x-impact-checker by tonkotsuboy/x-impact-checker
npx skills add https://github.com/tonkotsuboy/x-impact-checker --skill x-impact-checker基于开源推荐算法(19元素评分系统)分析 X 帖子,评估其病毒式传播潜力。
驱动对话和强烈分享信号的要素。
| 因子 | 最高分 | 评分指南 |
|---|---|---|
| 回复潜力 | 22 | 22:直接提问/可辩论的主张,12:邀请回应,4:仅为陈述 |
| 转推潜力 | 16 | 16:可操作的见解/令人惊讶的事实,8:有趣但小众,0:无分享价值 |
| 收藏潜力 | 12 | 12:引起情感共鸣/个人故事,6:有用的参考资料,0:吸引力低 |
| 引用潜力 | 10 | 10:强烈观点,邀请评论,5:发人深省,0:无引用价值 |
媒体互动和持续关注度指标。
| 因子 | 最高分 | 评分指南 |
|---|---|---|
| 停留时间 | 6 |
广告位招租
在这里展示您的产品或服务
触达数万 AI 开发者,精准高效
| 6:长文/详细内容,3:中等深度,0:可快速浏览 |
| 持续停留时间 | 4 | 4:需要持续关注的串文/故事线,2:中等复杂度,0:快速阅读 |
| 点击潜力 | 5 | 5:带有明确行动号召的诱人链接,3:有上下文的链接,1:裸链接,0:无链接 |
| 图片展开潜力 | 4 | 4:多张图片/视觉叙事,2:单张图片参考,0:无视觉内容 |
| 视频观看潜力 | 3 | 3:有吸引点的长视频(>5秒),2:短视频片段,0:无视频 |
| 引用点击潜力 | 3 | 3:需要验证的大胆主张,2:有趣的主张,0:内容自足 |
作者发现和长期价值信号。
| 因子 | 最高分 | 评分指南 |
|---|---|---|
| 个人资料点击 | 5 | 5:引发对作者的好奇心,3:展示专业知识,0:通用声音 |
| 关注潜力 | 4 | 4:展示持续价值,2:展示潜力,0:一次性内容 |
| 分享潜力 | 2 | 2:具有普遍分享价值,1:吸引力有限,0:无价值 |
| 通过私信分享 | 2 | 2:个人化/有共鸣的“发送给朋友”内容,1:有一定共鸣,0:通用 |
| 通过复制链接分享 | 2 | 2:值得参考/收藏,1:有用但非永恒,0:短暂内容 |
| 风险 | 范围 | 触发条件 |
|---|---|---|
| 不感兴趣 | -5 至 -15 | 标题党、无关内容 |
| 静音风险 | -5 至 -15 | 重复、恼人的模式 |
| 屏蔽风险 | -10 至 -25 | 冒犯性、攻击性语气 |
| 举报风险 | -15 至 -30 | 违反政策、垃圾信号 |
| 分数 | 等级 |
|---|---|
| 90-100 | S(卓越) |
| 75-89 | A(强劲) |
| 60-74 | B(良好) |
| 45-59 | C(一般) |
| 30-44 | D(低于平均水平) |
| 0-29 | F(潜力低) |
在整个报告中使用表情符号,以获得更好的视觉清晰度和参与度。
使用 TodoWrite 工具显示分析进度,包含以下任务:
分析帖子内容 (in_progress → completed)
计算所有元素的分数 (in_progress → completed)
生成前 5 项优先改进建议 (in_progress → completed)
创建优化版本 (in_progress → completed)
每个步骤完成后立即将任务标记为已完成。
分数 : 🎯 XX/100 (等级: X)
细分表 :
| 类别 | 因子 | 分数 | 最高分 | 评估 |
|----------|--------|-------|-----|------------|
| **💬 核心互动** | | | 60 | |
| | 💭 回复潜力 | X/22 | 22 | [原因] |
| | 🔄 转推潜力 | X/16 | 16 | [原因] |
| | ❤️ 收藏潜力 | X/12 | 12 | [原因] |
| | 💬 引用潜力 | X/10 | 10 | [原因] |
| **⏱️ 扩展互动** | | | 25 | |
| | 👀 停留时间 | X/6 | 6 | [原因] |
| | ⏳ 持续停留时间 | X/4 | 4 | [原因] |
| | 🔗 点击潜力 | X/5 | 5 | [原因] |
| | 🖼️ 图片展开 | X/4 | 4 | [原因] |
| | 🎥 视频观看 | X/3 | 3 | [原因] |
| | 🔍 引用点击 | X/3 | 3 | [原因] |
| **🤝 关系建立** | | | 15 | |
| | 👤 个人资料点击 | X/5 | 5 | [原因] |
| | ➕ 关注潜力 | X/4 | 4 | [原因] |
| | 📤 分享潜力 | X/2 | 2 | [原因] |
| | 💌 通过私信分享 | X/2 | 2 | [原因] |
| | 📋 通过链接分享 | X/2 | 2 | [原因] |
| **⚠️ 负面信号** | | | | |
| | 😐 不感兴趣风险 | -X | 0 至 -15 | [原因] |
| | 🔇 静音风险 | -X | 0 至 -15 | [原因] |
| | 🚫 屏蔽风险 | -X | 0 至 -25 | [原因] |
| | 🚨 举报风险 | -X | 0 至 -30 | [原因] |
| **🏆 总计** | | **XX/100** | | **等级: X** |
3. 📈 前 5 项优先改进建议 : 跨不同类别的具体、可操作建议
* 使用 ✅, 💡, 🎯 等表情符号突出关键改进点
4. ✨ 优化版本 : 应用了改进建议的重写帖子(使用原始语言)
评估标准:
改进策略:
评估标准:
改进策略:
评估标准:
改进策略:
评估标准:
改进策略:
评估标准:
改进策略:
评估标准:
与停留时间的区别:
改进策略:
评估标准:
改进策略:
评估标准:
改进策略:
评估标准:
VQV 资格(条件性):仅当视频似乎 >5 秒(长视频)时才适用满分(3 分)。从以下推断:"完整教程", "深入", "完整指南" 对比 "快速片段", "片段"
改进策略:
评估标准:
改进策略:
评估标准:
改进策略:
评估标准:
改进策略:
评估标准:
改进策略:
评估标准:
改进策略:
评估标准:
改进策略:
算法应用归一化来平衡正面和负面信号:
Final Score = Base Score (0-100) + Penalties (-75 to 0)
Normalized Score = max(0, min(100, Final Score))
扣分上限:
这可以防止单个负面信号完全主导分数,同时保持它们在算法中的重要性。
