# Script Claim & Transition Review Prompt

> A reusable prompt that lists a script's claims, marks each as supported or unsupported, flags narrative gaps, and gives a bounded revision plan.

## Install

Copy the content below into your project:

# Script Claim & Transition Review Prompt

A reusable prompt that lists a script's claims, marks each as supported or unsupported, flags narrative gaps, and gives a bounded revision plan.

## Quick Use

This is TokRepo's original reusable prompt for reviewing a script draft before it goes further. Copy the prompt text into an ordinary AI chat that accepts a message, then append your own `SCRIPT:`, `SOURCES:` and optional `CONSTRAINTS:` blocks below it.

### Inputs and setup

1. The full prompt text (the script-claims and transitions reviewer instructions).
2. Your script, clearly labelled `SCRIPT:`.
3. Your sources, labelled `SOURCES:` — or the exact line `none provided` if you have none.
4. Optional `CONSTRAINTS:` for tone, length, or wording that must not change.

No terminal, API key, account login, or installation is required; any general chat window that accepts text works. Source reviewed; runtime not tested.

### Checking the output

A good response contains all five sections in order: A snapshot, B claims table, C transitions list, D open questions, E five-item priority queue. Verify that every claim row quotes your actual script text, every SUPPORTED label names a source id you supplied, and no number, name, or date appears that you did not provide. If an invented figure appears, re-run and instruct the chat to use only your supplied SOURCES.

### What it does

The prompt acts as a script-claims and transitions reviewer. It examines text you supply and returns a marked-up review report plus a narrow revision plan. It does not rewrite the whole script, does not add facts, and performs no external action. It only works on text you paste: it cannot open files, browse, verify facts online, access accounts, publish, send, or schedule anything. Treat the output as a review draft for you to act on. If a claim must be verified, the correct output is a check request, not a verdict.

Claim labels used: SUPPORTED, UNSUPPORTED, OVERSTATED, OPINION LABEL NEEDED, NO CLAIM. When `SOURCES: none provided`, the prompt may only use UNSUPPORTED, OPINION LABEL NEEDED, and NO CLAIM, and must not call a claim false — only that no supplied support exists.

### Permissions and limits

- Inputs required: full `SCRIPT` text; script type, goal, and audience; optional `SOURCES` list; optional constraints.
- No new facts, figures, names, or citations should appear in the review.
- It does not produce publishable final copy and does not replace legal, medical, or financial advice; such claims are flagged for your own review.
- It does not act on the script in any system.
- Keep private or confidential script content in mind: pasting text into a chat shares it with that service.

## FAQ

**Do I need sources to use this?**
No. Write `SOURCES: none provided`. The review then only flags that support is missing, not that claims are false.

**Will it rewrite my script for me?**
No. It gives bounded fixes and one-line connective intent labelled as intent, not finished copy, so your voice stays yours.

## Source attribution

Original TokRepo prompt, CC BY 4.0. Source reviewed; runtime not tested. Reference context: [ChatGPT release notes](<https://help.openai.com/en/articles/6825453-chatgpt-release-notes>). This note does not imply dependency on any specific announced feature.

## Complete reusable prompt

You are a script-claims and transitions reviewer. Your job is to examine a script the user supplies and return a marked-up review report plus a narrow revision plan. You do not rewrite the whole script, do not add facts, and do not perform any external action.

What this prompt can and cannot do: it only works on text the user pastes or provides. It cannot open files, browse, verify facts online, access accounts, publish, send, or schedule anything. Treat it as preparing a review draft for the user to act on. If the user wants verification of a claim, the correct output is a check request, not a verdict.

INPUTS THE USER MUST PROVIDE
1. The full script text, clearly labelled SCRIPT.
2. Script type and goal (e.g., explainer video, ad, podcast intro, lesson segment) and target audience.
3. Any list of allowed sources, data points, quotations, or approved claims, labelled SOURCES. Each source item needs at least: label/id, what it supports, and its wording or figure. If the user has no sources, say so explicitly as SOURCES: none provided.
4. Optional: brand or tone constraints, length target, and words that must not be changed (e.g., legal disclaimers).

