twitter-bookmark-sync – OpenClaw Skill

---

name: twitter-bookmark-sync description: Automatically ranks your Twitter bookmarks daily and delivers a curated reading list

twitter-bookmark-sync

Automated Twitter bookmark curation and notification

Never miss important bookmarks. Automatically rank your Twitter bookmarks based on your interests and get a curated reading list delivered daily.

---

What It Does

• Learns what matters to you from your bookmarking patterns
• Adapts ranking weights automatically (interests decay unless reinforced)
• Categorizes bookmarks by topic and value type
• Delivers personalized value statements every morning
• Gets smarter the more you use it

---

Requirements

• macOS 10.15 or later
• Twitter account with bookmarks
• bird CLI (brew install steipete/tap/bird)
• Clawdbot (for scheduling and notifications)
• Twitter auth cookies configured (see Getting Ready)

---

Getting Ready

Step 1: Install bird CLI

brew install steipete/tap/bird

Step 2: Configure Twitter Authentication

Extract your Twitter cookies from your browser:

1. Open browser → https://x.com (logged in)

2. DevTools (Cmd+Option+I) → Application → Cookies → https://x.com

3. Copy these values:

   • auth_token
   • ct0

4. Save to config:

mkdir -p ~/.config/bird
cat > ~/.config/bird/config.json5 << 'EOF'
{
  authToken: "your_auth_token_here",
  ct0: "your_ct0_here"
}
EOF

5. Test:

bird whoami

---

Installation

clawdhub install twitter-bookmark-sync
cd ~/clawd/skills/twitter-bookmark-sync
./install.sh

The installer will:

1. Detect your timezone automatically
2. Set up daily cron jobs (fetch at midnight, notify at 8am)
3. Create your config file

---

Configuration

Edit ~/clawd/twitter-bookmark-sync-config.json:

{
  "fetch_time": "00:00",           // When to learn & rank (24h format)
  "notification_time": "08:00",     // When to send results
  "lookback_hours": 24,             // How far back to check
  "notification_channel": "telegram", // or "gmail", "slack"
  "output_dir": "~/Documents"      // Where to save reading lists
}

Ranking criteria (self-evolving):
~/clawd/twitter-bookmark-sync-criteria.json

This file updates automatically based on your bookmarking patterns.
Do not edit manually — let it learn from your behavior.

Notification Channels

Telegram (default):

{
  "notification_channel": "telegram"
}

Gmail (via gog skill):

{
  "notification_channel": "gmail",
  "gmail_to": "your.email@gmail.com"
}

Slack:

{
  "notification_channel": "slack",
  "slack_channel": "#bookmarks"
}

---

How It Works

Daily Schedule

Midnight (00:00) - Learning Phase:

1. Fetches bookmarks from last 24 hours
2. Categorizes each (topic + value type)
3. Updates ranking criteria:
   • Applies time decay (5% per day) to unused interests
   • Boosts weights for categories you're actively bookmarking
   • Discovers new patterns automatically
   • Normalizes all weights
4. Ranks new bookmarks using evolved criteria
5. Saves to ~/Documents/twitter-reading-YYYY-MM-DD.md

Morning (08:00) - Notification:

1. Analyzes WHY each bookmark matters to you
2. Sends value statements (not summaries)
3. Links to full reading list

Example notification:

📚 Twitter Reading List Ready!

**1. @someuser** (Score: 120)
💡 Career growth pathway • Investment strategy
🔗 https://x.com/...

**2. @another** (Score: 110)  
💡 Direct crypto insights • London transition
🔗 https://x.com/...

Self-Learning System

On first install:

• Initializes from USER.md profile
• Creates twitter-bookmark-sync-criteria.json
• 11 value categories with initial weights (0-100)

Every midnight:

• Categorizes your new bookmarks
• Updates category weights based on usage
• Old interests decay 5% per day
• Active interests stay strong
• New patterns emerge automatically

Example evolution:

Day 1:  crypto_insights: 100, relationships: 90
Day 10: crypto_insights: 100 (active), relationships: 60 (decaying)
Day 30: crypto_insights: 100, AI_tools: 75 (discovered), relationships: 35

Why this matters:

• Adapts to your changing interests
• No manual keyword management
• Gets better at predicting what you'll value
• Reflects YOUR actual behavior, not generic defaults

---

Manual Usage

Run immediately:

cd ~/clawd/skills/twitter-bookmark-sync
./scripts/sync.sh

Change schedule:

# Edit config
nano ~/clawd/twitter-bookmark-sync-config.json

# Reload cron jobs
./install.sh

---

Troubleshooting

"No bookmarks found"

• Check bird authentication: bird whoami
• Verify you have bookmarks: bird bookmarks -n 5

"Permission denied"

• Check bird config: ~/.config/bird/config.json5
• Verify cookies are valid (they expire)

"Notification not sent"

• Check Clawdbot is running: clawdbot status
• Verify notification channel in config
• Check logs: ~/clawd/logs/twitter-bookmark-sync.log

---

License

MIT

Twitter Bookmark Sync

Automatically ranks your Twitter bookmarks daily and delivers a curated reading list.

The problem: You bookmark tweets but never read them. They pile up and important content gets lost in the noise.

This tool: Self-learning bookmark curator that adapts to your interests, ranks by personal value, and delivers your best reads every morning.

