The Agent Skills Directory

[COMMAND_EXECUTION]: The skill executes shell commands for its core logic, such as project identification via pwd and running internal automation scripts (prepare_context.py, fetch_diaries.py, master_diary_sync.py) for context preparation and synchronization. It also attempts to run the qmd utility for semantic indexing.\n- [INDIRECT_PROMPT_INJECTION]: The skill ingests untrusted project data, creating a surface for potential indirect instructions.\n
Ingestion points: prepare_context.py reads README.md, package.json, pyproject.toml, and requirements.txt; fetch_diaries.py reads existing diary entries.\n
Boundary markers: None identified; content is processed without explicit delimiters or instructions for the agent to ignore embedded commands.\n
Capability inventory: The agent can write files, execute shell commands, and perform network requests via Notion sync scripts.\n
Sanitization: No sanitization or escaping is performed on ingested content before it is presented to the agent.\n- [EXTERNAL_DOWNLOADS]: The skill includes a requirements.txt file with standard dependencies (requests, urllib3, idna) required for its synchronization functionality.

diary