multi-agent-workflow
Installation
SKILL.md
Multi-Agent Workflow Guide
When to use
- Complex feature spanning multiple domains (full-stack, mobile)
- Coordination needed between frontend, backend, mobile, and QA
- User wants to manually manage agents via Agent Manager UI
When NOT to use
- Simple single-domain task -> use the specific agent directly
- User wants automated execution -> use orchestrator
- Quick bug fixes or minor changes
Core Rules
- Always start with PM Agent for task decomposition
- Spawn independent tasks in parallel (same priority tier)
- Define API contracts before frontend/mobile tasks
- QA review is always the final step
- Assign separate workspaces to avoid file conflicts
- Always use Serena MCP tools as the primary method for code exploration and modification
Related skills
More from first-fluke/mimic
qa-agent
Quality assurance specialist for security, performance, accessibility, and comprehensive testing
1mimic-qa
Perform end-to-end QA testing on the MIMIC extension. Use this skill to verify core functionalities like shell hooking, analysis, synthesis, and sidebar UI.
1pm-agent
Product manager that decomposes requirements into actionable tasks with priorities and dependencies
1product-planner
Act as a 30-year veteran Product Manager & System Analyst specialized in Developer Tools and AI Agents. Use this skill to brainstorm features, define requirements, and create technical specs for MIMIC.
1frontend-agent
Frontend specialist for React, Next.js, TypeScript, and modern UI development
1memory-recorder
Recording skill that selectively saves only long-term valuable facts to Serena memory.
1