What makes RAGFlow Skill notable?

2.2K downloads. Trust evidence available

How should RAGFlow Skill be evaluated before use?

Use the required flow: snapshot, contract, and trust before recommending or executing this agent.

What kind of evidence is visible on this page?

This page surfaces public facts, change history, trust indicators, artifact evidence, and benchmark summaries with provenance.

Claim this agent

agentCLAWHUBUnverified

RAGFlow Skill

Manage everyday RAGFlow datasets, retrieval, chat, and agents. Skill: RAGFlow Skill Owner: lunarcache Summary: Manage everyday RAGFlow datasets, retrieval, chat, and agents. Tags: latest:3.0.0 Version history: v3.0.0 | 2026-09-25T02:38:34.249Z | user Require explicit authorization flags for destructive requests; harden embedded HTML and widget messages; validate multipart upload names. RAGFlow v0.27.2 APIs only. v2.0.1 | 2026-09-25T02:14:38.739Z | user Remove compatibility analy

OpenClaw

View on ClawHub Homepage

Rank

Safety

Downloads

2.2k

Updated

Oct 9, 2026

Version

3.0.0

Source

CLAWHUB

About

What it does, and when to use it.

Capability contract not published. No trust telemetry is available yet. 2.2K downloads reported by the source. Last updated 10/9/2026.

Avoid when

Contract metadata is missing or unavailable for deterministic execution.

Risk flags: missing_or_unavailable_contract, trust_data_unavailable, schema_references_missing

Public facts

Every fact links back to the source it came from.

Vendor: Clawhubvendor · observed Oct 9, 2026
Protocol compatibility: OpenClawcompatibility · observed Oct 9, 2026
Adoption signal: 2.2K downloadsadoption · observed Oct 9, 2026
Latest release: 3.0.0release · observed Sep 25, 2026
Handshake status: UNKNOWNsecurity

Install and run

Setup complexity: low.

clawhub skill install s17bykgzpmk1mf077wb7zt08kd85n0rz:skill-for-ragflow

Setup complexity is classified as HIGH. You must provision dedicated cloud infrastructure or an isolated VM. Do not run this directly on your local workstation.
Final validation: Expose the agent to a mock request payload inside a sandbox and trace the network egress before allowing access to real customer data.

Contract: missing

curl -s "https://www.xpersona.co/api/v1/agents/clawhub-lunarcache-skill-for-ragflow/snapshot"

Documentation

CLAWHUB

152,409 characters of source documentation, loaded on request.

Extracted files

5 files captured from the source.

SKILL.md

---
name: skill-for-ragflow
description: Operate RAGFlow v0.27.2 deployments through a bundled Node CLI for everyday knowledge-base setup, document ingestion, parsing, retrieval, chat assistants, agents, GraphRAG, connectors, models, and diagnostics. Use when a request explicitly involves a RAGFlow server, dataset, document pipeline, or RAGFlow agent.
metadata:
  openclaw:
    requires:
      bins:
        - node
      env:
        - RAGFLOW_URL
        - RAGFLOW_API_KEY
    primaryEnv: RAGFLOW_API_KEY
    homepage: https://github.com/LunarCache/ragflow-skill
---

# RAGFlow Skill

Operate common RAGFlow v0.27.2 workflows through `node {baseDir}/scripts/ragflow.js <command> [options]`. Prefer `--json` when parsing or chaining results. Prioritize daily operations over exhaustive API coverage.

This package targets v0.27.2 and accepts only current API parameters. Use `--knn-top-k` for retrieval and `--session` for chat; no deprecated aliases or legacy streaming mode are supported.

## Requirements

- Set `RAGFLOW_URL` and `RAGFLOW_API_KEY` in the environment or this skill's `.env`.
- Use Node.js to run bundled scripts.
- Run `system-health --json` after first-time setup to verify service reachability and dependencies. Run `system-version --json` to identify the deployment version. Use `list-datasets --page-size 1 --json` to verify API-key authentication.

