blog-to-kindle

Scrape blogs/essay sites and compile into Kindle-friendly EPUB with AI-generated cover. Use for requests to download blogs for Kindle, compile essays into ebook, or send blog archives to Kindle. Supports Paul Graham, Kevin Kelly, Derek Sivers, Wait But Why, Astral Codex Ten, and custom sites.

3,891 stars

Best use case

blog-to-kindle is best used when you need a repeatable AI agent workflow instead of a one-off prompt.

Scrape blogs/essay sites and compile into Kindle-friendly EPUB with AI-generated cover. Use for requests to download blogs for Kindle, compile essays into ebook, or send blog archives to Kindle. Supports Paul Graham, Kevin Kelly, Derek Sivers, Wait But Why, Astral Codex Ten, and custom sites.

Teams using blog-to-kindle should expect a more consistent output, faster repeated execution, less prompt rewriting.

When to use this skill

  • You want a reusable workflow that can be run more than once with consistent structure.

When not to use this skill

  • You only need a quick one-off answer and do not need a reusable workflow.
  • You cannot install or maintain the underlying files, dependencies, or repository context.

Installation

Claude Code / Cursor / Codex

$curl -o ~/.claude/skills/blog-to-kindle/SKILL.md --create-dirs "https://raw.githubusercontent.com/openclaw/skills/main/skills/ainekomacx/blog-to-kindle/SKILL.md"

Manual Installation

  1. Download SKILL.md from GitHub
  2. Place it in .claude/skills/blog-to-kindle/SKILL.md inside your project
  3. Restart your AI agent — it will auto-discover the skill

How blog-to-kindle Compares

Feature / Agentblog-to-kindleStandard Approach
Platform SupportNot specifiedLimited / Varies
Context Awareness High Baseline
Installation ComplexityUnknownN/A

Frequently Asked Questions

What does this skill do?

Scrape blogs/essay sites and compile into Kindle-friendly EPUB with AI-generated cover. Use for requests to download blogs for Kindle, compile essays into ebook, or send blog archives to Kindle. Supports Paul Graham, Kevin Kelly, Derek Sivers, Wait But Why, Astral Codex Ten, and custom sites.

Where can I find the source code?

You can find the source code on GitHub using the link provided at the top of the page.

Related Guides

SKILL.md Source

# Blog to Kindle

Scrape blog/essay sites, compile into EPUB with cover art, and deliver to Kindle.

## Quick Start

```bash
# 1. Fetch essays from a supported site
uv run scripts/fetch_blog.py --site paulgraham --output ./pg-essays

# 2. Generate cover (uses Nano Banana Pro)
# See nano-banana-pro skill for cover generation

# 3. Compile to EPUB with cover
uv run scripts/compile_epub.py --input ./pg-essays --cover ./cover.png --output essays.epub

# 4. Send to Kindle
uv run scripts/send_to_kindle.py --file essays.epub --kindle-email user@kindle.com
```

## Workflow (MUST follow this order)

1. **Fetch** - Download all essays/posts from the blog
2. **Generate Cover** - Create cover art via Nano Banana Pro skill (DO NOT SKIP)
3. **Compile** - Combine into EPUB with cover embedded
4. **Send** - Email to Kindle address

⚠️ **Always generate and include cover before sending.** Never send without cover.

## Supported Sites

| Site | Key | URL Pattern |
|------|-----|-------------|
| Paul Graham | `paulgraham` | paulgraham.com/articles.html |
| Kevin Kelly | `kevinkelly` | kk.org/thetechnium |
| Derek Sivers | `sivers` | sive.rs/blog |
| Wait But Why | `waitbutwhy` | waitbutwhy.com/archive |
| Astral Codex Ten | `acx` | astralcodexten.com |

For unlisted sites, use `--site custom --url <archive-url>`.

## Cover Generation

Use the `nano-banana-pro` skill to generate covers. Prompt template:

```
Book cover for '[Author Name]: [Subtitle]'. 
Minimalist design with elegant typography. 
[Brand color] accent. Clean white/cream background. 
Simple geometric or abstract motif related to [topic].
Professional literary feel. No photos, no faces.
Portrait orientation book cover dimensions.
```

Generate at 2K resolution for good quality without huge file size.

