thaolst/ai-growth-agents-for-marketers / skills/multi-agent-workflow
multi-agent-workflow
VerifiedRun a two-stage research then planning workflow for growth campaigns. Use when the user wants to analyze past campaign data AND create a new plan based on that analysis in one connected workflow. Stage 1: analyze data and extract structured insights. Stage 2: use insights to build a campaign plan. Input: past campaign data, target, budget, timeline. Output: structured analysis followed by a specific campaign plan.
Multi-Agent Workflow: Research + Plan
Hai giai đoạn nối tiếp nhau. Output của giai đoạn 1 là input của giai đoạn 2.
Giai đoạn 1 — Research Agent
Đọc data campaign và xuất ra JSON có cấu trúc:
{
"top_performing_mechanics": [],
"underperforming_areas": [],
"segment_insights": {},
"recommended_focus": [],
"data_gaps": []
}
Chỉ trả về JSON, không giải thích thêm.
Giai đoạn 2 — Strategy Agent
Nhận JSON từ giai đoạn 1. Dựa trên analysis, viết campaign plan với:
- Strategy tổng thể và lý do
- Campaign cụ thể với mechanic, budget, timeline
- Giải thích tại sao mỗi quyết định dựa trên insight từ giai đoạn 1
Nguyên tắc
Không bỏ qua data gaps từ giai đoạn 1. Mọi quyết định trong plan phải có dẫn chứng từ analysis.
English
Two stages in sequence. Output of stage 1 is input of stage 2.
Stage 1: Analyze campaign data, return structured JSON with top performing mechanics, underperforming areas, segment insights, recommended focus, and data gaps.
Stage 2: Use the JSON analysis to build a specific campaign plan. Every decision must reference insights from stage 1.
Related skills
| Skill | Stars | Updated | Works with | Status | Install |
|---|---|---|---|---|---|
| reverse-engineer-anythingmorluto/reaReverse engineer native, managed, Electron/JavaScript, packaged, firmware, and browser targets with REA, and build agent environments (AgentEnv bundles) of web applications from a live instance or a capture, and of Linux desktop apps with a task from a request. Use shipped-artifact or requested runtime evidence to explain features, compare versions, decompile code, or guide a reconstruction. Skip REA for ordinary source-repository architecture analysis. | Stars: 468k | Updated | Claude CodeCodex | Verified | Install |
| diagnosing-superpowersobra/superpowersUse when a superpowers session went wrong and your human partner wants to know why — repeated work, ignored plans, stumbles, poor results, a skill that didn't fire, "it took too long", "why is it so expensive", "what is it doing" — or wants to build a bug report for the superpowers maintainers, for the current session or a past one identified by id or path, on any harness. | Stars: 321k | Updated | Claude CodeCodex | Verified | Install |
| dispatching-parallel-agentsobra/superpowersUse when facing 2+ independent tasks that can be worked on without shared state or sequential dependencies | Stars: 321k | Updated | Claude CodeCodex | Verified | Install |
| executing-plansobra/superpowersUse when executing an implementation plan in the current session as the implementer yourself — your human partner chose inline execution, or no subagent tool is available | Stars: 321k | Updated | Claude CodeCodex | Verified | Install |