Multi agent research
Skill thaolst/ai-growth-agents-for-marketers/skills/multi-agent-research
Run multi-agent research-to-planning pipeline using two sequential agents. Use when the user has campaign data and needs a structured plan without code. Agent 1 (Research) analyzes campaign data and returns structured JSON insights. Agent 2 (Strategy) takes those insights and produces a complete campaign plan. Input: campaign data, target, budget, timeline. Output: research findings as JSON → executable campaign plan.From its SKILL.md
npx -y skills add thaolst/ai-growth-agents-for-marketers --skill multi-agent-researchAssembled from the repository path, not quoted from the project. Check it against their README if it does not work.
2 things to look at
- reads credentialsReads from 1 credential source: `.agents/product-marketing-context.md`.
- 5 stars5 stars. Stars are a popularity signal and not a quality one, but at this level it is likely that nobody has read this closely except its author, and you would be relying on your own review.
SKILL.md
1.9 KB, 326 tokens by cl100k_base, as published. Nobody here has run it
Multi-Agent Research & Planning Agent
Bạn hướng dẫn marketer chạy hai agent nối tiếp nhau — không cần code, chỉ cần hai cuộc trò chuyện riêng trong Claude.
Context check: Reads
.agents/product-marketing-context.mdfor market context. If growth-mcp connected, pulls market data before research phase.
Workflow
Agent 1: Research
Input: campaign data, target, budget. Output: structured JSON insights về market, segments, past performance, recommendations.
Agent 2: Strategy
Input: JSON từ Agent 1 + constraints. Output: executable campaign plan với timeline, budget, mechanics, risks.
Khi nào dùng
- Có nhiều dữ liệu campaign cần phân tích trước khi lập kế hoạch
- Muốn structured research notes (JSON) trước khi viết plan
- Campaign phức tạp, cần separation of concerns
Related Skills
- campaign-planning — tổng quan plan
- campaign-brief — chi tiết từng campaign
- growth-mcp-connect — pull research data
English
Guide the marketer through a two-agent sequential pipeline — no code required, just two separate conversations in Claude.
Agent 1 (Research) → Agent 2 (Strategy) = executable campaign plan.
What ships with it
Read from the repository
Just SKILL.md. No reference files, no scripts.