Create separate Git working directories for issue fixes, pull request reviews, and feature development. Optional tmux terminal sessions help manage parallel tasks, return to ongoing work, and clean up completed sessions.
Review records across OMC sessions to find recurring obstacles in the agent's working environment. It turns evidence from timelines, logs, and notes into ranked proposals for checks, guidance, tools, or information access, with changes requiring user approval.
Compare a UI screenshot with reference images and receive a structured JSON assessment. Get a score, pass or revision status, concrete visual differences, and suggested edits for layout, spacing, typography, colors, and visual hierarchy.
Explain code structure, execution flow, and proposed changes with a focused visual, such as pseudocode, a tree, a Mermaid diagram, or a diff. Use a single HTML artifact when a richer layout is needed.
Break a development task into small requirements with explicit acceptance criteria, then repeat implementation and verification while saving progress. Completion depends on evidence for each requirement and reviewer approval, with configurable reviewers and a final cleanup check.
Develop behavior through one failing test and one minimal implementation at a time. Tests use agreed interfaces and expected results from specifications or documented examples, producing evidence of both failure and success, including for bug fixes.
Investigate why a bug, performance change, or experimental result occurred. Compare competing explanations using supporting and contradicting evidence, rank likely causes, and identify the next check that would best resolve uncertainty.
Set up or repair the OMC status display in Claude Code, then choose how much information it shows. Configure presets and individual elements to monitor task progress, context usage, and running agents during a session.
Find the appropriate skill for the work you need to do, from clarifying requirements to implementation, review, and verification. This routing guide selects the next skill or shows a manual command without performing the work itself.
Draft a pull request description from existing project records and verification results. Present the change with a compact visual, before-and-after evidence, rollback details, and its wider impact so reviewers can assess the work.
Research a question by splitting it into two to five topics and assigning parallel documentation agents. Get a combined summary, detailed findings for each topic, and source URLs from web searches and documentation lookups.
Guide a development brief through specification, dependent tickets, implementation, review, and verification. Coordinate parallel work while keeping human approval at key decisions and recording agreed vocabulary, business rules, and the reasons behind technical choices.
Break a large development brief into ordered goals and save plans, progress events, blockers, and evidence in the repository. Coordinate Claude Code sessions through handoff instructions, with final completion requiring cleanup, verification, and code review evidence.
Turn a short product idea into working code through requirements analysis, technical planning, implementation, testing, and review. It coordinates agents across these stages, fixes detected problems, and reports assumptions that still need a human decision.
Diagnose problems in OMC or Claude Code sessions using logs, execution traces, saved state, and focused reproduction. Receive a clear account of the failure, a supported cause hypothesis, and the smallest next corrective action.
Review completed code changes for defects, security risks, unnecessary complexity, and missing tests. Findings are verified and reported with severity, file locations, and concrete failure scenarios, with separate assessments of standards and intended behavior for larger changes.
Write or revise instructions, specifications, tickets, and skill files so an agent can act without prior chat history. Make rules checkable, explain their reasons, define completion criteria, and keep authoritative information in one place.
Carry an agreed development task through implementation and verification. Make small changes that follow existing patterns, divide independent work when useful, and report changed files, evidence that the code works, and any remaining issues.
Resolve a design question by building a temporary, runnable prototype. Explore logic through clickable scenarios or compare three structurally different interface variants, then record the user's decision while keeping the prototype separate from production code.
Investigate questions that need answers before work can proceed. Search repository code and documents, consult official technical documentation, and return sourced findings that separate verified facts, inferences, conflicting evidence, and remaining unknowns.
Set up, refresh, or repair oh-my-claudecode after a plugin, npm, or local development installation. Configure project or global instructions, status display, and team defaults, with quick updates for existing setups and support for resuming interrupted configuration.
Diagnose installation and configuration problems in oh-my-claudecode, including version mismatches, duplicate legacy hooks, and missing runtime requirements. Receive a status report with recommended fixes, with confirmed repairs preserving unrelated settings and custom content.
Turn a vague idea into a written specification through focused questions. The skill scores clarity across goals, constraints, and success criteria, explores hidden assumptions, and requires explicit approval before moving from planning to execution.
Turn support feedback or chat logs into a structured requirements document. Use numbered questions to clarify problems, goals, users, constraints, and open questions, then guide human review before handing approved requirements to development.
Is this your account? Link GitHub to bring it onto your creator page (Japanese)