[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M7BKJGFPDCG31VCK4XVYW0PY":3,"skill-same:01M7BKJGFPDCG31VCK4XVYW0PY":55},{"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},"01M7BKJGFPDCG31VCK4XVYW0PY","13f-analyzer",null,"Analyze SEC 13F holdings (INFOTABLE) to compute a fund’s AUM, stock-holding count, quarter-over-quarter changes, and top holders of a given stock.","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\u002Fcontrolled-skill-repair-experiments\u002Fresult\u002Fmmg2skill-gpt5.2-xhigh\u002Ffinal\u002Fsingle-sec-financial-report-RI-001\u002Fskills\u002F13f-analyzer\u002FSKILL.md",[],[],"2026-11-15 14:19:17",false,"---\nname: 13f-analyzer\ndescription: Analyze SEC 13F holdings (INFOTABLE) to compute a fund’s AUM, stock-holding\n  count, quarter-over-quarter changes, and top holders of a given stock.\n---\n\n## Steps\n1. From the workspace root (the directory that contains `13f-analyzer\u002F`), verify inputs and helper scripts exist so you don’t waste time “finding” them:\n   - Data: `\u002Froot\u002F2025-q2\u002FINFOTABLE.tsv`, `\u002Froot\u002F2025-q2\u002FCOVERPAGE.tsv`, `\u002Froot\u002F2025-q3\u002FINFOTABLE.tsv`, `\u002Froot\u002F2025-q3\u002FCOVERPAGE.tsv`\n   - Scripts: `ls 13f-analyzer\u002Fscripts\u002F`\n2. To get one fund’s summary in a single quarter (AUM and stock count), run:\n   ```bash\n   python3 13f-analyzer\u002Fscripts\u002Fone_fund_analysis.py \\\n     --accession_number \u003CACCESSION_NUMBER> \\\n     --quarter 2025-q3\n   ```\n   Interpret the printed fields precisely:\n   - `Total AUM` = sum of `VALUE` across all rows for that accession number (use this for “AUM”).\n   - `Number of stock holdings` = row-count after the helper’s `TITLEOFCLASS` stock filter. When asked “how many stocks”, use this field (not `Total number of holdings`, not unique CUSIPs, not COVERPAGE totals).\n3. To compare a fund between quarters and get the biggest dollar-value increases (top buys), run:\n   ```bash\n   python3 13f-analyzer\u002Fscripts\u002Fone_fund_analysis.py \\\n     --quarter 2025-q3 \\\n     --accession_number \u003CQ3_ACCESSION_NUMBER> \\\n     --baseline_quarter 2025-q2 \\\n     --baseline_accession_number \u003CQ2_ACCESSION_NUMBER>\n   ```\n   For a request “ranked by dollar value increase”, take the required number of CUSIPs from the beginning of the helper’s `Top 10 Buys` section, preserving order (don’t re-rank by shares or % change). Verify you return exactly *k* unique CUSIP strings.\n4. To rank which funds hold a given stock CUSIP by notional value, first follow the helper’s file-path convention (it reads `\u002Froot\u002FINFOTABLE.tsv`, not `\u002Froot\u002F\u003Cquarter>\u002FINFOTABLE.tsv`):\n   ```bash\n   ln -sf \u002Froot\u002F2025-q3\u002FINFOTABLE.tsv \u002Froot\u002FINFOTABLE.tsv\n   python3 13f-analyzer\u002Fscripts\u002Fholding_analysis.py \\\n     --cusip \u003CCUSIP> \\\n     --quarter 2025-q3 \\\n     --topk 10\n   ```\n   The output is ranked by summed `VALUE` per `ACCESSION_NUMBER`. Convert the top accession numbers to manager names using `fuzzy-name-search`’s exact accession-number lookup.\n5. When the task requires a deliverable file, write the final numbers\u002Flists into **`\u002Froot\u002Fanswers.json`** (absolute path) using the required schema, and verify it exists (e.g., `ls -l \u002Froot\u002Fanswers.json`).\n\n## Expected Result\nYou can (a) extract a quarter’s fund AUM and stock-holding count from the helper’s printed summary, (b) extract top buy CUSIPs from the helper’s Q2→Q3 comparison output, (c) rank top holders of a CUSIP in Q3 and map accession numbers to manager names, and (d) populate `\u002Froot\u002Fanswers.json` with the required fields.\n","## Steps\n1. From the workspace root (the directory that contains `13f-analyzer\u002F`), verify inputs and helper scripts exist so you don’t waste time “finding” them:\n   - Data: `\u002Froot\u002F2025-q2\u002FINFOTABLE.tsv`, `\u002Froot\u002F2025-q2\u002FCOVERPAGE.tsv`, `\u002Froot\u002F2025-q3\u002FINFOTABLE.tsv`, `\u002Froot\u002F2025-q3\u002FCOVERPAGE.tsv`\n   - Scripts: `ls 13f-analyzer\u002Fscripts\u002F`\n2. To get one fund’s summary in a single quarter (AUM and stock count), run:\n   ```bash\n   python3 13f-analyzer\u002Fscripts\u002Fone_fund_analysis.py \\\n     --accession_number \u003CACCESSION_NUMBER> \\\n     --quarter 2025-q3\n   ```\n   Interpret the printed fields precisely:\n   - `Total AUM` = sum of `VALUE` across all rows for that accession number (use this for “AUM”).\n   - `Number of stock holdings` = row-count after the helper’s `TITLEOFCLASS` stock filter. When asked “how many stocks”, use this field (not `Total number of holdings`, not unique CUSIPs, not COVERPAGE totals).