此技能执行启发式文本分析,而非机器学习预测。
缺失的元数据:
无法访问:
基于文本的启发式方法:
评分方法:
发布前优化以最大化互动潜力,而非事后分析或预测实际互动数字。
检测输入语言。用相同语言回复。保持优化版本为原始语言。
当输入为日语时:
日本語訳(English Original)コアエンゲージメント(Core Engagement)返信潜在力(Reply Potential)リツイート潜在力(Retweet Potential)当输入为英语时:
Core EngagementReply Potential供参考的带表情符号的日语翻译:
有关 X 开源算法(19 元素系统)的完整权重详情,请参阅 references/algorithm-weights.md。
每周安装次数
79
仓库
GitHub 星标数
23
首次出现
2026年1月20日
安全审计
安装于
opencode60
codex60
gemini-cli59
cursor59
claude-code55
github-copilot49
Analyze X posts for viral potential based on the open-source recommendation algorithm (19-element scoring system).
Conversation drivers and strong sharing signals.
| Factor | Max | Scoring Guide |
|---|---|---|
| Reply Potential | 22 | 22: Direct question/debatable claim, 12: Invites response, 4: Statement only |
| Retweet Potential | 16 | 16: Actionable insight/surprising fact, 8: Interesting but niche, 0: No share value |
| Favorite Potential | 12 | 12: Emotionally resonant/personal story, 6: Useful reference, 0: Low appeal |
| Quote Potential | 10 | 10: Strong opinion inviting commentary, 5: Thought-provoking, 0: No quote value |
Media interactions and sustained attention metrics.
| Factor | Max | Scoring Guide |
|---|---|---|
| Dwell Time | 6 | 6: Long-form/detailed content, 3: Medium depth, 0: Skimmable |
| Continuous Dwell Time | 4 | 4: Thread/story arc requiring sustained attention, 2: Medium complexity, 0: Quick read |
| Click Potential | 5 | 5: Compelling link with clear CTA, 3: Link with context, 1: Bare URL, 0: No link |
| Photo Expand Potential | 4 | 4: Multiple images/visual storytelling, 2: Single image reference, 0: No visual content |
| Video View Potential | 3 | 3: Long-form video with hook (>5s), 2: Short clip, 0: No video |
| Quoted Click Potential | 3 | 3: Bold claim inviting verification, 2: Interesting claim, 0: Self-contained |
Author discovery and long-term value signals.
| Factor | Max | Scoring Guide |
|---|---|---|
| Profile Click | 5 | 5: Creates author curiosity, 3: Shows expertise, 0: Generic voice |
| Follow Potential | 4 | 4: Demonstrates ongoing value, 2: Shows potential, 0: One-off content |
| Share Potential | 2 | 2: General sharing value, 1: Limited appeal, 0: No value |
| Share via DM | 2 | 2: Personal/relatable "send to friend" content, 1: Somewhat relatable, 0: Generic |
| Share via Copy Link | 2 | 2: Reference/bookmark worthy, 1: Useful but not evergreen, 0: Ephemeral |
| Risk | Range | Trigger |
|---|---|---|
| Not Interested | -5 to -15 | Clickbait, irrelevant content |
| Mute Risk | -5 to -15 | Repetitive, annoying patterns |
| Block Risk | -10 to -25 | Offensive, aggressive tone |
| Report Risk | -15 to -30 | Policy violations, spam signals |
| Score | Grade |
|---|---|
| 90-100 | S (Exceptional) |
| 75-89 | A (Strong) |
| 60-74 | B (Good) |
| 45-59 | C (Average) |
| 30-44 | D (Below average) |
| 0-29 | F (Low potential) |
Use emojis throughout the report for better visual clarity and engagement.
