name: kindle-sender description: Send Research Swarm documents to Kindle. Use when "send to Kindle", "send research to Kindle", "send someday-maybe to Kindle", "Kindle my research", "with links expanded", "send last week's research", "send January research". allowed-tools: Read, Bash, Glob, Write, AskUserQuestion

Kindle Sender

What This Does

Converts markdown documents from your Zettelkasten to EPUB and emails them to your Kindle for offline reading.

Four modes:

1. Research mode - Send all Research Swarm docs linked in today's daily note
2. Date range mode - Send research from a date range (last week, this month, etc.). Automatically scans daily notes in the range and extracts Research Swarm links.
3. Review mode - Send your Someday-Maybe.md backlog for Kindle review
4. Deep reading mode - Send with --expand-links to include full content of all linked documents as an appendix

When to Use

• "Send my research to Kindle"
• "Send today's research to Kindle"
• "Send last week's research to Kindle"
• "Send January research to Kindle"
• "Send research from Jan 15 to Jan 20"
• "Send someday-maybe to Kindle"
• "Send someday-maybe to Kindle with links expanded"
• "Kindle my research"

Prerequisites (One-Time Setup)

Before first use, configure these environment variables in ~/.zshrc:

export KINDLE_EMAIL="your-name@kindle.com"
export GMAIL_USER="your-email@gmail.com"
export GMAIL_APP_PASSWORD="your-app-password"

Setup steps:

1. Find your Kindle email:

   • Go to Amazon → Manage Content & Devices
   • Click "Preferences" tab
   • Look for "Personal Document Settings"
   • Your Kindle email ends in @kindle.com

2. Whitelist your sender email:

   • Same page, under "Approved Personal Document E-mail List"
   • Add your Gmail address

3. Create Gmail app password:

   • Go to Google Account → Security
   • Enable 2-Step Verification if not already
   • Go to "App passwords" (search for it)
   • Create a new app password for "Mail"
   • Use this password, NOT your regular Gmail password

4. Install Python dependencies:

   pip3 install pypandoc pypandoc_binary python-dateutil
   

   Note: python-dateutil is optional but recommended. Without it, relative dates like "last month" use a 30-day approximation.

5. Reload shell:

   source ~/.zshrc
   

Instructions

Standard Flow (All Modes)

Step 1: Determine what to send

• Daily notes: Find files in /Users/eddale/Documents/COPYobsidian/MAGI/Zettelkasten/YYYY-MM-DD.md
• Research mode: Extract [[Research Swarm - *]] links from Captures section
• Someday-maybe: Use the Someday-Maybe.md file
• Specific files: Use paths provided by user

Step 2: Run dry-run with --expand-links to see linked documents

cd /Users/eddale/Documents/GitHub/powerhouse-lab/skills/kindle-sender/tools
python3 send_to_kindle.py --files "file1.md" "file2.md" --expand-links --dry-run

Step 3: Show preview and ask about link expansion

Display what will be sent, then use AskUserQuestion with TWO questions:

1. Link expansion (unless user already said "with links expanded"):

   • Question: "Include linked documents as appendix?"
   • Options:
     • "Yes, expand links" - Include full content of all [[wikilinks]] as tappable appendix sections
     • "No, just the files" - Send documents without expanding links

2. Confirm send:

   • Question: "Send X documents to Kindle?"
   • Options: "Yes, send them" / "No, cancel"

Step 4: Send based on user choices

# With link expansion
python3 send_to_kindle.py --files "file1.md" --expand-links

# Without link expansion
python3 send_to_kindle.py --files "file1.md"

Step 5: Report results "Sent X documents to your Kindle. They should arrive within a few minutes."

