randyhaylor/ai-tools/pdf-to-text
ai-tools/pdf-to-text/SKILL.md
--- name: pdf-to-text description: "Convert PDF files to clean text. Handles both embedded-text PDFs and scanned/image PDFs via OCR. Use when the user wants to import, extract, or convert a PDF to text." allowed-tools: Bash, Read, Write argument-hint: [pdf-path] [output-path] --- # PDF to Text Import ## Workflow 1. **Check if PDF has embedded text** ```bash pdftotext <input.pdf> - | head -20 ``` - If output contains readable text → use `pdftotext` (fast, accurate) - If output i
tools
Updated Apr 20, 2026
$ install --global
skillsauthnpx skillsauth add randyhaylor/enhanceclaude ai-tools/pdf-to-textInstall this skill globally with one command. Works with Claude Code, Cursor, and Windsurf.
Security Scan Results
3 of 9 scanners reported clean
Some scanners were skipped, did not run, or reported a non-clean status. Review each row below.
3
Scanners Passed
9
Scanners in report
Clean
TrivyContainer and dependency vulnerability scanner
95%
Clean
SemgrepStatic code analysis for vulnerabilities
95%
Clean
mcp-scan (Snyk)Model Context Protocol security validation
95%
Skipped
Snyk (dep)Open source security scanning
50%
Skipped
Socket.devSupply chain security analysis
50%
Skipped
VirusTotalMulti-engine malware detection
50%
Skipped
CrowdStrikeAdvanced threat intelligence
50%
Skipped
OSV-ScannerOpen Source Vulnerability database check
50%
Skipped
OWASP Dep-Check
50%
Last scanned: Apr 20, 2026, 5:16 AM8.1s4 files scanned
SKILL.md
- name:
- pdf-to-text
- description:
- Convert PDF files to clean text. Handles both embedded-text PDFs and scanned/image PDFs via OCR. Use when the user wants to import, extract, or convert a PDF to text.
- allowed-tools:
- Bash, Read, Write
- argument-hint:
- [pdf-path] [output-path]
PDF to Text Import
Workflow
-
Check if PDF has embedded text
pdftotext <input.pdf> - | head -20- If output contains readable text → use
pdftotext(fast, accurate) - If output is empty or garbled → fall back to OCR
- If output contains readable text → use
-
Test scan first two pages and evaluate quality
pdftotext -f 1 -l 2 <input.pdf> -Read the output and check for:
- Garbled characters, mojibake, or encoding issues
- Missing words, merged lines, or broken paragraphs
- Headers/footers bleeding into body text
- Table or column data mangled into single lines
If quality is poor with
pdftotext, try OCR on the same two pages:pdftoppm -f 1 -l 2 -png <input.pdf> /tmp/test-scan tesseract /tmp/test-scan-1.png - 2>/dev/null rm /tmp/test-scan-*.pngCompare both outputs. Report findings to user before proceeding with full extraction.
If neither produces clean output, visually inspect the pages:
pdftoppm -f 1 -l 2 -png -r 200 <input.pdf> /tmp/visual-checkUse the Read tool to view
/tmp/visual-check-1.pngand/tmp/visual-check-2.png(Claude vision will render them). Compare what you see on the page to what the text extraction produced. Identify the specific issue (columns, watermarks, unusual fonts, embedded images of text, etc.) and recommend an extraction strategy before proceeding.rm /tmp/visual-check-*.png -
Extract text
Embedded text (preferred):
pdftotext <input.pdf> <output.txt>Scanned/image PDF (OCR fallback):
ocrmypdf --force-ocr <input.pdf> /tmp/ocr-temp.pdf pdftotext /tmp/ocr-temp.pdf <output.txt> rm /tmp/ocr-temp.pdfIf
ocrmypdfis not installed:# Convert pages to images, then OCR pdftoppm <input.pdf> /tmp/pdf-page -png tesseract /tmp/pdf-page-*.png <output> txt rm /tmp/pdf-page-*.png -
Report results
wc -l <output.txt> pdfinfo <input.pdf> | grep Pages- Report page count and line count to user
Arguments
$ARGUMENTS[0]— path to input PDF (required)$ARGUMENTS[1]— path to output txt file (optional, defaults to same name with .txt extension)
Tool Requirements
Requires at least one of:
pdftotext(from poppler-utils) — for embedded text PDFsocrmypdf+pdftotext— for scanned PDFstesseract+pdftoppm— OCR fallback if ocrmypdf unavailable
Check availability before starting:
which pdftotext ocrmypdf tesseract pdftoppm 2>/dev/null
If missing tools, tell the user what to install:
sudo apt install poppler-utils— pdftotext and pdftoppmsudo apt install tesseract-ocr— tesseractpip install ocrmypdf— ocrmypdf
Related Skills
randyhaylor/ai-tools/xstate
tools
VerifiedTrustedCommunity
# XState v5 Quick Reference ## How to Look Up API Details For complete function signatures, types, and interfaces, **grep `api-reference.md`** — do NOT read it in full (12k+ lines). Example: ``` Grep pattern="createActor" path="~/.claude/skills/xstate/api-reference.md" output_mode="content" -C 5 ``` Then use `Read` with `offset`/`limit` to get the full section. This is the primary way to get precise technical info when the quick reference below isn't enough. ## Design Workflow Recommended
SKILL.mdUpdated Apr 20, 2026
randyhaylor/vscode-agent-teams
tools
VerifiedTrustedCommunity
Workaround for agent teams in VS Code extension where TeamCreate teammates cannot execute tools. Uses an echo-back-and-resume pattern where agents return tool requests instead of executing them directly.
SKILL.mdUpdated Apr 20, 2026
randyhaylor/typographic-hierarchy
development
VerifiedTrustedCommunity
Format documentation, READMEs, and structured text using header hierarchy where each level stands alone. Use when creating docs, research notes, summaries, or when user requests 'scannable,' 'well-structured,' 'skimmable,' or 'readable at multiple depths' output. Applies to markdown, technical specs, and any hierarchical text formatting.
SKILL.mdUpdated Apr 20, 2026
randyhaylor/test-driven-development
development
VerifiedTrustedCommunity
Enforce strict Test-Driven Development workflow: write one test, make it pass, verify, then proceed. Prevents over-implementation and ensures code matches requirements exactly. Use when implementing new features, adding settings, or building functionality incrementally.
SKILL.mdUpdated Apr 20, 2026