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.
Getting it into your agent
It runs from inside its repository, so the clone comes first — what it calls does not travel with the file alone.
git clone --depth 1 https://github.com/HKUDS/OpenSpacenpx agentmods add skills/hkuds/openspace/pdf-verification-cli-enhanced-657992Wrote 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.
[](https://agentmods.dev/skills/hkuds/openspace/pdf-verification-cli-enhanced-657992)<a href="https://agentmods.dev/skills/hkuds/openspace/pdf-verification-cli-enhanced-657992"><img src="https://agentmods.dev/badge/skills/hkuds/openspace/pdf-verification-cli-enhanced-657992.svg" alt="Measured on agentmods" height="20"></a>- NVIDIA SkillSpector pass
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.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00024 | $0.04299 |
| Opus 5 | $0.00012 | $0.02150 |
| Sonnet 5 | $0.00005 | $0.00860 |
| Haiku 4.5 | $0.00002 | $0.00430 |
Grade C, and why
pdf-to-report-workflow scanned grade C with 2 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 4d 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.
Recursive force deletehighDestructive command
rm -rf with a variable or a broad path is one typo away from removing the wrong tree.
trap "rm -rf $WORKDIR" EXIT Runs shell commandslowCapability
Expected in a hook, worth knowing in a rule or an instructions file.
result = subprocess.run(['which', tool], How it starts
The opening of the file, as written. The whole thing — 585 lines — stays where its author put it; the contents beside it link to each section on GitHub.
PDF-to-Report Generation Workflow
This skill provides a complete end-to-end workflow for processing PDF documents: extracting content from source PDFs, assembling report data, and generating new PDF output files—all using command-line tools when Python libraries are unavailable.
When to Use This Skill
- Need to extract text/content from existing PDFs
- Need to create new PDF reports from extracted data
- Need to combine multiple PDF sources into a single report
- PyPDF2, reportlab, or similar Python PDF libraries are unavailable
- Working in minimal/containerized environments
Core Tools
Extraction Tools (poppler-utils)
1. pdfinfo - Extract PDF Metadata
# Get full PDF info
pdfinfo document.pdf
# Get only page count
pdfinfo document.pdf | grep Pages
# Extract page count as a number
pdfinfo document.pdf | grep Pages | awk '{print $2}'
Key metadata fields:
Pages: Number of pages in the PDFTitle: Document titleAuthor: Document authorCreationDate: When the PDF was createdModDate: Last modification date
2. pdftotext - Extract Text Content
# Extract all text to stdout
pdftotext document.pdf -
# Extract text to a file
pdftotext document.pdf output.txt
# Extract text from specific page range
pdftotext -f 1 -l 3 document.pdf output.txt
# Preserve layout (rough formatting)
pdftotext -layout document.pdf output.txt
Generation Tools (Choose based on availability)
1. enscript + ps2pdf - Text to PDF (Recommended)
Convert plain text to PDF via PostScript:
# Install if needed
apt-get install -y enscript ghostscript
# Convert text file to PDF
enscript -B -o output.ps input.txt && ps2pdf output.ps output.pdf
# One-liner
enscript -B input.txt -o - | ps2pdf - output.pdf
Options:
-B: No borders-o: Output file (- for stdout)-f: Font specification (e.g.,-fCourier10)
2. wkhtmltopdf - HTML to PDF
Convert HTML to PDF with full formatting support:
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.
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.
- 4d ago First seen · 585 lines · 0 tokens per session scan C 314d456cc499
pdf-to-report-workflow is a skill published in the GitHub repository HKUDS/OpenSpace (7,534 stars, last pushed 25d ago), licensed MIT. It adds 24 tokens to every session and 4,299 once invoked, about $0.0001 per session on Opus 5. A static security scan graded it C with 2 findings (recursive force delete, runs shell commands). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-09-03.
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.
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.
skill-doc-delivery
Convert markdown to DOCX, PPTX, XLSX, PDF office documents — use when you need exportable deliverables.
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.
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.
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…