twitter-cultivate
npx machina-cli add skill PHY041/claude-agent-skills/twitter-cultivate --openclawTwitter Account Cultivation Skill
Systematic approach to growing Twitter presence based on the open-source algorithm analysis.
Prerequisites
- Twikit installed (
pip install twikit) - Twitter cookies exported to:
~/crawlee-social-scraper/twitter_cookies.json(or wherever your Twikit setup lives — setTWIKIT_DIRenv var) - Your Twitter handle configured in state file
Core Metrics to Track
| Metric | Healthy Range | Impact |
|---|---|---|
| Following/Follower Ratio | < 0.6 | TweepCred score |
| Avg Views/Tweet | 20-40% of followers | Algorithm favor |
| Media Tweet % | > 50% | 10x engagement |
| Link Tweet % | < 20% | Avoid algorithm penalty |
| Reply Rate | Reply to 100% of comments | +75 weight boost |
Workflow: Full Health Check
Step 1: Analyze Account
cd ~/crawlee-social-scraper
source venv/bin/activate
python twitter_cultivate.py analyze <YOUR_USERNAME>
Step 2: Check Shadowban Status
python twitter_cultivate.py shadowban <YOUR_USERNAME>
Or manually check: shadowban.yuzurisa.com
Step 3: Analyze Following List
python twitter_cultivate.py unfollow-recs <YOUR_USERNAME> --limit 50
Recommends accounts to unfollow based on:
- No tweets in 90+ days (inactive)
- Never interacted with you (no value)
- Low follower count + high following (likely bots)
- No mutual engagement
Step 4: Find Engagement Opportunities
python twitter_cultivate.py opportunities --niche "AI,startup,founder"
Finds:
- Rising tweets in your niche to reply to
- Accounts similar to yours to engage with
- Trending topics you can contribute to
Step 5: Generate Weekly Report
python twitter_cultivate.py report
Account Health Scoring
Based on Twitter's open-source algorithm:
TweepCred Estimation
Score = PageRank × (1 / max(1, following/followers))
| Ratio | Estimated TweepCred | Algorithm Treatment |
|---|---|---|
| < 0.6 | 65+ (healthy) | All tweets considered |
| 0.6 - 2.0 | 40-65 | Limited consideration |
| 2.0 - 5.0 | 20-40 | Severe penalty |
| > 5.0 | < 20 | Only 3 tweets max |
Unfollow Strategy
Priority 1: Inactive Accounts
- No tweets in 90+ days
- Safe to unfollow, no relationship loss
Priority 2: Non-Engagers
- Never liked/replied to your tweets
- One-way relationship
Priority 3: Low-Value Follows
- High following/low followers (bot-like)
- No content in your niche
Execution Plan
Week 1: Unfollow 30 inactive accounts
Week 2: Unfollow 30 non-engagers
Week 3: Unfollow 30 low-value follows
Week 4: Evaluate ratio improvement
Target: Get ratio below 2.0, ideally below 0.6
Content Strategy (Algorithm-Optimized)
Tweet Types by Algorithm Weight
| Type | Weight | Recommendation |
|---|---|---|
| Tweet that gets author reply | +75 | ALWAYS reply to comments |
| Tweet with replies | +13.5 | Ask questions |
| Tweet with profile clicks | +12.0 | Be intriguing |
| Tweet with long dwell time | +10.0 | Use threads |
| Retweet | +1.0 | Low value |
| Like | +0.5 | Lowest value |
Content Mix
- 40% Value content (insights, tips, frameworks)
- 30% Engagement bait (questions, polls, hot takes)
- 20% Build-in-public (progress updates, wins, losses)
- 10% Promotion (with value attached)
Media Requirements
Every tweet should have ONE of:
- Image (infographic, screenshot, meme)
- Video (< 2:20, hook in first 3 sec)
- Poll
- Thread (7-10 tweets)
NEVER post text-only tweets
Posting Schedule
Optimal Times (General)
| Day | Best Time | Second Best |
|---|---|---|
| Tuesday | 9-10 AM | 1-2 PM |
| Wednesday | 9-10 AM | 3-4 PM |
| Thursday | 10-11 AM | 2-3 PM |
First 10 Minutes Protocol
1. Post at optimal time
2. Immediately self-reply with additional insight
3. Reply to ANY comment within 10 minutes
4. Have 2-3 "pod" members ready to RT
Frequency
- Minimum: 1 tweet/day
- Optimal: 3-5 tweets/day
- Gap: 30-60 min between tweets
Engagement Tactics
Reply Strategy (Most Important)
The algorithm gives +75 weight when you reply to replies on your tweets.
