Compare estimated AI model costs for a task using its complexity and expected text volume. Get a suitable low-cost recommendation, a cheaper but riskier alternative, and a premium option, with explicit assumptions behind the estimates.
Turn screenshot-based UI feedback into code fixes. Identify layout, styling, component, and state issues, trace their causes, agree on the scope of changes, and verify visual consistency across screen sizes and interaction states.
Turn an agreed plan into small work tickets, each covering a complete, testable feature across the necessary layers. Identify dependencies and available starting points so people or future agent sessions can pick up clearly bounded work.
Interpret the saved results of a completed AI council review. Count verdicts, check whether enough participants responded and whether models are independent, surface substantive dissent, and explain what action the outcome supports.
Verify code changes before committing or shipping by running tests, builds, and checks against requirements. Use fresh command output to support completion reports, confirm bug fixes, and check work reported by other agents.
Organize multi-step work into tasks, track dependencies and status, and save progress checkpoints. Record completed work, unfinished steps, and decision context so an agent can review the saved state and continue in a later session.
Research technical, market, or academic topics through multiple available AI providers working in parallel. Combine their findings into a report that preserves disagreements, identifies gaps, attributes sources, and recommends next steps with priorities.
Turn a technical choice into a structured debate between different AI model families. Assign explicit positions, launch the discussion, and summarize agreement, disagreement, and a recommendation supported by the strongest argument that survives the debate.
Verify work before reporting it as complete by running fresh checks and reading their results. Match each claim to evidence, including test output, build results, bug reproduction, code changes, and requirement checks.
Explore ideas and working methods through focused conversation, one question at a time. Identify recurring patterns, surprising contradictions, and distinctive approaches, then turn discoveries into named concepts and a documented session summary.
Turn a multi-step feature into an implementation plan that another engineer can follow without prior context. The plan includes exact file paths, complete code, test commands, expected results, and small, verifiable steps.
Check which AI providers Octopus can use before running a workflow. Get a compact table of availability, authentication, selected models, and billing categories, followed by prioritized fixes for detected problems.
Start the interactive Claude Octopus setup wizard to install and authenticate providers, configure RTK token optimization, choose a work mode, and complete onboarding. This skill directs configuration requests to the existing setup process.
Develop behavior changes by first observing an expected test failure, then making the smallest passing implementation. Refactor with tests passing, and document preserved behavior and measured runtime whenever tests are consolidated.
Create a product requirements document for a new feature or product. Clarify users, problems, goals, and constraints, then organize prioritized requirements, acceptance criteria, implementation phases, and risks into a structured document for AI-assisted development.
Coordinates multiple AI providers to research, define, implement, and validate development tasks. It supports parallel task decomposition, comparison of proposed solutions, cross-model critique, and quality checks that feed into combined reports and final deliverables.
Review code with multiple AI perspectives to identify quality, security, performance, and design issues. The workflow also examines test evidence and unfinished implementation, then combines findings into a review that can be shared on a pull request.
Review code or documents with available AI providers before delivery. Combine findings into a scored validation report that checks prior requirements and decisions, separates critical issues from warnings, and recommends next steps.
Clarify a feature’s requirements with multiple AI providers, combining technical constraints with user and business needs. Produce a scoped definition covering priorities, edge cases, exclusions, and a requirements checklist before implementation begins.
Audit changed code by tracing execution paths and matching them to existing tests. Show coverage gaps and test quality, then generate tests for high-priority gaps using the project's current framework, helpers, and naming conventions.
Research complex topics across multiple sources using available external AI providers, then combine the findings. Choose the depth, focus, and output format to receive a detailed report, concise summary, comparison table, or recommendations.
Finish a development branch by running tests and reviewing changes, then choose whether to create a pull request, merge locally, keep the branch, or discard it. Optional version and changelog updates support release preparation.
Sort incoming issues and pull requests, verify their claims, and assign clear triage states. Record missing information, decisions needed, and actionable handoff notes so maintainers can see which items are ready for work.
An early-stage framework for documenting an existing product’s design and architecture. Command parsing, output setup, and metadata generation are implemented; extracting colors, components, APIs, and architecture remains in progress or planned.
Is this your account? Link GitHub to bring it onto your creator page (Japanese)