Explorar skills

Wrap up a branch — run tests, create PR, merge or discard — use when implementation is done

Create zero-context implementation plans with bite-sized tasks — use for multi-step feature planning

Decompose and execute large changes, migrations, or multi-issue fixes in parallel with quality gates

Switch to Knowledge Work mode for research and writing — use when task is non-code focused

Route ordinary init, review, and security requests to Claude-native capabilities first; escalate to Octopus only when multi-LLM diversity adds value

Run a configurable multi-LLM council with personas, budget caps, synthesis, veto gates, and optional implementation handoff.

Multi-AI research using available external providers (Double Diamond Discover phase)

Structured multi-provider AI debates between Claude and available advisors — use for critical decisions

System architecture and API design with multi-AI consensus — use for design reviews and new subsystems

NLSpec authoring — use when you need a structured specification from multi-AI research and consensus

Roll back to a previous checkpoint via git — use when a change went wrong and you need to revert

Expert multi-AI code review with inline PR comments — use for thorough quality and security analysis