Productivity & Collaboration ✓ OpenAI · Official pdf-processingpdf-extractiondocument-renderingreportlabpdfplumberpypdfpoppler

PDF Document Workflow

Read, create, and visually validate PDFs where layout matters.

FollowSkills review · FSRS-2.0
Not recommended
46/ 100 5-point scale 2.3 / 5
Trust12 / 25 · 2.4/5

The skill scopes work to PDF tasks and specifies temporary and output locations plus dependencies, but it lacks confirmation before installation or external writes, sensitive-PDF handling, data-flow disclosure, rollback guidance, and dependency-integrity verification, so points are deducted.

Reliability8 / 20 · 2.0/5

The workflow is internally coherent and covers rendering, extraction, and final checks, but it contains no committed tests or key-path reproduction evidence. Missing dependencies are largely delegated to the user, and abnormal-input handling and failure diagnostics are thin, so points are deducted.

Adaptability9 / 15 · 3.0/5

The intended scenarios—reading, creating, and reviewing PDFs where layout matters—are clear. However, non-fit boundaries, semantic trigger precision, Chinese-language support, and environment-fit evidence are limited; local dependency installation is assumed, so points are deducted.

Convention7 / 15 · 2.3/5

The document is readable and includes triggers, workflow, dependencies, environment notes, commands, and quality criteria. License metadata is unknown, and versioning, changelog, maintenance ownership, update path, examples, and FAQs are absent; the repository README also states that the repository is deprecated, so points are deducted.

Effectiveness6 / 15 · 2.0/5

The instructions plausibly support PDF generation, extraction, rendering, and review with directly usable commands. Static evidence provides no representative verified outputs, so output completeness and marginal benefit over manual or alternative workflows remain uncertain; points are deducted.

Verifiability4 / 10 · 2.0/5

The supplied files are auditable and contain concrete tools, commands, and quality checks, but there is no test suite, CI coverage, or third-party execution evidence. The assessment therefore relies mainly on documentation claims, so points are deducted.

Evidence confidence:Low Reviewed Jul 20, 2026 Reviewed revision 49f948faa925
Before you use it
  • Dependency installation may perform system-level package installation or network downloads; obtain user confirmation and assess permissions first.
  • The skill does not state whether PDF contents leave the local environment and provides no guidance for sensitive documents, cleanup, or recovery.
  • The repository README marks the repository as deprecated; current maintenance status, licensing, and future update source require separate confirmation.
Review evidence [1][2][3][4]
See the full review method →

What it does & when to use it

This skill supports PDF tasks in which content, layout, and visual presentation all matter. It directs agents to render pages to PNG for visual review and to use reportlab for programmatic PDF generation. pdfplumber or pypdf can handle text extraction and quick checks, but they are not treated as layout-fidelity tools. The skill is part of the deprecated openai/skills repository, whose README points current Codex skill and plugin examples to the OpenAI Plugins repository.

Reads and reviews PDF content; renders pages to PNG with pdftoppm for visual inspection; generates PDFs with reportlab; extracts text and performs quick checks with pdfplumber or pypdf; re-renders after meaningful updates to check alignment, spacing, legibility, tables, images, headers, footers, and page numbering.

  1. A document reviewer needs to inspect both PDF content and page layout before approval.
  2. A developer needs to generate consistently formatted PDFs programmatically with reportlab.
  3. A user needs quick PDF text extraction or validation using pdfplumber or pypdf.
  4. A publishing workflow needs a final rendering check for clipping, overlap, broken tables, black squares, or unreadable glyphs.

Pros & cons

Pros
  • Prioritizes visual rendering rather than relying only on extracted text.
  • Covers generation, extraction, review, and final validation.
  • Names concrete tools including reportlab, pdfplumber, pypdf, and pdftoppm.
  • Defines conventions for temporary files and final artifacts.
Limitations
  • The repository is deprecated, so long-term adoption should be assessed against the OpenAI Plugins repository.
  • pdfplumber and pypdf do not provide layout-fidelity validation.
  • The workflow depends on Poppler and several Python packages, with no versions specified.
  • The source provides no test suite, platform verification matrix, or detailed error-recovery procedure.

