The Agent Skills Directory

[SAFE]: The content is entirely instructional and methodology-focused. It describes a workflow for managing multi-stage agent pipelines to reduce total execution time.
[COMMAND_EXECUTION]: The skill includes example terminal commands (e.g., using placeholders like {LOOP_TOOL}) to illustrate how a user might set up the staggered pipeline. These are benign educational examples and do not instruct the agent to execute arbitrary or dangerous code autonomously.
[DATA_EXFILTRATION]: No network operations or sensitive file access patterns were detected. The skill focuses on local directory structures (e.g., /specs, /plans) for managing task artifacts.

speculative-pipeline