Someone comments on your tweet
↓
Reply within 30 minutes (CRITICAL)
↓
Algorithm sees author engagement
↓
Tweet gets boosted to more feeds
Quote Tweet Strategy
Find viral tweet in your niche
↓
Quote with your unique take
↓
Add value, not just "great point"
↓
Post during optimal hours
Thread Formula
1/ Hook (curiosity gap or bold claim)
2-6/ Individual points with specifics
7/ Summary
8/ CTA: Question or "follow for more"
Real-time Monitor & Auto-Reply
Monitor target accounts and auto-generate contextual replies for maximum engagement.
cd ~/crawlee-social-scraper
# Interactive mode (recommended) - approve before posting
./start_monitor.sh
# Monitor only - just watch, no replies
./start_monitor.sh monitor
Customize Targets
./venv/bin/python3 twitter_monitor.py --interactive --targets "levelsio,marc_lou,thedankoe"
How It Works
- Polls target accounts every 60 seconds
- Detects new tweets
- Generates contextual reply
- Shows you the suggestion
- You approve/edit/skip
CLI Reference
cd ~/crawlee-social-scraper
source venv/bin/activate
# Full health check
python twitter_cultivate.py analyze <username>
# Check shadowban
python twitter_cultivate.py shadowban <username>
# Get unfollow recommendations
python twitter_cultivate.py unfollow-recs <username> --limit 50
# Find engagement opportunities
python twitter_cultivate.py opportunities --niche "AI,startup"
# Weekly report
python twitter_cultivate.py report
# Execute unfollow (with confirmation)
python twitter_cultivate.py unfollow <username> --execute
Weekly Routine
Daily (15 min)
- Post 1-3 tweets with media
- Reply to ALL comments on your tweets
- Engage with 5-10 tweets in your niche
- Check notifications and respond
Weekly (Saturday)
- Run full health check
- Review what content performed best
- Unfollow 10-20 low-value accounts
- Plan next week's content themes
Monthly
- Full ratio review (target < 2.0)
- Shadowban check
- Content audit (media %, link %)
- Milestone check (follower goals)
Recovery Plan (Low Follower Count)
Phase 1: Emergency Ratio Fix (Week 1-2)
If your ratio is > 5.0 (following >> followers):
- Unfollow 100+ inactive/non-engaging accounts
- Target: ratio < 5.0 as first milestone
Phase 2: Content Upgrade (Week 2-4)
If you have 0% media tweets:
- Add image/video to EVERY tweet
- Use Canva/Figma for quick graphics
- Screenshot interesting data/insights
Phase 3: Engagement Building (Week 3-6)
- Reply to 20+ tweets/day in your niche
- Quote tweet viral content with your take
- Join relevant Twitter communities
- DM potential collaborators
Phase 4: Consistency (Ongoing)
- 3-5 tweets/day
- Reply to 100% of comments
- Weekly analysis and adjustment
Source
git clone https://github.com/PHY041/claude-agent-skills/blob/main/skills/twitter-cultivate/SKILL.mdView on GitHub Overview
Twitter-cultivate is a growth system that evaluates account health using TweepCred and shadowban checks, analyzes your tweets, and surfaces engagement opportunities. It also provides actionable unfollow recommendations and tracks progress over time to improve reach and quality.
How This Skill Works
The skill runs health and content scans via your Twitter handle, computes TweepCred-based health metrics, checks for shadowban status, and reviews your following list to propose unfollow candidates. It then identifies engagement opportunities by spotting trending topics and relevant accounts in your niche, and compiles a weekly report with actionable insights.
When to Use It
- When you want a health check of your Twitter/X account (TweepCred, shadowban).
- When your follower/following ratio needs improvement and clean-up.
- When you need unfollow recommendations for inactive, non-reciprocal, or low-value accounts.
- When you want to discover engagement opportunities in your niche (AI, startup, founder).
- When you want a weekly progress report and actionable insights to grow reach.
Quick Start
- Step 1: Analyze your account with python twitter_cultivate.py analyze <YOUR_USERNAME>.
- Step 2: Check shadowban status with python twitter_cultivate.py shadowban <YOUR_USERNAME>.
- Step 3: Review health_report, unfollow_recommendations, and opportunities to act on insights.
Best Practices
- Run health checks regularly and monitor TweepCred scores and shadowban status.
- Prioritize engagement in your niche and use author-reply tactics that boost visibility.
- Maintain a healthy following/follower ratio (target < 0.6) to avoid penalties and preserve reach.
- Follow the unfollow plan: remove inactive, non-engagers, and low-value follows methodically.
- Use opportunities and weekly reports to iteratively refine your content strategy and timing.
Example Use Cases
- Founder in AI uses opportunities to reply to rising posts in the niche, driving meaningful conversations and followers.
- Creator runs weekly unfollow recs to prune inactive accounts and those with no mutual engagement, improving ratio.
- Health report flags no shadowban issues after a period of optimized posting and engagement practices.
- Weekly report highlights a shift toward more author replies and higher-value tweets, increasing engagement by 15-20%.
- Startup founder leverages content strategy insights to tailor tweets around trending topics in their domain.