The Agent Skills Directory

[COMMAND_EXECUTION]: The script scripts/test_skill.py uses subprocess.run to execute the skill's internal validation and classification scripts (scripts/validate.py and scripts/probe_reading_notes.py). These operations are restricted to the local package and are used for testing and deterministic classification of source descriptors.
[EXTERNAL_DOWNLOADS]: The skill is designed to fetch content from external URLs (including YouTube and general web pages) and process local documents (PDF, DOCX) as part of its primary summarization workflow, as documented in references/intake.md.
[PROMPT_INJECTION]: The skill presents an indirect prompt injection surface because it processes untrusted data from external sources.
- Ingestion points: Web URLs, YouTube transcripts, and local document files (PDF/DOCX) identified in references/intake.md.
- Boundary markers: Absent. The instructions do not specify the use of delimiters when processing external resource content.
- Capability inventory: The skill utilizes file reading, web fetching, and local Python script execution (scripts/test_skill.py) to perform its tasks.
- Sanitization: Absent. No explicit sanitization or filtering logic for external content is defined in the instructions.

reading-notes