Does maestro-flow auto-invoke its skills?

Not yet. It is indexed on Flowy as a plain plugin. Request auto-invocation on its page and Flowy will route its skills for you as you prompt.

Is maestro-flow free?

Yes. Flowy is free and open source, with nothing gated. You can read every skill in full before you install.

Development

Plugin

maestro-flow

Intent-driven workflow orchestration for multi-agent AI development — adaptive lifecycle engine, self-reinforcing knowledge graph, and visual dashboard for Claude Code, Gemini, Codex & more

FLOW.md

catlog22@catlog22

GitHub

Plugin Signal81/100Strong

maintained100

capable92

documented50

adopted58

Install

$ npx -y skills add catlog22/maestro-flow --agent claude-code

Run the curl in your terminal, the rest in Claude Code.

Stats

Python TypeScript JavaScript Node React

+7 tags

Bash SQLite Git GitHub LaTeX Anthropic MCP

511

Stars

Forks

Active

Maintenance

TypeScript

Language

9h ago

Last commit

4mo ago

Created

Repo: catlog22/maestro-flow

In this plugin

29 commands 25 agents 24 skills 3 MCP

See everything inside

What's inside

Skills

/maestro-helpMaestro Flow 命令帮助系统。搜索命令、浏览技能、工作流推荐、新手引导。Triggers on "maestro-help", "帮助", "命令", "怎么用", "skill", "workflow", "maestro 怎么用"./skill-generatorMeta-skill for creating new Claude Code skills with configurable execution modes. Supports sequential (fixed order) and autonomous (stateless) phase patterns. Use for skill scaffolding, skill creation, or building new workflows. Triggers on "create skill", "new skill", "skill /skill-iter-tuneIterative skill tuning via execute-evaluate-improve feedback loop. Uses maestro delegate Claude to execute skill, Agy to evaluate quality, and Agent to apply improvements. Iterates until quality threshold or max iterations. Triggers on "skill iter tune", "iterative skill /skill-simplifySKILL.md simplification with functional integrity verification. Analyze redundancy, optimize content, check no functionality lost. Triggers on "simplify skill", "optimize skill", "skill-simplify"./skill-tuningUniversal skill diagnosis and optimization tool. Detect and fix skill execution issues including context explosion, long-tail forgetting, data flow disruption, and agent coordination failures. Supports Agy CLI for deep analysis. Triggers on "skill tuning", "tune skill", "skill /team-arch-optUnified team skill for architecture optimization. Uses team-worker agent architecture with role directories for domain logic. Coordinator orchestrates pipeline, workers are team-worker agents. Triggers on "team arch-opt".

