claude-octopus

Reverse-engineer design systems, tokens, and components from live products or screenshots

Multi-AI requirements scoping using available external providers (Double Diamond Define phase)

Multi-AI validation, scoring, and review using available external providers (Double Diamond Deliver phase)

Multi-AI implementation using available external providers (Double Diamond Develop phase)

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

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

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

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

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

Auto-detect work context (Dev vs Knowledge) — use to tailor workflows based on current task type

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

Thorough research across multiple sources — use for complex topics needing broad synthesis

Environment diagnostics — check providers, auth, config, hooks, scheduler, and more

Run a full build-and-ship pipeline from a spec — use for hands-off project generation

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

Decompose large tasks across parallel agents — use for migrations, multi-file refactors, or batch work

Quick execution for ad-hoc tasks without full workflow overhead — use for small, self-contained requests

Package and finalize completed work for delivery — use when a feature is done and ready to ship

Review code in two passes: spec compliance then quality — use for thorough PR or feature reviews

Build features with tests-before-code rigor — use for new features needing test coverage

Design UI/UX systems with style guides, palettes, typography, and component specs for new interfaces

Evidence before claims — run verification commands before declaring work complete, fixed, or passing

Multi-AI requirements scoping using available external providers (Double Diamond Define phase)

Multi-AI validation, scoring, and review using available external providers (Double Diamond Deliver phase)

Multi-AI implementation using available external providers (Double Diamond Develop phase)

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

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

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

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

Quick execution for ad-hoc tasks without full workflow overhead — use for small, self-contained requests

Thorough research across multiple sources — use for complex topics needing broad synthesis

Design UI/UX systems with style guides, palettes, typography, and component specs for new interfaces

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

Auto-detect work context (Dev vs Knowledge) — use to tailor workflows based on current task type

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

Environment diagnostics — check providers, auth, config, hooks, scheduler, and more

Reverse-engineer design systems, tokens, and components from live products or screenshots

Run a full build-and-ship pipeline from a spec — use for hands-off project generation

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

Decompose large tasks across parallel agents — use for migrations, multi-file refactors, or batch work