The Agent Skills Directory

[INDIRECT_PROMPT_INJECTION]: The skill processes content from various markdown files and concept graphs to generate FAQ questions, answers, and quality reports. This is the primary function of the skill but presents a standard surface where text within those files could influence agent behavior.
Ingestion points: The skill reads docs/course-description.md, docs/learning-graph/03-concept-dependencies.csv, docs/glossary.md, and all files matching docs/**/*.md as specified in Step 1 and Step 2 of the workflow.
Boundary markers: The instructions do not define specific delimiters or "ignore embedded instructions" warnings for the agent when processing the textbook content.
Capability inventory: The skill writes to docs/faq.md, logs/faq.md, docs/learning-graph/faq-chatbot-training.json, docs/learning-graph/faq-quality-report.md, and docs/learning-graph/faq-coverage-gaps.md. It also modifies mkdocs.yml.
Sanitization: Step 9 of the workflow includes validation for uniqueness, link integrity, Bloom's distribution, and technical accuracy, though it does not explicitly mention security-specific filtering for the ingested text.
[COMMAND_EXECUTION]: The skill performs file system operations within the project directory to create FAQ documentation and quality reports. It also includes instructions in Step 10 to modify the mkdocs.yml configuration file to update the navigation structure, which is a standard operation for textbook project management.

faq-generator