The Agent Skills Directory

[COMMAND_EXECUTION]: The skill facilitates the creation and execution of architectural validation scripts that interact with the system shell. Evidence: assets/arch-fitness/checks/example.mjs.template utilizes node:child_process.execSync to run shell commands; assets/arch-fitness/verify.mjs uses node:child_process.spawnSync to execute generated check scripts.
[DYNAMIC_EXECUTION]: The skill implements a workflow for generating and running executable code at runtime. Evidence: It creates new script files in the scripts/arch/checks/ directory by populating templates with logic, which are then executed by a runner script to validate the project.
[INDIRECT_PROMPT_INJECTION]: The skill represents a surface for indirect prompt injection by processing repository data and user input to generate executable logic. Ingestion points: reads existing ADRs and Standards files from docs/adr/ and docs/standards/. Capability inventory: has the ability to write files and execute shell commands. Sanitization: relies on user review of proposed criteria and commands.
[EXTERNAL_DOWNLOADS]: The skill instructions direct the agent to install third-party tools using standard package managers. Evidence: references to npm, pip, and composer in dependencies.md for installing required tools from official registries.

arch-manage