Token导航 LogoToken导航TokenDH.com
图像处理敏感数据clawhub未标认证来源可访问clear审计通过

openclaw-minifluxOpenClaw miniflux 图像

Agent Skill

用于辅助图像生成、图片编辑、视觉素材处理或图像模型工作流。它适合让 Agent 根据文本生成图片、处理背景、整理视觉提示词或调用相关图像工具。使用时需要确认输入图片、版权来源、输出格式和模型限制;涉及人物、品牌、商品或公开展示素材时,应额外核对授权、真实性和内容合规边界。

总安装

13,596

周安装

550

GitHub Stars

公开资料未说明

下载量

4,268
OpenClaw

安装说明

本站只整理中文说明和来源信息,不托管安装包,也不代用户安装。

GitHub

来源数

2

许可证

MIT-0

最后核验

2026-05-01

来源状态

来源可访问

安装方式

通过对话安装

复制提示词发给支持本地命令或 Skills 的 AI 助手,先确认命令和权限,再让它执行。

请帮我安装这个 Agent Skill:openclaw-miniflux(OpenClaw miniflux 图像)
来源仓库:https://github.com/sinhong2011/openclaw-miniflux
安装命令:
openclaw skills install openclaw-miniflux
安装前请先检查当前环境是否支持对应 CLI,并向我确认将要执行的命令、安装目录、联网范围和文件读写权限;确认后再执行。

命令行安装

复制命令到本机终端执行。该命令会通过 OpenClaw 从第三方来源获取 Skill;本站只展示命令,不托管安装包,也不自动执行。

ClawHubOpenClaw
openclaw skills install openclaw-miniflux

简介

openclaw-miniflux 管理 Miniflux RSS 源与文章条目,支持未读统计与分类重命名。

  • 适合在 OpenClaw 中处理新闻聚合与信息筛选任务。
  • 通过 clawhub 安装,使用 openclaw skills install 命令,依赖 Miniflux 实例连接。
  • 安装前需确认 Miniflux API 地址与认证凭据正确配置。
  • 可处理订阅、取消订阅与类别管理,提升信息获取效率。

SKILL.md

name
miniflux
description
>

Miniflux

What it does

Provides access to a Miniflux RSS reader instance through 13 read tools and 10 write tools. Agents can browse feeds, search entries by status or date, read specific articles, check categories, and (if not in read-only mode) create/update/delete feeds and categories, import OPML, mark entries as read, and toggle bookmarks.

Inputs needed

  • For listing entries: status, date range, starred, pagination (all optional)
  • For feed-specific queries: feed ID
  • For single items: entry ID, feed ID, or user ID
  • For discovery: a URL to scan for feeds
  • For creating categories: a title
  • For updating categories: category ID and new title
  • For deleting categories: category ID
  • For subscribing to feeds: a feed URL and category ID
  • For updating feeds: feed ID, plus optional title, category_id, feed_url, site_url, user_agent
  • For deleting feeds: feed ID
  • For OPML import: an OPML XML string
  • For writes: entry IDs + status, or entry ID for bookmark toggle

Prerequisites

openclaw-miniflux-mcp binary

Download the latest binary for your platform from GitHub Releases:

PlatformBinary
Linux x86_64openclaw-miniflux-mcp-x86_64-unknown-linux-gnu
Linux ARM64openclaw-miniflux-mcp-aarch64-unknown-linux-gnu
macOS x86_64openclaw-miniflux-mcp-x86_64-apple-darwin
macOS ARM64openclaw-miniflux-mcp-aarch64-apple-darwin

Or install via Cargo:

cargo install openclaw-miniflux-mcp

MCP server configuration

Add the MCP server to your client configuration:

With API token (recommended):

{
  "mcpServers": {
    "miniflux": {
      "command": "/path/to/openclaw-miniflux-mcp",
      "args": [],
      "env": {
        "MINIFLUX_URL": "http://localhost:8080",
        "MINIFLUX_API_TOKEN": "<your-api-token>"
      }
    }
  }
}

With username/password:

