The Agent Skills Directory

[EXTERNAL_DOWNLOADS]: The skill requires downloading and running the ui-to-vue-converter package from the npm registry.
Evidence: npx ui-to-vue-converter@1.0.2 and npm install -g ui-to-vue-converter@1.0.2 in SKILL.md.
Note: The tool is pinned to version 1.0.2.
[COMMAND_EXECUTION]: The skill involves the execution of shell commands to facilitate the conversion and manage environment variables.
Evidence: Use of npx, npm, and export commands for tool invocation and API key configuration.
[DATA_EXFILTRATION]: The skill sends user-provided design screenshots to the DashScope API (Alibaba Cloud) for conversion processing.
Evidence: The documentation notes that screenshots are sent to an external model API and requires the DASHSCOPE_API_KEY for authentication.
[PROMPT_INJECTION]: The skill processes untrusted image files, creating a surface for indirect prompt injection attacks.
Ingestion points: Image files within the user-specified input directory (e.g., ./screenshots).
Boundary markers: No explicit markers are defined to isolate data from instructions during model processing.
Capability inventory: The skill has the capability to execute shell commands via npx and write to the local file system (./src).
Sanitization: No validation or sanitization of content extracted from the images is described.

ui-to-vue