The Agent Skills Directory

[EXTERNAL_DOWNLOADS]: The skill downloads the 'uv' installer from its official domain (astral.sh) and fetches the 'ouroboros-ai' package from standard registries using uvx.
[COMMAND_EXECUTION]: The skill executes various shell commands to detect the Python environment, check package versions, and interact with the GitHub API via the 'gh' CLI to star the author's repository upon user confirmation.
[INDIRECT_PROMPT_INJECTION]: The skill reads data from project files (CLAUDE.md) and tool outputs (git repository lists). This introduces an attack surface where maliciously named files or repository metadata could influence the agent's behavior during the onboarding process.
Ingestion points: Reads content from CLAUDE.md and repository lists from the ouroboros_brownfield tool.
Boundary markers: The skill lacks explicit boundary markers or instructions to ignore embedded commands when processing existing CLAUDE.md content.
Capability inventory: The skill has broad capabilities including shell execution, file system writes, and network access through CLI tools.
Sanitization: No specific sanitization or escaping is applied to the content read from external files before processing.
[DYNAMIC_EXECUTION]: The skill utilizes Python heredocs to dynamically generate and execute scripts for local configuration management (prefs.json). It also uses uvx for the isolated execution of the Ouroboros CLI.

setup