The Agent Skills Directory

[COMMAND_EXECUTION]: The skill instructs the agent to execute shell commands to manage directories, run Python tests via uv run pytest, and perform integration testing using docker exec and curl. These actions are directly related to the skill's primary function of developing and validating enrichment modules within a local development environment.
[EXTERNAL_DOWNLOADS]: The skill guides the user through researching and selecting external Python libraries from PyPI and sample files from GitHub. It includes mandatory checkpoints (Step 3 and Step 4) where the agent must stop and wait for explicit user approval before proceeding with any selected external resource.
[PROMPT_INJECTION]: The skill creates a surface for indirect prompt injection by design, as it involves fetching and parsing untrusted sample files from external repositories to test the generated enrichment modules. This is an inherent part of the skill's purpose for security analysis, and the risk is mitigated by requiring the user to approve the specific files used for testing.

enrichment-module-builder