miniflux
Browse, read, and manage Miniflux feed articles. Use when Claude needs to work with RSS/atom feeds via Miniflux - listing unread/new articles, reading article content, marking articles as read, and managing feeds/categories. Provides CLI access with flexible output formats (headlines, summaries, full content).
Why use this skill?
Efficiently browse, read, and manage your RSS/Atom feeds using the OpenClaw Miniflux skill. Automate your news consumption and article workflows with ease.
Install via CLI (Recommended)
clawhub install openclaw/skills/skills/shekohex/minifluxWhat This Skill Does
The Miniflux skill provides a powerful CLI-based interface for managing your RSS and Atom feeds directly through an AI agent. By connecting your instance of Miniflux, this skill enables automated reading, filtering, and organizing of web content. It supports listing articles by status (unread, read, starred), searching through your library, and managing article lifecycle states like 'mark as read' or 'mark as unread'. Whether you need a quick summary of your daily feeds or deep-dive access to long-form content with pagination, the Miniflux skill streamlines your information consumption pipeline.
Installation
To integrate this skill into your environment, use the OpenClaw hub CLI:
clawhub install openclaw/skills/skills/shekohex/miniflux
Once installed, ensure your credentials are set via environment variables (MINIFLUX_URL and MINIFLUX_API_KEY) for seamless agent authorization. The skill will automatically generate a config file at ~/.local/share/miniflux/config.json upon the first execution if standard credentials are provided via CLI flags.
Use Cases
- Automated Research: Have the agent scan tech blogs or news outlets for specific keywords and summarize relevant articles.
- Inbox Zero for Feeds: Use the agent to batch-process and mark large volumes of read articles in your feed reader.
- Content Curation: Quickly list and curate content to be starred or categorized based on your daily interests.
- Efficient Reading: Leverage the built-in pagination features to process long articles in manageable chunks without overwhelming the context window.
Example Prompts
- "Find all unread articles related to 'machine learning' in my feeds and give me a 500-character summary of each."
- "Check my current RSS feeds for new updates, list the top 5 most recent titles, and then mark them all as read."
- "Open the article with ID 842 and read the first 1000 characters so I can decide if it's worth saving to my reading list."
Tips & Limitations
- Pagination: Always use the
--offsetand--limitflags when dealing with massive articles to maintain agent context efficiency. - Output Formats: Utilize the
--jsonflag when piping output into other scripts or complex data processing workflows. - Performance: For large feeds, rely on the
--briefor--summaryflags initially to filter content before requesting full body text. - Environment: Ensure your Miniflux server is reachable from the machine where the OpenClaw agent is running, as this skill requires persistent network connectivity to the Miniflux API.
Metadata
Not sure this is the right skill?
Describe what you want to build — we'll match you to the best skill from 16,000+ options.
Find the right skillPaste this into your clawhub.json to enable this plugin.
{
"plugins": {
"official-shekohex-miniflux": {
"enabled": true,
"auto_update": true
}
}
}Tags(AI)
Flags: network-access, external-api