...\n\n## Verification\n- Total moved: ...\n- No leftovers: ...\n- No stray allowed files elsewhere: ...\n```\n\n## Examples\n\n### Example 1: Organizing Downloads (From Justin Dielmann)\n\n**User**: \"My Downloads folder is a mess with 500+ files. Help me organize it.\"\n\n**Process**:\n1. Analyzes Downloads folder\n2. Finds patterns: work docs, personal photos, installers, random PDFs\n3. Proposes structure\n4. Asks for confirmation\n5. Moves files intelligently\n\n### Example 2: Finding and Removing Duplicates\n\n**User**: \"Find duplicate files in my Documents and help me decide which to keep.\"\n\n(…)\n\n## Pro Tips\n\n1. **Start Small**: Begin with one messy folder to build trust\n2. **Regular Maintenance**: Run weekly cleanup\n3. **Consistent Naming**: Use consistent naming where appropriate\n4. **Archive Aggressively**: Move old projects to Archive instead of deleting\n\n## Best Practices\n\n### Folder Naming\n- Use clear, descriptive names\n- Avoid spaces (use hyphens or underscores)\n\n### File Naming\n- Be descriptive\n- Avoid version clutter\n\n### When to Archive\n- Projects not touched in 6+ months\n- Completed work that might be referenced later\n",{"name":5,"description":7},"main","cdcb6d230f3b15c3c33f8a2bdd16439f43602cbe","evaluation\u002Fresults\u002FSkillAxe\u002Ftasks\u002Forganize-messy-files\u002Frepaired_skill\u002Ffile-organizer",1,"https:\u002F\u002Fgithub.com\u002Flinyouxue\u002Fskill-repair-benchmark","https:\u002F\u002Fgithub.com\u002Flinyouxue","2026-11-14 20:28:35",{"source":8,"skillName":5,"commands":32,"prompt":42,"zipAvailable":43},[33,36,39],{"tool":34,"command":35},"npx","npx skills add linyouxue\u002Fskill-repair-benchmark --skill file-organizer",{"tool":37,"command":38},"bunx","bunx skills add linyouxue\u002Fskill-repair-benchmark --skill file-organizer",{"tool":40,"command":41},"pnpm","pnpm dlx skills add linyouxue\u002Fskill-repair-benchmark --skill file-organizer","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002Flinyouxue\u002Fskill-repair-benchmark\u002Fblob\u002Fmain\u002Fevaluation\u002Fresults\u002FSkillAxe\u002Ftasks\u002Forganize-messy-files\u002Frepaired_skill\u002Ffile-organizer\u002FSKILL.md",true,[],[46,53,60,67,72,77],{"skillNo":47,"name":48,"nameZh":6,"description":49,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":50,"categories":51,"keywords":52,"publishedAt":19},"01M7E1HGVRY73NBJ022CJG13X6","video-frame-extraction","Extract frames from video files and save them as images using OpenCV","https:\u002F\u002Fgithub.com\u002Flinyouxue\u002Fskill-repair-benchmark\u002Fblob\u002Fmain\u002Fjpg-ocr-stat\u002Fresult\u002Fskilltta-claude4.7\u002Fgroup_03\u002Frun_03\u002Finputs\u002Fskills\u002Fvideo-frame-extraction\u002FSKILL.md",[],[],{"skillNo":54,"name":55,"nameZh":6,"description":56,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":57,"categories":58,"keywords":59,"publishedAt":19},"01M7E1HAG5R7CJ9C8NYJS771MB","openai-vision","Analyze images and multi-frame sequences using OpenAI GPT vision models","https:\u002F\u002Fgithub.com\u002Flinyouxue\u002Fskill-repair-benchmark\u002Fblob\u002Fmain\u002Fjpg-ocr-stat\u002Fresult\u002Fskilltta-claude4.7\u002Fgroup_03\u002Frun_03\u002Finputs\u002Fskills\u002Fopenai-vision\u002FSKILL.md",[],[],{"skillNo":61,"name":62,"nameZh":6,"description":63,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":64,"categories":65,"keywords":66,"publishedAt":19},"01M7E1H7DADKB6QBWKC2KQ63SZ","image-ocr","Extract text content from images using Tesseract OCR via Python, including structured field extraction from receipts and forms","https:\u002F\u002Fgithub.com\u002Flinyouxue\u002Fskill-repair-benchmark\u002Fblob\u002Fmain\u002Fjpg-ocr-stat\u002Fresult\u002Fskilltta-claude4.7\u002Fgroup_03\u002Frun_03\u002Finputs\u002Fskills\u002Fimage-ocr\u002FSKILL.md",[],[],{"skillNo":68,"name":48,"nameZh":6,"description":49,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":69,"categories":70,"keywords":71,"publishedAt":19},"01M7E1H0WBNT43TENGQY7AVZHD","https:\u002F\u002Fgithub.com\u002Flinyouxue\u002Fskill-repair-benchmark\u002Fblob\u002Fmain\u002Fjpg-ocr-stat\u002Fresult\u002Fskilltta-claude4.7\u002Fgroup_03\u002Frun_02\u002Finputs\u002Fskills\u002Fvideo-frame-extraction\u002FSKILL.md",[],[],{"skillNo":73,"name":55,"nameZh":6,"description":56,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":74,"categories":75,"keywords":76,"publishedAt":19},"01M7E1GTC7D4N4Q2EF03875J9E","https:\u002F\u002Fgithub.com\u002Flinyouxue\u002Fskill-repair-benchmark\u002Fblob\u002Fmain\u002Fjpg-ocr-stat\u002Fresult\u002Fskilltta-claude4.7\u002Fgroup_03\u002Frun_02\u002Finputs\u002Fskills\u002Fopenai-vision\u002FSKILL.md",[],[],{"skillNo":78,"name":62,"nameZh":6,"description":63,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":79,"categories":80,"keywords":81,"publishedAt":19},"01M7E1GQ92CWFMGH53KSSE4WER","https:\u002F\u002Fgithub.com\u002Flinyouxue\u002Fskill-repair-benchmark\u002Fblob\u002Fmain\u002Fjpg-ocr-stat\u002Fresult\u002Fskilltta-claude4.7\u002Fgroup_03\u002Frun_02\u002Finputs\u002Fskills\u002Fimage-ocr\u002FSKILL.md",[],[]]