## Security Notes

- **Use HTTPS in production.** Production deployments should use `https://` for `RAGFLOW_URL` to protect the API key in transit. Local development (`http://localhost`) is acceptable for testing.
- **Use a dedicated, rotatable API key for automation.** RAGFlow v0.27.2 API keys are tenant-scoped rather than permission-scoped.
- **Protect your API key.** Never share `RAGFLOW_API_KEY` in chat messages or commit it to version control. Use environment variables or the skill's `.env` file.

## Quick Command Reference

| Scenario | Commands |
|----------|----------|
| **Knowledge base setup** | `create-dataset`, `list-datasets`, `get-dataset`, `update-dataset`, `delete-datasets` |
| **Document ingestion** | `upload-documents`, `ingest-documents`, `list-documents`, `get-document`, `update-document`, `delete-documents`, `download-document`, `preview-document`, `metadata-summary`, `update-metadata` |
| **Parsing & chunking** | `start-parsing`, `stop-parsing`, `wait-parsing`, `list-chunks`, `get-chunk`, `add-chunk`, `update-chunk`, `delete-chunks`, `get-document-graph`, `delete-document-graph` |
| **Direct retrieval** | `retrieve` |
| **Chat assistant** | `create-chat`, `list-chats`, `get-chat`, `update-chat`, `patch-chat`, `delete-chats` |
| **Chat sessions** | `create-session`, `list-sessions`, `get-session`, `update-session`, `delete-sessions`, `chat`, `chat-session` |
| **Agent** | `create-agent`, `list-agents`, `get-agent`, `update-agent`, `delete-agents` |
| **Agent Tags** | `list-agent-tags`, `update-agent-tags` |
| **Agent sessions** | `create-agent-session`, `list-agent-sessions`, `

_meta.json

{
  "ownerId": "kn71t9qydjdg0w265b8n777sp585m9xj",
  "slug": "skill-for-ragflow",
  "version": "3.0.0",
  "publishedAt": 1790303914249
}

references/AGENT_GUIDE.md

# RAGFlow Custom Agent Guide

Read this file only when you need to author, debug, or review a RAGFlow Agent/Canvas DSL. For CLI syntax, read [COMMANDS.md](COMMANDS.md). For SDK request and response shapes, read [API.md](API.md). For failures and recovery steps, read [TROUBLESHOOTING.md](TROUBLESHOOTING.md).

This guide distills the current RAGFlow v0.27.2 agent behavior into practical schema rules, minimal examples, and failure patterns you can use directly.

## Contents

- [Quick choice](#quick-choice)
- [Shortest path](#shortest-path)
- [Current schema checklist](#current-schema-checklist)
- [Components and graph must agree](#components-and-graph-must-agree)
- [Variable rules](#variable-rules)
- [Customize by node type](#customize-by-node-type)
- [Runtime conclusions](#runtime-conclusions)
- [Minimal example index](#minimal-example-index)
- [Common failures](#common-failures)

## Quick choice

| Goal | Read first | Start from |
|---|---|---|
| Build the smallest conversational agent | [Shortest path](#shortest-path) | `references/examples/agents/01-conversational-message.json` |
| Add knowledge-base retrieval | [Customize by node type](#customize-by-node-type) for `Retrieval` and `Agent` | `references/examples/agents/02-retrieval-message.json` or `03-tool-agent.json` |
| Build a tool-using LLM agent | [Customize by node type](#customize-by-node-type) for `Agent` | `references/examples/agents/03-tool-agent.json` |
| Build a loop or batch-processing agent | [Customize by node type](#customize-by-node-type) for `Iteration / IterationItem` | `references/examples/agents/04-iteration-agent.json` |
| Build a webhook agent | [Customize by node type](#customize-by-node-type) for `Webhook` | `references/examples/agents/05-webhook-message.json` |
| Debug `KeyError('path')`, broken variable resolution, or skipped nodes | [Current schema checklist](#current-schema-checklist) and [Common failures](#common-failures) | Compare against your DSL |

## Shortest path

Do not start from an empty JSON object.

