[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M7BTMPHQNPP87400MB3W5CFQ":3,"skill-same:01M7BTMPHQNPP87400MB3W5CFQ":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},"01M7BTMPHQNPP87400MB3W5CFQ","file-organizer",null,"Organize large mixed file sets into a required folder structure by *document content*, with verification that every file is placed exactly once and no strays remain.","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\u002FMMG2Skill-GPT52-Gold31-20260923\u002Fsubmission\u002Ftasks\u002Forganize-messy-files\u002Fskills\u002Ffile-organizer\u002FSKILL.md",[],[],"2026-11-15 14:19:17",false,"---\nname: file-organizer\ndescription: Organize large mixed file sets into a required folder structure by *document\n  content*, with verification that every file is placed exactly once and no strays\n  remain.\n---\n\n## Steps\n1. **Inventory and freeze scope**\n   - Locate the target directory; count all candidate files and record extensions.  \n   - Capture a manifest (paths + counts) before moving anything.\n2. **Create the required folder structure (exact names)**\n   - Create destination folders (e.g., `LLM\u002F`, `trapped_ion_and_qc\u002F`, `black_hole\u002F`, `DNA\u002F`, `music_history\u002F`) under the specified root.\n3. **Extract content text in a way suitable for classification**\n   - Prefer a **single Python driver script** for batch processing (avoids fragile shell pipelines\u002Fquoting).  \n   - For **PDFs**: extract more than just the first page when needed (start with first ~2–5 pages; escalate if low confidence).  \n   - For **DOCX\u002FPPTX**: extract text via `pandoc\u002Fmarkitdown` if available; otherwise fallback to ZIP\u002FXML extraction (OOXML).\n4. **Classify with confidence + escalation (don’t “dump” unknowns)**\n   - Compute per-subject scores using subject-specific signals (keywords\u002Fphrases), but treat results as **provisional**.  \n   - If **all scores are 0** or the best score is weak\u002Fclose to the runner-up:\n     - Re-extract with **more text** (more PDF pages; include PPTX notes; include additional DOCX parts).  \n     - If still ambiguous, mark the file for **manual sampling** (e.g., print title\u002Fabstract lines) and only then assign.  \n   - Only use “last folder” logic *after* deeper extraction\u002Fmanual sampling shows no evidence for the other four subjects; keep a short review log so decisions are auditable.\n5. **Move each file exactly once (no renaming, no content edits)**\n   - Move (not copy) into exactly one destination folder; handle name collisions by aborting and asking (don’t rename silently).\n6. **Post-move verification (must-pass checks)**\n   - Recount totals under the new root equals the original manifest count.  \n   - Confirm **no stray files** remain outside the five folders.  \n   - Optionally remove the now-empty source folder only after counts match.\n## Expected Result\nAll documents are placed into exactly one of the five required folders based on content, with a clear verification that totals match and nothing is left out or misplaced due to “unknown → default” shortcuts.\n","## Steps\n1. **Inventory and freeze scope**\n   - Locate the target directory; count all candidate files and record extensions.  \n   - Capture a manifest (paths + counts) before moving anything.\n2. **Create the required folder structure (exact names)**\n   - Create destination folders (e.g., `LLM\u002F`, `trapped_ion_and_qc\u002F`, `black_hole\u002F`, `DNA\u002F`, `music_history\u002F`) under the specified root.\n3. **Extract content text in a way suitable for classification**\n   - Prefer a **single Python driver script** for batch processing (avoids fragile shell pipelines\u002Fquoting).  \n   - For **PDFs**: extract more than just the first page when needed (start with first ~2–5 pages; escalate if low confidence).  \n   - For **DOCX\u002FPPTX**: extract text via `pandoc\u002Fmarkitdown` if available; otherwise fallback to ZIP\u002FXML extraction (OOXML).\n4. **Classify with confidence + escalation (don’t “dump” unknowns)**\n   - Compute per-subject scores using subject-specific signals (keywords\u002Fphrases), but treat results as **provisional**.  \n   - If **all scores are 0** or the best score is weak\u002Fclose to the runner-up:\n     - Re-extract with **more text** (more PDF pages; include PPTX notes; include additional DOCX parts).  \n     - If still ambiguous, mark the file for **manual sampling** (e.g., print title\u002Fabstract lines) and only then assign.  \n   - Only use “last folder” logic *after* deeper extraction\u002Fmanual sampling shows no evidence for the other four subjects; keep a short review log so decisions are auditable.\n5. **Move each file exactly once (no renaming, no content edits)**\n   - Move (not copy) into exactly one destination folder; handle name collisions by aborting and asking (don’t rename silently).\n6. **Post-move verification (must-pass checks)**\n   - Recount totals under the new root equals the original manifest count.  \n   - Confirm **no stray files** remain outside the five folders.  \n   - Optionally remove the now-empty source folder only after counts match.\n## Expected Result\nAll documents are placed into exactly one of the five required folders based on content, with a clear verification that totals match and nothing is left out or misplaced due to “unknown → default” shortcuts.\n",{"name":5,"description":7},"main","cdcb6d230f3b15c3c33f8a2bdd16439f43602cbe","evaluation\u002Fresults\u002FMMG2Skill-GPT52-Gold31-20260923\u002Fsubmission\u002Ftasks\u002Forganize-messy-files\u002Fskills\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\u002FMMG2Skill-GPT52-Gold31-20260923\u002Fsubmission\u002Ftasks\u002Forganize-messy-files\u002Fskills\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",[],[]]