← Back to Skills Marketplace
Jina Reader
by
Eric Santos
· GitHub ↗
· v0.0.2
· MIT-0
10349
Downloads
5
Stars
0
Active Installs
4
Versions
Install in OpenClaw
/install jina-reader
Description
Web content extraction via Jina AI Reader API. Three modes: read (URL to markdown), search (web search + full content), ground (fact-checking). Extracts clea...
Usage Guidance
Install only if you are comfortable sending requested URLs, search queries, CSS selectors, and fact-check text to Jina AI. Avoid private intranet links, secrets, credentials, personal data, regulated data, or confidential business material unless that third-party processing is approved.
Capability Assessment
Purpose & Capability
The documented purpose is web reading, search, and fact-checking through Jina AI, and the script only calls the corresponding Jina endpoints for those modes.
Instruction Scope
The docs identify Jina AI Reader API usage, but they could more prominently warn that submitted URLs, queries, CSS selectors, and statements leave the local environment.
Install Mechanism
The artifact contains a SKILL.md and one shell script using curl and jq; no install hooks, package installation, obfuscation, or hidden setup behavior were found.
Credentials
Network access and optional JINA_API_KEY use are proportionate for this API integration, but users should treat submitted inputs as third-party processed data.
Persistence & Privilege
No background workers, persistence, privilege escalation, destructive actions, or broad local file access were found; the only local credential read is JINA_API_KEY or ~/.config/jina/api_key for bearer authentication.
How to Use
- Make sure OpenClaw is installed (local or Docker)
- Run the install command in chat:
/install jina-reader - After installation, invoke the skill by name or use
/jina-reader - Provide required inputs per the skill's parameter spec and get structured output
Version History
v0.0.2
API key now resolves from $JINA_API_KEY env or ~/.config/jina/api_key file (canonical local path)
v0.0.1
Initial release.
- Web content extraction via Jina AI Reader API with three modes: read, search, and ground.
- Supports clean content extraction to markdown, HTML, text, or screenshot.
- Allows region-specific extraction, removal, and waiting with CSS selectors.
- Enables web search with full content and fact-checking from the command line.
- Protects server IP and supports geo-proxying.
- Free tier API key with 10M tokens (no signup required).
v1.1.0
Web content extraction via Jina AI: read, search, ground modes
v1.0.0
Initial release: 3 modes (read, search, ground), CSS selectors, geo-proxy, cache control
Metadata
Frequently Asked Questions
What is Jina Reader?
Web content extraction via Jina AI Reader API. Three modes: read (URL to markdown), search (web search + full content), ground (fact-checking). Extracts clea... It is an AI Agent Skill for Claude Code / OpenClaw, with 10349 downloads so far.
How do I install Jina Reader?
Run "/install jina-reader" in the OpenClaw or Claude Code chat to install it in one step — no extra setup required.
Is Jina Reader free?
Yes, Jina Reader is completely free, licensed under MIT-0. You can download, install and use it at no cost.
Which platforms does Jina Reader support?
Jina Reader is cross-platform and runs anywhere OpenClaw / Claude Code is available (cross-platform).
Who created Jina Reader?
It is built and maintained by Eric Santos (@ericsantos); the current version is v0.0.2.
More Skills