x-boost
- Repo stars 12
- License MIT
- Author repo go-viral
X Post Optimizer
Helps craft posts optimized for the X recommendation algorithm based on open-source algorithm analysis.
How the Algorithm Scores Posts
The algorithm predicts 19 engagement actions and combines them:
Positive signals (boost reach):
- Likes, Replies, Retweets, Quotes
- Dwell time (time spent reading)
- Profile clicks, Follows from post
- Shares (DM, copy link)
- Video quality views, Photo expands
Negative signals (kill reach):
- "Not interested" clicks
- Blocks, Mutes, Reports
Instructions
When asked to optimize a post or write for X:
1. Hook First
- Lead with the most compelling point
- Stop the scroll in first 5 words
- Use pattern interrupts
2. Maximize Dwell Time
- Add depth that rewards reading
- Use line breaks for scanability
- Include images/videos that make people pause
3. Encourage Replies
- End with questions
- Make takes that invite discussion
- Leave threads open-ended
4. Avoid Author Penalty
The algorithm applies exponential decay to rapid posts from same author:
score = base_score × decay^(post_count)
Recommendation: Space posts 2-4 hours apart for maximum individual reach.
5. Leverage In-Network Advantage
Posts to followers rank higher than discovery posts. Build genuine following over chasing virality.
Quick Checklist
When reviewing a draft post, check:
- Hook in first line?
- Rewards reading (dwell time)?
- Invites replies?
- No spam/repetitive content?
- Authentic voice (not engagement bait)?
- Appropriate timing from last post?
What Doesn't Work
- Engagement pods (artificial patterns detected)
- Keyword stuffing (algorithm learns behavior, not keywords)
- Rapid-fire posting (author diversity penalty)
- Controversial content that triggers blocks/mutes
Example Optimization
Before:
Just launched my new product! Check it out at example.com
After:
I spent 6 months building something I wish existed 3 years ago.
The problem: [specific pain point]
The solution: [what you built]
Here's what surprised me most about the process:
[insight that invites discussion]
What's been your experience with [related topic]?
Why it's better:
- Hook creates curiosity (dwell time)
- Structure rewards reading
- Ends with question (replies)
- Authentic story (avoids mute/block signals)
- Fluxly category
- Documentation
- Author-declared agents
- No explicit declaration found; this is not inferred or tested compatibility
- Static check
- 94 / 100 · heuristic scan, not runtime safety proof
- Author / version / license
- @guzus · MIT
- Fluxly token estimate
- Lean
- Fluxly setup estimate
- Plug-and-play
- External API key
- No requirement detected
- Detected OS requirements
- Unspecified
- Runtime requirements
- Unspecified
- Detected file/system behavior
-
- Read-only
- Write / modify
- Detected network behavior
- Local-only
- Install commands
- None (reference only)
Profile is derived at build time from SKILL.md and install vectors. Subject to drift from author intent.
Heads up: 未限定 allowed-tools,默认拥有全部工具权限。
The current SKILL.md does not define a fixed output example. The algorithm predicts 19 engagement actions and combines them: Positive signals (boost reach): Likes, Replies, Retweets, Quotes
When asked to optimize a post or write for X:
Lead with the most compelling point Stop the scroll in first 5 words Use pattern interrupts
Add depth that rewards reading Use line breaks for scanability Include images/videos that make people pause
End with questions Make takes that invite discussion Leave threads open-ended
The algorithm applies exponential decay to rapid posts from same author: Recommendation: Space posts 2-4 hours apart for maximum individual reach.
# X Post Optimizer
Helps craft posts optimized for the X recommendation algorithm based on open-source algorithm analysis.
## How the Algorithm Scores Posts
The algorithm predicts **19 engagement actions** and combines them:
**Positive signals (boost reach):**
- Likes, Replies, Retweets, Quotes
- Dwell time (time spent reading)
- Profile clicks, Follows from post
- Shares (DM, copy link)
- Video quality views, Photo expands
**Negative signals (kill reach):**
- "Not interested" clicks
- Blocks, Mutes, Reports
## Instructions
When asked to optimize a post or write for X:
### 1. Hook First
- Lead with the most compelling point
- Stop the scroll in first 5 words
- Use pattern interrupts
### 2. Maximize Dwell Time
- Add depth that rewards reading
- Use line breaks for scanability
- Include images/videos that make people pause
### 3. Encourage Replies
- End with questions
- Make takes that invite discussion
- Leave threads open-ended
### 4. Avoid Author Penalty
The algorithm applies exponential decay to rapid posts from same author:
```
score = base_score × decay^(post_count)
```
**Recommendation:** Space posts 2-4 hours apart for maximum individual reach.
### 5. Leverage In-Network Advantage
Posts to followers rank higher than discovery posts. Build genuine following over chasing virality.
## Quick Checklist
When reviewing a draft post, check:
- [ ] Hook in first line?
- [ ] Rewards reading (dwell time)?
- [ ] Invites replies?
- [ ] No spam/repetitive content?
- [ ] Authentic voice (not engagement bait)?
- [ ] Appropriate timing from last post?
## What Doesn't Work
- Engagement pods (artificial patterns detected)
- Keyword stuffing (algorithm learns behavior, not keywords)
- Rapid-fire posting (author diversity penalty)
… Author text anchors workflow facts; Fluxly only indexes current sections, terms, files, and commands.
sections -> How the Algorithm Scores Posts → Instructions → 1. Hook First → 2. Maximize Dwell Time → 3. Encourage Replies → 4. Avoid Author Penalty
terms -> 19 engagement actions · Positive signals (boost reach) · Negative signals (kill reach) · Recommendation · Before · After · Why it's better
files/cmd -> images/videos · spam/repetitive · blocks/mutes · mute/block
body sha256 -> f1356edcf02a
Decide Fit First
Design Intent
How To Use It
Boundaries And Review