The Agent Skills Directory

[SAFE]: The skill content consists of technical documentation and code examples for the Effect library. No malicious instructions, obfuscation, or safety bypasses were detected.
[COMMAND_EXECUTION]: The skill instructs the agent to run standard validation commands such as typecheck, tests, and smoke tests after making edits. These are legitimate development workflows and do not involve privilege escalation or suspicious shell operations.
[DATA_EXFILTRATION]: There are no patterns indicating the exfiltration of sensitive data. The skill does not access sensitive files (like .env or SSH keys) or make unauthorized network requests.
[REMOTE_CODE_EXECUTION]: The skill does not download or execute external scripts. It relies on a local vendored copy of the Effect library located in the project's own repository.

effect-batching