Show all 24 skills

/team-coordinateUniversal team coordination skill with dynamic role generation. Uses team-worker agent architecture with role-spec files. Only coordinator is built-in -- all worker roles are generated at runtime as role-specs and spawned via team-worker agent. Beat/cadence model for /team-issueUnified team skill for issue resolution. Uses team-worker agent architecture with role directories for domain logic. Coordinator orchestrates pipeline, workers are team-worker agents. Triggers on "team issue"./team-lifecycle-v4Full lifecycle team skill — plan, develop, test, review in one coordinated session. Role-based architecture with coordinator-driven beat model. Triggers on "team lifecycle v4"./team-perf-optUnified team skill for performance optimization. Coordinator orchestrates pipeline, workers are team-worker agents. Supports single/fan-out/independent parallel modes. Triggers on "team perf-opt"./team-reviewUnified team skill for code review. 3-role pipeline: scanner, reviewer, fixer. Triggers on team-review./team-swarmSwarm intelligence team skill — ACO-driven multi-agent exploration with hybrid LLM coordinator + Python optimization controller. Coordinator generates swarm-config from user task, then runs K iterations of N parallel ants guided by pheromone state. Universal task space via /team-testingUnified team skill for testing team. Progressive test coverage through Generator-Critic loops, shared memory, and dynamic layer selection. Triggers on "team testing"./workflow-skill-designerMeta-skill for designing orchestrator+phases structured workflow skills. Creates SKILL.md coordinator with progressive phase loading, TodoWrite patterns, and data flow. Triggers on "design workflow skill", "create workflow skill", "workflow skill designer"./scholar-anti-ai-writingRemove AI writing patterns from academic prose. Detects and fixes inflated symbolism, promotional language, superficial analyses, vague attributions, AI vocabulary, and formulaic structures. Supports English and Chinese. Triggers on "remove AI patterns", "humanize text",/scholar-citation-verifyFour-layer citation verification for academic papers. Scans LaTeX/BibTeX files, verifies every citation via WebSearch and Google Scholar, generates verification report with fix suggestions. Triggers on "verify citations", "check references", "citation verification", "prevent /scholar-experimentSystematic experimental results analysis workflow for ML/AI research papers. Connects experimental data to publication-ready Results sections with statistical validation, visualizations, and quality checks. Triggers on "analyze experimental results", "generate results section",/scholar-ideationResearch ideation workflow from literature search to research planning. Triggers on "brainstorm research ideas", "identify research gaps", "conduct gap analysis", "start research project", "conduct literature review", "define research question", "select research method", "plan /scholar-latex-organizerOrganize messy conference LaTeX template .zip files into clean Overleaf-ready structure. Extracts, analyzes, cleans up, and generates README with submission requirements. Triggers on "organize LaTeX template", "clean up template", "prepare Overleaf template", "整理LaTeX模板"./scholar-publishPost-acceptance conference preparation workflow covering presentation slides, academic posters, and promotion content. Triggers on "scholar publish", "conference preparation", "prepare presentation", "create poster", "write promotion", "post-acceptance"./scholar-rebuttal-proEnhanced academic paper review response workflow with Agy/CLI collaborative analysis and multi-perspective discussion. Produces structured rebuttal documents with evidence-based strategies. Triggers on "rebuttal", "respond to reviewers", "review response", "审稿回复"./scholar-reviewSystematic academic paper review workflow covering self-review before submission and rebuttal writing after receiving reviewer feedback. Triggers on "review paper", "self-review", "write rebuttal", "respond to reviewers", "analyze review comments", "paper review"./scholar-thesis-docxCreate, revise, and format thesis or dissertation Word documents with strict academic formatting control. Use when an AI agent needs to generate or revise thesis content, normalize Word styles, follow a school template, fix captions or page numbers or section levels, or produce /scholar-writingEnd-to-end academic paper writing workflow. Takes a research repository and produces a publication-ready LaTeX manuscript for top ML/AI conferences (NeurIPS, ICML, ICLR, ACL, AAAI, COLM). Covers repo understanding, structure planning, section drafting, citation management,

Agents

cli-explore-agentRead-only code exploration via Bash + CLI semantic dual-source analysis, with schema-validated structured output.cross-role-reviewerCompares Decision Digests across role analysis files in a brainstorm session to surface conflicts, gaps, and synergies. Read-only — returns structured text for the orchestrator to apply.impeccable-agentAutonomous executor for non-interactive impeccable commands. Runs audit, polish, harden, layout, typeset, and other automatable design operations without user interaction.ralph-executorDeprecated compatibility alias for run-executor role-design-authorGenerates multi-file role analysis for a brainstorm session — analysis.md index + per-feature files + optional findings under {output_dir}/{role}/.run-executorSingle-step executor — session next(inline-brief)/run brief(backtrack) + inline skill execution, unnamed nesting for multi-agent orchestration

Show all 25 agents

team-supervisorResident pipeline supervisor agent. Message-driven lifecycle for cross-checkpoint quality observation and health monitoring.team-workerUnified worker agent for team pipelines. Executes role-specific logic loaded from a role_spec file within a built-in task lifecycle (discover, execute, report).ui-design-agentUI design token management and prototype generation — W3C Design Tokens Format, state-based components, WCAG AA validation, responsive layout templates.workflow-analyzerEvaluates technical topics, proposals, or decisions across multiple dimensions with evidence-based scoring and recommendations.workflow-codebase-mapperAnalyzes existing codebase from a specific focus area, spawned in parallel workflow-collab-plannerCollaborative planner working within pre-allocated task ID ranges workflow-debuggerHypothesis-driven debugging with structured evidence logging workflow-executorImplements single tasks atomically with verification and commit discipline workflow-external-researcherExternal research agent using Exa MCP for API details, design patterns, and technology evaluation workflow-integration-checkerCross-phase integration validation for milestone audits workflow-nyquist-auditorTest coverage audit with gap detection and test stub generation workflow-phase-researcherResearches implementation approach for a specific roadmap phase workflow-plan-checkerValidates plan quality with up to 3 revision rounds workflow-plannerCreates execution plans with task decomposition, waves, and dependencies workflow-project-researcherDomain research for project initialization, spawned with different focus angles workflow-research-synthesizerMerges multiple researcher outputs into a unified research summary workflow-reviewerMulti-dimensional code review agent — analyzes changed files for a single review dimension workflow-roadmapperCreates project roadmap with phased milestones from research and requirements workflow-verifierGoal-backward verification across three layers (existence, substance, connection)

