The Agent Skills Directory

[COMMAND_EXECUTION]: The skill utilizes the Bash tool for repository discovery, executing commands like git rev-parse to determine the repository root and ls to identify existing configuration and script files.
[DYNAMIC_EXECUTION]: The skill generates a local developer CLI and a justfile from static templates and then executes them using the Bash tool to perform environment audits and verify repository invariants.
[INDIRECT_PROMPT_INJECTION]: The skill processes repository files which may contain untrusted data, constituting a potential injection surface. 1. Ingestion points: Reads package.json, existing scripts, and TRACKER.md using the Read and Grep tools. 2. Boundary markers: The skill does not employ specific boundary markers or ignore instructions when reading these repository files. 3. Capability inventory: The skill has access to Read, Write, Edit, and Bash tools, allowing it to modify the file system and execute code. 4. Sanitization: There is no evidence of specific logic sanitization or validation of the data extracted from repository scripts during the migration process.

setup-engineer