{
  "mcpServers": {
    "miniflux": {
      "command": "/path/to/openclaw-miniflux-mcp",
      "args": [],
      "env": {
        "MINIFLUX_URL": "http://localhost:8080",
        "MINIFLUX_USERNAME": "<username>",
        "MINIFLUX_PASSWORD": "<password>"
      }
    }
  }
}

Read-only mode (disables write tools):

{
  "mcpServers": {
    "miniflux": {
      "command": "/path/to/openclaw-miniflux-mcp",
      "args": ["--read-only"],
      "env": {
        "MINIFLUX_URL": "http://localhost:8080",
        "MINIFLUX_API_TOKEN": "<your-api-token>"
      }
    }
  }
}

The user will need to:

  1. Replace the binary path with wherever they downloaded/installed it
  2. Replace MINIFLUX_URL with their Miniflux instance URL
  3. Get an API token from Miniflux: Settings > API Keys > Create a new API key
  4. Restart their MCP client after saving

Workflow

Browsing feeds

  1. Call miniflux_get_feeds to see all subscriptions
  2. Call miniflux_get_feed_entries with a feed ID to see its entries
  3. Call miniflux_get_entry to read a specific article

Searching entries

Call miniflux_get_entries with filters:

  • status: "unread", "read", or "removed"
  • starred: true for bookmarked entries
  • after / before: Unix timestamps for date ranges
  • limit: Number of results (default varies, recommend 20)
  • order: "published_at" and direction: "desc" for newest first

Triaging unread articles

  1. Call miniflux_get_entries with status: "unread", limit: 20
  2. Read interesting entries with miniflux_get_entry
  3. Mark reviewed entries as read: miniflux_update_entry_status with status: "read"
  4. Bookmark important ones: miniflux_toggle_bookmark

Adding new feeds

  1. Call miniflux_discover_subscription with a website URL to find available feeds
  2. Present discovered feeds to the user
  3. If needed, call miniflux_create_category to create a new category
  4. Call miniflux_create_feed with the feed URL and category ID to subscribe

Managing feeds

  • Update: miniflux_update_feed with feed ID and any fields to change (title, category_id, feed_url, site_url, user_agent)
  • Delete: miniflux_delete_feed with feed ID to unsubscribe
  • Refresh: miniflux_refresh_feed with feed ID to fetch new entries now

Managing categories

  • List: miniflux_get_categories to see all categories
  • Create: miniflux_create_category with a title
  • Rename: miniflux_update_category with category ID and new title
  • Delete: miniflux_delete_category with category ID (feeds move to default category)

Importing/Exporting

  • Export: miniflux_export_opml to get all feeds as OPML XML
  • Import: miniflux_import_opml with an OPML XML string to bulk-add feeds

Guardrails

  • Default to small page sizes (limit=20) to avoid overwhelming responses
  • On 401/403 errors, tell the user to check their API token or credentials
  • On connection errors, tell the user to verify their MINIFLUX_URL
  • Confirm with the user before marking large batches of entries as read
  • In read-only mode, explain the limitation clearly when a write is attempted
  • When listing returns empty results, suggest checking filters or confirming the instance has data

适合场景

01

文本生成图片

02

图片风格化

03

产品图和创意图

04

需要 FLUX 模型时

能力概览

能力 1

调用 FLUX 图像模型

能力 2

支持文本生图和图像改写

能力 3

覆盖 LoRA 或风格适配

能力 4

适合创意视觉生成

安装后应在对应宿主中按原始 README 的触发条件使用;具体调用方式请以来源页面和 README 为准。

平台分布

OpenClaw

91.8%
按下载量换算3,918

安全审计

VirusTotal

通过

ClawScan

通过

Static analysis

未展示

权限和风险

敏感数据

该 Skill 可能接触密钥、Token、环境变量或敏感配置,应进入高风险复核队列,默认不自动发布。

安装前确认

本站仅展示第三方公开信息,不托管安装包,不提供自动安装或运行环境。安装前应自行审查源码、依赖和命令行为。当前只有一个来源,正式发布前建议补源仓库或其他目录站核验。

来源信息

继续浏览同类 Skills