tweet-draft-reviewer

Compare original and translation side by side

🇺🇸

Original

English

🇨🇳

Translation

Chinese

Tweet Draft Reviewer

推文草稿审核工具

Paste a tweet draft and get a score out of 10, a rule-by-rule breakdown, and a rewrite if the score is below 7. Takes 30 seconds. Saves you from posting something that sounds like a chatbot wrote it.

Built on 8 voice rules distilled from real content analysis — what separates high-engagement tweets from the ones that get skimmed.

粘贴推文草稿，即可获得满分10分的评分、逐条规则的合规性拆解，如果得分低于7分还会自动生成改写版本。整个过程仅需30秒，帮你避免发布听起来像聊天机器人写的内容。

本工具基于从真实内容分析中提炼出的8条语气规则制定——这些规则正是高互动推文和被用户一划而过的推文的核心区别。

How to Use

使用指南

Single draft:

Review this tweet draft: [paste tweet here]

Batch scan:

Review all tweet drafts in my content/tweet-drafts/ folder.

单篇草稿审核：

Review this tweet draft: [paste tweet here]

批量扫描审核：

Review all tweet drafts in my content/tweet-drafts/ folder.

Skill Instructions (for Claude Code)

技能说明（针对Claude Code）

When this skill is invoked, follow these phases exactly.

调用本技能时，请严格遵循以下阶段流程：

PHASE 1: INTAKE

阶段1：信息录入

Determine input mode:

Mode A — Direct paste: User provided draft text inline. Proceed to PHASE 2 with that text.

Mode B — Folder scan: User asked to review drafts folder. Run:

bash

VAULT="${VAULT_PATH:-$(pwd)}"
find "$VAULT/content/tweet-drafts" -name "*.md" 2>/dev/null | while read f; do
  if ! grep -q 'reviewed: true' "$f" 2>/dev/null; then
    echo "UNREVIEWED:$f"
  fi
done

If no vault path was given and no

content/tweet-drafts/

exists in the current directory, ask:

Where is your tweet drafts folder? (full path, e.g. /root/obsidian-vault/content/tweet-drafts)

Mode C — Ambiguous: No draft provided and no folder context. Ask:

Paste your tweet draft here, or tell me the path to your tweet-drafts folder and I'll scan it.

判断输入模式：

模式A——直接粘贴： 用户直接提供了草稿文本，携带该文本进入阶段2。

模式B——文件夹扫描： 用户要求审核草稿文件夹，执行以下命令：

bash

VAULT="${VAULT_PATH:-$(pwd)}"
find "$VAULT/content/tweet-drafts" -name "*.md" 2>/dev/null | while read f; do
  if ! grep -q 'reviewed: true' "$f" 2>/dev/null; then
    echo "UNREVIEWED:$f"
  fi
done

如果未提供知识库路径，且当前目录下不存在

content/tweet-drafts/

，则询问：

Where is your tweet drafts folder? (full path, e.g. /root/obsidian-vault/content/tweet-drafts)

模式C——输入模糊： 未提供草稿，也没有文件夹上下文信息，询问：

Paste your tweet draft here, or tell me the path to your tweet-drafts folder and I'll scan it.

PHASE 2: ANALYZE

阶段2：分析审核

Apply all 8 rules to the draft. For each rule, record ✅ PASS or ❌ FAIL with a one-line reason.

对草稿应用全部8条规则，每条规则标注✅通过或❌未通过，并附上一行原因说明。

The 8 Rules

8条审核规则

Rule 1: No "I" opener

FAIL: First word is exactly
```
I
```
(standalone — not "In", "It", "If")
PASS: Anything else

Rule 2: Strong opener

FAIL: First sentence ends with
```
?
```
OR starts with "Have you", "Do you", "Are you", "What if", "What would"
PASS: Declarative statement, specific number/fact, named scenario, or emotional setup

Rule 3: No AI tells

FAIL: Contains any of:

delve

certainly

game-changing

game changer

it's worth noting

invaluable

unleash

revolutionize

transformative

PASS: None of those words detected

Rule 4: No generic closers

FAIL: Ends with (or contains near the end):

what do you think

drop a comment

thoughts?

let me know in the comments

agree?

sound familiar?

