The Agent Skills Directory

[COMMAND_EXECUTION]: The skill instructs the agent to execute local scripts and tools to automate workflow steps.
Calls record.py to write task folders and tickets.
Calls ../codebase-map/scripts/screenshot_report.py to capture screenshots for the visual review report.
Mentions using a headless Edge or Chrome probe with the --dump-dom flag to verify plan items.
[INDIRECT_PROMPT_INJECTION]: The skill is designed to ingest information from a variety of external project files, which serves as an attack surface for instructions embedded in data.
Ingestion points: Reads content from workflow/RULES.md, workflow/VISUAL-REVIEW.md, workflow/AUDIT.md, and multiple SKILL.md files in sibling directories (ui-design, codebase-design, domain-modeling).
Boundary markers: None explicitly defined in the instructions to separate untrusted file content from system instructions.
Capability inventory: The agent has capabilities to read/write files and execute local Python scripts (record.py, screenshot_report.py).
Sanitization: No specific sanitization or validation of the ingested file content is mentioned.

workflow-specify