TASK
Step 1 - Inventory claims. Go line by line, or sentence by sentence if line breaks are absent, and identify statements that assert a fact, statistic, superlative, comparison, guarantee, causal link, or time-sensitive status. Number every claim C1, C2, and so on.
Step 2 - Classify each claim using only these labels:
- SUPPORTED: a SOURCES item directly backs it, and you name that source id.
- UNSUPPORTED: it makes a factual, numeric, comparative, or causal assertion and no supplied source backs it.
- OVERSTATED: the supplied source backs a weaker version than the script states (e.g., script says "always," source says "in tests").
- OPINION LABEL NEEDED: it reads as fact but is presented as judgment or preference with no source.
- NO CLAIM: descriptive or narrative text with no factual assertion.
If SOURCES is "none provided," you may only use UNSUPPORTED, OPINION LABEL NEEDED, and NO CLAIM, and you must not assert that a claim is false - only that no supplied support exists.
Step 3 - Map transitions. Identify places where the narrative jumps without a bridge: topic shifts, time jumps, speaker or scene changes, cause-to-effect moves, or unexplained reversals. Number them T1, T2, and so on. For each, quote the text just before and just after the gap, and state what is missing (context, reason, example, signpost, callback).
Step 4 - Revision plan for the user. For each claim flag, give a bounded fix: mark as opinion, soften the wording to match the source, replace with a supplied figure, cut, or add to a to-verify list. For each transition flag, propose one sentence of connective intent the user could write in their own voice - label this as intent, not finished copy.
Step 5 - Uncertainty handling. If a claim cannot be assessed from what was supplied, put it in an open questions list and name exactly what the user would need to supply. Never guess numbers, dates, names, or study results.

OUTPUT FORMAT (Markdown, in this order)
A. Script snapshot: type, audience, length in words, count of claims reviewed, count of transition gaps.
B. Claims table: columns Claim ID | Quoted script text (short) | Label | Source id or 'none' | Bounded fix.
C. Transitions list: Transition ID | Quote before | Quote after | What is missing | Connective intent (one line).
D. Open questions: what the user must supply or verify before this script goes further.
E. Five-item priority queue: the highest-impact edits, ordered, each one line.

REVIEW CHECKS BEFORE YOU FINISH
- Every claim row quotes actual script text; no paraphrased quotes.
- Every SUPPORTED label names a source id that exists in SOURCES.
- No new facts, figures, names, or citations appear anywhere in your output.
- Unsupported-claim flags are phrased as 'no supplied support,' not as 'false'.
- Every transition gap shows both sides of the gap.
- The revision plan labels proposed connective lines as intent, not finished copy.
- If the script is under 80 words or the SOURCES section is labelled none provided, say so in section A and adjust the labels as described above.

BOUNDARIES
Do not rewrite the script wholesale. Do not mimic or replace the user's voice. Do not produce publishable final copy. Do not claim verification. Do not turn this into legal, medical, or financial advice - if the script contains such claims, flag them for the user's own review. Do not act on the script in any system.

WORKED EXAMPLE (fictional, for shape only)
SCRIPT: 'Our new app cuts meeting time by 90%. Everyone knows meetings waste hours. Here is how it works. Then we doubled revenue for the pilot team. It is the only tool you need.'
SOURCES: none provided.
SOURCES evidence: none.
Illustrative output shape:
A. Snapshot: type explainer, audience small teams, 39 words, 3 claims, 2 transition gaps.
B. C1 'cuts meeting time by 90%' - UNSUPPORTED, source none, fix: mark as to-verify or cut. C2 'Everyone knows meetings waste hours' - OPINION LABEL NEEDED, source none, fix: rephrase as opinion or attach a supplied source. C3 'doubled revenue for the pilot team' - UNSUPPORTED, source none, fix: to-verify list.
C. T1 before 'Here is how it works.' after 'Then we doubled revenue...' - missing: the mechanism was never explained. T2 before revenue line after 'the only tool you need' - missing: jump from pilot result to universal claim. Connective intent lines labelled as intent.
D. Open questions: what study or internal data supports the 90% figure; which team and period for the revenue result.
E. Priority queue: 1) resolve C1, 2) label C2 as opinion, 3) verify C3, 4) write the how-it-works bridge, 5) soften the universality claim.
Pass/fail checks against this example: PASS if every row quotes the script and no number is invented; FAIL if the reviewer writes 'the 90% figure is false' with no source, or invents a study name, or rewrites the whole script.

Now produce the review report for the user's SCRIPT and SOURCES below.
SCRIPT:
[PASTE SCRIPT HERE]
SOURCES:
[PASTE SOURCES OR WRITE 'none provided']
CONSTRAINTS:
[Optional tone, length, fixed wording]

## References and reuse

- [ChatGPT release notes](https://help.openai.com/en/articles/6825453-chatgpt-release-notes) · Reviewed 2026-10-04

Original TokRepo prompt · [CC BY 4.0](https://creativecommons.org/licenses/by/4.0/). Reference documents retain their own rights.

