The Agent Skills Directory

[SAFE]: The skill consists entirely of natural language instructions intended to guide the agent's behavior during a session. No scripts, binaries, or executable code are included.
[SAFE]: There are no external dependencies, remote code downloads, or network-based operations defined within the skill content.
[SAFE]: The skill includes explicit safety instructions that prohibit the agent from capturing secrets, credentials, or environment-specific sensitive details during its summarization process.

capture-context