The Agent Skills Directory

[COMMAND_EXECUTION]: The skill executes command-line tools including uv for package management and the asta / asta-autodiscovery CLI for running scientific experiments and managing authentication.
[EXTERNAL_DOWNLOADS]: Installs the asta-autodiscovery tool from the vendor's repository using the uv tool manager.
[INDIRECT_PROMPT_INJECTION]: The skill processes and summarizes experimental outcomes, including AI-generated hypotheses and code, which introduces an indirect prompt injection surface. * Ingestion points: The skill reads experiment nodes (hypothesis, code, outcome) as described in assets/interpreting-results.md. * Boundary markers: No explicit delimiters or instructions are provided to the agent to treat experimental outputs as untrusted data. * Capability inventory: The skill has the ability to execute bash commands and write JSON files as defined in SKILL.md. * Sanitization: There are no instructions for sanitizing or validating the experimental content before it is processed by the agent.

autodiscovery