Commands

/maestro-companionQuick execution for small tasks — minimal run lifecycle (start + done) with evidence recording. Full LLM capability, scoped to mechanically clear tasks./maestro-forkCreate or sync session worktree for parallel dev /maestro-guardManage editing boundary restrictions /maestro-impeccableUse when designing, auditing, polishing, improving, or codifying frontend UI — websites, dashboards, landing pages, components, design systems /maestro-initInitialize project with auto state detection /maestro-issueIntent-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

Show all 29 commands

/maestro-knowhowIntent-driven knowhow precipitation — describe what you want to capture (记一个关于X的决策 / 保存这段代码模板 / 写个部署配方 / 存个调试技巧) and the workflow infers the type and records it into .workflow/knowhow/. Pure capture surface; knowhow 的管理/审计走 /maestro-knowledge；项目约束规则走 /maestro-spec add。Triggers /maestro-knowledgeIntent-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./maestro-learnUser-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 /maestro-mergeMerge session worktree branch back to main /maestro-nextUnified 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 /maestro-odysseyLong-running iterative cycle — one entry, six modes (debug|improve|planex|review|security|ui). Shared archaeology/audit → fix → verify → generalize → discover → persist skeleton with mode-specific dimensions. User-invoked campaign entry; single-step fixes route via /maestro-next /maestro-overlayCreate or edit command overlays from natural language, or auto-generate them from workflow deficiency signals /maestro-ralphClosed-loop policy over the canonical Session/Run chain /maestro-session-sealSeal current session with knowledge candidate review and DAG progression /maestro-specIntent-driven spec precipitation — state a constraint in natural language (加一条规范：禁止用 any / 记录架构约束：服务间走 gRPC / 质量规则：覆盖率≥80%) and the workflow infers the category and records a <spec-entry>. Spec = 项目约束规则（编码规范、架构约束、质量标准）；可复用知识文档走 /maestro-knowhow capture。Triggers on "maestro-spec /maestro-updateDetect version, preview changes, apply workflow upgrades /maestroIntent-to-chain planner over the canonical Session/Run lifecycle /analyze| Keywords | Capability | Prefix | |----------|------------|--------| | analyze, scan, audit, map, identify | analyzer | ANALYZE | | design, plan, strategy, refactoring-plan | designer | DESIGN | | refactor, implement, fix, apply | refactorer | REFACTOR | | validate, build,/dispatch| Input | Source | Required | |-------|--------|----------| | User requirement | From coordinator Phase 1 | Yes | | Session folder | From coordinator Phase 2 | Yes | | Pipeline definition | From SKILL.md Pipeline Definitions | Yes | | Parallel mode | From team-session.json /monitor- SPAWN_MODE: background - ONE_STEP_PER_INVOCATION: true - FAST_ADVANCE_AWARE: true - WORKER_AGENT: team-worker /analyze-taskParse user task description -> detect required capabilities -> build dependency graph -> design dynamic roles with role-spec metadata. Outputs structured task-analysis.json with frontmatter fields for role-spec generation./fix1. Read original task + feedback/revision notes from task description 2. Load original implementation context (files modified, approach taken) 3. Analyze feedback to identify specific changes needed 4. Apply fixes: - Agent mode: Edit tool for targeted changes - CLI mode: Resume /implementDirect implementation using Edit/Write/Bash tools:/review-code- Plan file (plan.json) - Git diff or modified files list - Test results (if available)/review-spec- All spec docs in {run_dir}/outputs/spec/ - Quality gate config from specs/quality-gates.md /converge``` Bash: python <skill_root>/scripts/aco.py --session {run_dir}/work/team report ```/init-swarm- `swarm-config.json` from Phase 1 (in-memory or already written to candidate session path) - `session_id` already computed (`TS-<slug>-<date>`) - `skill_root` = `<project>/.claude/skills/team-swarm`/iterate| Entry | Trigger | Action | |-------|---------|--------| | **Iteration start** | Phase 3 invoked OR previous iteration converged=false | Run "Iteration Start" workflow | | **Iteration end** | All ants of current iter reported via callback | Run "Iteration End" workflow |