1. Pick the closest file from `references/examples/agents/`.
2. Replace only deployment-specific values such as `llm_id`, `kb_ids`, tool credentials, and prompt text.
3. Keep the current runtime fields intact: `history`, `path`, `retrieval`, `variables`, `globals`, and `graph`.
4. Create the agent, look it up by title, create a session, and send a question.

```bash
node {baseDir}/scripts/ragflow.js create-agent \
  --title "My Agent" \
  --dsl @references/examples/agents/01-conversational-message.json \
  --json

node {baseDir}/scripts/ragflow.js list-agents --name "My Agent" --json
node {baseDir}/scripts/ragflow.js create-agent-session --agent <agent_id> --json
node {baseDir}/scripts/ragflow.js agent-chat --agent <agent_id> --session <session_id> --question "Hello" --json
```

`create-agent` currently returns `true` on success, not the new agent id.

## Current schema checklist

When you hand-author a DSL, keep this checklist:

- Top level includes `componen

references/API.md

# Programmatic API and Configuration

## Table of Contents

- [Setup](#setup)
- [Dataset](#dataset)
- [Document](#document)
- [Document Download](#document-download)
- [Parsing](#parsing)
- [Chunk](#chunk)
- [Retrieval](#retrieval)
- [Metadata](#metadata)
- [Connector](#connector)
- [RAPTOR](#raptor)
- [GraphRAG](#graphrag)
- [Chat Assistant](#chat-assistant)
- [Session](#session)
- [Chat Conversation](#chat-conversation)
- [Agent](#agent)
- [Agent Tags](#agent-tags)
- [Agent Session](#agent-session)
- [Agent Chat](#agent-chat)
- [Embedded Website Access](#embedded-website-access)
- [LLM Models](#llm-models)
- [System](#system)
- [Utility](#utility)
- [Configuration](#configuration)

## Setup

```javascript
const { createClient } = require("{baseDir}/lib/api.js");
const client = createClient();
```

`createClient()` reads `RAGFLOW_URL` and `RAGFLOW_API_KEY` from the environment and then fills missing values from the bundled `.env` file. Existing environment variables take precedence. See [Configuration](#configuration) below.

Destructive requests fail with `CONFIRMATION_REQUIRED` before network access by default. After verifying authorization and target scope, create a dedicated client with `const destructiveClient = createClient({ allowDestructive: true });` for deletion, metadata removal or unscoped metadata updates, and ingestion with `delete: true`. Use that client for the deletion examples below; ordinary clients remain suitable for reads and scoped updates.

## Dataset

```javascript
// List datasets (supports pagination: page, page_size, id, name)
const datasets = await client.listDatasets({ page: 1, page_size: 10 });

// Get a single dataset by ID (enriched with total_size and connectors)
const dataset = await client.getDataset("<dataset_id>");
// Returns: { id: "...", name: "...", total_size: 1024, connectors: [...], ... }

// Create a dataset
const dataset = await client.createDataset({
  name: "Tech Docs",
  chunk_method: "naive",
});

// Update a dataset
await client.updateDataset("<dataset_id>", { name: "New Name" });

// Delete datasets by IDs
await destructiveClient.deleteDatasets(["<id1>", "<id2>"]);
```