\n3. To compare a fund between quarters and get the biggest dollar-value increases (top buys), run:\n   ```bash\n   python3 13f-analyzer\u002Fscripts\u002Fone_fund_analysis.py \\\n     --quarter 2025-q3 \\\n     --accession_number \u003CQ3_ACCESSION_NUMBER> \\\n     --baseline_quarter 2025-q2 \\\n     --baseline_accession_number \u003CQ2_ACCESSION_NUMBER>\n   ```\n   For a request “ranked by dollar value increase”, take the required number of CUSIPs from the beginning of the helper’s `Top 10 Buys` section, preserving order (don’t re-rank by shares or % change). Verify you return exactly *k* unique CUSIP strings.\n4. To rank which funds hold a given stock CUSIP by notional value, first follow the helper’s file-path convention (it reads `\u002Froot\u002FINFOTABLE.tsv`, not `\u002Froot\u002F\u003Cquarter>\u002FINFOTABLE.tsv`):\n   ```bash\n   ln -sf \u002Froot\u002F2025-q3\u002FINFOTABLE.tsv \u002Froot\u002FINFOTABLE.tsv\n   python3 13f-analyzer\u002Fscripts\u002Fholding_analysis.py \\\n     --cusip \u003CCUSIP> \\\n     --quarter 2025-q3 \\\n     --topk 10\n   ```\n   The output is ranked by summed `VALUE` per `ACCESSION_NUMBER`. Convert the top accession numbers to manager names using `fuzzy-name-search`’s exact accession-number lookup.\n5. When the task requires a deliverable file, write the final numbers\u002Flists into **`\u002Froot\u002Fanswers.json`** (absolute path) using the required schema, and verify it exists (e.g., `ls -l \u002Froot\u002Fanswers.json`).\n\n## Expected Result\nYou can (a) extract a quarter’s fund AUM and stock-holding count from the helper’s printed summary, (b) extract top buy CUSIPs from the helper’s Q2→Q3 comparison output, (c) rank top holders of a CUSIP in Q3 and map accession numbers to manager names, and (d) populate `\u002Froot\u002Fanswers.json` with the required fields.\n",{"name":5,"description":7},"main","cdcb6d230f3b15c3c33f8a2bdd16439f43602cbe","controlled-skill-repair-experiments\u002Fresult\u002Fmmg2skill-gpt5.2-xhigh\u002Ffinal\u002Fsingle-sec-financial-report-RI-001\u002Fskills\u002F13f-analyzer",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 13f-analyzer",{"tool":37,"command":38},"bunx","bunx skills add linyouxue\u002Fskill-repair-benchmark --skill 13f-analyzer",{"tool":40,"command":41},"pnpm","pnpm dlx skills add linyouxue\u002Fskill-repair-benchmark --skill 13f-analyzer","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002Flinyouxue\u002Fskill-repair-benchmark\u002Fblob\u002Fmain\u002Fcontrolled-skill-repair-experiments\u002Fresult\u002Fmmg2skill-gpt5.2-xhigh\u002Ffinal\u002Fsingle-sec-financial-report-RI-001\u002Fskills\u002F13f-analyzer\u002FSKILL.md",true,[45,51],{"path":46,"resourceType":47,"resourceTypeDesc":48,"sizeBytes":49,"sourceHtmlUrl":50},"scripts\u002Fholding_analysis.py","SCRIPT","脚本",1451,"https:\u002F\u002Fgithub.com\u002Flinyouxue\u002Fskill-repair-benchmark\u002Fblob\u002Fmain\u002Fcontrolled-skill-repair-experiments\u002Fresult\u002Fmmg2skill-gpt5.2-xhigh\u002Ffinal\u002Fsingle-sec-financial-report-RI-001\u002Fskills\u002F13f-analyzer\u002Fscripts\u002Fholding_analysis.py",{"path":52,"resourceType":47,"resourceTypeDesc":48,"sizeBytes":53,"sourceHtmlUrl":54},"scripts\u002Fone_fund_analysis.py",4317,"https:\u002F\u002Fgithub.com\u002Flinyouxue\u002Fskill-repair-benchmark\u002Fblob\u002Fmain\u002Fcontrolled-skill-repair-experiments\u002Fresult\u002Fmmg2skill-gpt5.2-xhigh\u002Ffinal\u002Fsingle-sec-financial-report-RI-001\u002Fskills\u002F13f-analyzer\u002Fscripts\u002Fone_fund_analysis.py",[56,63,70,77,82,87],{"skillNo":57,"name":58,"nameZh":6,"description":59,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":60,"categories":61,"keywords":62,"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":64,"name":65,"nameZh":6,"description":66,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":67,"categories":68,"keywords":69,"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":71,"name":72,"nameZh":6,"description":73,"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},"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":78,"name":58,"nameZh":6,"description":59,"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},"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":83,"name":65,"nameZh":6,"description":66,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":84,"categories":85,"keywords":86,"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":88,"name":72,"nameZh":6,"description":73,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":89,"categories":90,"keywords":91,"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",[],[]]