MCP

maestronode claude_dms3-chrome-devtoolsnpx exahttp

README

Read on GitHub

Maestro-Flow

意图驱动的多智能体工作流编排框架

说出你要做什么，Maestro 自动规划、调度、执行、验证。

简体中文 | English

大多数 AI 编程工具只能让一个 Agent 做一件事。 Maestro-Flow 让多个 Agent 协同完成从头脑风暴到部署上线的全流程 — 自适应决策引擎根据实际结果动态调整策略，知识图谱将每次执行的经验自动积累到下一次。

核心能力

自适应编排 — Ralph v2 引擎读取项目状态，将自然语言意图分类到 40+ 种命令链，在关键节点根据实际执行结果动态决策：继续、回退、还是插入修复循环。不写 YAML，不配置管线。

跨后端调度 — 同一工作流中混用 Claude、Codex、Gemini、Qwen、OpenCode，四种编排模式按需组合：Delegate（异步委派）、Team（角色协作）、Wave（依赖并行）、Swarm（蚁群探索）。

知识自增强 — Agent 执行中发现的模式、陷阱、决策，自动持久化为 Spec 和 Knowhow。Hook 系统将相关知识注入后续 Agent 的提示词 — 项目越用越聪明。

长周期自校正 — Odyssey 系列命令运行数小时级的自主循环，每个检查点自适应调整策略，直到满足验收标准。

安装

npm install -g maestro-flow
maestro install          # 交互式选择安装组件

需要 Node.js ≥ 18 和 Claude Code CLI。多 Agent 工作流可选装 Codex CLI、agy CLI。

快速上手

Ralph — 闭环策略层

主入口。说出目标，Ralph 自动判断开发阶段、构建命令链、在 decision 节点动态调整：

/maestro-ralph "实现 OAuth2 认证，支持 refresh token"

# Ralph 自动构建链：analyze → plan → execute → verify → review → test
# 遇到失败 → 自动插入 debug → fix → retry 循环
# 遇到新项目 → 自动前置 brainstorm → blueprint

maestro session status        # 查看当前会话进度
/maestro-ralph -c             # 从 decision 暂停点恢复
/maestro-ralph -y "..."       # 全自动，无需确认

核心管线

意图输入 → Ralph 分类（40+ 链类型）
              │
              ▼
brainstorm → blueprint(opt) → analyze → plan → execute → verify
                                                           ◆ decision
                                    review ── ◆ ── test ── ◆ ── milestone
                                                           ◆ → 下一里程碑

三种质量模式控制管线深度：

模式	管线	适用场景
`full`	verify → business-test → review → test-gen → test	生产环境、安全关键
`standard`	verify → review → test	默认平衡
`quick`	verify → CLI-review	原型、热修

其他入口

/maestro "添加用户资料页"            # 意图到链规划，自动选链
/maestro-next "修复重定向 bug"       # 纯路由：分类意图 → companion / 单 Run / /maestro
/maestro-companion "修正 README 拼写"  # 轻量执行：最小 Run 生命周期

Odyssey — 长周期自主循环

适合大型调试、深度重构、UI 优化等需要持续迭代的场景：

统一入口 /maestro-odyssey <intent> --mode <name>，六种模式：

模式	循环模式
`--mode debug`	考古分析 → 诊断 → 修复 → 确认 → 泛化 → 知识沉淀
`--mode planex`	需求解析 → 计划 → 执行 → 严格验证 → 修复循环
`--mode improve`	多维审计 → 深度诊断 → 定向修复 → 验证 → 泛化
`--mode review`	多维审查 → 定向修复 → 测试 → 泛化 → 知识沉淀
`--mode security`	分层安全审计（OWASP + 依赖 + 密钥 + STRIDE），只读
`--mode ui`	视觉巡检 → 多维审计 → 发散探索 → 修复 → 验证

Odyssey 持续运行直到验收标准达成，中间自适应调整策略，发现的知识自动持久化。

文档

入门

	指南	说明
01	快速开始	安装、第一个工作流、核心概念
02	安装指南	组件选择、工作空间配置
03	Ralph 引擎	自适应决策、quality 模式、session 管理
04	命令大全	64 个命令的用法、流程图、管线衔接

