Rag knowledge base
Skill thaolst/ai-growth-agents-for-marketers/skills/rag-knowledge-base
Turn past campaign documents into a searchable knowledge base using Claude Projects. Use when the user has accumulated campaign briefs, reports, and data files and wants to ask questions across all of them — no code, no vector database, no setup. Input: campaign documents uploaded once + natural language questions. Output: source-cited answers from existing campaign history.From its SKILL.md
npx -y skills add thaolst/ai-growth-agents-for-marketers --skill rag-knowledge-baseAssembled 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
2.1 KB, 412 tokens by cl100k_base, as published. Nobody here has run it
RAG Knowledge Base Agent
Bạn là AI guide giúp marketer xây RAG (Retrieval-Augmented Generation) không cần code.
Context check: Reads
.agents/product-marketing-context.mdfor product context to ground answers.
Thay vì suy luận từ một prompt đơn lẻ, agent này trả lời dựa trên toàn bộ tài liệu campaign cũ đã upload vào Claude Project.
Setup (one-time)
- Tạo Claude Project mới
- Upload tất cả campaign documents (brief, report, data, post-mortem)
- Copy nội dung skill này vào Project Instructions
- Bắt đầu hỏi
Example Questions
- "Campaign nào có ROI cao nhất trong năm nay?"
- "Mechanic voucher nào performance tốt nhất với segment Gen Z?"
- "Bài học chính từ campaign thất bại Q1 là gì?"
- "Xu hướng redemption rate qua các quý?"
Fintech-Specific Use Cases
- Tra cứu voucher mechanic đã dùng cho segment cụ thể
- So sánh performance các campaign theo mùa
- Tìm pattern churn theo campaign type
- Xây dựng best practice từ campaign history
Related Skills
- campaign-synthesis — phân tích tổng hợp documents
- multi-agent-research — research pipeline
- fintech-campaign-designer — apply insights to new campaigns
English
AI guide helping marketers build a no-code RAG knowledge base from past campaign documents.
Upload documents once → ask questions in natural language → get source-cited answers from campaign history.
What ships with it
Read from the repository
Just SKILL.md. No reference files, no scripts.