---

⚡ What It Does

Your bookmarks get smarter over time.

The tool:

• Learns what you care about from your bookmarking patterns
• Adapts ranking weights based on what you actually save
• Decays old interests automatically (unless reinforced)
• Delivers personalized value statements every morning

The more you bookmark, the better it gets at knowing what matters to you.

Zero manual work needed.

---

🛠️ Getting Ready

Before installing this skill:

You'll need:

• macOS 10.15 (Catalina) or later
• Twitter account with bookmarks
• Homebrew for installing dependencies

Install through Homebrew:

# Install bird CLI
brew install steipete/tap/bird

# Install jq
brew install jq

Set up Twitter authentication:

1. Open browser → https://x.com (logged in)

2. DevTools (Cmd+Option+I) → Application → Cookies → https://x.com

3. Copy these values:

   • auth_token
   • ct0

4. Save to config:

mkdir -p ~/.config/bird
cat > ~/.config/bird/config.json5 << 'EOF'
{
  authToken: "your_auth_token_here",
  ct0: "your_ct0_here"
}
EOF

5. Test:

bird whoami

---

🚀 Installation

clawdhub install twitter-bookmark-sync
cd ~/clawd/skills/twitter-bookmark-sync
./install.sh

The installer will:

• Verify dependencies
• Create your config file
• Guide you through cron setup
• Run a test sync

---

🔧 How It Works

Result: A self-learning curator that gets smarter with every bookmark.

The schedule:

Midnight (00:00) - Learning & Ranking:

1. Fetches bookmarks from last 24 hours
2. Categorizes each by topic and value type
3. Updates ranking algorithm:
   • Applies time decay (5% per day) to old interests
   • Reinforces categories you're actively bookmarking
   • Discovers new interest patterns automatically
   • Normalizes weights to maintain balance
4. Ranks new bookmarks using evolved criteria
5. Saves to ~/Documents/twitter-reading-YYYY-MM-DD.md

Morning (08:00) - Notification:

1. Analyzes why each bookmark matters to YOU specifically
2. Sends value-focused statements (not content summaries)
3. Links to full reading list

Self-Learning Algorithm:

Initial state (from USER.md):

• London transition: weight 100
• Crypto insights: weight 100
• Career growth: weight 95
• Investment strategy: weight 90
• ... (11 categories total)

After 30 days (example evolution):

• If you bookmark lots of crypto → crypto weight stays high (100)
• If you stop bookmarking relationships → weight decays (90 → 85 → 81...)
• If you bookmark AI tools daily → new category emerges ("discovered_ai_tools": 65)

Decay mechanics:

• 5% weight reduction per day for unused categories
• When you bookmark a category again → decay resets
• Floor: minimum weight of 10 (never disappears completely)

Configuration:

{
  "fetch_time": "00:00",           // When to learn & rank
  "notification_time": "08:00",     // When to notify
  "lookback_hours": 24,             // How far back to check
  "notification_channel": "telegram" // Where to send
}

Ranking criteria stored in: ~/clawd/twitter-bookmark-sync-criteria.json
(Evolves automatically — you don't edit this manually)

---

---

📚 Additional Information

Everything below is optional. The skill works out-of-the-box with defaults.

This section contains:

• Advanced configuration
• Notification channel setup
• Manual usage
• Troubleshooting

You don't need to read this for initial installation.

---

<details> <summary><b>Advanced Configuration</b></summary> <br>

Edit ~/clawd/twitter-bookmark-sync-config.json:

Change timing:

{
  "fetch_time": "23:00",  // 11pm instead of midnight
  "notification_time": "07:00"  // 7am instead of 8am
}

Change lookback window:

{
  "lookback_hours": 24  // Check last 24 hours instead of 16
}

Customize interests:

{
  "keywords_high": [
    "your", "specific", "interests"
  ],
  "keywords_medium": [
    "secondary", "topics"
  ]
}

</details> <details> <summary><b>Notification Channels</b></summary> <br>

Telegram (default):

{
  "notification_channel": "telegram"
}

Results sent to your Telegram chat.

Gmail (via gog skill):

{
  "notification_channel": "gmail",
  "gmail_to": "your.email@gmail.com"
}

Requires gog skill installed and configured.

Slack:

{
  "notification_channel": "slack",
  "slack_channel": "#bookmarks"
}

Results sent to specified Slack channel.

</details> <details> <summary><b>Manual Usage</b></summary> <br>

Run sync immediately:

cd ~/clawd/skills/twitter-bookmark-sync
./scripts/sync.sh

Send notification now:

./scripts/notify.sh

Check logs:

tail -f ~/clawd/logs/twitter-bookmark-sync.log

</details> <details> <summary><b>Troubleshooting</b></summary> <br>

"No bookmarks found"

Check bird authentication:

bird whoami

Verify you have bookmarks:

bird bookmarks -n 5

"Permission denied"

Make scripts executable:

chmod +x ~/clawd/skills/twitter-bookmark-sync/scripts/*.sh
chmod +x ~/clawd/skills/twitter-bookmark-sync/scripts/*.py

"Twitter cookies expired"

Re-extract cookies from browser and update ~/.config/bird/config.json5

"Notification not sent"

Check Clawdbot status:

clawdbot status

Verify notification channel in config.

</details>

---

License

MIT