The Agent Skills Directory

[SAFE]: The skill serves as a procedural guide for repository maintenance and contribution. It defines standards for frontmatter, documentation, and platform gating without introducing malicious behaviors or security vulnerabilities.
[COMMAND_EXECUTION]: The skill instructs the agent to use the terminal tool to execute local repository scripts, such as scripts/run_tests.sh and website/scripts/generate-skill-docs.py. These are legitimate operations intended for a local development environment and are documented neutrally as part of the standard contributor workflow.
[DYNAMIC_EXECUTION]: Includes a Python validation snippet using standard libraries (pathlib, re) and the ruamel.yaml package to verify that skill frontmatter adheres to project requirements. This utility is intended for local validation and does not involve network access or unsafe data processing.

hermes-agent-skill-authoring