The Agent Skills Directory

[DYNAMIC_EXECUTION]: The scripts scripts/activate_rules.py and scripts/audit_installation.py utilize importlib.util.spec_from_file_location to dynamically load internal helper scripts (such as workflow/scripts/global_policy.py and activate_rules.py) using paths calculated at runtime relative to the script location.
[COMMAND_EXECUTION]: The scripts/readiness.py script invokes the git command-line tool using subprocess.run to gather workspace identity information, including the repository root, current branch, and commit hash.
[INDIRECT_PROMPT_INJECTION]: The skill's workflow involves reading project-specific files (e.g., package.json, composer.json, and various .md files) to assess rules readiness, which creates a potential surface for indirect prompt injection if those project files contain malicious instructions.
Ingestion points: The scripts readiness.py and version_facts.py read configuration and markdown files from the target project directory during the inspection process.
Boundary markers: The skill employs explicit markers ( and ) to delineate its injected instructions when modifying global configuration files.
Capability inventory: The skill possesses the capability to read project files, write to global agent instruction files, and execute shell commands (specifically git).
Sanitization: scripts/activate_rules.py performs regex-based validation on the library path to prevent the inclusion of unexpected Markdown or shell control characters in generated instruction blocks.

rule-maker