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-enhanced-899f5bgit 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-899f5b)<a href="https://agentmods.dev/skills/hkuds/openspace/pdf-download-extract-fallback-enhanced-899f5b"><img src="https://agentmods.dev/badge/skills/hkuds/openspace/pdf-download-extract-fallback-enhanced-899f5b/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-899f5b"><img src="https://agentmods.dev/badge/skills/hkuds/openspace/pdf-download-extract-fallback-enhanced-899f5b.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 | $0.00027 | $0.02730 |
| Opus 5 | $0.00014 | $0.01365 |
| Sonnet 5 | $0.00005 | $0.00546 |
| Haiku 4.5 | $0.00003 | $0.00273 |
Grade A, and why
pdf-extract-progressive-tools 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 8d 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.
How it starts
The opening of the file, as written. The whole thing — 318 lines — stays where its author put it; the contents beside it link to each section on GitHub.
PDF Text Extraction with Progressive Tool Fallback
This skill provides a robust workflow for extracting text from PDF documents using a sequenced approach with agent tools, with explicit fallback mechanisms based on observed tool behavior.
Critical Insight from Execution Data
read_file often returns binary/image data for PDFs, not extracted text. When this occurs, immediately escalate to run_shell with pdftotext before attempting Python-based extraction.
Entry Point: Determine Your Starting Point
Before beginning, identify your scenario:
| Scenario | Start Here | Skip |
|---|---|---|
| PDF already on local disk | Step 1 (read_file attempt) | Download steps |
| PDF at a web URL | Download first, then Step 1 | None |
| PDF content already extracted | Step 4 (Quality verification) | Steps 1-3 |
Overview
PDF extraction failures cascade when tool sequencing is unclear. This workflow ensures maximum success rate through explicit tool progression:
- read_file - Quick attempt, but may return binary data
- run_shell + pdftotext - Reliable extraction when read_file fails
- execute_code_sandbox + PyMuPDF - Final fallback for complex PDFs
Step-by-Step Instructions
Step 1: Attempt read_file First
Always try the simplest approach first:
Tool: read_file
Path: document.pdf
Expected outcome: Extracted text content
Critical check: Examine the returned content:
- ✅ Text visible: Proceed to Step 4 (Quality verification)
- ⚠️ Binary/image data detected: Immediately proceed to Step 2
- ❌ File not found: Verify path or download first
Binary data indicators:
- Content starts with
%PDF-header without text extraction - Content appears as garbled characters or base64
- Content contains PNG/JPEG markers within PDF wrapper
- File size seems reasonable but no readable text
Step 2: Escalate to run_shell with pdftotext
When read_file returns binary data, do NOT attempt execute_code_sandbox yet. Use run_shell immediately:
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.
- 8d ago First seen · 318 lines · 27 tokens per session scan A bcf5f4c35b6a
pdf-extract-progressive-tools is a skill published in the GitHub repository HKUDS/OpenSpace (7,565 stars, last pushed 1mo ago), licensed MIT. It adds 27 tokens to every session and 2,730 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.
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…