Usd Editor
v0.1.0Guide for modifying USD ASCII (.usda) files, including prims, properties, composition arcs, variants, and transforms. Use when editing or reviewing .usda fil...
⭐ 0· 105·0 current·0 all-time
byTom Krikorian@tomkrikorian
MIT-0
Download zip
LicenseMIT-0 · Free to use, modify, and redistribute. No attribution required.
Security Scan
OpenClaw
Benign
high confidencePurpose & Capability
The skill's name/description match the included instructions and reference docs for USD editing. One minor mismatch: the SKILL.md instructs use of USD command-line tools but the skill declares no required binaries — this is reasonable for an instruction-only skill but means the agent will need those tools available at runtime to follow the guidance.
Instruction Scope
Runtime instructions are focused on editing .usda files, preserving composition, and using USD CLI tools. They do not direct reading unrelated system files, exfiltration, or contacting external endpoints.
Install Mechanism
No install spec and no code files — lowest-risk pattern for an instruction-only skill. The skill only contains documentation and examples.
Credentials
No environment variables, credentials, or config paths are requested. The references to USD tools are proportional to the stated task.
Persistence & Privilege
always is false and the skill is user-invocable. It does not request persistent privileges or modify other skills or system settings.
Assessment
This skill appears coherent and instruction-only: it provides guidance and examples for editing .usda files and recommends using official USD CLI tools. Before installing/using it, ensure the USD command-line tools (usdcat, usdedit, usdtree, usdchecker, usdzip, usdrecord, etc.) are available on the agent environment if you expect the agent to run them. Because the skill can be invoked by the agent to edit files, confirm the agent has appropriate file access and that you keep backups or use usdedit --noeffect to preview changes. There are no requests for credentials or external endpoints; nevertheless review any outputs the agent proposes to write and avoid granting the agent unrelated system or network privileges.Like a lobster shell, security has layers — review code before you run it.
latestvk972rb73rdxjxa5cfyys5ckjm9837ymb
License
MIT-0
Free to use, modify, and redistribute. No attribution required.