日常使用

指南	说明
CLI 命令参考	35+ 终端命令速查
知识管理	知识图谱、Spec、Knowhow、Wiki 全景
Spec 系统	项目规则的编写、加载与自动注入
质量管线	verify → review → test 三级管线
Hook 机制	17 个 Hook 的触发时机与上下文预算控制

指南	说明
工作流结构	四层命令拓扑、六条规范路径
多 Agent 协调	Delegate / Team / Wave / Swarm 详解
Delegate 异步执行	跨 CLI 委派、消息注入、链式调用
Overlay 扩展	不改源码给命令加行为
Worktree 并行开发	里程碑级分支隔离
跨项目共享	多项目 link/unlink 知识库
MCP 工具	9 个 MCP 端点工具参考
团队协作	2–8 人 Collab 模式
搜索系统	BM25F 全文搜索与 KG 集成
知识系统架构	Run ledger、知识协调、检索多样性与安全剪枝
学习工具	复盘、跟读、拆解、探究四件套
MaestroGraph 设计	统一知识图谱引擎架构
领域知识设计	语义词汇表与概念关系网络

项目规模

333 个 TypeScript 源文件 / ~80k 行代码 / 64 斜杠命令 / 45 技能包 / 23 Agent 定义 / 35+ CLI 命令 / 92 模板

技术栈 Commander.js · MCP SDK · better-sqlite3 · web-tree-sitter · React 19 · Zustand · Tailwind CSS 4 · Hono · Vite 6

maestro/
├── src/                     # 核心 CLI（Commander.js + MCP SDK）
│   ├── commands/            # 35+ CLI 命令
│   ├── mcp/                 # MCP 服务器（stdio）
│   ├── graph/               # 知识图谱（SQLite + tree-sitter）
│   └── core/                # 工具注册、扩展加载
├── dashboard/               # Web 仪表盘（React 19）
├── .claude/
│   ├── commands/            # 64 斜杠命令
│   ├── agents/              # 23 Agent 定义
│   └── skills/              # 45 技能包
├── workflows/               # 115 工作流定义
└── templates/               # 92 JSON 模板

	Superpowers	OpenSpec	Trellis	Maestro-Flow
定位	Agent 技能框架	规格驱动开发	多平台 Agent 治具	意图驱动编排
架构	纯 `.md`，无运行时	CLI + Git	CLI + `.trellis/`	CLI + MCP + SQLite
路由	手动选技能	手动命令序列	固定阶段	AI 分类 40+ 链
多 Agent	子 Agent 调度	单 Agent	Channel 模式	4 模式 × 5 后端
知识	仅 Git	Git 归档	文件日志	SQLite KG + 自动注入
长时工作	上下文窗口	手动 continue	日志恢复	有状态 Odyssey 循环
自校正	review-fix 循环	手动重验	手动	Decision 节点自动重试

各有所长：Superpowers 的 prompt 工程方法论最成熟；OpenSpec 的需求规格化最严谨；Trellis 的多平台统一做得最好；Maestro-Flow 聚焦全生命周期编排、跨后端调度和知识自增强。

致谢

GET SHIT DONE — Spec 驱动开发与上下文工程理念
Claude-Code-Workflow — 前身项目，开创多 CLI 编排
Impeccable — UI 设计技能（Apache-2.0）
Awesome Architecture — 架构知识库（maestro arch-kb），31 个架构模板 + 40 章教程 + 6 个案例（MIT）

