twitter-algorithm-optimizer
Analyze and optimize tweets for maximum reach using Twitter's open-source algorithm insights. Rewrite and edit user tweets to improve engagement and visibility based on how the recommendation system ranks content.
Install with Tessl CLI
npx tessl i github:davepoon/buildwithclaude --skill twitter-algorithm-optimizer69
Quality
55%
Does it follow best practices?
Impact
97%
1.31xAverage score across 3 eval scenarios
Optimize this skill with Tessl
npx tessl skill review --optimize ./plugins/all-skills/skills/twitter-algorithm-optimizer/SKILL.mdEvaluation results
100%
54%Developer Audience Growth: Tweet Optimization
Tweet analysis and algorithmic rewrite
Framework analysis present
0%
100%
SimClusters community focus
70%
100%
Direct question in rewrite
0%
100%
Single topic per tweet
30%
100%
Engagement bait critique
80%
100%
Engagement bait removed
100%
100%
Calls to action in rewrites
20%
100%
Community language in rewrites
100%
100%
Algorithmic why explained
50%
100%
TwHIN identity consistency
10%
100%
Without context: $0.1761 · 1m 25s · 8 turns · 13 in / 3,988 out tokens
With context: $0.5596 · 2m 42s · 22 turns · 185 in / 7,733 out tokens
91%
-5%Product Launch Tweet Sequence
Content strategy and signal-type optimization
Three labeled variants
100%
100%
Reply variant has question
100%
100%
Retweet variant is actionable
100%
90%
Bookmark variant is reference-worthy
100%
100%
No engagement bait
100%
100%
Signal-type explanation
100%
100%
Passive promotion avoided
100%
100%
Timing advice included
100%
100%
Community/niche targeting
87%
87%
Calls to action present
100%
50%
Thread recommended
50%
50%
Without context: $0.1127 · 48s · 9 turns · 13 in / 1,960 out tokens
With context: $0.4487 · 1m 39s · 20 turns · 27 in / 4,741 out tokens
100%
20%Twitter Content Audit: Diagnosing Inconsistent Engagement
Credibility building and negative signal avoidance
Off-topic pivot diagnosed
90%
100%
TwHIN / identity mechanism named
40%
100%
Reply-guy syndrome diagnosed
90%
100%
Negative signals from controversy
90%
100%
Over-frequency diagnosed
90%
100%
Tweepcred / authority impact named
40%
100%
Recovery: niche return
90%
100%
Recovery: quality over volume
90%
100%
Recovery: quality engagement
90%
100%
Algorithmic mechanisms in recommendations
90%
100%
Without context: $0.2194 · 1m 36s · 8 turns · 13 in / 4,254 out tokens
With context: $0.5152 · 2m 37s · 20 turns · 435 in / 6,987 out tokens
- Evaluated
- Agent
- Claude Code
- Model
- Claude Sonnet 4.6
Table of Contents
Is this your skill?
If you maintain this skill, you can claim it as your own. Once claimed, you can manage eval scenarios, bundle related skills, attach documentation or rules, and ensure cross-agent compatibility.