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-debug-unbufferedgit 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-debug-unbuffered)<a href="https://agentmods.dev/skills/hkuds/openspace/pdf-debug-unbuffered"><img src="https://agentmods.dev/badge/skills/hkuds/openspace/pdf-debug-unbuffered/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-debug-unbuffered"><img src="https://agentmods.dev/badge/skills/hkuds/openspace/pdf-debug-unbuffered.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 | $0.00025 | $0.00725 |
| Opus 5.5 | $0.00010 | $0.00290 |
| Sonnet 5.5 | $0.00005 | $0.00145 |
| Haiku 4.5 | $0.00003 | $0.00072 |
Grade A, and why
pdf-debug-unbuffered 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 1mo 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 — 96 lines — stays where its author put it; the contents beside it link to each section on GitHub.
PDF Generation Debug Technique
When Python PDF libraries (reportlab, fpdf, etc.) fail with generic "unknown error" messages, the actual cause is often hidden due to output buffering or error swallowing. This skill provides a technique to expose the real traceback.
Core Technique
Run the Python script with the -u flag (unbuffered output) and pipe stderr through head to capture the actual error:
python -u your_script.py 2>&1 | head -100
Or more specifically, to focus on stderr:
python -u your_script.py 2>&1 | head -50
Why This Works
-uflag: Forces Python to run in unbuffered mode, ensuring output (including errors) is flushed immediately rather than held in buffers that may be lost on crash2>&1: Redirects stderr to stdout so both streams are captured togetherhead: Limits output to show the most relevant error messages at the top
Step-by-Step Debugging
Step 1: Identify the failing script
Locate the Python script that generates the PDF and is producing generic errors.
Step 2: Run with unbuffered output
python -u generate_pdf.py 2>&1 | head -100
Step 3: Analyze the traceback
Look for:
- Import errors (missing dependencies)
- File path issues (invalid paths, permission errors)
- Font registration problems (common with reportlab)
- Memory or resource constraints
Step 4: Fix the underlying issue
Address the specific error revealed in the traceback.
Step 5: Re-run normally
Once fixed, run the script without the debug flags to confirm it works:
python generate_pdf.py
Common Issues Revealed
| Symptom | Likely Cause |
|---|---|
| "unknown error" on PDF save | File path doesn't exist or no write permissions |
| Generic failure during build | Missing font files or font registration issues |
| Silent crash | ImportError for missing dependencies |
| Incomplete PDF | Script terminated early due to unhandled exception |
Alternative Approaches
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.
- 1mo ago First seen · 96 lines · 25 tokens per session scan A fe0b76463482
pdf-debug-unbuffered is a skill published in the GitHub repository HKUDS/OpenSpace (7,766 stars, last pushed 2mo ago), licensed MIT. It adds 25 tokens to every session and 725 once invoked, about $0.0001 per session on Opus 5.5. 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
latex-rescue
Diagnose and repair LaTeX build failures in local projects or supplied logs. Make minimal source fixes, preserve scientific content and reference keys, and report actual build evidence and unresolved errors.
sk-create-diff
Local, Git-free before/after review of an edited document (text, Markdown, HTML, DOCX, text PDF) as a self-contained HTML report.
tikz
Audit and fix TikZ visual collisions in any .tex file. Use when labels overlap arrows, text sits on boxes, or arrows cross each other. Applies mathematical gap calculations and Bézier depth formulas — no eyeballing.
overleaf-compile
Recompile an Overleaf project and extract its build logs, errors and warnings in a standardized format. Use when asked to compile/recompile an Overleaf paper, debug why a PDF build fails, see what's broken after pushing changes, or pull LaTeX/biber errors and warnings out of an Overleaf project. Drives an…
latex-compilation-fix
Auto-diagnose and fix common LaTeX compilation errors for the PKU thesis template including missing packages, font issues, citation undefined, overfull hboxes, and float placement. Use when xelatex fails or produces warnings.
apify-youtube-transcript-scraper
Get YouTube captions, timestamped quotations, SRT/VTT and translated transcripts for videos, channels and playlists through the harshmaur/youtube-transcript-scraper Apify Actor.