Skip to content

aiskillstore/marketplace / skills/0xkynz/pdf-processing

pdf-processing

Verified

Extract text and tables from PDF files, fill forms, merge documents. Use when working with PDF files or when the user mentions PDFs, forms, or document extraction.

FileKindSize
SKILL.mdskill md1.2 KB
skill-report.jsonconfig8.3 KB

skill-report.json

View on GitHub
{
  "schema_version": "2.0",
  "meta": {
    "generated_at": "2026-07-04T13:38:06.389Z",
    "slug": "0xkynz-pdf-processing",
    "source_url": "https://github.com/0xkynz/codekit/tree/main/templates/skills/pdf-processing",
    "source_ref": "main",
    "model": "codex",
    "analysis_version": "3.0.0",
    "source_type": "community",
    "content_hash": "5f7317da27ce56533fcaa510c0d4efa4d85faa09730168ed91033d7c33794c7b",
    "tree_hash": "9456ffc7a27789ba0bbb84eb856441935f4c045a03eade0f1a6770c85b0dcacc",
    "provenance": {
      "model_effective": "codex",
      "fallback_chain": [
        {
          "agent": "codex",
          "outcome": "success"
        }
      ],
      "analysis_version": "3.0.0"
    }
  },
  "skill": {
    "name": "pdf-processing",
    "description": "Extract text, tables, form data, and page-level content from PDFs. Use this skill for PDF analysis, form workflows, and document operations.",
    "summary": "Extract PDF text, tables, forms, and pages with practical library guidance.",
    "icon": "📦",
    "version": "1.0.1",
    "author": "0xkynz",
    "license": "MIT",
    "category": "data",
    "tags": [
      "pdf",
      "document-processing",
      "text-extraction",
      "forms",
      "tables"
    ],
    "supported_tools": [
      "claude",
      "codex",
      "claude-code"
    ],
    "risk_factors": [
      "external_commands"
    ]
  },
  "security_audit": {
    "risk_level": "safe",
    "is_blocked": false,
    "safe_to_publish": true,
    "analysis_status": "ok",
    "summary": "The only static finding points to a Markdown Python code fence in SKILL.md, not actual shell execution. No prompt injection, exfiltration intent, or unsafe behavioral instruction was found in the reviewed skill text.",
    "remediation": [],
    "risk_factor_evidence": [
      {
        "factor": "external_commands",
        "evidence": [
          {
            "file": "SKILL.md",
            "line_start": 14,
            "line_end": 19
          }
        ]
      }
    ],
    "static_findings": [
      {
        "id": "external_commands:SKILL.md:14:ruby-shell-backtick-execution",
        "category": "external_commands",
        "severity": "medium",
        "pattern": "Ruby/shell backtick execution",
        "file": "SKILL.md",
        "line_start": 14,
        "line_end": 19,
        "snippet": "```python"
      }
    ],
    "finding_verdicts": [
      {
        "id": "external_commands:SKILL.md:14:ruby-shell-backtick-execution",
        "verdict": "false_positive",
        "confidence": 0.96,
        "reason": "SKILL.md lines 14-19 contain a fenced Python example using pdfplumber, not Ruby backtick or shell execution. The snippet is documentation only and does not define executable skill code."
      }
    ],
    "semantic_findings": [],
    "critical_findings": [],
    "high_findings": [],
    "medium_findings": [],
    "low_findings": [],
    "dangerous_patterns": [],
    "files_scanned": 1,
    "total_lines": 50,
    "audit_model": "codex",
    "audited_at": "2026-07-04T13:38:06.389Z",
    "agent_auto_install_policy": "allowed",
    "manual_install_policy": "allowed"
  },
  "content": {
    "user_title": "Process PDFs with Reliable Extraction",
    "value_statement": "PDF workflows often require text, tables, forms, and page operations across inconsistent documents. This skill guides Claude, Codex, and Claude Code through practical PDF processing tasks.",
    "seo_keywords": [
      "Claude",
      "Codex",
      "Claude Code",
      "PDF processing",
      "PDF text extraction",
      "PDF table extraction",
      "PDF form filling",
      "document automation",
      "pdfplumber",
      "PyPDF2"
    ],
    "actual_capabilities": [
      "Extract text from single pages or complete PDF documents.",
      "Identify and extract tables for structured review or export.",
      "Work with PDF form fields and fillable document workflows.",
      "Plan merge, split, rotation, and watermark operations.",
      "Recommend suitable Python libraries for extraction and manipulation."
    ],
    "limitations": [
      "Scanned PDFs may need OCR before text extraction works.",
      "Complex layouts can require manual validation after extraction.",
