Agent Claude Code
Hypothesis-driven debugging with structured evidence logging.
Agent Claude Code
Hypothesis-driven debugging with structured evidence logging.
Agent Claude Code
Implements single tasks atomically with verification and commit discipline.
Agent Claude Code
External research agent using Exa MCP for API details, design patterns, and technology evaluation.
Agent Claude Code
Cross-phase integration validation for milestone audits.
Agent Claude Code
Test coverage audit with gap detection and test stub generation.
Agent Claude Code
Researches implementation approach for a specific roadmap phase.
Agent Claude Code
Validates plan quality with up to 3 revision rounds.
Agent Claude Code
Creates execution plans with task decomposition, waves, and dependencies.
Agent Claude Code
Domain research for project initialization, spawned with different focus angles.
Agent Claude Code
Merges multiple researcher outputs into a unified research summary.
Agent Claude Code
Multi-dimensional code review agent — analyzes changed files for a single review dimension.
Agent Claude Code
Creates project roadmap with phased milestones from research and requirements.
Agent Claude Code
Goal-backward verification across three layers (existence, substance, connection).
Command Claude Code
Quick execution for small tasks — minimal run lifecycle (start + done) with evidence recording. Full LLM capability, scoped to mechanically clear tasks.
Command Claude Code
Create or sync session worktree for parallel dev.
Command Claude Code
Manage editing boundary restrictions.
Command Claude Code
Use when designing, auditing, polishing, improving, or codifying frontend UI — websites, dashboards, landing pages, components, design systems.
Command Claude Code
Initialize project with auto state detection.
Command Claude Code
Intent-driven issue lifecycle management — describe what you want in natural language (报告一个 bug / 列出开放 issue / 关掉 ISS-xxx / 关联到 task / 扫描发现问题) and the workflow routes to the right operation. Operates on .workflow/issues/. 知识管理走 /maestro-knowledge;knowhow 沉淀走 /maestro-knowhow;约束规则走 /maestro-spec。Triggers on "issue 管理"…
Command Claude Code
A command for saving reusable project knowledge, such as decisions, code templates, deployment instructions, and debugging tips, in the project’s .workflow/knowhow/ folder.
Command Claude Code
Intent-driven knowledge-store and Run knowledge lifecycle management — audit/prune, stage candidates (with signal recording), review/resolve/promote candidates, harvest artifacts, or manage wiki/domain knowledge.
Command Claude Code
User-invoked learning toolkit — guided reading, investigation, pattern extraction, or second opinions. Manual /maestro-learn only; NEVER auto-invoke for code exploration or analysis — route those intents to the analyze step via /maestro-next.
Command Claude Code
Merge session worktree branch back to main.
Command Claude Code
Unified entry for all development intents — classify intent, assess complexity, route to the correct execution channel: /maestro-companion (lightweight), standard single run, or /maestro and /maestro-ralph (multi-step manual/orchestrated). Pure router, never runs execution loops itself.