The Agent Skills Directory

[COMMAND_EXECUTION]: The skill utilizes the GitHub CLI (gh) via a Bash tool to search and fetch commit history. This is a functional requirement for the 'technical work' summary but involves executing shell commands with parameters (date and author) provided by the environment or instructions.
[INDIRECT_PROMPT_INJECTION]: The skill processes untrusted external data which could potentially contain malicious instructions intended to influence the agent's behavior during the summary or memory capture phases.
Ingestion points: Output from the gh search commits command (commit messages) and user conversation text in SKILL.md.
Boundary markers: The instructions do not specify the use of delimiters or 'ignore embedded instructions' prompts when processing the fetched commit data.
Capability inventory: The agent has access to Bash, Write, Edit, and Glob tools, enabling it to modify local files like journal entries, .claude/memories/, and about-taylor.md based on the ingested content.
Sanitization: No explicit instructions are provided to sanitize or validate the content of commit messages before summarizing them or committing them to long-term memory files.

daily-review