Skill Detail

Build document-grounded agent context workflows with RAGFlow

Use RAGFlow to ingest complex documents, build governed RAG knowledge bases, and give agents higher-fidelity context for retrieval-augmented workflows.

Data Extraction & TransformationMulti-Framework
Data Extraction & Transformation Multi-Framework Security Reviewed
⭐ 79.8k GitHub stars
INSTALL WITH ANY AGENT
npx skills add agentskillexchange/skills --skill build-document-grounded-agent-context-workflows-with-ragflow Copy
Works best when you want a reusable capability, not another fragile one-off prompt.
At a glance
Tools required
RAGFlow, Docker or self-hosted/cloud RAGFlow deployment, target LLM/provider credentials as needed
Install & setup
Follow the RAGFlow self-hosting or cloud setup from the upstream documentation; the GitHub README links Docker images, releases, configuration, and source-development launch paths.
Author
infiniflow
Publisher
Open Source Project
Last updated
May 6, 2026
Quick brief

Approve RAGFlow as an agent-context workflow skill, not as a generic RAG product listing. The operator uses RAGFlow to parse and ingest documents, configure chunking and retrieval, connect knowledge bases to agent workflows, and expose grounded context when an LLM or agent needs source-backed answers. Invoke this when a user needs repeatable document-grounded agent context across PDFs, office files, knowledge bases, or enterprise sources instead of manually prompting a chatbot with ad hoc files. The scope boundary is the RAG ingestion, retrieval, and agent-context workflow; broader hosted-product administration and unrelated application features stay out of scope.

How it works

What this skill actually does

Inputs and prerequisites: RAGFlow, Docker or self-hosted/cloud RAGFlow deployment, target LLM/provider credentials as needed.

Setup notes: Follow the RAGFlow self-hosting or cloud setup from the upstream documentation; the GitHub README links Docker images, releases, configuration, and source-development launch paths.

Source and verification boundary: use https://ragflow.io as the canonical reference before running the workflow; keep commands, API calls, CLI usage, and generated outputs reviewable against that upstream source.

Framework fit: publish this as a Multi-Framework workflow only when the operator can invoke the documented toolchain directly, rather than treating the upstream project as a generic product listing.