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 robust-file-creationgit 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/robust-file-creation)<a href="https://agentmods.dev/skills/hkuds/openspace/robust-file-creation"><img src="https://agentmods.dev/badge/skills/hkuds/openspace/robust-file-creation/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/robust-file-creation"><img src="https://agentmods.dev/badge/skills/hkuds/openspace/robust-file-creation.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 1 finding, up to medium
These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →
- medium Excessive Agency · line 86 Skill enables autonomous high-impact decisions without human-in-the-loop verification. Critical operations (destructive commands, financial transactions, data deletion) should require explicit user confirmation.Fix: Add human-in-the-loop confirmation for destructive, irreversible, or high-impact operations. Never auto-execute commands that modify files, send data, or alter system state.
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 | $0.00662 |
| Opus 5 | $0.00013 | $0.00331 |
| Sonnet 5 | $0.00005 | $0.00132 |
| Haiku 4.5 | $0.00003 | $0.00066 |
Grade A, and why
robust-file-creation 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 5d 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 — 86 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Robust File Creation Strategy
When creating complex project structures, automated tools like execute_code_sandbox and shell_agent may fail with 'unknown error' on filesystem operations. This skill provides a reliable fallback strategy using explicit shell commands.
When to Use
Apply this pattern when:
execute_code_sandboxfails with unknown error on file/directory creationshell_agentfails to complete filesystem operations after retries- You need to create nested directory structures with multiple files
- Task progress is blocked by filesystem tool failures
Fallback Procedure
Step 1: Detect the Failure
When either execute_code_sandbox or shell_agent fails on filesystem operations (especially after automatic retries), immediately switch to the manual hybrid approach.
Step 2: Create Directories Explicitly
Use run_shell with mkdir -p for each required directory:
run_shell command="mkdir -p /path/to/nested/directory"
The -p flag ensures parent directories are created automatically.
Step 3: Write Files Individually
Use write_file tool for each file with explicit path and content:
write_file path="/path/to/file.py" content="..."
Do not attempt to batch multiple file creations in a single operation.
Step 4: Verify Creation (Optional)
Confirm the structure was created correctly:
run_shell command="ls -la /path/to/directory"
# or
run_shell command="tree /path/to/directory"
Complete Example Flow
[execute_code_sandbox fails on project setup]
↓
[run_shell mkdir -p src/components]
[run_shell mkdir -p src/utils]
[run_shell mkdir -p tests]
↓
[write_file path="src/main.py" content="..."]
[write_file path="src/components/widget.py" content="..."]
[write_file path="tests/test_main.py" content="..."]
↓
[run_shell ls -la src/ # verify]
Best Practices
- Create all directories first before writing any files to avoid path errors
- Write files one at a time rather than attempting batch operations
- Use absolute or clearly relative paths to avoid ambiguity
- Verify after creation when working on critical deliverables
- Document the structure in comments or SKILL.md if it's complex
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.
- 5d ago First seen · 86 lines · 25 tokens per session scan A 995dab9f2c90
robust-file-creation is a skill published in the GitHub repository HKUDS/OpenSpace (7,544 stars, last pushed 27d ago), licensed MIT. It adds 25 tokens to every session and 662 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
webgl-holographic-foil
A self-contained WebGL2 hero: thin-film interference over a crushed-foil surface whose palette shifts with the viewing angle; move the cursor to tilt the film.
general-video
Author or edit a custom HyperFrames composition when no specialized workflow fits, or when BRIEF.md sets flow: companion. Use for longer or multi-scene pieces, brand and sizzle reels, montages, static loops, static title cards, footage remixes, and freeform builds. Use motion-graphics instead for a short unnarrated…
html-ppt-hermes-cyber-terminal
OpenDesign + BYOK: choosing and wiring your own model, hands-on — cost, quality, and the routing decision. Built as a decision-grade AI literacy deck for engineers, IT, applied-AI teams.
html-ppt-taste-brutalist
16:9 HTML deck in tactical-telemetry / CRT-terminal taste. Deactivated-CRT charcoal slides, white-phosphor monospace, hazard-red accent, scanline overlay, ASCII syntax, density over decoration. Distilled from Leonxlnx/taste-skill brutalist-skill (Tactical Telemetry mode).
chengfeng-check-updates
An environment manager for a video-editing system. It checks whether its skills and runtime—the software needed to run them—are installed and compatible.
infographic-template-updater
Update template catalogs and UI prompts after adding new infographic templates (src/templates/.ts), including SKILL.md template list, site gallery template mappings, and the AIPlayground prompt list.