The Agent Skills Directory

[EXTERNAL_DOWNLOADS]: The skill instructs the agent to fetch the project's README file from a remote repository at the start of its operation.
Evidence: curl -s https://raw.githubusercontent.com/remorses/tuistory/refs/heads/main/README.md
Context: The source is the official GitHub repository for the tool, which is controlled by the skill's author.
[INDIRECT_PROMPT_INJECTION]: The skill allows the agent to read, snapshot, and interact with output from background terminal processes, which serves as an ingestion point for untrusted data.
Ingestion points: Data is ingested through terminal inspection commands such as tuistory read and tuistory snapshot.
Boundary markers: The skill does not define specific delimiters or instructions to ignore potential commands embedded in terminal output.
Capability inventory: The agent has the ability to execute shell commands, interact with interactive CLI tools, and modify project configuration files like package.json.
Sanitization: There is no explicit sanitization or filtering of terminal output before it is presented to the agent, though this is expected behavior for a logging and process management tool.

tuistory