The Agent Skills Directory

[EXTERNAL_DOWNLOADS]: The skill uses the archlang CLI tool which is downloaded from the author's official NPM package registry (@chanmeng666/archlang) via npx or npm install.
[COMMAND_EXECUTION]: The skill involves running shell commands using the archlang tool to compile, finish, and batch process architectural drawings.
[INDIRECT_PROMPT_INJECTION]: The skill processes user-provided .arch floor plan files, creating a potential surface for indirect prompt injection if the input files contain malicious content.
Ingestion points: The skill reads and compiles .arch files provided by the user (SKILL.md).
Boundary markers: There are no explicit delimiters or instructions to ignore embedded commands within the processed files.
Capability inventory: The skill uses shell commands such as archlang compile, archlang finish, and archlang batch (SKILL.md).
Sanitization: No specific sanitization or validation of the input file content is mentioned prior to execution.

archlang-export