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/document-gen-fallback-enhanced-enhanced-9f3b1fWrote 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/document-gen-fallback-enhanced-enhanced-9f3b1f)<a href="https://agentmods.dev/skills/hkuds/openspace/document-gen-fallback-enhanced-enhanced-9f3b1f"><img src="https://agentmods.dev/badge/skills/hkuds/openspace/document-gen-fallback-enhanced-enhanced-9f3b1f/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/document-gen-fallback-enhanced-enhanced-9f3b1f"><img src="https://agentmods.dev/badge/skills/hkuds/openspace/document-gen-fallback-enhanced-enhanced-9f3b1f.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 | $0.00030 | $0.04827 |
| Opus 5 | $0.00015 | $0.02413 |
| Sonnet 5 | $0.00006 | $0.00965 |
| Haiku 4.5 | $0.00003 | $0.00483 |
Grade A, and why
document-gen-dual-backend 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 10d 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 — 649 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Document Generation: Dual-Backend Workflow (Unicode-Safe)
When to Use
Default Approach: Lightweight Direct Execution (Recommended for 90% of tasks)
For most document generation tasks, use direct write_file + run_shell without shell_agent:
- Generating documents in standard formats (
.docx,.pdf,.html) from Markdown - Content is straightforward with minimal special characters
- You already know the pandoc/ReportLab commands needed
- Quick single-format or multi-format output is needed
Fallback Approach: shell_agent Delegation (For Complex Scenarios Only)
Use shell_agent delegation only when:
- Automated fallback handling between backends requires complex logic
- Dynamic content generation needs programmatic decision-making
- You need to capture and analyze error messages for intelligent retry logic
When shell_agent May Be Useful (Optional)
Only consider shell_agent delegation for:
- Complex error recovery requiring automated backend switching
- Dynamic workflows with conditional branching based on generation results
Core Technique
For simple tasks (default): Use direct write_file + run_shell with pandoc or ReportLab (no shell_agent needed)
For complex tasks requiring fallback logic: Split the workflow into discrete, observable steps with two PDF generation paths:
Path A (Pandoc): Best for Markdown-to-PDF conversion with rich text formatting Path B (ReportLab): Best for programmatic PDF generation without LaTeX dependencies
Workflow steps:
- Content creation → Use
write_fileto create source document (Markdown) - Choose PDF backend → Decide between pandoc (rich formatting) or ReportLab (programmatic control)
- Unicode handling → Apply sanitization for pandoc; ReportLab handles Unicode natively
- Format conversion → Use
run_shellwith appropriate commands for each format - Verification → Check output files exist and are valid
⚠️ Backend Selection Guide
| Requirement | Recommended Backend | Rationale |
|---|---|---|
| Markdown source with headers, lists, tables | Pandoc | Native Markdown parsing |
| Heavy Unicode/special characters | ReportLab | Native UTF-8 support, no sanitization needed |
| LaTeX not available | ReportLab | Pure Python, no external dependencies |
| Precise layout control (positions, graphics) | ReportLab | Programmatic canvas control |
| Quick DOCX + PDF + HTML batch | Pandoc | Single tool, multiple outputs |
| Tables with complex formatting | Pandoc | Better table rendering |
| Dynamic/charts/graphs in PDF | ReportLab | Drawing operations 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.
- 10d ago First seen · 649 lines · 30 tokens per session scan A 006839791dab
document-gen-dual-backend is a skill published in the GitHub repository HKUDS/OpenSpace (7,552 stars, last pushed 28d ago), licensed MIT. It adds 30 tokens to every session and 4,827 once invoked, about $0.0002 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 2026-08-30.
Other skills, from other repositories
orbit-notion
Open Orbit briefing skill — selected by the Orbit pipeline when Notion is the user's only connected connector, or when the user explicitly scopes their daily digest to Notion. Pulls the past 24 hours of document edits, comments, mentions, and database row changes from the user's authenticated Notion connection and…
instrument-data-to-allotrope
Convert laboratory instrument output files (PDF, CSV, Excel, TXT) to Allotrope Simple Model (ASM) JSON format or flattened 2D CSV. Use this skill when scientists need to standardize instrument data for LIMS systems, data lakes, or downstream analysis. Supports auto-detection of instrument types. Outputs include full…
baoyu-youtube-transcript
A tool for downloading the written captions, subtitles, chapter information, speaker labels, and cover image from a YouTube video using its URL or ID.
feishu
Work with Feishu or Lark bots, docs, sheets, bitables, approval flows, and OpenAPI/MCP setup without hardcoding credentials.
read
Reads URLs and PDFs by fetching source content, defaulting to concise summaries for plain read requests and clean Markdown when asked to convert, save, quote, cite, or feed downstream work. Use when users ask in any language to read, fetch, check, summarize, quote, cite, convert, or save a URL or PDF. Not for local…
overleaf-sync
A two-way connection between a local paper folder and Overleaf, a web-based LaTeX editor for writing research papers. It lets you move changes between the local files and the shared Overleaf project.