How to install

The skill is located at skills/.curated/pdf/SKILL.md. The README documents installation through Codex's skill installer: $skill-installer pdf. Restart Codex after installation so it can load the skill. The repository is deprecated; the README recommends the OpenAI Plugins repository for current Codex skill and plugin examples.

How to use

In a skill-enabled Codex environment, provide a concrete PDF request such as: "Use the PDF skill to review this PDF: render its pages, inspect the layout, then extract the text." For PDF creation, request reportlab generation and a rendering check after each meaningful update. The source does not document the exact trigger mechanism.

Compared to similar skills

Compared with a workflow based only on pdfplumber or pypdf, this skill adds page rendering with Poppler to validate layout. Compared with a PDF-generation-only workflow, it requires visual review before delivery.

FAQ

What dependencies are required?
The source lists Poppler/pdftoppm plus the Python packages reportlab, pdfplumber, and pypdf. It recommends uv for dependency management.
Does it guarantee perfect PDF layout?
No. It requires rendered-page inspection and explicitly says pdfplumber and pypdf should not be relied on for layout fidelity.
Does it require network access or MCP?
The PDF workflow shows no network calls or MCP requirement. It does require local filesystem access and shell commands.
Where should outputs go?
The skill specifies tmp/pdfs/ for intermediate files and output/pdf/ for final artifacts when working in this repository.

More skills from this repository

All from openai/skills

Productivity & Collaboration ✓ OpenAI · Official

Goal Definition Assistant

Turn vague intentions into measurable, verifiable goals with clear scope and stopping conditions.

Dev & Engineering ✓ OpenAI · Official

Codex CLI Builder

Turn APIs, scripts, and existing tools into durable, composable command-line interfaces.

Design & Frontend ✓ OpenAI · Official

Codex Image Studio

Generate and edit production-ready raster assets for projects.

Dev & Engineering ✓ OpenAI · Official

OpenAI Developer Docs Assistant

Current, official guidance for building with OpenAI products, APIs, and Codex.

Dev & Engineering ✓ OpenAI · Official

Skill Creator Guide

A practical guide to designing, writing, validating, and iterating reusable Codex skills.

Dev & Engineering ✓ OpenAI · Official

ASP.NET Core Engineering Guide

Guides developers through building, reviewing, and upgrading ASP.NET Core apps.

Dev & Engineering ✓ OpenAI · Official

ChatGPT Apps Builder

Build documented ChatGPT apps that pair an MCP server with a widget UI.

Design & Frontend ✓ OpenAI · Official

Figma Code Connect Mapper

Link Figma components to their code implementations for traceable design-code consistency.

Design & Frontend ✓ OpenAI · Official

Figma Blank File Creator

Create a blank Figma Design or FigJam file in the selected drafts folder.

Design & Frontend ✓ OpenAI · Official

Figma Design Implementer

Turn Figma specifications into production-ready frontend code with verifiable visual fidelity.

Dev & Engineering ✓ OpenAI · Official

Playwright Browser Automation Skill

Drive a real browser from the terminal for web interaction, extraction, and UI debugging.

Automation & Ops ✓ OpenAI · Official

Security Best Practices Review

Security review and secure-by-default guidance for Python, JavaScript/TypeScript, and Go projects.

Design & Frontend ✓ OpenAI · Official

Hatch Pet Animation Workshop

Turn character or brand cues into validated, packageable Codex animated pets.

Productivity & Collaboration ✓ OpenAI · Official

Linear Workflow Manager

Manage Linear tickets, projects, and team workflows directly through Codex.

Automation & Ops ✓ OpenAI · Official

Repository Threat Modeler

Builds evidence-grounded, actionable AppSec threat models for code repositories.

Automation & Ops ✓ OpenAI · Official

Sentry Production Error Explorer

Inspect Sentry issues, events, and basic production health through the Sentry CLI.

Design & Frontend ✓ OpenAI · Official

Figma Design System Rules Builder

Generates project-specific rules for consistent Figma-to-code implementation.

Writing & Content ✓ OpenAI · Official

Audio Transcribe

Turn audio or video speech into text with optional speaker labels.

Design & Frontend ✓ OpenAI · Official

Figma Design System Builder

Build and validate a professional Figma design system from code.

Design & Frontend ✓ OpenAI · Official

Figma Design-to-Code Assistant

Fetch Figma design context and turn selected nodes into production code.

Related skills