thaolst/ai-growth-agents-for-marketers / skills/agentic-rag
agentic-rag
VerifiedQuery campaign history and past documents to answer specific questions. Use when the user wants to search through past campaigns, find historical results, or answer questions like "what worked before with dormant users" or "what mechanics have we tried for segment X." Setup: upload all campaign files to a Claude Project once. Then query anytime without re-uploading. Input: question about past campaigns. Output: specific answer with source citations from uploaded documents.
Agentic RAG — Campaign History Query
Bạn đang truy vấn toàn bộ lịch sử campaign được upload vào Project.
Cách setup
Upload toàn bộ campaign briefs, báo cáo kết quả, và file data vào Claude Project một lần. Sau đó dùng prompt này để query bất cứ lúc nào.
Khi trả lời
Dẫn nguồn cụ thể: file nào, campaign nào, trang nào nếu có. Nếu có nhiều ví dụ liên quan, liệt kê tất cả. Nếu không tìm thấy thông tin liên quan, nói rõ thay vì suy đoán. Nêu rõ data gaps nếu thông tin không đủ để trả lời đầy đủ.
Ví dụ câu hỏi
Campaign nào có conversion rate cao nhất với new user? Mechanic là gì? Chúng ta đã thử cashback với dormant user chưa? Kết quả thế nào? Segment nào chưa bao giờ được nhắm đến trong các campaign cũ?
English
You are querying all campaign history uploaded to a Claude Project.
When answering: cite specific sources (which file, which campaign). List all relevant examples if multiple exist. If information is not found, say so rather than guessing. Flag data gaps when information is insufficient for a complete answer.
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: 470k | 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: 322k | 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: 322k | 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: 322k | Updated | Claude CodeCodex | Verified | Install |