The Agent Skills Directory

[NO_CODE]: The skill consists entirely of markdown instructions and JSON evaluation data. It does not include any scripts, executables, or code that could perform operations on the host system or network. Behavior is entirely dependent on the instructions provided to the agent.
[COMMAND_EXECUTION]: While the skill instructs the agent to use the target coding agent's capabilities (API, UI, or local storage updates), it contains specific safeguards: it mandates establishing the storage format before editing, rechecking IDs and titles before writes, and skipping entries if concurrent changes are detected. These instructions promote safe state management.
[PRIVILEGE_ESCALATION]: The skill explicitly defines its scope as 'Conversation Naming' and instructs the agent to keep file, project, and skill renaming outside of its scope. It also cautions against operations that might have side effects on pinned or archived states.

conversation-namer