The Agent Skills Directory

[SAFE]: The skill is purely instructional, providing frameworks for agent interaction, debate, and synthesis without any functional code or system-level operations.
[NO_CODE]: No scripts, binaries, or configuration files capable of execution are present in the skill package.
[EXTERNAL_DOWNLOADS]: There are no references to external URLs, remote scripts, or package registries.
[DATA_EXFILTRATION]: The skill does not access local files, environment variables, or network sockets, precluding any data exfiltration risk.
[PROMPT_INJECTION]: The provided instructions use standard pedagogical language to structure agent workflows and do not contain patterns intended to bypass safety filters or override core instructions.

team-coordination