seb1n/awesome-ai-agent-skills / documents-and-files/pdf-processing
pdf-processing
VerifiedInspect, extract, OCR, create, merge, split, reorder, rotate, annotate, fill, redact, compress, secure, and verify PDF documents while preserving source files and visual fidelity. Use when working with one or more .pdf files; converting documents to or from PDF; extracting text, tables, images, metadata, forms, or page ranges; applying true redactions or signatures; diagnosing malformed, encrypted, scanned, or inaccessible PDFs; or validating that a PDF transformation preserved the intended content and layout.
| File | Kind | Size |
|---|---|---|
| SKILL.md | skill md | 9.7 KB |
| agents/openai.yaml | config | 215 B |
| assets/processing-record-template.md | markdown | 1.0 KB |
| references/tool-routing.md | markdown | 3.0 KB |
| references/verification-checklist.md | markdown | 2.6 KB |
| scripts/inspect_pdf.pyexecutable | script | 12.6 KB |
references/tool-routing.md
View on GitHub# PDF tool routing
Read this reference after inventorying the environment. Choose by capability and test on a copy; tool availability and behavior vary by version.
| Need | Suitable capability | Common local options when present | Required check |
|---|---|---|---|
| Structural inventory | Read metadata, page tree, encryption, objects | `qpdf`, `pdfinfo`, pypdf | Re-open and compare page count |
| Text extraction | Preserve page association and layout hints | `pdftotext`, PyMuPDF, pdfplumber | Compare representative pages visually |
| OCR | Render pages and add/search a text layer | OCRmyPDF, Tesseract with a PDF pipeline | Check language, confidence, names, numbers |
| Render pages | Deterministic page rasterization | Poppler, MuPDF, Ghostscript | Inspect changed pages at readable scale |
| Merge/split/rotate | Rewrite page trees without rasterizing | `qpdf`, pypdf, MuPDF | Confirm order, labels, bookmarks, forms |
| Tables | Geometry-aware extraction | pdfplumber, Camelot/Tabula when appropriate | Reconcile row/column totals to the page |
| Create PDF | Layout engine with font embedding | ReportLab, browser print, office export | Render and check fonts, links, pagination |
| True redaction | Remove underlying page objects | PyMuPDF or another redaction-capable editor | Search objects/text with a second method |
| Forms | Read/write AcroForm fields | pypdf, dedicated PDF editor | Open in intended viewer and inspect values |
| Repair/linearize | Validate and rewrite malformed structure | `qpdf`, Ghostscript as a controlled fallback | Compare content; rewriting can discard features |
| PDF/A or PDF/UA | Dedicated conformance validator | veraPDF or equivalent | Retain machine-readable validation report |
## Routing rules
1. Prefer existing workspace tools and user-approved applications.
2. Do not assume a Python package, command-line tool, GUI, font, or OCR language pack is installed.
3. Avoid office-suite round trips for PDFs that must retain exact geometry, forms, layers, or signatures.
4. Avoid rasterizing text PDFs unless the user accepts loss of searchability, accessibility, vectors, links, and signatures.
5. Use at least two independent methods for high-stakes redaction or document integrity checks.
6. Record exact tool versions for repeatability.
7. For untrusted files, use a disposable low-privilege sandbox with no secrets/network, read-only input, isolated output, resource/time limits, and disabled JavaScript/actions/form submission/external fetches/attachment activation/rich media/host integrations.
8. Verify the exact parser/renderer exposes or inherently enforces those controls. If it does not, stop after raw-byte inspection; availability alone is not a safe routing decision.
9. For redaction, select a tool and save mode that performs a complete non-incremental rewrite with garbage/object cleanup; reject an output that retains prior revisions.
If no suitable tool exists, stop before changing the file. Explain the capability gap, expected installation, privacy implications, and a non-destructive fallback.
Related skills
| Skill | Stars | Updated | Works with | Status | Install |
|---|---|---|---|---|---|
| canvas-designanthropics/skillsCreate beautiful visual art in .png and .pdf documents using design philosophy. You should use this skill when the user asks to create a poster, piece of art, design, or other static piece. Create original visual designs, never copying existing artists' work to avoid copyright violations. | Stars: 198k | Updated | Claude CodeCodex | Verified | Install |
| docxanthropics/skillsUse this skill whenever the user wants to create, read, edit, or manipulate Word documents (.docx files) or Word templates (.dotx files). Triggers include: any mention of 'Word doc', 'word document', '.docx', '.dotx', or requests to produce professional documents with formatting like tables of contents, headings, page numbers, or letterheads. Also use when extracting or reorganizing content from .docx or .dotx files, inserting or replacing images in documents, performing find-and-replace in Word files, working with tracked changes or comments, or converting content into a polished Word document. If the user asks for a 'report', 'memo', 'letter', 'template', or similar deliverable as a Word or .docx file, use this skill. Do NOT use for PDFs, spreadsheets, Google Docs, or general coding tasks unrelated to document generation. | Stars: 198k | Updated | Claude CodeCodex | Verified | Install |
| pdfanthropics/skillsUse this skill whenever the user wants to do anything with PDF files. This includes reading or extracting text/tables from PDFs, combining or merging multiple PDFs into one, splitting PDFs apart, rotating pages, adding watermarks, creating new PDFs, filling PDF forms, encrypting/decrypting PDFs, extracting images, and OCR on scanned PDFs to make them searchable. If the user mentions a .pdf file or asks to produce one, use this skill. | Stars: 198k | Updated | Claude CodeCodex | Verified | Install |
| pptxanthropics/skillsUse this skill any time a .pptx or .potx file is involved in any way — as input, output, or both. This includes: creating slide decks, pitch decks, or presentations; reading, parsing, or extracting text from any .pptx or .potx file (even if the extracted content will be used elsewhere, like in an email or summary); editing, modifying, or updating existing presentations; combining or splitting slide files; working with templates (.potx), layouts, speaker notes, or comments. Trigger whenever the user mentions "deck," "slides," "presentation," or references a .pptx or .potx filename, regardless of what they plan to do with the content afterward. If a .pptx or .potx file needs to be opened, created, or touched, use this skill. | Stars: 198k | Updated | Claude CodeCodex | Verified | Install |