ASP源码
PHP源码
.NET源码
JSP源码
Miniflux News 技能通过 Openclaw Skills 将您的个人 RSS 聚合器直接集成到 AI 工作流中。它允许您查询 Miniflux 实例中的未读条目,检索文章全文,并在不离开智能体环境的情况下进行智能分选。通过利用 Miniflux REST API,该技能在您精心策划的新闻源与 AI 驱动的内容分析之间架起了一座无缝桥梁,使其成为 Openclaw Skills 集合中不可或缺的一部分。
下载入口:https://github.com/openclaw/skills/tree/main/skills/hartlco/miniflux-news
从源直接安装技能的最快方式。
npx clawhub@latest install miniflux-news
将技能文件夹复制到以下位置之一
全局模式~/.openclaw/skills/
工作区
/skills/
优先级:工作区 > 本地 > 内置
将此提示词复制到 OpenClaw 即可自动安装。
请帮我使用 Clawhub 安装 miniflux-news。如果尚未安装 Clawhub,请先安装(npm i -g clawhub)。
要在您的 Openclaw Skills 环境中开始使用此技能,请配置您的凭据:
~/.config/clawdbot/miniflux-news.json 创建配置文件:{
"url": "https://your-miniflux.example",
"token": "your-api-token"
}
python3 skills/miniflux-news/scripts/miniflux.py configure --url "https://your-miniflux.example" --token "your-api-token"
export MINIFLUX_URL="https://your-miniflux.example"
export MINIFLUX_TOKEN="your-api-token"
Miniflux News 技能通过 Openclaw Skills 中的以下结构管理数据:
| 数据组件 | 描述 |
|---|---|
| 配置文件 | 在 ~/.config/clawdbot/miniflux-news.json 存储 url 和 token。 |
| 条目元数据 | 包括用于列表显示的 id、title、url 和 feed_title。 |
| 内容负载 | 获取全文 content 或 snippet 用于摘要任务。 |
| 类别 | 检索类别名称和 ID 列表,用于定向过滤。 |
name: miniflux-news
description: Fetch and triage the latest unread RSS/news entries from a Miniflux instance via its REST API using an API token. Use when the user asks to get the latest Miniflux unread items, list recent entries with titles/links, or generate short summaries of specific Miniflux entries. Includes a bundled script to query Miniflux (/v1/entries and /v1/entries/{id}) using credentials from ~/.config/clawdbot/miniflux-news.json (or MINIFLUX_URL and MINIFLUX_TOKEN overrides).
Use the bundled script to fetch entries, then format a clean list and optionally write summaries.
This skill reads Miniflux credentials from a local config file by default.
Path:
~/.config/clawdbot/miniflux-news.jsonFormat:
{
"url": "https://your-miniflux.example",
"token": ""
}
Create/update it using the script:
python3 skills/miniflux-news/scripts/miniflux.py configure r
--url "https://your-miniflux.example" r
--token ""
You can override the config file (useful for CI):
export MINIFLUX_URL="https://your-miniflux.example"
export MINIFLUX_TOKEN=""
Token scope: Miniflux API token with read access.
List latest unread items (default):
python3 skills/miniflux-news/scripts/miniflux.py entries --limit 20
Filter by category (by name):
python3 skills/miniflux-news/scripts/miniflux.py entries --category "News" --limit 20
If you need machine-readable output:
python3 skills/miniflux-news/scripts/miniflux.py entries --limit 50 --json
Show the full article content stored in Miniflux (useful for reading or for better summaries):
python3 skills/miniflux-news/scripts/miniflux.py entry 123 --full --format text
If you want the raw HTML as stored by Miniflux:
python3 skills/miniflux-news/scripts/miniflux.py entry 123 --full --format html
List categories:
python3 skills/miniflux-news/scripts/miniflux.py categories
This skill must never mark anything as read implicitly. Only do it when the user explicitly asks to mark specific ids as read.
Mark specific ids as read:
python3 skills/miniflux-news/scripts/miniflux.py mark-read 123 124 --confirm
Mark all unread entries in a category as read (still explicit, requires --confirm; includes a safety --limit):
python3 skills/miniflux-news/scripts/miniflux.py mark-read-category "News" --confirm --limit 500
Fetch full content for a specific entry id (machine-readable):
python3 skills/miniflux-news/scripts/miniflux.py entry 123 --json
Summarization rules:
MINIFLUX_URL/MINIFLUX_TOKEN or create ~/.config/clawdbot/miniflux-news.json.