Publisher: OpenAI · Editorial profile by AI Tools Ratings · Review method
Not runtime tested; source-document review only. No security certification.
What task is this skill designed for?
Create a short client report from supplied figures, render each page, and inspect the result for clipped tables and unreadable labels.
What input and output should you expect?
Input: An approved report outline, source figures and page-size requirements. Use synthetic figures for an initial trial.
Output: Expected, not independently tested: a PDF in output/pdf/ and rendered page images used for visual review.
What does it need to run?
A Codex environment with file access and command execution. The source names Python reportlab, pdfplumber and pypdf, plus Poppler for rendering; dependency installation may require network access and administrator support.
Author-provided Codex skill in OpenAI's skills repository; not independently executed on Codex, Claude Code or Cursor.
How should you approach installation?
- Open the pinned source below and inspect its dependencies and referenced files.
- Follow the repository's current Codex installation instructions for this specific skill; no installation command has been independently verified here.
- Try a synthetic one-page report in an isolated working folder, then check both extracted text and rendered page images.
Installation guide: discovery, dependencies and runtime checks
What files, accounts or data can it access?
Can read supplied documents, create local files and invoke rendering tools. Dependency installation may contact package registries. This editorial review does not establish all possible runtime behavior.
What does the skill cost?
No skill purchase is listed. Agent usage, rendering dependencies and any external services have their own terms.
What are its limits and alternatives?
Text extraction cannot establish layout fidelity. Scanned documents may need a separate OCR workflow. Page rendering and visual inspection remain necessary; the skill does not guarantee accessible PDF tagging.
For simple searchable-text extraction, a direct PDF library can be simpler. Use this workflow when page appearance is part of acceptance.
What could you ask in a small trial?
Try this with a small sample:
Create a one-page PDF from these synthetic figures. Render it to images, check table clipping and report any visual checks you could not perform.
How would you verify the result?
- Compare extracted values with the synthetic source figures.
- Inspect every rendered page for clipping, font substitution and unreadable labels.
- Check that the output opens in an ordinary PDF reader.
Use a baseline and record acceptance evidence before treating a successful task as a reliable workflow.
Which source and license were checked?
Read the reviewed SKILL.md at its pinned commit · Complete reviewed folder
Repository and current publisher guidance
Checked:
Apache-2.0 — identified in skills/.curated/pdf/LICENSE.txt at the reviewed commit. Third-party assets and dependencies may have separate terms. License evidence
Version details and review scope
Source: openai/skills/skills/.curated/pdf
Reviewed commit: 49f948faa9258a0c61caceaf225e179651397431
SKILL.md SHA-256: d108cf2b36355ab37eb5962933f4d09785ec002f3105c506129320209306b9d2
Source-document review. Source text and stated dependencies were inspected for this profile. Referenced code was not comprehensively audited, no runtime test was performed, and source files are not mirrored here.