@catlog22 — 创建者 & 维护者

加入微信群交流：

Linux DO：学AI，上L站！

MIT License

File tree

1521

catlog22/maestro-flowView on GitHub

.claude/
  agents/
    cli-explore-agent.md
    cross-role-reviewer.md
    impeccable-agent.md
    ralph-executor.md
    role-design-author.md
    run-executor.md
    team-supervisor.md
    team-worker.md
    ui-design-agent.md
    workflow-analyzer.md
    workflow-codebase-mapper.md
    workflow-collab-planner.md
    workflow-debugger.md
    workflow-executor.md
    workflow-external-researcher.md
    workflow-integration-checker.md
    workflow-nyquist-auditor.md
    workflow-phase-researcher.md
    workflow-plan-checker.md
    workflow-planner.md
    workflow-project-researcher.md
    workflow-research-synthesizer.md
    workflow-reviewer.md
    workflow-roadmapper.md
    workflow-verifier.md
  commands/
    maestro-companion.md
    maestro-fork.md
    maestro-guard.md
    maestro-impeccable.md
    maestro-init.md
    maestro-issue.md
    maestro-knowhow.md
    maestro-knowledge.md
    maestro-learn.md
    maestro-merge.md
    maestro-next.md
    maestro-odyssey.md
    maestro-overlay.md
    maestro-ralph.md
    maestro-session-seal.md
    maestro-spec.md
    maestro-update.md
    maestro.md
  scheduled_tasks.lock
  settings.json
  settings.local.json
  skills/
    maestro-help/
      index/
        catalog.json
      phases/
        01-parse-intent.md
        02-search-present.md
        03-workflow-guide.md
      SKILL.md
    skill-generator/
      phases/
        01-requirements-discovery.md
        02-structure-generation.md
        03-phase-generation.md
        04-specs-templates.md
        05-validation.md
      SKILL.md
      specs/
        cli-integration.md
        execution-modes.md
        reference-docs-spec.md
        scripting-integration.md
        skill-requirements.md
      templates/
        autonomous-action.md
        autonomous-orchestrator.md
        code-analysis-action.md
        llm-action.md
        script-template.md
        sequential-phase.md
        skill-md.md
    skill-iter-tune/
      phases/
        01-setup.md
        02-execute.md
        03-evaluate.md
        04-improve.md
        05-report.md
      SKILL.md
      specs/
        evaluation-criteria.md
      templates/
        eval-prompt.md
        execute-prompt.md
    skill-simplify/
      phases/
        01-analysis.md
        02-optimize.md
        03-check.md
      SKILL.md
    skill-tuning/
      phases/
        actions/
          action-abort.md
          action-agy-analysis.md
          action-analyze-requirements.md
          action-apply-fix.md
          action-complete.md
          action-diagnose-agent.md
          action-diagnose-context.md
          action-diagnose-dataflow.md
          action-diagnose-docs.md
          action-diagnose-memory.md
          action-diagnose-token-consumption.md
          action-generate-report.md
          action-init.md
          action-propose-fixes.md
          action-verify.md
        orchestrator.md
        state-schema.md
      SKILL.md
      specs/
        category-mappings.json
        dimension-mapping.md
        problem-taxonomy.md
        quality-gates.md
        skill-authoring-principles.md
        tuning-strategies.md
      templates/
        diagnosis-report.md
        fix-proposal.md
    team-arch-opt/
      roles/
        analyzer/
          role.md
        coordinator/
          commands/
            analyze.md
            dispatch.md
            monitor.md
          role.md
        designer/
          role.md
        refactorer/
          role.md
        reviewer/
          role.md
        validator/
          role.md
      SKILL.md
      specs/
        pipelines.md
        team-config.json
    team-coordinate/
      roles/
        coordinator/
          commands/
            analyze-task.md
            dispatch.md
            monitor.md
          role.md
      SKILL.md
      specs/
        knowledge-transfer.md
        pipelines.md
        quality-gates.md
        role-spec-template.md
    team-issue/
      roles/
        coordinator/
          commands/
            analyze.md
            dispatch.md
            monitor.md
          role.md
        explorer/
          role.md
        implementer/
          role.md
        integrator/
          role.md
        planner/
          role.md
        reviewer/
          role.md
      SKILL.md
      specs/
        pipelines.md
        team-config.json
    team-lifecycle-v4/
      roles/
        analyst/
          role.md
        coordinator/
          commands/
            analyze.md
            dispatch.md
            monitor.md
          role.md
        executor/
          commands/
            fix.md
            implement.md
          role.md
        planner/
          role.md
        reviewer/
          commands/
            review-code.md
            review-spec.md
          role.md
        supervisor/
          role.md
        tester/
