Shadergraph Editor
v0.1.0Author, load, and troubleshoot Reality Composer Pro Shader Graph materials for RealityKit on visionOS. Use when building Shader Graph materials, exposing pro...
⭐ 0· 114·0 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 name/description match the instructions: the skill is a guidance/reference tool for authoring and troubleshooting Shader Graph materials. It declares no binaries, env vars, or installs, which is appropriate for a documentation-style skill. Minor note: the UI metadata (agents/openai.yaml) references icon assets that are not present in the provided file manifest; this is a packaging/metadata inconsistency but not a security concern.
Instruction Scope
SKILL.md confines actions to authoring guidance, runtime mapping of promoted inputs, and optional USD/MaterialX inspection for debugging. It does not instruct the agent to read unrelated system files, exfiltrate data, or call external endpoints. Note: the skill references sample files (samples/...) — those samples are described but not bundled in the provided manifest, so the agent will need access to the user's repo/project files to follow the 'start from sample' workflow.
Install Mechanism
No install spec or code is included (instruction-only). Nothing is downloaded or written to disk by the skill itself.
Credentials
No environment variables, credentials, or config paths are requested. The lack of secret access aligns with a purely instructional/reference skill.
Persistence & Privilege
always is false and the skill does not request elevated or persistent system privileges. Model invocation is allowed (the platform default) but the skill's scope and lack of credentials mean autonomous invocation has limited risk here.
Assessment
This is an instruction-only, documentation-style skill and appears coherent with its stated goal—no credentials or installs are required. Before installing: 1) confirm whether you want the agent to access your project files (the skill expects to reference samples in a repo); 2) be aware the agent’s autonomous invocation is allowed by default—if you permit it, ensure you trust it to open or edit your local project; 3) note the UI metadata references icon files not bundled here (packaging issue only). If you want stricter limits, disable autonomous invocation or only invoke the skill manually.Like a lobster shell, security has layers — review code before you run it.
latestvk9752w9c7681nqjhtb7sjfbgk1837tnw
License
MIT-0
Free to use, modify, and redistribute. No attribution required.