The Agent Skills Directory

[SAFE]: The skill acts as a documentation layer or 'router' that explains the purpose and relationships between other skills in the repository. It does not perform any actions itself.
[NO_CODE]: There are no executable scripts, binaries, or shell commands included in the skill files. All provided files are markdown or YAML configuration.
[INDIRECT_PROMPT_INJECTION]: The skill documents workflows for triaging bugs and feature requests, which implies the ingestion of untrusted external data. While this creates a potential attack surface for the skills that handle that data, this router skill does not process input itself and serves only as a guide.

ask-matt