PASS: Ends with a statement, directive, punchline, or thread hook

Rule 5: Corey Test (specificity)

FAIL: Uses vague language without specifics — "it changed how I work", "massive results", "so much better" — no numbers, names, or concrete outcomes
PASS: Contains at least one specific: a number, timeframe, named tool, or concrete result

Rule 6: Character count

PASS: 280 characters or fewer
THREAD PASS: Over 280 chars BUT sections are numbered (1/, 2/, 3/) or clearly separated with line breaks — count as PASS
FAIL: Over 280 chars with no thread formatting

Rule 7: Single point

FAIL: Makes 3+ distinct unrelated claims with no clear through-line
PASS: One core idea, even if supported by 2–3 details

Rule 8: Punchy rhythm

FAIL: Any sentence over 20 words OR preamble like "I've been thinking a lot about..." / "Something I've noticed recently is..."
PASS: Short sentences, no preamble, gets to the point by line 2 at latest

规则1：禁止以"I"开头

未通过：第一个单词是独立的
```
I
```
（不包括"In"、"It"、"If"等开头的单词）
通过：其他所有情况

规则2：开头有吸引力

未通过：第一句话以
```
?
```
结尾，或者以"Have you"、"Do you"、"Are you"、"What if"、"What would"开头
通过：陈述性语句、具体数字/事实、明确场景、或者情绪铺垫类开头

规则3：无AI常用话术

未通过：包含以下任意词汇：

delve

、

certainly

、

game-changing

、

game changer

、

it's worth noting

、

invaluable

、

unleash

、

revolutionize

、

transformative

通过：未检测到上述词汇

规则4：无通用结尾

未通过：以（或接近结尾处包含）以下内容：

what do you think

、

drop a comment

、

thoughts?

、

let me know in the comments

、

agree?

、

sound familiar?

通过：以陈述、指令、梗点、或者thread引流内容结尾

规则5：Corey测试（具体性要求）

未通过：使用模糊无具体内容的表述，比如"it changed how I work"、"massive results"、"so much better"，没有数字、名称或者具体结果
通过：包含至少一个具体信息：数字、时间范围、指定工具、或者具体结果

规则6：字符数要求

通过：字符数≤280
Thread通过：字符数>280，但内容有编号（1/、2/、3/）或者用换行明确分隔，视为通过
未通过：字符数>280，且无thread格式排版

规则7：单一核心观点

未通过：提出3个及以上完全无关的主张，没有清晰的主线
通过：只有一个核心观点，哪怕有2-3个辅助细节支撑

规则8：节奏明快

未通过：任何句子超过20个单词，或者有类似"I've been thinking a lot about..." / "Something I've noticed recently is..."这类铺垫性开头
通过：短句，无铺垫，最晚在第二行就切入核心内容

PHASE 3: OUTPUT

阶段3：结果输出

Print this exact format:

TWEET REVIEW
────────────

Score: X/10

Rule-by-Rule:
1. ✅/❌ No "I" opener — [reason]
2. ✅/❌ Strong opener — [reason]
3. ✅/❌ No AI tells — [reason]
4. ✅/❌ No generic closers — [reason]
5. ✅/❌ Corey Test — [reason]
6. ✅/❌ Character count — [reason + actual count]
7. ✅/❌ Single point — [reason]
8. ✅/❌ Punchy rhythm — [reason]

────────────

Scoring table (passes → score):

Passes	Score
8	10/10
7	9/10
6	8/10
5	6/10
4	5/10
3	4/10
2	3/10
1	1/10
0	0/10

If score ≥ 7:

→ Ready to post. Use Typefully or your scheduler to queue it.

If score < 7 — add a rewrite:

Suggested Rewrite:

[rewritten tweet that fixes all failing rules]

严格按照以下格式输出：

TWEET REVIEW
────────────

Score: X/10

Rule-by-Rule:
1. ✅/❌ No "I" opener — [reason]
2. ✅/❌ Strong opener — [reason]
3. ✅/❌ No AI tells — [reason]
4. ✅/❌ No generic closers — [reason]
5. ✅/❌ Corey Test — [reason]
6. ✅/❌ Character count — [reason + actual count]
7. ✅/❌ Single point — [reason]
8. ✅/❌ Punchy rhythm — [reason]

────────────

评分表（通过数→对应得分）：

通过数	得分
8	10/10
7	9/10
6	8/10
5	6/10
4	5/10
3	4/10
2	3/10
1	1/10
0	0/10

如果得分≥7：

→ Ready to post. Use Typefully or your scheduler to queue it.