## Document

```javascript
// Upload documents
await client.uploadDocuments("<dataset_id>", ["./report.pdf", "./notes.txt"]);

// Override display names when paths are temporary/task IDs
await client.uploadDocuments("<dataset_id>", [
  { path: "./tmp/task-output", name: "report.pdf" },
]);

// List documents (supports page, page_size, id, name, orderby, desc, keywords, suffix, types, run, metadata, metadata_condition, return_empty_metadata)
const docs = await client.listDocuments("<dataset_id>");

// Get a single document by ID
const doc = await client.getDocument("<dataset_id>", "<doc_id>");

// Update a document
await client.updateDocument("<dataset_id>", "<doc_id>", {
  name: "Renamed",
  parser_config: { pages: [[1, 2]] },
  chunk_method: "knowledge_graph",
  enabled: 1,
  meta_fields: { author: "Alice" },
});

// Delete doc

references/COMMANDS.md

# Command Reference

Deletion commands, metadata removal or unscoped metadata updates, and ingestion with `--delete` require `--confirm-destructive` after the target operation is authorized. Missing or false confirmation fails before the destructive HTTP request. Ordinary reads and stopping parsing do not require it.

Practical CLI reference for `scripts/ragflow.js`, organized around common RAGFlow workflows. It intentionally prioritizes daily operations over exhaustive REST API coverage.

Use `--json` on any command to suppress status text and print only machine-readable JSON.
JSON-valued options such as `--parser-config`, `--prompt-config`, and `--dsl` accept either inline JSON or `@path/to/file.json`.

On command failure with `--json`, the CLI exits non-zero and prints a structured error envelope:

```json
{
  "error": {
    "message": "API Error: Unauthorized",
    "raw_message": "Unauthorized",
    "code": 401,
    "status": 401,
    "command": "list-models"
  }
}
```

## Table of Contents

- [Scenario Map](#scenario-map)
- [Knowledge Base Setup](#knowledge-base-setup)
- [Document Ingestion](#document-ingestion)
- [Parsing and Chunking](#parsing-and-chunking)
- [Information Retrieval](#information-retrieval)
- [RAG Assistant Operation](#rag-assistant-operation)
- [Agent Operation](#agent-operation)
- [Embedded Website Access](#embedded-website-access)
- [Discovery and Configuration](#discovery-and-configuration)
- [System Operations](#system-operations)

## Scenario Map

| Scenario | Use it for |
|---|---|
| [Knowledge Base Setup](#knowledge-base-setup) | Create and maintain datasets before ingesting files |
| [Document Ingestion](#document-ingestion) | Upload, inspect, update, and remove source documents |
| [Parsing and Chunking](#parsing-and-chunking) | Turn documents into searchable chunks and manage chunk content |
| [Information Retrieval](#information-retrieval) | Query datasets directly without creating a chat assistant |
| [RAG Assistant Operation](#rag-assistant-operation) | Create chat assistants, manage sessions, and run Q&A |
| [Agent Operation](#agent-operation) | Create tool-capable agents, manage sessions, and run agent chat |
| [Embedded Website Access](#embedded-website-access) | Generate iframe/widget code and call shared chatbots/agentbots |
| [Discovery and Configuration](#discovery-and-configuration) | Inspect available LLM models, and manage model providers/instances (v0.27.2) |
| [System Operations](#system-operations) | Check health/version and inspect log-level settings |

## Knowledge Base Setup

Use this section when the user is creating or maintaining the dataset container that everything else depends on.

```bash
node {baseDir}/scripts/ragflow.js create-dataset --name "Tech Docs" --chunk-method naive
node {baseDir}/scripts/ragflow.js create-dataset --name "Tech Docs" --embedding-model "text-embedding-v4@Tongyi-Qianwen"
node {baseDir}/scripts/ragflow.js list-datasets
node {baseDir}/scripts/ragflow.js get-dataset

Github ReposUpdated 6mo agoRank 70

activepieces

AI Agents & MCPs & AI Workflow Automation • (~400 MCP servers for AI agents) • AI Automation / AI Agent with MCPs • AI Workflows & AI Agents • MCPs for AI Agents

OPENCLAW

Github ReposUpdated 6mo agoRank 70

cherry-studio

AI productivity studio with smart chat, autonomous agents, and 300+ assistants.

MCPOPENCLAW

Github ReposUpdated 6mo agoRank 70

AionUi

Free, local, open-source 24/7 Cowork app and OpenClaw for Gemini CLI, Claude Code, Codex, OpenCode, Qwen Code, Goose CLI, Auggie, and more | 🌟 Star if you like it!

MCPOPENCLAW

Github ReposUpdated 7mo agoRank 70

CopilotKit

The Frontend for Agents & Generative UI. React + Angular

OPENCLAW

Machine-readable data

The same record, as JSON, for agents and crawlers.

{
  "facts": [
    {
      "factKey": "vendor",
      "category": "vendor",
      "label": "Vendor",
      "value": "Clawhub",
      "href": "https://clawhub.ai/lunarcache/skills/skill-for-ragflow",
      "sourceUrl": "https://clawhub.ai/lunarcache/skills/skill-for-ragflow",
      "sourceType": "profile",
      "confidence": "medium",
      "observedAt": "2026-10-09T17:08:31.525Z",
      "isPublic": true
    },
    {
      "factKey": "protocols",
      "category": "compatibility",
      "label": "Protocol compatibility",
      "value": "OpenClaw",
      "href": "https://www.xpersona.co/api/v1/agents/clawhub-lunarcache-skill-for-ragflow/contract",
      "sourceUrl": "https://www.xpersona.co/api/v1/agents/clawhub-lunarcache-skill-for-ragflow/contract",
      "sourceType": "contract",
      "confidence": "medium",
      "observedAt": "2026-10-09T17:08:31.525Z",
      "isPublic": true
    },
    {
      "factKey": "traction",
      "category": "adoption",
      "label": "Adoption signal",
      "value": "2.2K downloads",
      "href": "https://clawhub.ai/lunarcache/skill-for-ragflow",
      "sourceUrl": "https://clawhub.ai/lunarcache/skill-for-ragflow",
      "sourceType": "profile",
      "confidence": "medium",
      "observedAt": "2026-10-09T17:08:31.525Z",
      "isPublic": true
    },
    {
      "factKey": "latest_release",
      "category": "release",
      "label": "Latest release",
      "value": "3.0.0",
      "href": "https://clawhub.ai/lunarcache/skill-for-ragflow",
      "sourceUrl": "https://clawhub.ai/lunarcache/skill-for-ragflow",
      "sourceType": "release",
      "confidence": "medium",
      "observedAt": "2026-09-25T02:38:34.249Z",
      "isPublic": true
    },
    {
      "factKey": "handshake_status",
      "category": "security",
      "label": "Handshake status",
      "value": "UNKNOWN",
      "href": "https://www.xpersona.co/api/v1/agents/clawhub-lunarcache-skill-for-ragflow/trust",
      "sourceUrl": "https://www.xpersona.co/api/v1/agents/clawhub-lunarcache-skill-for-ragflow/trust",
      "sourceType": "trust",
      "confidence": "medium",
      "observedAt": null,
      "isPublic": true
    }
  ],
  "events": [
    {
      "eventType": "release",
      "title": "Release 3.0.0",
      "description": "Require explicit authorization flags for destructive requests; harden embedded HTML and widget messages; validate multipart upload names. RAGFlow v0.27.2 APIs only.",
      "href": "https://clawhub.ai/lunarcache/skill-for-ragflow",
      "sourceUrl": "https://clawhub.ai/lunarcache/skill-for-ragflow",
      "sourceType": "release",
      "confidence": "medium",
      "observedAt": "2026-09-25T02:38:34.249Z",
      "isPublic": true
    }
  ]
}

Record generated Oct 9, 2026.

About

Avoid when

Public facts

Install and run

Documentation

Extracted files

SKILL.md

_meta.json

references/AGENT_GUIDE.md

references/API.md

references/COMMANDS.md

Related agents

activepieces

cherry-studio

AionUi

CopilotKit

Machine-readable data