## Kindle Delivery

Default Kindle address (Simon): `simonpilkington74_8oVjpj@kindle.com`

Uses Mail.app via AppleScript to send. Ensure:
- Sender email is on Kindle approved list
- File under 50MB (EPUB compresses well)

## State Tracking

State files stored in `~/.clawdbot/state/blog-kindle/`:
- `{site}-last-fetch.json` - Last fetch timestamp, article count
- `{site}-sent.json` - List of sent article IDs

Use for incremental updates (only fetch new posts).

## Manual Workflow (no scripts)

If scripts unavailable, follow this pattern:

1. **Fetch**: curl archive page → parse article links → fetch each → convert to markdown
2. **Combine**: Concatenate markdown with YAML frontmatter (title, author)
3. **Cover**: Generate via Nano Banana Pro
4. **Convert**: `pandoc combined.md -o output.epub --epub-cover-image=cover.png --toc`
5. **Send**: AppleScript Mail.app with attachment

See `references/manual-workflow.md` for detailed steps.

Related Skills

BlogBurst - Virtual CMO Agent

3891
from openclaw/skills

Your AI Chief Marketing Officer. Autonomous agent that runs your entire marketing — auto-posts to Twitter/X, Bluesky, Telegram, Discord, auto-engages with your audience (replies, likes, follows), runs SEO/GEO audits, tracks competitors, scans communities for opportunities, learns what works, and continuously optimizes. 50+ countries, 1000+ posts published. Free tier available.

Marketing Automation

blog-image-claw-skill

3891
from openclaw/skills

Generate ai blog image generator images with AI via the Neta AI image generation API (free trial at neta.art/open).

bearblog

3891
from openclaw/skills

Create and manage blog posts on Bear Blog (bearblog.dev). Supports extended Markdown, custom attributes, and browser-based publishing.

---

3891
from openclaw/skills

name: article-factory-wechat

Content & Documentation

humanizer

3891
from openclaw/skills

Remove signs of AI-generated writing from text. Use when editing or reviewing text to make it sound more natural and human-written. Based on Wikipedia's comprehensive "Signs of AI writing" guide. Detects and fixes patterns including: inflated symbolism, promotional language, superficial -ing analyses, vague attributions, em dash overuse, rule of three, AI vocabulary words, negative parallelisms, and excessive conjunctive phrases.

Content & Documentation

find-skills

3891
from openclaw/skills

Helps users discover and install agent skills when they ask questions like "how do I do X", "find a skill for X", "is there a skill that can...", or express interest in extending capabilities. This skill should be used when the user is looking for functionality that might exist as an installable skill.

General Utilities

tavily-search

3891
from openclaw/skills

Use Tavily API for real-time web search and content extraction. Use when: user needs real-time web search results, research, or current information from the web. Requires Tavily API key.

Data & Research

baidu-search

3891
from openclaw/skills

Search the web using Baidu AI Search Engine (BDSE). Use for live information, documentation, or research topics.

Data & Research

agent-autonomy-kit

3891
from openclaw/skills

Stop waiting for prompts. Keep working.

Workflow & Productivity

Meeting Prep

3891
from openclaw/skills

Never walk into a meeting unprepared again. Your agent researches all attendees before calendar events—pulling LinkedIn profiles, recent company news, mutual connections, and conversation starters. Generates a briefing doc with talking points, icebreakers, and context so you show up informed and confident. Triggered automatically before meetings or on-demand. Configure research depth, advance timing, and output format. Walking into meetings blind is amateur hour—missed connections, generic small talk, zero leverage. Use when setting up meeting intelligence, researching specific attendees, generating pre-meeting briefs, or automating your prep workflow.

Workflow & Productivity

self-improvement

3891
from openclaw/skills

Captures learnings, errors, and corrections to enable continuous improvement. Use when: (1) A command or operation fails unexpectedly, (2) User corrects Claude ('No, that's wrong...', 'Actually...'), (3) User requests a capability that doesn't exist, (4) An external API or tool fails, (5) Claude realizes its knowledge is outdated or incorrect, (6) A better approach is discovered for a recurring task. Also review learnings before major tasks.

Agent Intelligence & Learning

botlearn-healthcheck

3891
from openclaw/skills

botlearn-healthcheck — BotLearn autonomous health inspector for OpenClaw instances across 5 domains (hardware, config, security, skills, autonomy); triggers on system check, health report, diagnostics, or scheduled heartbeat inspection.

DevOps & Infrastructure