如果得分<7——补充改写版本：

Suggested Rewrite:

[rewritten tweet that fixes all failing rules]

PHASE 4: SELF-CRITIQUE

阶段4：自我校验

Before delivering the output, check:

All 8 rules evaluated — Count the rule lines in your output. There must be exactly 8. If any are missing, add them.
Score matches pass count — Count the ✅ marks. Verify the score matches the table above. Correct it if not.
Rewrite quality — If a rewrite was provided, check it against all 8 rules mentally. Does it pass the ones the original failed? If the rewrite would score below 7 itself, rewrite it again.
Reason quality — Each rule result must have a specific reason, not a generic one. "Too vague" is not enough — say what specifically is vague.

Fix anything that fails before delivering.

输出结果前，请检查：

全部8条规则都已评估 —— 数一下输出里的规则条目，必须刚好8条，有遗漏请补充。
得分与通过数匹配 —— 数一下✅的数量，验证得分是否符合上面的评分表，不匹配请修正。
改写质量合格 —— 如果提供了改写版本，对照8条规则检查，是否修复了原草稿未通过的所有问题？如果改写版本本身得分低于7，请重新改写。
原因说明具体 —— 每条规则的结果必须有具体原因，不能太笼统。比如只说"太模糊"不够，要说明具体哪里模糊。

所有不符合要求的内容修正后再输出。

Example Review

审核示例

Input:

I've been thinking a lot about how AI is really changing the way founders 
approach content creation and productivity, and I think it's worth noting 
that the teams who figure out async AI workflows are going to have a 
massive advantage. What do you think about this?

Output:

TWEET REVIEW
────────────

Score: 2/10

Rule-by-Rule:
1. ❌ No "I" opener — Starts with "I've"
2. ❌ Strong opener — Slow setup, no hook, no specific fact
3. ❌ No AI tells — Contains "it's worth noting"
4. ❌ No generic closers — Ends with "What do you think about this?"
5. ❌ Corey Test — "massive advantage" is vague, no numbers or concrete outcome
6. ✅ Character count — 248 chars
7. ✅ Single point — Focused on async AI workflows
8. ❌ Punchy rhythm — Run-on sentence, preamble opener

────────────

Suggested Rewrite:

The founders winning right now aren't working harder.

They have agents running at 2am. Content drafted. Research done.
Queue processed.

By 7am they're reviewing output, not creating it.

Async AI ops is the new early morning routine.

输入：

I've been thinking a lot about how AI is really changing the way founders 
approach content creation and productivity, and I think it's worth noting 
that the teams who figure out async AI workflows are going to have a 
massive advantage. What do you think about this?

输出：

TWEET REVIEW
────────────

Score: 2/10

Rule-by-Rule:
1. ❌ No "I" opener — Starts with "I've"
2. ❌ Strong opener — Slow setup, no hook, no specific fact
3. ❌ No AI tells — Contains "it's worth noting"
4. ❌ No generic closers — Ends with "What do you think about this?"
5. ❌ Corey Test — "massive advantage" is vague, no numbers or concrete outcome
6. ✅ Character count — 248 chars
7. ✅ Single point — Focused on async AI workflows
8. ❌ Punchy rhythm — Run-on sentence, preamble opener

────────────

Suggested Rewrite:

The founders winning right now aren't working harder.

They have agents running at 2am. Content drafted. Research done.
Queue processed.

By 7am they're reviewing output, not creating it.

Async AI ops is the new early morning routine.

Batch Mode Output

批量模式输出

When scanning a folder, output one review block per file:

📄 content/tweet-drafts/linkedin-ai-post.md
[full review block]

📄 content/tweet-drafts/founder-ops.md
[full review block]

────────────
BATCH SUMMARY
Reviewed: 4 drafts
Ready to post (≥7): 2
Need rewrite (<7): 2

扫描文件夹时，每个文件对应输出一个审核块：

📄 content/tweet-drafts/linkedin-ai-post.md
[full review block]

📄 content/tweet-drafts/founder-ops.md
[full review block]

────────────
BATCH SUMMARY
Reviewed: 4 drafts
Ready to post (≥7): 2
Need rewrite (<7): 2

Requirements

使用要求

Claude Code with bash tool access (for folder scan mode)
No external APIs — pure LLM reasoning for the review
Tweet drafts folder at
```
content/tweet-drafts/
```
(optional — direct paste always works)
Files in the drafts folder are marked
```
reviewed: true
```
to skip them in future scans

具备bash工具访问权限的Claude Code（用于文件夹扫描模式）
无外部API依赖——审核完全基于LLM推理完成
推文草稿文件夹路径为
```
content/tweet-drafts/
```
（可选——直接粘贴草稿始终可用）
草稿文件夹中的文件标注
```
reviewed: true
```
后，后续扫描会自动跳过