x-content-optimizer
Compare original and translation side by side
🇺🇸
Original
English🇨🇳
Translation
ChineseX Optimizer
X优化器
Audit content against X's recommendation algorithm (Phoenix/Grok-based) and provide optimization suggestions.
基于X的推荐算法(基于Phoenix/Grok)审核内容并提供优化建议。
Workflow
工作流程
Input Content → Algorithm Audit → Issue Report → Fact Check → Suggested Revision → User Approval → Final Output输入内容 → 算法审核 → 问题报告 → 事实核查 → 建议修订版本 → 用户确认 → 最终输出Step 1: Receive Content
步骤1:接收内容
Accept content in any format:
- Direct text paste
- Markdown file
- Multiple tweets (thread)
Identify content type:
- Single Tweet: Under 280 chars, one post
- X Article: Long-form native content
- Thread: Multiple connected tweets
支持接收任意格式的内容:
- 直接粘贴文本
- Markdown文件
- 多条推文(推文串)
识别内容类型:
- 单条推文:少于280字符,单条帖子
- X文章:原生长内容
- 推文串:多条关联推文
Step 2: Algorithm Audit
步骤2:算法审核
Reference: algorithm-rules.md
参考文档:algorithm-rules.md
Audit Categories
审核类别
A. Positive Signal Potential
| Signal | Check |
|---|---|
| Favorite | Emotional resonance or valuable insight? |
| Reply | Discussion hook or question? |
| Repost | Share-worthy content? |
| Dwell | Depth to hold attention? |
| Click | Curiosity-inducing hook? |
B. Negative Signal Risk
| Signal | Check |
|---|---|
| Not Interested | Relevant to target audience? |
| Mute/Block | Respectful, not spammy? |
| Report | Policy compliant? |
C. Learned Penalties
| Factor | Check |
|---|---|
| External Links | Core value IN content, not behind link? |
| Clickbait | Payoff matches promise? |
D. Format & Structure
- Hook strength (first line/50 chars)
- Content completeness
- Engagement driver (CTA/question)
- Readability (line breaks, emphasis)
A. 正向信号潜力
| 信号类型 | 核查要点 |
|---|---|
| 点赞 | 是否具备情感共鸣或有价值的见解? |
| 回复 | 是否包含讨论钩子或问题? |
| 转发 | 是否为值得分享的内容? |
| 停留时长 | 是否有足够深度吸引用户注意力? |
| 点击 | 是否包含引发好奇心的钩子? |
B. 负向信号风险
| 信号类型 | 核查要点 |
|---|---|
| 不感兴趣 | 是否与目标受众相关? |
| 静音/屏蔽 | 是否尊重用户,无垃圾信息? |
| 举报 | 是否符合平台政策? |
C. 已知惩罚项
| 影响因素 | 核查要点 |
|---|---|
| 外部链接 | 核心价值是否在内容内,而非链接背后? |
| 标题党 | 实际内容是否匹配承诺? |
D. 格式与结构
- 钩子吸引力(开头行/前50字符)
- 内容完整性
- 互动驱动因素(行动号召/问题)
- 可读性(换行、强调)
Step 3: Generate Audit Report
步骤3:生成审核报告
Format:
undefined格式:
undefinedAudit Report
审核报告
Score Summary
评分摘要
- Positive Signal Potential: [HIGH/MEDIUM/LOW]
- Negative Signal Risk: [HIGH/MEDIUM/LOW]
- Overall Algorithm Fit: [EXCELLENT/GOOD/NEEDS WORK/POOR]
- 正向信号潜力:[高/中/低]
- 负向信号风险:[高/中/低]
- 整体算法适配度:[优秀/良好/需改进/较差]
Issues Found
发现的问题
-
- Impact: [Which signal affected]
- Fix: [Specific suggestion]
-
...
-
[问题描述]:[解释说明]
- 影响:[涉及的信号类型]
- 修复建议:[具体方案]
-
[问题描述]:[解释说明] ...
Strengths
优势
- [What works well]
undefined- [表现良好的方面]
undefinedStep 4: Fact Check
步骤4:事实核查
CRITICAL: Before adding or suggesting any factual information (numbers, dates, statistics, claims about products/companies), you MUST:
- Identify factual claims in the content that need verification
- Search and verify using WebSearch tool
- Only include verified facts in the optimized version
- Remove or flag unverifiable claims - never fabricate data
Examples requiring verification:
- Product launch dates ("X was released in...")
- Statistics ("X% of users...")
