The Agent Skills Directory

[COMMAND_EXECUTION]: The skill instructs the agent to execute local initialization scripts (./test/scripts/init-influxdb3.sh), run tests via yarn and docker compose, and use curl for interacting with local service endpoints on ports 8181 and 8282. These are standard operations for a development and testing workflow.
[DATA_EXPOSURE]: The skill manages local authentication tokens and configuration files, such as test/.influxdb3/core/.token and .env.test. Accessing and creating these files is a core part of the setup process and is handled within the local project directory or the user's home directory.
[INDIRECT_PROMPT_INJECTION]: The skill processes data from local JSON files (e.g., extracting tokens using jq) and interpolates these values into shell commands and configuration files. This represents a data ingestion surface where the risk is mitigated by the fact that the sources are locally generated by the skill's own initialization scripts.
Ingestion points: ~/influxdata-docs/.influxdb3/enterprise/admin-token.json and test/.influxdb3/core/.token (SKILL.md).
Boundary markers: None present.
Capability inventory: Shell command execution (curl, jq, docker, yarn) and file writing (.env.test) across the setup workflows in SKILL.md.
Sanitization: None present; the skill assumes the integrity of the locally generated JSON token files.

influxdb3-test-setup