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-download-extract-fallback-enhancedgit 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-download-extract-fallback-enhanced)<a href="https://agentmods.dev/skills/hkuds/openspace/pdf-download-extract-fallback-enhanced"><img src="https://agentmods.dev/badge/skills/hkuds/openspace/pdf-download-extract-fallback-enhanced/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.
<a href="https://agentmods.dev/skills/hkuds/openspace/pdf-download-extract-fallback-enhanced"><img src="https://agentmods.dev/badge/skills/hkuds/openspace/pdf-download-extract-fallback-enhanced.svg" alt="Reviewed on agentmods" width="80" 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 | $0.00036 | $0.02419 |
| Opus 5 | $0.00018 | $0.01210 |
| Sonnet 5 | $0.00007 | $0.00484 |
| Haiku 4.5 | $0.00004 | $0.00242 |
Grade A, and why
pdf-extract-ordered-fallback scanned grade A with 1 finding 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 6d 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.
Many PDF hosting sites use JavaScript-based redirects or block automated requests. Use curl with a realistic browser user-agent: How it starts
The opening of the file, as written. The whole thing — 270 lines — stays where its author put it; the contents beside it link to each section on GitHub.
PDF Download and Extract with Ordered Fallback
This skill provides a robust workflow for acquiring PDF documents from web sources and extracting their text content, with a clearly ordered sequence of tool invocations to maximize success rate.
Overview
When working with PDFs from web sources, encounters with JavaScript redirects, corrupted files, missing tools, or inaccessible content are common. This workflow ensures maximum success rate through a严格 ordered fallback sequence that prioritizes shell-based tools over Python sandbox execution.
Ordered Tool Chain Summary
| Step | Tool | Method | Priority |
|---|---|---|---|
| 0 | read_file | Direct PDF text extraction | First attempt |
| 1 | run_shell | pdftotext command | Primary fallback (if Step 0 returns binary/fails) |
| 2 | execute_code_sandbox | PyMuPDF Python library | Secondary fallback (if Step 1 fails) |
| 3 | Domain knowledge | Manual content generation | Last resort |
Key principle: Always try shell tools (run_shell) before Python sandbox (execute_code_sandbox) when both are viable options. Shell execution is more reliable in constrained environments.
Step-by-Step Instructions
Step 0: Initial Extraction Attempt with read_file Tool
First, attempt to extract PDF text using the read_file tool. This is the simplest approach and handles many PDFs correctly:
read_file filetype="pdf" file_path="path/to/document.pdf"
Expected outcomes:
- Success: Returns extracted text content - proceed to use this directly
- Binary/Image data returned: The tool failed to extract text; file content is raw binary or image data
- Immediate action: Proceed to Step 1 (run_shell with pdftotext)
- Error returned: Tool failed entirely; proceed to Step 1 (run_shell with pdftotext)
Critical: If read_file returns binary data (PNG/JPEG headers, raw PDF bytes), do NOT attempt to parse it manually. Immediately switch to shell-based pdftotext.
Step 1: Download PDF with Browser User-Agent
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.
- 6d ago First seen · 270 lines · 0 tokens per session scan A f399b17c4ff3
pdf-extract-ordered-fallback is a skill published in the GitHub repository HKUDS/OpenSpace (7,552 stars, last pushed 28d ago), licensed MIT. It adds 36 tokens to every session and 2,419 once invoked, about $0.0002 per session on Opus 5. A static security scan graded it A with 1 finding (makes network calls). 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…