[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M7AVFQDAP34GRM6H1ABFJKMH":3,"skill-same:01M7AVFQDAP34GRM6H1ABFJKMH":54},{"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":34,"commitSha":35,"skillDirectory":36,"forksCount":14,"repositoryHtmlUrl":37,"repositoryHomepageUrl":6,"ownerHtmlUrl":38,"ownerBlogUrl":6,"ownerDescription":6,"updatedAt":39,"install":40,"resources":53},"01M7AVFQDAP34GRM6H1ABFJKMH","pdf-extract",null,"Use when extracting text, images, tables, or metadata from PDF files. MUST load to choose the correct extraction library based on PDF complexity — simple text vs structured data vs complex layouts.","MinhDuyDEV\u002Fmd-pikit","MinhDuyDEV","https:\u002F\u002Favatars.githubusercontent.com\u002Fu\u002F94704296?v=4","01M7AVDRJB5JM5VG5B6K49X0EZ","Nguyễn Viết Minh Duy","01M7AVDRKDB3JPGHFE4HGK1Z5M",0,"MIT","https:\u002F\u002Fgithub.com\u002FMinhDuyDEV\u002Fmd-pikit\u002Fblob\u002Fmain\u002F.pi\u002Fskills\u002Fpdf-extract\u002FSKILL.md",[],[],"2026-11-15 14:19:17",false,"---\nname: pdf-extract\ndescription: Use when extracting text, images, tables, or metadata from PDF files. MUST load to choose the correct extraction library based on PDF complexity — simple text vs structured data vs complex layouts.\nversion: 1.0.0\ntags: [research, integration]\ndependencies: []\nagent_types: [planner, worker, reviewer]\ntools: []\n---\n\n# PDF Extraction\n\n## Iron Laws\n\n\u003CEXTREMELY-IMPORTANT>\n- **Match the library to the PDF.** Simple text → `pdf-parse` or `pdfjs`. Structured data → `pdfplumber` (Python) or `camelot`. Complex layouts → vision model (GPT-4V, Claude).\n- **Test on a sample first.** Don't pick a library for a 500-page contract PDF before seeing it extract right.\n- **Tables are not text.** `pdftotext` won't give you a table. Use a table-aware tool.\n- **Scanned PDFs need OCR first.** `pytesseract`, `tesseract`, or vision model. Don't expect text from an image.\n- **Preserve structure when needed.** A table is a 2D thing; flattening to 1D text loses it.\n\u003C\u002FEXTREMELY-IMPORTANT>\n\n## When to Use\n\nExtracting text from PDFs; tabular data; images; metadata; \"convert this PDF to X\"; batch processing; RAG.\n\n## When NOT to Use\n\nData exists in a non-PDF format (use that); copy-paste works; one-time, hand inspection.\n\n## Library Selection\n\n| PDF type | Library |\n|---|---|\n| Simple text, English | `pdf-parse`, `pdfplumber` |\n| Complex text, multi-column | `pdfplumber` (layout-aware) |\n| Tables (financial, scientific) | `camelot`, `tabula-py`, `pdfplumber` |\n| Scanned (image-based) | `pytesseract` (OCR), or vision model |\n| Mixed (text + tables + images) | Vision model (GPT-4V, Claude) |\n| Form fields | `pdf-lib`, `pdfrw`, `pypdf` |\n\nWhen in doubt: `pdfplumber` for English text, vision model for weird layouts.\n\n## Workflow\n\n1. **Inspect the PDF.** Open it, look at the structure. Is it text or scanned? Tables? Forms? Images? Multi-column?\n2. **Pick the library** based on the structure.\n3. **Test on a small sample.** Extract 1-5 pages. Is the output what you expected?\n4. **Scale up.** Run on the full set. Watch for failures (encrypted, corrupted, etc.).\n5. **Verify.** Spot-check. Automated extraction lies silently — a missing column, a merged cell.\n\n## Common Patterns\n\n```python\n# pdfplumber — text + tables\nimport pdfplumber\nwith pdfplumber.open(\"file.pdf\") as pdf:\n    for page in pdf.pages:\n        text = page.extract_text()\n        tables = page.extract_tables()\n\n# pytesseract — OCR\nimport pytesseract\nfrom PIL import Image\ntext = pytesseract.image_to_string(Image.open(\"scan.png\"))\n```\n\n## Common Mistakes\n\n`pdftotext` on a scanned PDF (no text to extract); `pdf-parse` on a multi-column PDF (text jumbled); flattening tables to text (loses structure); no verification (output silently wrong); choosing a library for a 500-page PDF without testing on 5 pages; OCR on text-based PDF (overkill, slower, less accurate); batch processing without error handling (one bad PDF kills the run).