Mode-Specific Commands

Daily note research (single day):

python3 send_to_kindle.py --daily-note "YYYY-MM-DD" [--expand-links] [--dry-run]

Date range research (multiple days):

# Last week's research
python3 send_to_kindle.py --start-date "7 days ago" --end-date today [--expand-links] [--dry-run]

# Specific month
python3 send_to_kindle.py --start-date 2026-01-01 --end-date 2026-01-31 [--expand-links] [--dry-run]

# Specific date range
python3 send_to_kindle.py --start-date "Jan 15" --end-date "Jan 20" [--expand-links] [--dry-run]

Someday-maybe:

python3 send_to_kindle.py --someday-maybe [--expand-links] [--dry-run]

Specific files:

python3 send_to_kindle.py --files "Doc1.md" "Doc2.md" [--expand-links] [--dry-run]

Script Options

Date Format Support

The --start-date and --end-date flags accept flexible date formats:

Troubleshooting

Examples

Example 1: Research with link expansion choice

User: Send my research to Kindle
Claude: Found 3 Research Swarm documents in today's Captures:
  1. Research Swarm - Markdown to Kindle Workflow - 2026-01-09.md
  2. Research Swarm - API Design Patterns - 2026-01-09.md
  3. Research Swarm - Newsletter Growth - 2026-01-09.md

  These documents contain 27 linked documents total.

  [AskUserQuestion with two questions:]
  1. Include linked documents as appendix? → Yes/No
  2. Send these 3 documents to Kindle? → Yes/No

User: Yes to both
Claude: Sent 3 documents (with 27 linked docs expanded) to your Kindle.

Example 2: Daily notes batch

User: Send my daily notes from Monday through Friday to Kindle
Claude: Found 5 daily notes (Jan 12-16). Dry run shows 100 linked documents.

  [AskUserQuestion:]
  1. Include linked documents as appendix? → User selects "Yes, expand links"
  2. Send 5 documents to Kindle? → User selects "Yes, send them"

Claude: Sent 5 documents with 100 linked docs as appendices. Arriving shortly.

Example 3: User explicitly requests link expansion

User: Send someday-maybe to Kindle with links expanded
Claude: Will send Someday-Maybe.md with 13 linked documents:
  - PROJECT - Email Agent
  - Research - Claude Code Testing Infrastructure - 2026-01-06
  - ...

  [AskUserQuestion - skip link expansion question since user specified it:]
  Send Someday-Maybe.md to Kindle? → Yes/No

User: Yes
Claude: Sent Someday-Maybe.md (with 13 referenced documents) to your Kindle.

Example 4: User declines link expansion

User: Send today's research to Kindle
Claude: Found 2 Research Swarm documents with 15 linked docs.

  [AskUserQuestion:]
  1. Include linked documents as appendix? → User selects "No, just the files"
  2. Send 2 documents to Kindle? → Yes

Claude: Sent 2 documents to your Kindle. They should arrive within a few minutes.

Example 5: Date range - last week's research

User: Send last week's research to Kindle
Claude: Scanning daily notes from 2026-01-15 to 2026-01-22...
  Found 5 daily notes with 12 unique Research Swarm documents:
  - Research Swarm - Newsletter Monetization - 2026-01-15.md
  - Research Swarm - API Patterns - 2026-01-17.md
  ...

  [AskUserQuestion:]
  1. Include linked documents as appendix? → Yes/No
  2. Send 12 documents to Kindle? → Yes/No

# Runs:
python3 send_to_kindle.py --start-date "7 days ago" --end-date today [--expand-links]

Example 6: Date range - specific month

User: Send January research to Kindle
Claude: Scanning daily notes from 2026-01-01 to 2026-01-31...
  Found 18 daily notes with 42 unique Research Swarm documents.

# Runs:
python3 send_to_kindle.py --start-date 2026-01-01 --end-date 2026-01-31 [--expand-links]

Example 7: Date range - specific dates

User: Send research from Jan 15 to Jan 20
Claude: Scanning daily notes from 2026-01-15 to 2026-01-20...

# Runs:
python3 send_to_kindle.py --start-date "Jan 15" --end-date "Jan 20" --dry-run