RetentaRetenta

Evidence record · captured 2026-10-10

OpenAI PDF

A render-first process for reading, creating, and reviewing PDFs with layout-aware visual checks and programmatic generation or extraction tools.

Official publisherUnverifiedSource reviewedBehavior not tested
Source review

Editorial assessment

This is a source-only assessment. It does not claim runtime or security testing.

What it does

This skill insists that PDF work be judged from rendered pages, using extraction libraries for content checks and ReportLab for creation while treating the final visual pass as the release gate.

Best for

  • Creating a polished programmatic PDF
  • Reviewing layout-sensitive PDF content
  • Extracting text while retaining awareness that layout may not survive extraction

Strengths in the source

  • Makes the distinction between text extraction and visual fidelity explicit.
  • Provides a repeatable render-inspect-update loop and concrete defect checklist.
  • Keeps temporary renders separate from final deliverables.

Limitations

  • It depends on system and Python packages that may not be installed.
  • The top-level source does not cover advanced forms, signatures, or PDF accessibility tagging.
  • No sample document was rendered during this review.
  • The pinned publisher repository is deprecated in favor of OpenAI's plugins repository, so confirm the current distribution path before adopting it.

When not to use it

  • The task only needs plain text already supplied outside a PDF
  • A document format other than PDF is the required output

Reviewed by Retenta editorial on 2026-10-10; scope: source only.

Files included in this review
  • skills/.curated/pdf/SKILL.md
  • README.md
  • skills/.curated/pdf/LICENSE.txt

Evidence and boundaries

Execution · not tested

Retenta reviewed the pinned source but did not install or execute this skill.

Security · not tested

No sandbox run, dependency audit, or independent security assessment is claimed.

Pinned publisher source
skills/.curated/pdf/SKILL.md
Revision
49f948faa9258a0c61caceaf225e179651397431
License evidence
Apache-2.0The pinned skill directory includes an Apache License, Version 2.0 LICENSE.txt.
Last source change
2026-01-30
Independent verification
The source is controlled by OpenAI; Retenta has not independently verified its runtime behavior or security.
Upstream repository
Open publisher repository

Compatibility

Codex

documented

OpenAI's repository documents curated skills for Codex and installation through the built-in skill installer.

Requirements and access

  • Poppler for page rendering
  • reportlab for generation when needed
  • pdfplumber or pypdf for extraction and structural checks

Referenced tools

pdftoppmreportlabpdfplumberpypdf

Install from the source

The pinned README documents name-based installation for curated skills and says to restart Codex. It also marks this repository deprecated in favor of OpenAI's plugins repository, so confirm the current path before adopting it.

View the SKILL.md at its source Verify the publisher's install documentation

More Documents, data and media skills →

Codex skill installer

$skill-installer pdf

Thyme RAG Capsules

Make this skill’s state durable, governed, and portable.

A Retenta capsule lets agents recall prior work, append provenance-stamped progress, and carry the memory to the next run.

Create durable agent memoryUnderstand the evidence labels