The Agent Skills Directory

[SAFE]: The skill defines a set of instructional guidelines for AI agents to follow a 'batch execution' workflow. It includes rules for plan verification, cognitive traps to avoid, and a structured process for executing tasks in groups while waiting for human feedback between steps.- [SAFE]: The skill does not contain any executable code, external network requests, or sensitive file access patterns. It relies on standard markdown-based instructions and mermaid/graphviz diagrams for visualization.
[SAFE]: All referenced 'sub-skills' (e.g., godmode:workspace-isolation, godmode:merge-protocol) are internal references to the agent's expected capabilities and do not represent untrusted external dependencies.

task-runner