The Agent Skills Directory

[COMMAND_EXECUTION]: The skill executes local Python scripts, specifically scripts/quality_gates/four_us_score.py and scripts/quality_gates/banned_word_check.py, to evaluate and validate generated marketing copy. These scripts are part of the skill's own directory structure and are used for quality assurance purposes.
[INDIRECT_PROMPT_INJECTION]: The skill builds its operational context by reading project files which could potentially contain untrusted data. * Ingestion points: Reads MARKETING.md, CLAUDE.md, README.md, PROJECT.md, and package.json from the project root. * Boundary markers: No explicit delimiters are specified in the instructions for separating the read content from the system prompt. * Capability inventory: The skill has the capability to execute local scripts and write files to the workspace/ directory. * Sanitization: The skill incorporates quality gates, including a banned word check script, to sanitize output before final delivery.
[DYNAMIC_EXECUTION]: Phase 4 (Quality Gates) involves the dynamic execution of Python logic to process and score the ad copy files produced in Phase 3.

kai-retarget