The Agent Skills Directory

[COMMAND_EXECUTION]: The skill instructs the agent to execute shell commands using the ha CLI tool, specifically ha preset validate and ha preset install, to verify the integrity and configuration of preset packages.
[REMOTE_CODE_EXECUTION]: The skill documentation describes how to author and configure script-based entrypoints (e.g., scripts/run.mjs) within the preset manifests. These scripts are intended to be executed by the Harness Anything platform to perform automation tasks.
[PROMPT_INJECTION]: The skill handles the migration of legacy v2 package manifests into the current v3 schema. This ingestion of external configuration data presents an indirect prompt injection surface. The skill mitigates this risk by providing specific instructions to perform exact-field validation and to delete all unknown or legacy keys that do not match the new contract.

preset-creator