      "Encrypted PDFs require valid access before processing.",
      "The skill gives guidance and examples, not a bundled executable tool."
    ],
    "use_cases": [
      {
        "title": "Extract Contract Tables",
        "description": "Pull tables and key text from contract PDFs for review and reporting.",
        "target_user": "Legal operations teams"
      },
      {
        "title": "Automate Form Workflows",
        "description": "Read and fill repeatable PDF forms with consistent field handling.",
        "target_user": "Operations analysts"
      },
      {
        "title": "Prepare Document Batches",
        "description": "Plan merging, splitting, rotation, and watermark steps for PDF batches.",
        "target_user": "Administrative staff"
      }
    ],
    "prompt_templates": [
      {
        "title": "Extract Basic Text",
        "scenario": "Beginner extraction from a simple PDF.",
        "prompt": "Extract the text from this PDF and summarize the main sections. Note any pages where extraction appears incomplete."
      },
      {
        "title": "Find Tables",
        "scenario": "Intermediate table extraction from reports.",
        "prompt": "Extract the tables from this PDF report. Preserve row labels, column headings, and page references."
      },
      {
        "title": "Review Form Fields",
        "scenario": "Advanced form inspection and preparation.",
        "prompt": "Inspect this fillable PDF form. List the fields, expected values, validation concerns, and safe fill order."
      },
      {
        "title": "Design Batch Workflow",
        "scenario": "Advanced multi-document processing plan.",
        "prompt": "Create a PDF processing workflow for these documents. Include extraction, validation, merge rules, and error handling steps."
      }
    ],
    "output_examples": [
      {
        "input": "A user asks to extract text from a ten-page policy PDF.",
        "output": "A page-by-page text summary with notes for missing text, unusual formatting, and pages that may need OCR."
      },
      {
        "input": "A user provides a PDF invoice with tables.",
        "output": "A clean table summary with invoice fields, line items, totals, and page references for verification."
      },
      {
        "input": "A user needs to combine several PDF files into one packet.",
        "output": "A merge plan that orders documents, checks page orientation, and identifies where watermarks or rotations are needed."
      }
    ],
    "best_practices": [
      "Check encryption and permissions before attempting extraction.",
      "Validate extracted text and tables against the source pages.",
      "Use pdfplumber for extraction and PyPDF2 for page manipulation."
    ],
    "anti_patterns": [
      "Assuming scanned pages contain extractable text without OCR.",
      "Trusting extracted tables without comparing them to the PDF layout.",
      "Merging documents without checking page order, rotation, and duplicate pages."
    ],
    "faq": [
      {
        "question": "Can this skill process scanned PDFs?",
        "answer": "It can identify when OCR is needed, but scanned images need an OCR tool before normal text extraction."
      },
      {
        "question": "Does this skill include executable code?",
        "answer": "No. It provides guidance and examples for using common PDF libraries."
      },
      {
        "question": "Which libraries does it recommend?",
        "answer": "It recommends pdfplumber for extraction and PyPDF2 for common document manipulation tasks."
      },
      {
        "question": "Can it extract tables?",
        "answer": "Yes. It supports table extraction guidance and encourages validation for complex layouts."
      },
      {
        "question": "Can it fill PDF forms?",
        "answer": "Yes. It describes form field extraction and fillable form workflows."
      },
      {
        "question": "Is it safe for confidential documents?",
        "answer": "Review your tool environment first. The skill itself does not add network or storage behavior."
      }
    ]
  },
  "file_structure": [
    {
      "name": "SKILL.md",
      "type": "file",
      "path": "SKILL.md",
      "lines": 50
    }
  ]
}
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: 198kUpdated Claude CodeCodexVerifiedInstall
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: 198kUpdated Claude CodeCodexVerifiedInstall
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: 198kUpdated Claude CodeCodexVerifiedInstall
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: 198kUpdated Claude CodeCodexVerifiedInstall