The Agent Skills Directory

[INDIRECT_PROMPT_INJECTION]: The skill ingests and processes instructions from local project files, including AGENTS.md, CLAUDE.md, style guides, and the application's source code. This exposure could allow malicious instructions embedded in these files to influence the agent's behavior during the migration process.
Ingestion points: Project configuration files (AGENTS.md, CLAUDE.md), 3D style guides (3D-STYLE.md), and application source code/tests identified during the survey phase (as detailed in references/survey.md).
Boundary markers: The skill does not define specific delimiters or instructions for the agent to ignore or isolate embedded prompts within the ingested project data.
Capability inventory: The skill possesses extensive capabilities including file system modification, NPM package installation, execution of build and test scripts (e.g., vite, vitest), and browser automation for visual regression testing.
Sanitization: The instructions do not specify any sanitization or validation steps for content retrieved from external project files before it is used to guide the agent's actions.
[COMMAND_EXECUTION]: The skill involves the execution of various shell commands and development utilities such as wc, ripgrep, and git, as well as vendor-specific CLI tools like three-studio and three-audit for code measurement and verification.
[EXTERNAL_DOWNLOADS]: The skill directs the agent to install several NPM packages under the @zkmake scope. These packages and the referenced documentation URL (zkmake.github.io) are resources associated with the skill's author and are used for their intended purpose of providing shared development utilities.

kit-adopt