agentleFS
ShawnBaekShawnBaek/kindle-weekly-letter/.claude/skills/setup-kindle/SKILL.md

setup-kindle

Skill2 starsChanged 8 months agoMITView on GitHub

Set up Kindle Weekly Letter — configure email, Kindle device, and scheduling. Use when a new user wants to get started.

  • Reads credentials
  • Installs packages

The file

Show its rules and text

We split this skill into the rules it gives an agent

15 rules. About 0 are common, 11 are distinctive, and 4 are very specific to this project.

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈11

    Distinctive · estimate

    This author's own choices. Worth a look.

  • 4

    Very specific

    Tied to their project's names, files or tools. Probably skip.

  • Common
  • Distinctive
  • Very specific
  1. Distinctive:

    If no venv, create one and install:

    line 18
  2. Distinctive:

    Ask the user which email provider they use.

    line 25
  3. Distinctive:

    Ask the user for their Kindle email address.

    line 43
  4. Distinctive:

    Add the email address from Step 2

    line 57
  5. Very specific:

    Create .env file with the collected info:

    line 61
  6. Distinctive:

    Ask the user to check their Kindle.

    line 77
  7. Distinctive:

    Verify the sender email is in Kindle's approved list

    line 78
  8. Distinctive:

    Check the Kindle email address is correct

    line 79
  9. Distinctive:

    Ask what time they want:

    line 84
  10. Distinctive:

    Daily collection: Default 9am local time

    line 85
  11. Distinctive:

    Weekly EPUB: Default Sunday midnight local time

    line 86
  12. Distinctive:

    Ask their timezone, then convert to local system time for launchd.

    line 88
  13. Very specific:

    Create launchd plists following the pattern in: ~/Library/LaunchAgents/com.kindle-letter.daily-collector.plist

    line 90
  14. Very specific:

    Run /collect-now to start collecting immediately

    line 105
  15. Very specific:

    Run /add-topic to customize topics

    line 106

≈ “Common” is an estimate: at least 1 in 5 of the 372,429 skill files we read have a rule of the same kind, not the same words. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.

Keep what fits and drop the rest. Your version, ready for your agents.
Files
SKILL.md

Kindle Weekly Letter — Setup Guide

Walk the user through the complete setup process.

Step 1: Prerequisites Check

Run:

cd !`git rev-parse --show-toplevel` && python3 --version && (test -d .venv && echo "venv exists" || echo "no venv")

If no venv, create one and install:

uv venv && source .venv/bin/activate && uv pip install -e .

Step 2: Email Configuration

Ask the user which email provider they use. Support:

ProviderSMTP HostPort
Gmailsmtp.gmail.com465
Yahoosmtp.mail.yahoo.com465
Outlook/Hotmailsmtp-mail.outlook.com587
iCloudsmtp.mail.me.com587

Guide them to generate an App Password (not their regular password):

  • Gmail: Google Account → Security → 2-Step Verification → App Passwords
  • Yahoo: Account Security → Generate app password
  • Outlook: Microsoft Account → Security → App Passwords
  • iCloud: appleid.apple.com → Sign-In and Security → App-Specific Passwords

Step 3: Kindle Email

Ask the user for their Kindle email address.

How to find it:

  1. Go to Amazon → Manage Your Content and Devices
  2. Click Preferences tab
  3. Scroll to Personal Document Settings
  4. Find "Send-to-Kindle E-Mail" — it looks like username@kindle.com

Step 4: Approve Sender

IMPORTANT: Tell the user they must add their sender email to Kindle's approved list:

  1. On the same Personal Document Settings page
  2. Scroll to Approved Personal Document E-mail List
  3. Click Add a new approved e-mail address
  4. Add the email address from Step 2

Step 5: Write .env

Create .env file with the collected info:

EMAIL_ADDRESS=user@provider.com
EMAIL_APP_PASSWORD=xxxx xxxx xxxx xxxx
KINDLE_EMAILS=username@kindle.com
SMTP_HOST=smtp.provider.com
SMTP_PORT=465

Step 6: Test Email

Send a test EPUB:

source .venv/bin/activate && python3 -m src.epub_builder --input output/sample_content.json --output output/test.epub && python3 -m src.email_sender --epub output/test.epub

Ask the user to check their Kindle. If it doesn't arrive within 5 minutes:

  • Verify the sender email is in Kindle's approved list
  • Check the Kindle email address is correct
  • Try a different SMTP port (587 instead of 465 or vice versa)

Step 7: Schedule

Ask what time they want:

  • Daily collection: Default 9am local time
  • Weekly EPUB: Default Sunday midnight local time

Ask their timezone, then convert to local system time for launchd.

Create launchd plists following the pattern in: ~/Library/LaunchAgents/com.kindle-letter.daily-collector.plist

Load them:

launchctl load ~/Library/LaunchAgents/com.kindle-letter.daily-collector.plist
launchctl load ~/Library/LaunchAgents/com.kindle-letter.sunday-compiler.plist

Step 8: Done!

Tell the user:

  • Email is configured and tested
  • Daily collection runs at [time]
  • Weekly EPUB compiles on Sunday at [time]
  • Run /collect-now to start collecting immediately
  • Run /add-topic to customize topics
  • Edit sources.json to vote/edit sources per topic

Download now (ZIP)

Does it work?

Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.

No reviews yet

People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.

  • It worked
  • Partly
  • It didn't
What did you use it for? e.g. Reviewing pull requests in a Rails app

Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.

Your trail

Files you open will collect here, so you can find them again.

Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.

Now do this for your own.

Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.