jxnl/pdf-viewing
agents/skills/pdf-viewing/SKILL.md
OCR PDFs with docling while tracking per-page text and rasterize PDFs to images. Use for PDF ingestion, page-aware text extraction, rendering pages to images, or inspecting PDF metadata, with outputs saved under a local project directory.
$ install --global
skillsauthnpx skillsauth add jxnl/dots pdf-viewingInstall 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: May 25, 2026, 6:28 AM130.7s3 files scanned
SKILL.md
- name:
- pdf-viewing
- description:
- OCR PDFs with docling while tracking per-page text and rasterize PDFs to images. Use for PDF ingestion, page-aware text extraction, rendering pages to images, or inspecting PDF metadata, with outputs saved under a local project directory.
PDF Viewing
Overview
Use this skill to OCR PDFs with docling and preserve page numbers, rasterize pages into images, or inspect PDF metadata. Always save outputs under a local project directory (default: ./.pdf-artifacts/<pdf-stem>).
Quick Start
- Create a local venv in the project and install deps as dev dependencies:
uv venv uv add --dev docling typer pymupdf - Run the OCR tool:
uv run python scripts/pdf_tools.py ocr path/to/file.pdf --out-dir ./.pdf-artifacts/<pdf-stem> - Run the rasterizer:
uv run python scripts/pdf_tools.py rasterize path/to/file.pdf --out-dir ./.pdf-artifacts/<pdf-stem>
Tasks
OCR with page tracking
- Command:
uv run python scripts/pdf_tools.py ocr <pdf-path> - Output (default):
./.pdf-artifacts/<pdf-stem>/ocr-pages.jsonandocr-pages.txt - Behavior: Copies the input PDF into the output dir and writes per-page text with page numbers.
Explicit flags
--out-dir <dir>: output directory (relative paths are rooted at the project root)--project-root <dir>: base path for relative output paths--copy-pdf / --no-copy-pdf: control whether the input PDF is copied into the output dir--pages <ranges>: page ranges like1-3,5,8-10--pages-json <name>: JSON filename for per-page text--pages-text <name>: TXT filename for per-page text--manifest <name>: manifest filename (defaultmanifest.json)--overwrite / --no-overwrite: overwrite existing outputs--dry-run: show what would be written
Rasterize to images
- Command:
uv run python scripts/pdf_tools.py rasterize <pdf-path> - Output (default):
./.pdf-artifacts/<pdf-stem>/images/page-0001.jpg(etc.) - Behavior: Renders each PDF page to an image at the requested DPI.
Explicit flags
--out-dir <dir>: output directory (relative paths are rooted at the project root)--project-root <dir>: base path for relative output paths--copy-pdf / --no-copy-pdf: control whether the input PDF is copied into the output dir--pages <ranges>: page ranges like1-3,5,8-10--dpi <int>: rasterization DPI--format <jpg|png|webp>: output image format--quality <1-100>: for jpg/webp--images-dir <name>: directory for output images--images-manifest <name>: JSON manifest name with image paths--manifest <name>: manifest filename (defaultmanifest.json)--overwrite / --no-overwrite: overwrite existing outputs--dry-run: show what would be written
Inspect metadata
- Command:
uv run python scripts/pdf_tools.py inspect <pdf-path> - Output: writes metadata to stdout and
manifest.jsonunless--no-manifest
Clean artifacts
- Command:
uv run python scripts/pdf_tools.py clean <pdf-path> - Behavior: Removes the artifact directory for the PDF.
Notes
- Keep outputs inside the current project by using the default output directory or a relative
--out-dir. - If docling requires extra OCR backends in your environment, install them before running OCR.
Tools
scripts/pdf_tools.py: Typer CLI withocr,rasterize,inspect, andcleancommands.
Related Skills
jxnl/yeet
tools
VerifiedTrustedCommunity
Use only when the user explicitly asks to stage, commit, push, and open a GitHub pull request in one flow using the GitHub CLI (`gh`).
182SKILL.mdUpdated May 25, 2026
jxnl/tweet-like-me
development
VerifiedTrustedCommunity
Use when Codex needs to write, rewrite, critique, or reply on Twitter/X in Jason Liu's personal voice. Trigger for requests like "tweet like me", "write this in my style", "make this sound like Jason", "draft a reply", or when Jason asks for Twitter copy about Codex, product building, feedback, launches, quote-tweets, or operator/value takes.
182SKILL.mdUpdated May 25, 2026
jxnl/simple-html-artifact
development
VerifiedTrustedCommunity
Build or refine single-file information-first HTML artifacts, especially index.html or text.html pages, with strong information hierarchy, restrained styling, accessible semantics, and minimal AI-generated frontend tells. Use when creating static HTML reports, research pages, explainers, briefs, dashboards, note indexes, or simple front ends whose goal is comprehension rather than marketing conversion.
182SKILL.mdUpdated May 25, 2026
jxnl/self-improve
development
VerifiedTrustedCommunity
Codex-specific, session-driven self-improvement for Codex behavior and project instructions. Use when the user asks to inspect past Codex sessions, run a "dream" pass over prior interactions, mine repeated user corrections/preferences, improve or draft skills, update repo/project `AGENTS.md` guidance, or propose durable edits to global `~/.codex/AGENTS.md`.
182SKILL.mdUpdated May 25, 2026