Summarizes the current Claude Code conversation into an evidence-backed map of goals, changes in direction, completed outcomes, current work, and open decisions. Use it to regain context after interruptions, session switching, or conversation compaction.
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.
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, 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.
Prepare and guide software releases using rules discovered in the project and its automated build workflows. It tracks version files, helps draft release notes, runs release steps with confirmation, and checks the published result.
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.
Define repeatable workflows and their dependencies in JSON, then execute them through a CLI. Combine commands, read-only agent tasks, parallel branches, and human approval steps, with journal records that support recovery after interruption.
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.
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.
Simplify bloated AI-generated code by removing dead code, duplicated logic, and unnecessary layers while checking that existing behavior stays intact. Use a limited cleanup scope, verify changes with relevant checks, or request a review without edits.
Send questions, review requests, or implementation tasks to a supported local AI command-line tool through one shared command. The wrapper handles provider-specific options and saves the result as a Markdown file for later reference.
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.
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.
Turn a successful workflow from the current session into a reusable OMC skill draft. Capture inputs, ordered steps, decision rules, pitfalls, and verification evidence, then choose an appropriate storage location.
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.
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.
Keep code changes small by checking whether they are needed, reusing existing helpers, and choosing standard or available tools first. It guides planning and implementation while preserving validation, security, accessibility, and the functionality the user requested.
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.
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.
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.
Turn a development idea into an actionable plan with implementation steps, testable acceptance criteria, and risk mitigations. Gather requirements through focused questions, generate plans directly from detailed requests, or review proposals from multiple perspectives.
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.
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.
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.
Is this your account? Link GitHub to bring it onto your creator page (Japanese)