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
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.
npx skills add HKUDS/OpenSpace --skill pdf-extraction-fallbacks-7d54a9git clone --depth 1 https://github.com/HKUDS/OpenSpaceWrote 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-extraction-fallbacks-7d54a9)<a href="https://agentmods.dev/skills/hkuds/openspace/pdf-extraction-fallbacks-7d54a9"><img src="https://agentmods.dev/badge/skills/hkuds/openspace/pdf-extraction-fallbacks-7d54a9.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 | $0.00025 | $0.01872 |
| Opus 5 | $0.00013 | $0.00936 |
| Sonnet 5 | $0.00005 | $0.00374 |
| Haiku 4.5 | $0.00003 | $0.00187 |
Grade A, and why
pdf-extraction-fallbacks-7d54a9 scanned grade A with 2 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 4d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
curl -L -o document.pdf "URL_HERE" Runs shell commandslowCapability
Expected in a hook, worth knowing in a rule or an instructions file.
result = subprocess.run( How it starts
The opening of the file, as written. The whole thing — 258 lines — stays where its author put it; the contents beside it link to each section on GitHub.
PDF Extraction Fallbacks
This skill provides a robust workflow for extracting text from PDFs when source documents may fail to download or extract due to JavaScript protection, CORS restrictions, or encoding issues.
When to Use
- Downloading regulatory documents from government/agency websites
- Extracting text from PDFs that may be JavaScript-protected
- Handling PDFs with potential CORS or encoding issues
- When you need reliable text extraction with guaranteed fallbacks
Core Workflow
Step 1: Download with Validation
# Download PDF and immediately validate
curl -L -o document.pdf "URL_HERE"
# Check file size (reject if < 1KB - likely error page)
FILE_SIZE=$(stat -f%z document.pdf 2>/dev/null || stat -c%s document.pdf 2>/dev/null)
if [ "$FILE_SIZE" -lt 1024 ]; then
echo "FAIL: File too small ($FILE_SIZE bytes) - likely error page"
# Log the actual content to diagnose
head -c 500 document.pdf
exit 1
fi
# Check for HTML/error content instead of PDF
if head -c 500 document.pdf | grep -qi "<!DOCTYPE html\|<html\|error\|access denied"; then
echo "FAIL: Downloaded HTML/error page instead of PDF"
exit 1
fi
Step 2: Sequential Extraction Fallbacks
Try extraction methods in order of reliability:
Fallback 1: pdftotext (poppler-utils)
if command -v pdftotext &> /dev/null; then
pdftotext -layout document.pdf output.txt 2>/dev/null
if [ -s output.txt ] && [ $(wc -c < output.txt) -gt 100 ]; then
echo "SUCCESS: pdftotext extraction"
exit 0
fi
fi
Fallback 2: PyMuPDF (fitz)
import fitz # PyMuPDF
def extract_with_pymupdf(pdf_path):
try:
doc = fitz.open(pdf_path)
text = ""
for page in doc:
text += page.get_text()
doc.close()
if len(text.strip()) > 100:
return text
return None
except Exception as e:
print(f"PyMuPDF failed: {e}")
return None
Fallback 3: pdfplumber
import pdfplumber
def extract_with_pdfplumber(pdf_path):
try:
text = ""
with pdfplumber.open(pdf_path) as pdf:
for page in pdf.pages:
page_text = page.extract_text()
if page_text:
text += page_text + "\n"
if len(text.strip()) > 100:
return text
return None
except Exception as e:
print(f"pdfplumber failed: {e}")
return None
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 · 258 lines · 25 tokens per session scan A b2475dbc5a82
pdf-extraction-fallbacks-7d54a9 is a skill published in the GitHub repository HKUDS/OpenSpace (7,534 stars, last pushed 26d ago), licensed MIT. It adds 25 tokens to every session and 1,872 once invoked, about $0.0001 per session on Opus 5. A static security scan graded it A with 2 findings (makes network calls, 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…