reliable-pdf-extraction-ac5f89

reliable-pdf-extraction-ac5f89 is a skill for Claude Code, Codex from HKUDS/OpenSpace. It costs 27 tokens per session (723 once invoked), scanned A, original, MIT.

A workflow for extracting text from PDF files when a file-reading tool returns errors, binary data, or poor formatting. It uses PDF-specific command-line tools or libraries.

In plain words
What is it for?
Reading PDF text, checking PDF metadata, preserving layout, and extracting tables.
Why use it?
It makes PDF text extraction more reliable, especially for files with complex layouts.

Skill for Claude CodeCodex

Written for no agent in particular: nothing here depends on one.

Good fit Reading PDF text, checking PDF metadata, preserving layout, and extracting tables.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/hkuds/openspace/reliable-pdf-extraction-ac5f89
About the project

OpenSpace is a skill-management layer for AI agents that stores, retrieves, evaluates, shares, and improves reusable workflows. It is intended for people using multiple coding agents who want skills to be reused and refined based on task outcomes. The catalogue provides 200 skills for use with OpenSpace and the agents it supports.

HKUDS/OpenSpace · 7,544 stars · on GitHub

Install

Getting it into your agent

One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.

Any agent
npx skills add HKUDS/OpenSpace --skill reliable-pdf-extraction-ac5f89
Clone the repo
git clone --depth 1 https://github.com/HKUDS/OpenSpace

Made for: Claude Code, Codex.

Wrote this? Show the measurements

A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.

agentmods badge for reliable-pdf-extraction-ac5f89

README.md
[![agentmods](https://agentmods.dev/badge/skills/hkuds/openspace/reliable-pdf-extraction-ac5f89/github.svg)](https://agentmods.dev/skills/hkuds/openspace/reliable-pdf-extraction-ac5f89)
Your own site
<a href="https://agentmods.dev/skills/hkuds/openspace/reliable-pdf-extraction-ac5f89"><img src="https://agentmods.dev/badge/skills/hkuds/openspace/reliable-pdf-extraction-ac5f89/github.svg" alt="Measured on agentmods" height="20"></a>

Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.

agentmods 80×15 button for reliable-pdf-extraction-ac5f89

Your own site · 80×15
<a href="https://agentmods.dev/skills/hkuds/openspace/reliable-pdf-extraction-ac5f89"><img src="https://agentmods.dev/badge/skills/hkuds/openspace/reliable-pdf-extraction-ac5f89.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 27 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 723 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe. Third-party audits
  • NVIDIA SkillSpector pass 7 Sept 2026
How audits are shown
Origin original No closer match found in the catalogue.
Token cost

What it costs to keep this loaded

Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.

ModelPer sessionOnce invoked
Fable 5.1 $0.00027 $0.00723
Opus 5 $0.00014 $0.00362
Sonnet 5 $0.00005 $0.00145
Haiku 4.5 $0.00003 $0.00072

Measured 5d ago against content hash c0b0a2227ffd, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-09, from the pricing page.

Security

Grade A, and why

reliable-pdf-extraction-ac5f89 scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 5d ago.

A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.

Nothing flagged

None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.

benchmarks/gdpval/skills/reliable-pdf-extraction-ac5f89/SKILL.md · 121 lines

How it starts

The opening of the file, as written. The whole thing — 121 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Reliable PDF Text Extraction

Problem

The read_file tool with filetype='pdf' can be unreliable for PDF text extraction. It may:

  • Return binary image data instead of text
  • Fail with errors on certain PDF structures
  • Lose formatting or structured content

Solution

Use run_shell with dedicated PDF extraction tools instead of relying on read_file for PDFs.

Methods

Method 1: pdftotext (Recommended)

pdftotext input.pdf output.txt

Or to extract to stdout:

pdftotext input.pdf -

With layout preservation:

pdftotext -layout input.pdf output.txt

Method 2: pdfinfo (Metadata)

pdfinfo input.pdf

Useful for checking page count, dimensions, and PDF properties before extraction.

Method 3: Python with PyMuPDF (fitz)

import fitz  # PyMuPDF

doc = fitz.open("input.pdf")
text = ""
for page in doc:
    text += page.get_text()
doc.close()

Method 4: Python with pdfplumber (Tables)

import pdfplumber

with pdfplumber.open("input.pdf") as pdf:
    for page in pdf.pages:
        text = page.extract_text()
        tables = page.extract_tables()

Workflow

  1. Check PDF exists and is readable:

    pdfinfo input.pdf 2>/dev/null || echo "PDF not accessible"
    
  2. Extract text using pdftotext:

    pdftotext -layout input.pdf - > extracted_text.txt
    
  3. If pdftotext fails, try Python fallback:

    import fitz
    doc = fitz.open("input.pdf")
    for i, page in enumerate(doc):
        print(f"--- Page {i+1} ---")
        print(page.get_text())
    doc.close()
    
  4. Verify extraction succeeded:

    • Check output is non-empty
    • Verify text is readable (not binary/garbled)
    • Confirm expected content is present

When to Use

Tool Best For
pdftotext Fast, simple text extraction
pdftotext -layout Preserving spacing/formatting
PyMuPDF Complex PDFs, programmatic access
pdfplumber Tables and structured data

Read the full file on GitHub · 121 lines

Files

What ships with it

1 file beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.

Changes

What this file has done since we first saw it

Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.

  1. 5d ago First seen · 121 lines · 27 tokens per session scan A c0b0a2227ffd

Subscribe to this mod's changes

reliable-pdf-extraction-ac5f89 is a skill published in the GitHub repository HKUDS/OpenSpace (7,544 stars, last pushed 27d ago), licensed MIT. It adds 27 tokens to every session and 723 once invoked, about $0.0001 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-09-03.

Related

Other skills, from other repositories

pydicom

Use pydicom to read, inspect, write, transform, and safely preflight local DICOM datasets and pixel data. Applies to DICOM metadata, transfer syntaxes, compression plugins, frames, private elements, JSON, and bounded de-identification review.

K-Dense-AI/scientific-agent-skills · 56 tokens

foundry-hosted-agent-validation

Step-by-step process for validating a Python Foundry hosted agent sample (under python/samples/04-hosting/foundry-hosted-agents/) end to end — running it locally (native runtime and azd ai agent run) and after deploying it to an Azure AI Foundry project with azd. Use this when asked to validate a hosted agent sample.

microsoft/agent-framework · 82 tokens

skill-doc-delivery

Convert markdown to DOCX, PPTX, XLSX, PDF office documents — use when you need exportable deliverables.

nyldn/claude-octopus · 29 tokens

parse-document

Convert a PDF, scan, image of a page, or office file to clean markdown through the connected Superlinked MCP edge, so the source document is not read into model context directly. Use when the user asks to read, parse, OCR, extract from, summarize, or answer questions about a document.

superlinked/sie · 64 tokens

meta-web-to-pdf-briefing

Render a topic into a distributable PDF briefing in three steps: web search → bullet summary → styled PDF. Trigger when the user asks for a PDF briefing on a single topic.

opensquilla/opensquilla · 45 tokens

chat-complex-documents

Chat with and search your complex documents — ask questions, extract tables and fields, and get answers grounded in the source. Connects the hosted Unstructured Transform MCP server to parse, structure, and enrich PDFs, Word/Excel/PowerPoint, images, scanned files, emails, and 60+ other formats into clean, AI-ready…

vellum-ai/vellum-assistant · 90 tokens