Token导航 LogoToken导航TokenDH.com
研究检索external-serviceclawhub未标认证来源可访问clear审计提醒

blog-generator博客生成器

Agent Skill

blog-generator 用于查找、检索和筛选相关信息,适合在 OpenClaw 中需要根据关键词、任务场景或来源线索快速定位候选结果时使用。可结合来源仓库、安装命令和原始 README 继续核验具体用法。安装前建议确认权限范围、维护状态,以及是否会触发联网、命令执行或文件读写。

总安装

15,515

周安装

653

GitHub Stars

公开资料未说明

下载量

5,433
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:blog-generator(博客生成器)
来源仓库:https://github.com/austindixson/blog-generator
安装命令:
openclaw skills install blog-generator
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 blog-generator

简介

分析日记条目和聊天历史记录,识别高价值主题并自动生成博客文章。

  • 适用于 OpenClaw 中内容创作与知识沉淀类任务。
  • 通过 openclaw skills install blog-generator 安装使用。
  • 依赖用户输入的历史数据质量,建议人工校验生成内容的准确性。
  • 适用宿主包括 OpenClaw,接入前应确认版本、权限和运行环境要求。

SKILL.md

name
blog-generator
displayName
Blog Generator | OpenClaw Skill
description
Analyzes journal entries and chat history to identify high-value topics and automatically generate blog posts.
version
1.0.0

Blog Generator | OpenClaw Skill

Description

Analyzes journal entries and chat history to identify high-value topics and automatically generate blog posts.

Blog Generator | OpenClaw Skill

Automatically generates blog posts by analyzing journal entries, chat history, and recent activity to identify high-value, high-search-volume topics related to OpenClaw.

Usage

  • As a scheduled cron job to automatically generate blog content weekly or daily
  • Manually to create blog posts from recent journal analysis
  • To identify and document high-value solutions and discoveries
# X-format articles as HTML; humanizer runs between generations; header from visual-explainer
python3 /Users/ghost/.openclaw/workspace/skills/blog-generator/scripts/blog_generator.py

# Skip humanizer (e.g. no OPENROUTER_API_KEY)
python3 /Users/ghost/.openclaw/workspace/skills/blog-generator/scripts/blog_generator.py --no-humanize

# Custom humanizer or visual-explainer paths
python3 /Users/ghost/.openclaw/workspace/skills/blog-generator/scripts/blog_generator.py --humanizer-path /Users/ghost/Downloads/humanizer-1.0.0 --visual-explainer-path /Users/ghost/.openclaw/workspace/skills/visual-explainer-main

# Classic format (overview/problem/solution), still HTML
python3 /Users/ghost/.openclaw/workspace/skills/blog-generator/scripts/blog_generator.py --format classic

# JSON output
python3 /Users/ghost/.openclaw/workspace/skills/blog-generator/scripts/blog_generator.py --days 14 --max-topics 5 --json

What this skill does

  • Scans journal entries from the last N days for interesting topics (discoveries, obstacles, solutions)
  • Identifies high-value topics based on keyword relevance and problem-solving value
  • Researches search volume and keyword opportunities (heuristic-based, can be enhanced with APIs)
  • Generates structured blog posts with overview, problem, solution, and takeaways sections
  • Saves blog posts to /Users/ghost/.openclaw/blogs/ as HTML only (X-article format, header from visual-explainer, humanizer between generations)

Integration as a Cron Job

This skill is designed to run periodically (daily or weekly) via OpenClaw cron to automatically generate blog content.

Example Cron Job Configuration (Daily):

{
  "payload": {
    "kind": "agentTurn",
    "message": "Run blog-generator skill to analyze journal entries and generate high-value blog posts.",
    "model": "openrouter/google/gemini-2.5-flash",
    "thinking": "low",
    "timeoutSeconds": 300
  },
  "schedule": {
    "kind": "cron",
    "cron": "0 9 * * *"
  },
  "delivery": {
    "mode": "announce"
  },
  "sessionTarget": "isolated",
  "name": "Blog Post Generator"
}

Example Cron Job Configuration (Weekly):

{
  "payload": {
    "kind": "agentTurn",
    "message": "Run blog-generator skill with --days 7 --max-topics 3 to generate weekly blog posts from journal analysis.",
    "model": "openrouter/google/gemini-2.5-flash",
    "thinking": "low",
    "timeoutSeconds": 300
  },
  "schedule": {
    "kind": "cron",
    "cron": "0 10 * * 1"
  },
  "delivery": {
    "mode": "announce"
  },
  "sessionTarget": "isolated",
  "name": "Weekly Blog Generator"
}

Output Format

HTML only (no Markdown). Output is in the format accepted by X articles: one header (from visual-explainer), then article body with no interlaced visuals.

  • File: /Users/ghost/.openclaw/blogs/YYYYMMDD_slugified-title.html
  • Article structure: X-style (long-form): punchy hook, short paragraphs, "two types of people" framing, pivot, stakes. Use --format classic for overview/problem/solution.
  • Header: From visual-explainer only. Default path: /Users/ghost/.openclaw/workspace/skills/visual-explainer-main. The skill’s scripts/generate_header.py is called with section: "header" and returns an html_snippet (hero with title and optional summary). No diagrams or images in the body.
  • Humanizer: Runs between generations by default. Each article’s body is sent through /Users/ghost/Downloads/humanizer-1.0.0 (requires OPENROUTER_API_KEY) before rendering to HTML. Use --no-humanize to skip.

Topic Scoring

Topics are scored based on:

  • High-value keywords: OpenClaw-specific terms, problem-solving language
  • Content type: Solutions score highest, then obstacles, then discoveries
  • Content depth: Longer, more detailed content scores higher
  • Search volume indicators: Keywords like "how to", "tutorial", "fix" increase value

Requirements

  • Journal entries in /Users/ghost/.openclaw/journal/
  • Blogs directory writable at /Users/ghost/.openclaw/blogs/
  • Chat history analyzer skill (for journal entries)

How it works

  1. Scans journal directory for markdown files from the last N days
  2. Extracts topics from discoveries, obstacles, and solutions sections
  3. Scores topics based on keyword relevance and value
  4. Selects top N high-value topics
  5. Generates structured blog posts with problem/solution format
  6. Saves posts to blogs directory with timestamped filenames

Enhancement Opportunities

  • Integrate with Google Keyword Planner API for real search volume data
  • Use AI model to enhance blog post quality and SEO optimization
  • Cross-reference with existing blog posts to avoid duplicates
  • Generate multiple variations of posts for A/B testing

适合场景

01

调用多模型

02

代码和文本生成

03

Agent 推理流程

04

OpenRouter 模型接入

能力概览

能力 1

统一调用多种 LLM

能力 2

支持 Claude、Gemini、Kimi 等模型

能力 3

适合聊天、代码和推理任务

能力 4

可作为 Agent 模型调用入口

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

89.05%
按下载量换算4,838

安全审计

VirusTotal

可疑

ClawScan

可疑

Static analysis

未展示

权限和风险

external-service

该 Skill 可能调用第三方服务、云服务或外部模型 API,使用前需要确认账号、额度、数据发送范围和服务条款。

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。来源安全扫描存在 warning/failed 结果,不能写成本站确认安全。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