          role.md
        writer/
          role.md
      SKILL.md
      specs/
        knowledge-transfer.md
        pipelines.md
        quality-gates.md
      templates/
        architecture.md
        epics.md
        product-brief.md
        requirements.md
    team-perf-opt/
      roles/
        benchmarker/
          role.md
        coordinator/
          commands/
            analyze.md
            dispatch.md
            monitor.md
          role.md
        optimizer/
          role.md
        profiler/
          role.md
        reviewer/
          role.md
        strategist/
          role.md
      SKILL.md
      specs/
        pipelines.md
        team-config.json
    team-review/
      roles/
        coordinator/
          commands/
            analyze.md
            dispatch.md
            monitor.md
          role.md
        fixer/
          role.md
        reviewer/
          role.md
        scanner/
          role.md
      SKILL.md
      specs/
        dimensions.md
        finding-schema.json
        pipelines.md
        team-config.json
    team-swarm/
      roles/
        analyst/
          role.md
        ant/
          role.md
        coordinator/
          commands/
            converge.md
            init-swarm.md
            iterate.md
          role.md
        scorer/
          role.md
      scripts/
        aco.py
        pheromone.py
        scoring.py
        test_aco.py
      SKILL.md
      specs/
        ant-output-schema.md
        convergence-criteria.md
        pheromone-schema.md
        swarm-config-template.json
        swarm-protocol.md
    team-testing/
      roles/
        analyst/
          role.md
        coordinator/
          commands/
            analyze.md
            dispatch.md
            monitor.md
          role.md
        executor/
          role.md
        generator/
          role.md
        strategist/
          role.md
      SKILL.md
      specs/
        pipelines.md
        team-config.json
    workflow-skill-designer/
      phases/
        01-requirements-analysis.md
        02-orchestrator-design.md
        03-phase-design.md
        04-validation.md
      SKILL.md
.codebuddy/
  settings.local.json
.codex/
  agent-overrides/
    team-supervisor.md
    team-worker.md
  agents/
    cli-explore-agent.toml
    cross-role-reviewer.toml
    impeccable-agent.toml
    ralph-executor.toml
    role-design-author.toml
    run-executor.toml
    team-supervisor.toml
    team-worker.toml
    ui-design-agent.toml
    workflow-analyzer.toml
    workflow-codebase-mapper.toml
    workflow-collab-planner.toml
    workflow-debugger.toml
    workflow-executor.toml
    workflow-external-researcher.toml
    workflow-integration-checker.toml
    workflow-nyquist-auditor.toml
    workflow-phase-researcher.toml
    workflow-plan-checker.toml
    workflow-planner.toml
    workflow-project-researcher.toml
    workflow-research-synthesizer.toml
    workflow-reviewer.toml
    workflow-roadmapper.toml
    workflow-verifier.toml
  config.toml
  multi-agents-v2-schema.md
  skills/
    maestro/
    maestro-companion/
      SKILL.md
    maestro-fork/
      SKILL.md
    maestro-guard/
      SKILL.md
    maestro-help/
      index/
        catalog.json
      phases/
        01-parse-intent.md
        02-search-present.md
        03-workflow-guide.md
      SKILL.md
    maestro-impeccable/
      SKILL.md
    maestro-init/
      SKILL.md
    maestro-issue/
      SKILL.md
    maestro-knowhow/
      SKILL.md
    maestro-knowledge/
      SKILL.md
    maestro-learn/
      SKILL.md
    maestro-merge/
      SKILL.md
    maestro-next/
      SKILL.md
    maestro-odyssey/
      SKILL.md
    maestro-overlay/
      SKILL.md
    maestro-ralph/
      optimization-strategy.md
      SKILL.md
    maestro-session-seal/
      SKILL.md
    maestro-spec/
      SKILL.md
    maestro-update/
      SKILL.md
... 1600 more

Showing a partial view of a very large repo.

FAQ

maestro-flow is a Claude Code plugin with 24 hand-picked skills for development work, indexed on Flowy. Install it with the command on its page. It includes maestro-help, skill-generator, skill-iter-tune. Its skills do not fire on their own yet. Request auto-invocation to have Flowy route them as you prompt. Free and open source.

What is maestro-flow?: Intent-driven workflow orchestration for multi-agent AI development — adaptive lifecycle engine, self-reinforcing knowledge graph, and visual dashboard for Claude Code, Gemini, Codex & more
How do I install maestro-flow?: Run these in Claude Code: npx -y skills add catlog22/maestro-flow --agent claude-code. Then prompt normally.
Does maestro-flow auto-invoke its skills?: Not yet. It is indexed on Flowy as a plain plugin. Request auto-invocation on its page and Flowy will route its skills for you as you prompt.
Is maestro-flow free?: Yes. Flowy is free and open source, with nothing gated. You can read every skill in full before you install.