菜单
Ultimate Mastra Framework development toolkit for agent orchestration, workflow design, and MCP integration
用 Codex 或 Claude 帮你安装 复制这段 Prompt，粘贴到 Codex、Claude 或其他助手里，让它检查 Skill 页面并帮你完成安装。
基于 SOC 职业分类
Structured task execution with quality gates, parallel waves, and pm-db tracking — solo or with multi-agent teams (--team). Use this skill when the user wants to execute a task list, run implementation tasks, start building a feature from a plan, run tasks in parallel with a team of agents, or says things like 'execute these tasks', 'start building', 'run the implementation', 'execute the plan', 'execute with a team', or 'start phase execute'. Also triggers on '/start-phase execute' and '/start-phase-execute-team' commands.
Assess and score codebase architecture health — layer separation, SOLID compliance, module coupling (FAN-IN/FAN-OUT), circular dependencies, drift from documented patterns. Use whenever the user asks to assess/review/grade architecture quality, wants an architecture score, or asks how healthy the codebase's architecture is. Analysis-only report + refactoring tasks; for docs-vs-code drift use document-hub-analyze.
Deep analysis of codebase for code duplication. Detects exact, structural, and pattern-level duplicates, generates comprehensive reports with refactoring suggestions and metrics.
Use when Mark reports a bug by pasting a raw artifact with little or no prose — a stack trace, an HTTP request/response trace (URL + method + status like 500/403/404/502), a console/React/Prisma error, a ChunkLoadError, a shell error, or a screenshot of a visual defect — or when he says things like 'still failing', 'clicking X does nothing', 'no inline editor on the rendered page', 'do we have local postgres/pgvector?', or 'identify the true error'. This is the front-to-back debugging procedure — extract the trigger and reproduction from terse input, probe whether the underlying plumbing even exists, localize by contrasting known-good vs broken, and drive to a durable root cause rather than a workaround. Reach for this BEFORE proposing any fix.
Deep analysis of codebase vs documentation alignment (cline-docs/). Detects drift, identifies undocumented code, extracts missing glossary terms, and provides actionable recommendations without making changes. Use this skill when the user asks "are the docs up to date", "check documentation quality", "what's missing from the docs", or wants a read-only audit before deciding what to update. For actually making changes, use document-hub-update instead.
Bootstrap a new project's documentation hub by creating the four core documentation files (systemArchitecture.md, keyPairResponsibility.md, glossary.md, techStack.md) with initial content based on codebase analysis.
| name | mastra-dev |
| description | Ultimate Mastra Framework development toolkit for agent orchestration, workflow design, and MCP integration |
| args | {"command":{"type":"string","description":"Operation to perform (create-agent, create-workflow, server, mcp, etc.)","required":true},"options":{"type":"object","description":"Command-specific options","required":false}} |
A comprehensive skill for developing, managing, and debugging Mastra Framework applications: automated scaffolding (agents, workflows, tools), server/Studio lifecycle, MCP integration, and analysis/debugging via the /mastra-dev CLI (skill.sh → scripts/main.py). Targets the AIForge Mastra app at apps/mastra (configurable via .mastra-dev-config.json).
/mastra-dev server status # Check Mastra server
/mastra-dev analyze # Analyze current setup
/mastra-dev create-agent --name "contract-analyzer" --model "anthropic/claude-3-5-sonnet-20241022"
/mastra-dev create-workflow --name "form-generation" --description "Auto-fill government forms"
/mastra-dev server start # Start server (port 6000)
/mastra-dev studio start # Observability UI (port 4111)
| Area | Commands | What they do |
|---|---|---|
| Agents | create-agent, list-agents, analyze-agent | Scaffold agent in src/agents/, auto-register in mastra.config.ts; inventory and inspect agents |
| Workflows | create-workflow, add-step, test-workflow, list-workflows | Scaffold DAG workflows in src/workflows/ (.then()/.parallel()/.branch()), add typed steps, execute with test input |
| Tools | create-tool, list-tools, test-tool | Scaffold Zod-validated tools in src/tools/, test independently |
| Server | server start|stop|status|logs, studio start | Manage Express server (port 6000, logs at apps/mastra/logs/mastra.log) and Mastra Studio (port 4111) |
| MCP | mcp add-client, mcp configure-server, mcp list-servers, mcp test, mcp remove-client | Consume external MCP servers (stdio or HTTP) and expose Mastra agents/workflows/tools via mcp.config.ts |
| Analysis | analyze, validate, debug-workflow, show-graph | Full setup scan, config validation, execution debugging from DB logs, ASCII DAG visualization |
Full flag lists, generated-file examples, and sample outputs per command: references/command-reference.md.
This skill is the CLI/scaffolding hub. For Mastra concepts, APIs, and hand-written code patterns, route to the satellite skill for the topic — each carries a full guide that loads only when invoked:
| Topic | Skill |
|---|---|
| Agent creation, tools-on-agents, networks, processors, guardrails, voice, structured output | mastra-agents |
| Workflow DAGs, control flow, suspend/resume, HITL, time travel, state | mastra-workflows |
| MCPClient/MCPServer code, tool creation and publishing | mastra-mcp-tools |
| Memory: storage backends, history, working/semantic memory, threads | mastra-memory |
| RAG: chunking, embedding, vector DBs, retrieval, GraphRAG | mastra-rag |
| Streaming: agent/workflow/tool streams, SSE, AI SDK React/Next.js | mastra-streaming |
| Evals: scorers, datasets, experiments, CI | mastra-evals |
| Deployment: server adapters, auth, middleware, client SDK, cloud | mastra-deploy |
| Workspace: filesystem providers, sandbox execution, skills, search | mastra-workspace |
| Team orchestration and execution planning for Mastra work | mastra-planning |
references/cli-faq.md — the five core how-do-I questions (create agent, build multi-step workflow, integrate MCP servers, debug execution, inventory constructs) with full invocations. Read when a user asks "how do I X with /mastra-dev".references/command-reference.md — per-command docs for all six areas: every flag, generated TypeScript, sample outputs. Read before running an unfamiliar command or explaining its behavior.references/configuration.md — .mastra-dev-config.json options, AIForge app integration (directory layout, auto-registration), and the four templates/*.template.ts variables. Read when configuring paths/ports or debugging generation output.references/best-practices.md — DO/DON'T checklists for agents, workflows, tools, MCP, and testing. Read before designing new constructs.references/troubleshooting.md — ten common issues (server down, unregistered agent, schema errors, MCP timeouts, Studio blank, TS/DB/permission/Python errors, workflow not exposed) with fixes. Read when a command or the server fails.references/use-cases.md — three end-to-end walkthroughs (contract analysis system, form auto-filling, multi-agent research). Read for a full build recipe to adapt./feature-new - Complete feature development workflow/security-quality-assess - Security vulnerability scanning/pm-db - Project management databaseFor issues, questions, or contributions: