RAGFlow Skill

Operate RAGFlow v0.25.x deployments through the bundled Node CLI and API client. Use when user needs to manage RAGFlow datasets, documents, uploads, parsing,...

This skill appears to do what it claims: a local Node CLI and API client for a RAGFlow server. Before installing: (1) ensure RAGFLOW_URL points to a server you trust and that the RAGFLOW_API_KEY has only the permissions you intend (it can create/delete datasets, documents, sessions, tokens); (2) be cautious when asking the agent to run upload commands — the CLI will read and send any local file path you provide, which can leak secrets if misused; (3) destructive commands (delete-*) are irreversible on the server — follow the skill's confirmation guidance and consider using a throwaway dataset when testing; (4) if you enable autonomous agent invocation for this skill, understand that the agent could call the CLI to modify the remote server (create/delete/upload) — limit autonomy or scope of the API key if needed. Overall the bundle is internally consistent with its stated purpose.

Type: OpenClaw Skill Name: skill-for-ragflow Version: 1.2.0 The skill bundle is a legitimate and well-structured toolset for managing RAGFlow v0.25.x deployments. It provides a Node.js CLI (scripts/ragflow.js) and API client (lib/api.js) to perform CRUD operations on datasets, documents, and agents. While the skill possesses high-risk capabilities such as reading local files for upload and managing sensitive API/beta tokens, these behaviors are explicitly aligned with its stated purpose. Notably, SKILL.md contains defensive instructions directing the AI agent to redact sensitive authentication material from user-facing responses. The inclusion of a diagnostic script (scripts/repro-delete-chunks.js) to troubleshoot server-side race conditions further indicates a focus on operational reliability rather than malice.