Agent Skills › viralcode/openwhale › miniflux-news

miniflux-news

GitHub

通过 Miniflux API 获取、筛选和摘要未读 RSS 新闻条目。支持配置凭证、列出最新条目、查看全文、分类管理及显式标记已读，并提供结构化摘要生成能力。

skills/miniflux-news/SKILL.md viralcode/openwhale

Trigger Scenarios

用户请求获取最新的 Miniflux 未读项用户要求列出带有标题和链接的近期条目用户需要生成特定 Miniflux 条目的简短摘要

Install

npx skills add viralcode/openwhale --skill miniflux-news -g -y

More Options

Use without installing

npx skills use viralcode/openwhale@miniflux-news

指定 Agent (Claude Code)

npx skills add viralcode/openwhale --skill miniflux-news -a claude-code -g -y

安装 repo 全部 skill

npx skills add viralcode/openwhale --all -g -y

预览 repo 内 skill

npx skills add viralcode/openwhale --list

SKILL.md

Frontmatter

{
    "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)."
}

Miniflux News

Use the bundled script to fetch entries, then format a clean list and optionally write summaries.

Setup (credentials)

This skill reads Miniflux credentials from a local config file by default.

Config file (recommended)

Path:

~/.config/clawdbot/miniflux-news.json

Format:

{
  "url": "https://your-miniflux.example",
  "token": "<api-token>"
}

Create/update it using the script:

python3 skills/miniflux-news/scripts/miniflux.py configure \
  --url "https://your-miniflux.example" \
  --token "<api-token>"

Environment variables (override)

You can override the config file (useful for CI):

export MINIFLUX_URL="https://your-miniflux.example"
export MINIFLUX_TOKEN="<api-token>"

Token scope: Miniflux API token with read access.

Fetch latest entries

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

Response formatting

Return a tight bullet list: [id] title — feed + link.
Ask how many the user wants summarized (e.g., “summarize 3” or “summarize ids 123,124”).

View full content

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

Mark entries as read (explicit only)

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

Summarize entries

Fetch full content for a specific entry id (machine-readable):

python3 skills/miniflux-news/scripts/miniflux.py entry 123 --json

Summarization rules:

Prefer 3–6 bullets max.
Lead with the “so what” in 1 sentence.
If content is empty or truncated, say so and summarize from title + available snippet.
Don’t invent facts; quote key numbers/names if present.

Troubleshooting

If the script says missing credentials: set MINIFLUX_URL/MINIFLUX_TOKEN or create ~/.config/clawdbot/miniflux-news.json.
If you get HTTP 401: token is wrong/expired.
If you get HTTP 404: base URL is wrong (should be the Miniflux web root).