Use TodoWrite tool to show analysis progress with these tasks:
Analyzing post content (in_progress → completed)
Calculating scores across all elements (in_progress → completed)
Generating top 5 priority improvements (in_progress → completed)
Creating optimized version (in_progress → completed)
Mark each task as completed immediately after finishing that step.
Score : 🎯 XX/100 (Grade: X)
Breakdown Table :
| Category | Factor | Score | Max | Assessment |
|----------|--------|-------|-----|------------|
| **💬 Core Engagement** | | | 60 | |
| | 💭 Reply Potential | X/22 | 22 | [reason] |
| | 🔄 Retweet Potential | X/16 | 16 | [reason] |
| | ❤️ Favorite Potential | X/12 | 12 | [reason] |
| | 💬 Quote Potential | X/10 | 10 | [reason] |
| **⏱️ Extended Engagement** | | | 25 | |
| | 👀 Dwell Time | X/6 | 6 | [reason] |
| | ⏳ Continuous Dwell Time | X/4 | 4 | [reason] |
| | 🔗 Click Potential | X/5 | 5 | [reason] |
| | 🖼️ Photo Expand | X/4 | 4 | [reason] |
| | 🎥 Video View | X/3 | 3 | [reason] |
| | 🔍 Quoted Click | X/3 | 3 | [reason] |
| **🤝 Relationship Building** | | | 15 | |
| | 👤 Profile Click | X/5 | 5 | [reason] |
| | ➕ Follow Potential | X/4 | 4 | [reason] |
| | 📤 Share Potential | X/2 | 2 | [reason] |
| | 💌 Share via DM | X/2 | 2 | [reason] |
| | 📋 Share via Link | X/2 | 2 | [reason] |
| **⚠️ Negative Signals** | | | | |
| | 😐 Not Interested Risk | -X | 0 to -15 | [reason] |
| | 🔇 Mute Risk | -X | 0 to -15 | [reason] |
| | 🚫 Block Risk | -X | 0 to -25 | [reason] |
| | 🚨 Report Risk | -X | 0 to -30 | [reason] |
| **🏆 TOTAL** | | **XX/100** | | **Grade: X** |
3. 📈 Top 5 Priority Improvements : Specific, actionable suggestions across different categories
* Use emojis like ✅, 💡, 🎯 to highlight key improvements
4. ✨ Optimized Version : Rewritten post with improvements applied (in original language)
Evaluation Criteria:
Improvement Strategies:
Evaluation Criteria:
Improvement Strategies:
Evaluation Criteria:
Improvement Strategies:
Evaluation Criteria:
Improvement Strategies:
Evaluation Criteria:
Improvement Strategies:
Evaluation Criteria:
Difference from Dwell Time:
Improvement Strategies:
Evaluation Criteria:
Improvement Strategies:
Evaluation Criteria:
Improvement Strategies:
Evaluation Criteria:
VQV Eligibility (Conditional): Full scoring (3 points) applies only if video appears to be >5 seconds (long-form). Inferred from: "full tutorial", "in-depth", "complete guide" vs "quick clip", "snippet"
Improvement Strategies:
Evaluation Criteria:
Improvement Strategies:
Evaluation Criteria:
Improvement Strategies:
Evaluation Criteria:
Improvement Strategies:
Evaluation Criteria:
Improvement Strategies:
Evaluation Criteria:
Improvement Strategies:
Evaluation Criteria:
Improvement Strategies:
The algorithm applies normalization to balance positive and negative signals:
Final Score = Base Score (0-100) + Penalties (-75 to 0)
Normalized Score = max(0, min(100, Final Score))
Penalty Capping:
This prevents a single negative signal from completely dominating the score while maintaining their importance in the algorithm.
This skill performs heuristic text-based analysis, not ML prediction.
Missing Metadata:
Cannot Access:
Text-Based Heuristics:
Scoring Approach:
Pre-publishing optimization to maximize engagement potential, not post-hoc analytics or prediction of actual engagement numbers.
Detect input language. Respond in same language. Keep optimized version in original language.
When input is in Japanese:
日本語訳(English Original)コアエンゲージメント(Core Engagement)返信潜在力(Reply Potential)リツイート潜在力(Retweet Potential)When input is in English:
Core EngagementReply PotentialJapanese translations with emojis for reference:
See references/algorithm-weights.md for complete weight details from X's open-source algorithm (19-element system).
Weekly Installs
79
Repository
GitHub Stars
23
First Seen
Jan 20, 2026
Security Audits
Gen Agent Trust HubPassSocketPassSnykPass
Installed on
opencode60
codex60
gemini-cli59
cursor59
claude-code55
github-copilot49
DOCX文件创建、编辑与分析完整指南 - 使用docx-js、Pandoc和Python脚本
51,800 周安装