The Agent Skills Directory

[INDIRECT_PROMPT_INJECTION]: The skill instructs the agent to read and carry forward information from external files such as RUN.md and historical run memories (docs/runs/<RUN-ID>.md) when proposing new work or updating documentation.
Ingestion points: The agent is directed to read RUN.md and relevant run memories at the start of a session.
Boundary markers: There are no instructions provided to treat these files as untrusted or to ignore any embedded commands or instructions they might contain.
Capability inventory: The skill has the ability to execute shell commands via the cherries CLI, run Python scripts using uv, write to the local filesystem, and archive data to remote locations.
Sanitization: The skill does not define any sanitization or validation steps for the content of the documentation files before they are processed by the agent.
[COMMAND_EXECUTION]: The skill relies on the execution of various cherries CLI commands for project initialization, running experiments, archiving records, and managing maintenance tasks. These commands are integral to the stated purpose of managing a Cherries experiment repository.

run-cherries-experiments