- Company announcements ("Company just launched...")
- Performance metrics ("reduces time by X%")
If no verifiable source exists, either:
- Remove the claim entirely
- Replace with qualitative language ("significantly improves" instead of fake percentages)
- Ask user if they have a source
重要提示:在添加或建议任何事实性信息(数字、日期、统计数据、关于产品/公司的声明)之前,必须执行以下操作:
- 识别内容中需要验证的事实声明
- 使用WebSearch工具进行搜索和验证
- 仅在优化版本中包含已验证的事实
- 移除或标记无法验证的声明 - 切勿编造数据
需要核查的示例:
- 产品发布日期(如“X发布于……”)
- 统计数据(如“X%的用户……”)
- 公司公告(如“公司刚刚发布……”)
- 性能指标(如“将时间减少X%”)
如果没有可验证的来源,可选择以下方式之一:
- 完全移除该声明
- 替换为定性描述(如用“显著提升”替代虚假百分比)
- 询问用户是否有相关来源
Step 5: Generate Optimized Version
步骤5:生成优化版本
Provide complete rewritten version addressing all issues.
Format:
undefined提供解决所有问题的完整重写版本。
格式:
undefinedOptimized Version
优化版本
[Full rewritten content]
[完整重写内容]
Changes Made
所作修改
- [Change]: [Why it improves algorithm score]
- [Change]: [Why it improves algorithm score]
undefined- [修改内容]:[为何能提升算法评分]
- [修改内容]:[为何能提升算法评分]
undefinedStep 6: Offer One-Click Apply
步骤6:提供一键应用选项
If content is from a file:
Would you like me to apply these changes to the file?If direct text:
Here's your optimized content ready to copy.如果内容来自文件:
是否需要我将这些修改应用到文件中?如果是直接文本:
以下是可供复制的优化后内容。Content-Specific Guidelines
特定内容类型指南
Single Tweet
单条推文
- Hook in first 50 chars (preview visibility)
- Core value delivered completely
- End with engagement driver
- External links: provide context first
- 前50字符设置钩子(预览可见区域)
- 完整传递核心价值
- 结尾添加互动驱动因素
- 外部链接:先提供上下文
X Article
X文章
- Title: curiosity + specific value
- Opening: validate the click
- Body: structured sections
- Closing: summary + CTA
- Advantage: keeps users on platform (dwell time)
- 标题:兼具好奇心与明确价值
- 开头:匹配用户点击预期
- 正文:分结构化章节
- 结尾:总结+行动号召
- 优势:提升用户平台停留时长
Thread
推文串
- Tweet 1: Standalone hook (must work alone)
- Tweet 2-3: Engagement point (question)
- Middle: Value delivery
- Final: CTA (repost, follow)
- Each tweet: Complete and independent
- 第1条:独立钩子(可单独成立)
- 第2-3条:设置互动点(问题)
- 中间部分:传递价值
- 最后一条:行动号召(转发、关注)
- 每条推文:完整且独立
Quick Reference
快速参考
High-Impact Improvements
高影响力优化措施
- Add question/discussion hook → ↑ Reply
- Add quotable statement → ↑ Repost
- Strengthen opening hook → ↑ Click, Dwell
- Remove/contextualize external links → ↑ Dwell Time
- Add specific data/examples → ↑ Credibility, Share
- 添加问题/讨论钩子 → ↑ 回复量
- 添加可引用语句 → ↑ 转发量
- 强化开头钩子 → ↑ 点击量、停留时长
- 移除/添加外部链接上下文 → ↑ 停留时长
- 添加具体数据/示例 → ↑ 可信度、分享量
Common Issues
常见问题
| Issue | Impact | Fix |
|---|---|---|
| Weak hook | Low click/dwell | Rewrite first line |
| Link-only value | User leaves platform | Add value IN content |
| No engagement driver | Low reply | Add question/CTA |
| Wall of text | Low dwell | Add line breaks |
| Off-topic | "Not interested" signal | Clarify audience fit |
| 问题 | 影响 | 修复方案 |
|---|---|---|
| 钩子吸引力弱 | 点击量/停留时长低 | 重写开头 |
| 价值仅存在于链接中 | 用户离开平台 | 在内容内添加价值 |
| 无互动驱动因素 | 回复量低 | 添加问题/行动号召 |
| 大段无换行文本 | 停留时长低 | 添加换行 |
| 偏离主题 | 触发“不感兴趣”信号 | 明确受众适配性 |