← Back to Skills Marketplace
71
Downloads
0
Stars
0
Active Installs
1
Versions
Install in OpenClaw
/install ragflow-skill-python0418
Description
Use for RAGFlow dataset tasks: create, list, inspect, update, or delete datasets; upload, list, update, or delete documents; start or stop parsing; check par...
Usage Guidance
This skill appears to do what it claims. Before installing:
- Only set RAGFLOW_API_URL to a trusted RAGFlow server; the provided RAGFLOW_API_KEY will be sent as a Bearer token to that URL. Treat that key as sensitive.
- Prefer creating a scoped API key with least privilege (e.g., read-only for listing/search, restricted for delete/upload) rather than using a highly privileged account.
- The SKILL.md requires explicit user confirmation before deletes, but the delete scripts only accept --ids (no interactive prompt). Ensure your agent enforces confirmation before invoking delete commands.
- Review any included agent config (e.g., agents/openai.yaml) before use to confirm no unexpected autonomous workflows are configured.
- If you need higher assurance, run the bundled scripts manually in a controlled environment first to observe their behavior and ensure the API URL is correct.
Capability Analysis
Type: OpenClaw Skill
Name: ragflow-skill-python0418
Version: 1.0.0
The skill bundle is a well-structured integration for the RAGFlow API, providing scripts for dataset management, document uploading, parsing, and retrieval. The Python scripts (e.g., `datasets.py`, `upload.py`, `search.py`) use standard libraries like `urllib` for API communication and follow secure practices by handling credentials via environment variables. The `SKILL.md` file includes proactive security guardrails, such as requiring explicit user confirmation before any deletion operations and forbidding the fabrication of API responses.
Capability Tags
Capability Assessment
Purpose & Capability
The skill name/description (RAGFlow dataset tasks) matches the bundled Python scripts and the two environment variables (RAGFLOW_API_URL, RAGFLOW_API_KEY). The required binary (python3) is appropriate. All scripts make HTTP calls to the provided base URL and require the RAGFlow API key for Authorization, which is expected for this purpose.
Instruction Scope
SKILL.md restricts the agent to use the bundled scripts in scripts/ and documents expected CLI commands and guardrails (e.g., require explicit confirmation before deletes). The scripts themselves require explicit IDs for delete operations but do not perform interactive confirmation; the SKILL.md relies on the agent to enforce interactive confirmation. This is a design/operational note (agent must follow the guardrail) rather than evidence of malicious behavior.
Install Mechanism
No install spec is provided (instruction-only / scripts bundled with the skill). There are no downloads or archive extracts. Risk from installation is minimal.
Credentials
Only RAGFLOW_API_URL and RAGFLOW_API_KEY are required; the primaryEnv is RAGFLOW_API_KEY. These variables are necessary and proportionate for an HTTP client interacting with a RAGFlow API. The code does not request unrelated secrets or filesystem config paths.
Persistence & Privilege
The skill is not always-enabled and does not request elevated platform privileges. It does not modify other skills or system-wide agent settings. Autonomous invocation is allowed (platform default) but is not combined with other privilege escalations here.
How to Use
- Make sure OpenClaw is installed (local or Docker)
- Run the install command in chat:
/install ragflow-skill-python0418 - After installation, invoke the skill by name or use
/ragflow-skill-python0418 - Provide required inputs per the skill's parameter spec and get structured output
Version History
v1.0.0
Initial release of ragflow-dataset-ingest skill:
- Enables creation, listing, inspection, updating, and deletion of RAGFlow datasets.
- Supports uploading, listing, updating, and deleting documents within datasets.
- Provides commands for parsing management: start, stop, and check parse progress or status.
- Allows chunk retrieval from datasets and listing of configured RAGFlow models.
- Includes guardrails for safe deletion and parsing operations, with strict adherence to IDs and output fields.
- Enforces output formatting and error handling as per reference guidelines.
Metadata
Frequently Asked Questions
What is ragflow-skill-python0418?
Use for RAGFlow dataset tasks: create, list, inspect, update, or delete datasets; upload, list, update, or delete documents; start or stop parsing; check par... It is an AI Agent Skill for Claude Code / OpenClaw, with 71 downloads so far.
How do I install ragflow-skill-python0418?
Run "/install ragflow-skill-python0418" in the OpenClaw or Claude Code chat to install it in one step — no extra setup required.
Is ragflow-skill-python0418 free?
Yes, ragflow-skill-python0418 is completely free, licensed under MIT-0. You can download, install and use it at no cost.
Which platforms does ragflow-skill-python0418 support?
ragflow-skill-python0418 is cross-platform and runs anywhere OpenClaw / Claude Code is available (cross-platform).
Who created ragflow-skill-python0418?
It is built and maintained by chang (@liberalchang); the current version is v1.0.0.
More Skills