Bellman

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.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Explaining branches and function call order
• Showing UI, module, or file responsibilities
• Comparing structure before and after a change

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.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Clarifying instructions in CLAUDE.md
• Making specifications and tickets actionable
• Adding completion criteria to skill procedures

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.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Carrying a multi-step implementation through verification
• Resuming work with recorded progress
• Tracking evidence for each requirement

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.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Checking completed changes before release
• Reviewing compliance with documented development standards
• Checking implementation against ticket requirements

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.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Adding behavior through small test-first steps
• Reproducing a bug before fixing it
• Checking results against specifications

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.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Investigating bugs and regressions
• Explaining latency and resource usage
• Tracing unexpected experimental results

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.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Setting up or repairing the status display
• Switching to a minimal status line
• Viewing running agents and their tasks

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.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Choosing a skill for unclear requirements
• Finding the next step after plan approval
• Locating debugging or verification skills

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.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Drafting a pull request description
• Explaining a refactor with a compact diagram
• Presenting existing before-and-after check results

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.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Researching implementation best practices
• Comparing libraries for a project
• Looking up current framework conventions

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.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Tracking development work across Claude Code sessions
• Managing ordered goals with attempts and evidence
• Requiring cleanup, verification, and review before completion

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.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Turning a development brief into a specification and tickets
• Coordinating parallel implementation across dependent tickets
• Approving acceptance criteria and testing boundaries

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.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Building a product from a short idea
• Creating a bookstore inventory API
• Developing a habit-tracking command-line tool

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.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Diagnosing a broken Claude Code workflow
• Investigating unexpected hook or agent behavior
• Narrowing down causes of failing tests or commands

Build a lasting Markdown knowledge base for project decisions, architecture, and session discoveries. Search pages by keywords and tags, use results to answer with citations, and check for outdated content, broken links, and structural problems.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Preserving project decisions across sessions
• Finding past debugging discoveries
• Checking knowledge pages for broken links and stale content

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.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Implementing a feature with a small code diff
• Bringing an expanding implementation back within scope
• Checking for reusable code before adding helpers

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.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Preserving a hard-won debugging workflow
• Turning project-specific procedures into skill drafts
• Deciding whether a workflow belongs in a skill or documentation

Configure OMC notifications for Telegram, Discord, or Slack through guided questions. Choose events such as session completion or requests for input, set destinations and mentions where supported, and optionally send a test message to check delivery.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Receiving alerts when a session finishes
• Getting notified when Claude needs input
• Setting Discord or Slack notification mentions

Coordinate multiple agents on a shared task list to complete development work. Break tasks into clear responsibilities, manage dependencies, and move through planning, implementation, verification, and bounded repair cycles with recorded handoffs.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Fixing TypeScript errors across several modules
• Sharing build-error investigation among agents
• Implementing responsive layouts across pages

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.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Removing duplicate logic and unused code
• Simplifying unnecessary wrappers without changing behavior
• Cleaning up only a specified set of changed files

Turns vague development requests into reviewed plans through planning, architecture, and quality-review agents. It compares alternatives, defines testable acceptance criteria, and records decisions, stopping before implementation unless execution has been explicitly approved.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Defining the scope of a vague development request
• Comparing implementation approaches before coding
• Planning migrations or security-sensitive changes

Check whether a feature, fix, or refactor actually works using existing tests, build checks, direct commands, or manual validation. Get a concise account of the evidence, including what passed, what failed, and what remains unverified.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Checking that a bug fix works
• Verifying a newly added feature
• Checking behavior after a refactor

Stop active OMC workflows and clean up their runtime state while preserving progress where the mode supports resuming. It distinguishes the current session from all sessions and offers graceful shutdown or forced cancellation without bypassing ownership checks.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Stopping the current session's automated workflow
• Pausing Autopilot while keeping progress for resuming
• Shutting down a running agent team

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.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Running repeatable build and test workflows
• Resuming a workflow after a crash
• Adding human approval before deployment