The Agent Skills Directory

[COMMAND_EXECUTION]: The skill instructs the agent to use standard system utilities including mkdir -p for directory creation and basename for determining project names based on the working directory.
[DYNAMIC_EXECUTION]: The skill utilizes a python3 command-line snippet to generate precise ISO 8601 timestamps for session metadata.
[DATA_EXPOSURE]: The skill interacts with the local file system by reading from the current working directory and writing session state data to a specific directory in the user's home folder (~/.smtm/sessions/).
[INDIRECT_PROMPT_INJECTION]: The skill extracts information from the conversation history and persists it to disk, which could include untrusted content that might influence future sessions during restoration.
Ingestion points: Extracts conclusions, ruled-out directions, and hypotheses directly from the active conversation context in SKILL.md.
Boundary markers: The skill uses structured YAML frontmatter and Markdown headers to delimit the saved content.
Capability inventory: The skill performs file system writes and executes small utility shell commands.
Sanitization: Implements basic slugification (lowercase conversion and punctuation removal) for filenames generated from user-provided titles.

money-save