\n\n## Red Flags\n\nNo sample test before full run; no verification of output; `pdftotext` on scanned PDF; no error handling on batch; \"the extraction worked on 1 page\" assumption for the full 500; tables flattened to text; \"I'll fix the output in post\" (extraction should be correct); \"the library says it supports tables\" (test it on YOUR tables).\n\n## Anti-Patterns\n\n**Wrong library for the PDF** (text vs scanned vs tables); **no sample test**; **no verification**; **flattening tables** (loses structure); **OCR on text-based PDF**; **batch without error handling**; **\"the library supports X\"** (test YOUR data); **\"I'll fix in post\"** (extraction should be right).\n","# PDF Extraction\n\n## Iron Laws\n\n\u003CEXTREMELY-IMPORTANT>\n- **Match the library to the PDF.** Simple text → `pdf-parse` or `pdfjs`. Structured data → `pdfplumber` (Python) or `camelot`. Complex layouts → vision model (GPT-4V, Claude).\n- **Test on a sample first.** Don't pick a library for a 500-page contract PDF before seeing it extract right.\n- **Tables are not text.** `pdftotext` won't give you a table. Use a table-aware tool.\n- **Scanned PDFs need OCR first.** `pytesseract`, `tesseract`, or vision model. Don't expect text from an image.\n- **Preserve structure when needed.** A table is a 2D thing; flattening to 1D text loses it.\n\u003C\u002FEXTREMELY-IMPORTANT>\n\n## When to Use\n\nExtracting text from PDFs; tabular data; images; metadata; \"convert this PDF to X\"; batch processing; RAG.\n\n## When NOT to Use\n\nData exists in a non-PDF format (use that); copy-paste works; one-time, hand inspection.\n\n## Library Selection\n\n| PDF type | Library |\n|---|---|\n| Simple text, English | `pdf-parse`, `pdfplumber` |\n| Complex text, multi-column | `pdfplumber` (layout-aware) |\n| Tables (financial, scientific) | `camelot`, `tabula-py`, `pdfplumber` |\n| Scanned (image-based) | `pytesseract` (OCR), or vision model |\n| Mixed (text + tables + images) | Vision model (GPT-4V, Claude) |\n| Form fields | `pdf-lib`, `pdfrw`, `pypdf` |\n\nWhen in doubt: `pdfplumber` for English text, vision model for weird layouts.\n\n## Workflow\n\n1. **Inspect the PDF.** Open it, look at the structure. Is it text or scanned? Tables? Forms? Images? Multi-column?\n2. **Pick the library** based on the structure.\n3. **Test on a small sample.** Extract 1-5 pages. Is the output what you expected?\n4. **Scale up.** Run on the full set. Watch for failures (encrypted, corrupted, etc.).\n5. **Verify.** Spot-check. Automated extraction lies silently — a missing column, a merged cell.\n\n## Common Patterns\n\n```python\n# pdfplumber — text + tables\nimport pdfplumber\nwith pdfplumber.open(\"file.pdf\") as pdf:\n    for page in pdf.pages:\n        text = page.extract_text()\n        tables = page.extract_tables()\n\n# pytesseract — OCR\nimport pytesseract\nfrom PIL import Image\ntext = pytesseract.image_to_string(Image.open(\"scan.png\"))\n```\n\n## Common Mistakes\n\n`pdftotext` on a scanned PDF (no text to extract); `pdf-parse` on a multi-column PDF (text jumbled); flattening tables to text (loses structure); no verification (output silently wrong); choosing a library for a 500-page PDF without testing on 5 pages; OCR on text-based PDF (overkill, slower, less accurate); batch processing without error handling (one bad PDF kills the run).\n\n## Red Flags\n\nNo sample test before full run; no verification of output; `pdftotext` on scanned PDF; no error handling on batch; \"the extraction worked on 1 page\" assumption for the full 500; tables flattened to text; \"I'll fix the output in post\" (extraction should be correct); \"the library says it supports tables\" (test it on YOUR tables).\n\n## Anti-Patterns\n\n**Wrong library for the PDF** (text vs scanned vs tables); **no sample test**; **no verification**; **flattening tables** (loses structure); **OCR on text-based PDF**; **batch without error handling**; **\"the library supports X\"** (test YOUR data); **\"I'll fix in post\"** (extraction should be right).