The Agent Skills Directory

[EXTERNAL_DOWNLOADS]: The skill instructions direct the agent to download the ouraclaw repository from the author's GitHub account (github.com/montagao/ouraclaw) and install its dependencies using bun install if the tool is not already present on the system.
[COMMAND_EXECUTION]: The skill uses shell commands to manage the tool installation (git clone, bun install, bun link) and to retrieve sleep data (ouraclaw score, ouraclaw sleep).
[INDIRECT_PROMPT_INJECTION]: The skill ingests and processes health metrics from the Oura Ring API, creating a potential surface for indirect instructions if the source data were maliciously crafted.
Ingestion points: Standard output from the ouraclaw CLI tool in SKILL.md.
Boundary markers: None identified in the prompt instructions.
Capability inventory: Shell command execution, local file system access for repository cloning, and dependency installation.
Sanitization: No specific filtering or sanitization of the CLI output is defined.

ouraclaw