VTL Image Analysis
v1.0.0Measure compositional structure in AI-generated images using the Visual Thinking Lens (VTL) framework. Detects default-mode bias (center lock, radial collaps...
⭐ 0· 385·0 current·0 all-time
MIT-0
Download zip
LicenseMIT-0 · Free to use, modify, and redistribute. No attribution required.
Security Scan
OpenClaw
Benign
high confidencePurpose & Capability
Name/description match the included scripts and files. Required binary (python3) and listed Python packages (numpy, opencv-python-headless, scikit-image, scipy, pyyaml) are appropriate for image processing and YAML parsing. There are no unrelated credentials, binaries, or config paths requested.
Instruction Scope
SKILL.md confines runtime actions to running the included probe and regen scripts, inspecting operator rules, and reporting measured coordinates; it enforces a hard-stop on low-confidence measurements. The instructions do not ask the agent to read unrelated files, environment variables, or transmit data to external endpoints.
Install Mechanism
No complex install spec beyond pip packages (declared in SKILL.md metadata). All packages are standard for numeric/image processing. There are no downloads from arbitrary URLs or extract/install steps that would write unknown code to disk beyond the skill folder.
Credentials
The skill requests no environment variables or credentials. It operates on local image files and local operator/metrics files only. Required resources are proportional to the functionality.
Persistence & Privilege
Skill is not always-enabled (always: false) and does not attempt to modify other skills or system-wide configuration. It writes prompts.json (user-specified path) as output but otherwise does not demand persistent presence or elevated privileges.
Assessment
This skill appears coherent and limited to local image analysis and deterministic prompt-patching. Before installing: (1) ensure you trust the skill source (it will run Python code on images you provide), (2) review operators.yaml if you want to control what prompt patches are appended, (3) be aware the scripts read image files and write an output JSON (prompts.json) to the working directory, and (4) dependencies like opencv/scipy install native wheels—install them in a virtualenv if you prefer isolation. The code uses an AST-checked evaluator for rule triggers (a cautious pattern) and contains no network calls or requests for secrets.Like a lobster shell, security has layers — review code before you run it.
latestvk97e9nevch7rwr514zd7jgw3f181vrw6
License
MIT-0
Free to use, modify, and redistribute. No attribution required.
Runtime requirements
🎛️ Clawdis
Binspython3