\n",{"name":5,"tags":24,"tools":27,"version":28,"agent_types":29,"description":7,"dependencies":33},[25,26],"research","integration",[],"1.0.0",[30,31,32],"planner","worker","reviewer",[],"main","01207a96514af9f9c4d7d6cb594b936c6a9ddb10",".pi\u002Fskills\u002Fpdf-extract","https:\u002F\u002Fgithub.com\u002FMinhDuyDEV\u002Fmd-pikit","https:\u002F\u002Fgithub.com\u002FMinhDuyDEV","2026-08-20 02:00:33",{"source":8,"skillName":5,"commands":41,"prompt":51,"zipAvailable":52},[42,45,48],{"tool":43,"command":44},"npx","npx skills add MinhDuyDEV\u002Fmd-pikit --skill pdf-extract",{"tool":46,"command":47},"bunx","bunx skills add MinhDuyDEV\u002Fmd-pikit --skill pdf-extract",{"tool":49,"command":50},"pnpm","pnpm dlx skills add MinhDuyDEV\u002Fmd-pikit --skill pdf-extract","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002FMinhDuyDEV\u002Fmd-pikit\u002Fblob\u002Fmain\u002F.pi\u002Fskills\u002Fpdf-extract\u002FSKILL.md",true,[],[55,62,69,76,83,90],{"skillNo":56,"name":57,"nameZh":6,"description":58,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":59,"categories":60,"keywords":61,"publishedAt":19},"01M7AVGJR1RSRVA3VJT8ZW4Y27","writing-skills","Use when creating new skills, editing existing skills, or verifying skills work before deployment - applies TDD to process documentation by testing with subagents before writing, iterating until bulletproof against rationalization. Includes complete pressure testing methodology.","https:\u002F\u002Fgithub.com\u002FMinhDuyDEV\u002Fmd-pikit\u002Fblob\u002Fmain\u002F.pi\u002Fskills\u002Fwriting-skills\u002FSKILL.md",[],[],{"skillNo":63,"name":64,"nameZh":6,"description":65,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":66,"categories":67,"keywords":68,"publishedAt":19},"01M7AVGE076BNB3J7JDBGAKD2T","verification-before-completion","Use when about to claim work is complete, fixed, or passing, before committing or creating PRs - requires running verification commands and confirming output before making any success claims; evidence before assertions always","https:\u002F\u002Fgithub.com\u002FMinhDuyDEV\u002Fmd-pikit\u002Fblob\u002Fmain\u002F.pi\u002Fskills\u002Fverification-before-completion\u002FSKILL.md",[],[],{"skillNo":70,"name":71,"nameZh":6,"description":72,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":73,"categories":74,"keywords":75,"publishedAt":19},"01M7AVGAYJ6APXRB9QWBG7482S","typescript-coding-standards","Use when writing, refactoring, or reviewing TypeScript code that needs strong domain modeling, typed errors, schema parsing, safe adapters, test seams, or maintainable module boundaries.","https:\u002F\u002Fgithub.com\u002FMinhDuyDEV\u002Fmd-pikit\u002Fblob\u002Fmain\u002F.pi\u002Fskills\u002Ftypescript-coding-standards\u002FSKILL.md",[],[],{"skillNo":77,"name":78,"nameZh":6,"description":79,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":80,"categories":81,"keywords":82,"publishedAt":19},"01M7AVG8CE5BTR2CRFPHHVJCJZ","test-driven-development","Use when implementing a feature, bugfix, or behavior-changing refactor — require a failing behavior test before production code, then make the smallest change that passes.","https:\u002F\u002Fgithub.com\u002FMinhDuyDEV\u002Fmd-pikit\u002Fblob\u002Fmain\u002F.pi\u002Fskills\u002Ftest-driven-development\u002FSKILL.md",[],[],{"skillNo":84,"name":85,"nameZh":6,"description":86,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":87,"categories":88,"keywords":89,"publishedAt":19},"01M7AVG5FJH3WTG9XR2G0608ND","source-driven-development","Use when unfamiliar libraries, dependency internals, external APIs, framework behavior, migrations, or current ecosystem guidance require official documentation, version-matched source, read the tests, and cited evidence.","https:\u002F\u002Fgithub.com\u002FMinhDuyDEV\u002Fmd-pikit\u002Fblob\u002Fmain\u002F.pi\u002Fskills\u002Fsource-driven-development\u002FSKILL.md",[],[],{"skillNo":91,"name":92,"nameZh":6,"description":93,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":94,"categories":95,"keywords":96,"publishedAt":19},"01M7AVG37PZ77CF35KAR6E93ZJ","security-and-hardening","Use when auditing security, implementing authentication or authorization, handling secrets, or validating data across external trust boundaries.","https:\u002F\u002Fgithub.com\u002FMinhDuyDEV\u002Fmd-pikit\u002Fblob\u002Fmain\u002F.pi\u002Fskills\u002Fsecurity-and-hardening\u002FSKILL.md",[],[]]