maestro-flow

Manifest-driven knowledge asset generator — converts any structured package into maestro knowhow + spec entries with ref linking. Triggers on "codify-to-knowhow", "style to knowhow", "知识固化".

Check workflow delegation prompts against agent role definitions for content separation violations. Detects conflicts, duplication, boundary leaks, and missing contracts. Triggers on "check delegation", "delegation conflict", "prompt vs role check".

Adversarial review of code quality findings. Challenges insights with counter-evidence, verifies claims against source code, and produces structured verdicts. Triggers on 'insight-challenge', 'challenge finding', '审查发现'.

Quick execution for small tasks (≤1-2 files, no artifact handoff) — minimal run lifecycle (create + complete only) with evidence recording. Can read/write/run any tool, but scoped to tasks completable in a few actions. Not for multi-step workflows or tasks needing downstream gates

Create or sync session worktree for parallel dev

Manage editing boundary restrictions

Maestro 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".

Use when designing, auditing, polishing, improving, or codifying frontend UI — websites, dashboards, landing pages, components, design systems

Initialize project with auto state detection

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

Project management hub — status, issues, knowledge stores, and drift/rebuild sync. knowledge 子命令覆盖 capture（knowhow 沉淀）/ audit（知识审计）/ harvest / wiki / domain；约束类规则走 /maestro-spec add。Triggers on "项目状态", "issue 管理", "知识沉淀", "knowhow capture", "knowledge audit", "知识审计", "drift 同步".

Merge session worktree branch back to main

Unified entry for all development intents — classify intent, assess complexity, route to the correct execution channel: /maestro-companion (lightweight), standard single run, or /maestro (multi-step with manual/ralph engine). Pure router, never runs execution loops itself

Long-running iterative cycle — one entry, five modes (debug|improve|planex|review|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

Create or edit command overlays from natural language, or auto-generate them from workflow deficiency signals

Adaptive lifecycle orchestrator for explicit Ralph lifecycle, continuation, or engine requests

Seal current session with knowledge extraction and DAG progression

Multi-step orchestration engine with dual execution modes — ralph (Agent dispatch, decision gates, drift, auto-retry) and manual (per-step confirm, direct LLM execution). Triggered by /maestro-next routing or invoked directly

Manage project specs — add, load, remove entries, or initialize the spec system. 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-manage knowledge capture。Triggers on "maestro-spec add", "记录规范", "添加约束", "添加规则", "加载规范", "maestro-spec setup", "初始化规范".

Detect version, preview changes, apply workflow upgrades

Generate or convert Claude Code prompt files — command orchestrators, skill files, agent role definitions, or style conversion of existing files. Follows GSD-style content separation with built-in quality gates. Triggers on "create command", "new command", "create skill", "new skill", "create agent", "new agent", "convert command", "convert skill", "convert agent", "prompt generator", "优化".

Systematic tech-debt identification and safe reduction — plan → confirm → execute with per-change test verification. For explicit refactoring requests; casual tech-debt mentions route via /maestro-next

Remove 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", "anti-AI polish", "去除AI写作痕迹", "人性化处理".

Four-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 fake citations", "引用验证".

Systematic 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", "statistical analysis of experiments", "compare model performance", "create results visualization".

Research 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 research", "research ideation".

Organize 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".

Post-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".

Enhanced 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".

Systematic 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".

Create, 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 evidence-based Mermaid figures and LaTeX-formatted code listings for a thesis document.

End-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, anti-AI polishing, and conference formatting. Triggers on "write paper", "draft paper", "scholar writing", "paper writing workflow".

OWASP Top 10 and STRIDE security auditing with supply chain analysis

Meta-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 generator".

Iterative 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 tuning", "tune skill".

SKILL.md simplification with functional integrity verification. Analyze redundancy, optimize content, check no functionality lost. Triggers on "simplify skill", "optimize skill", "skill-simplify".

Universal 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 diagnosis", "optimize skill", "skill debug".

ACO swarm intelligence with modular Workflow composition and adversarial decision gates. Coordinator drives iteration loop; 4 composable Workflow scripts handle exploration, scoring, convergence, and synthesis — each with built-in adversarial patterns.

Unified 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".

Unified team skill for brainstorming team. Uses team-worker agent architecture with role directories for domain logic. Coordinator orchestrates pipeline, workers are team-worker agents. Triggers on "team brainstorm".