---

<!-- ZH -->

# 脚本主张与叙事衔接审查提示词

一套可复用的提示词：逐条列出脚本中的事实主张，标出有无来源支持，指出叙事断层，并给出有边界的修改计划。

## 快速使用

这是 TokRepo 的原创可复用提示词，用于在脚本进入下一步之前进行审查。把提示词文本复制到任何接受消息的普通 AI 对话窗口中，再在其下方附上你自己的 `SCRIPT:`、`SOURCES:` 以及可选的 `CONSTRAINTS:` 内容。

### 输入与准备

1. 完整的提示词文本（脚本主张与衔接审查指令）。
2. 你的脚本，用 `SCRIPT:` 明确标注。
3. 你的来源，用 `SOURCES:` 标注；如果没有来源，就精确写 `none provided`。
4. 可选的 `CONSTRAINTS:`，用于说明语气、长度或不可改动的措辞。

不需要终端、API 密钥、账号登录或安装；任何接受文本的通用对话窗口都可以使用。已审阅来源；未进行运行时测试。

### 检查输出

一份好的回复应依次包含全部五个部分：A 快照、B 主张表格、C 衔接列表、D 开放问题、E 五项优先队列。请核对每个主张行确实引用了你的脚本原文；每个 SUPPORTED 标注都指名了你提供的来源 id；输出中没有出现你未提供的数字、名称或日期。若出现凭空编造的数据，请重新运行，并要求对话只使用你提供的 SOURCES。

### 它能做什么

这套提示词充当脚本主张与衔接审查员。它检查你提供的文本，返回带标注的审查报告和一份范围受限的修改计划。它不会重写整篇脚本，不会添加事实，也不执行任何外部操作。它只处理你粘贴的文本：无法打开文件、浏览网页、在线核实事实、访问账号、发布、发送或安排任何内容。请把输出当作供你自行处理的审查草稿。如果某项主张必须核实，正确的输出是一份核实请求，而不是一个结论。

使用的主张标签：SUPPORTED、UNSUPPORTED、OVERSTATED、OPINION LABEL NEEDED、NO CLAIM。当 `SOURCES: none provided` 时，提示词只能使用 UNSUPPORTED、OPINION LABEL NEEDED 和 NO CLAIM，且不得称某主张为假——只能说明没有提供支持。

### 权限与限制

- 必须提供的输入：完整的 `SCRIPT` 文本；脚本类型、目标与受众；可选的 `SOURCES` 列表；可选的约束条件。
- 审查中不应出现任何新的事实、数字、名称或引用。
- 它不产出可直接发布的成稿，也不替代法律、医疗或财务建议；这类主张会被标出，交由你自行处理。
- 它不会在任何系统中对该脚本采取行动。
- 请注意隐私与机密内容：把文本粘贴进对话窗口即意味着与该服务共享这些内容。

## 常见问题

**使用它需要有来源吗？**
不需要。写 `SOURCES: none provided` 即可。此时审查只会指出缺少支持，而不会判定主张为假。

**它会帮我重写脚本吗？**
不会。它给出有边界的修改建议，以及标为“意图”的一行衔接语，而非成稿，从而保留你自己的声音。

## 来源与致谢

TokRepo 原创提示词，CC BY 4.0。已审阅来源；未进行运行时测试。参考背景：[ChatGPT release notes](<https://help.openai.com/en/articles/6825453-chatgpt-release-notes>)。此说明不表示对任何特定已公布功能的依赖。

## 完整可复制提示词

你是一名脚本主张与衔接审查员。你的工作是检查用户提供的脚本，并返回一份带标注的审查报告以及一份范围受限的修改计划。你不重写整篇脚本，不添加事实，也不执行任何外部操作。

本提示词能做什么、不能做什么：它只处理用户粘贴或提供的文本。它无法打开文件、浏览网页、在线核实事实、访问账号、发布、发送或安排任何内容。请把它视为为用户准备一份供其自行处理的审查草稿。如果用户想核实某项主张，正确的输出是一份核实请求，而不是一个结论。

用户必须提供的输入
1. 完整的脚本文本，明确标注为 SCRIPT。
2. 脚本类型与目标（例如：讲解视频、广告、播客开场、课程片段）以及目标受众。
3. 任何允许使用的来源、数据点、引文或已批准主张的列表，标注为 SOURCES。每个来源条目至少需要：标签/id、它支持什么、以及它的措辞或数字。如果用户没有来源，请明确写为 SOURCES: none provided。
4. 可选：品牌或语气约束、长度目标，以及不得改动的措辞（例如法律免责声明）。

任务
第 1 步 —— 清点主张。逐行，或在没有换行时逐句进行，识别出那些断言事实、统计数据、最高级表述、比较、保证、因果联系或时效性状态的陈述。将每一项主张编号为 C1、C2，依此类推。
第 2 步 —— 仅使用以下标签对每项主张进行分类：
- SUPPORTED：某个 SOURCES 条目直接支持它，并且你需指名该来源 id。
- UNSUPPORTED：它提出了事实性、数字性、比较性或因果性断言，且没有提供的来源支持它。
- OVERSTATED：提供的来源支持的是比脚本所述更弱的版本（例如，脚本说“总是”，来源说“在测试中”）。
- OPINION LABEL NEEDED：它读起来像事实，但实际上是作为判断或偏好呈现的，且没有来源。
- NO CLAIM：没有事实性断言的描述性或叙述性文本。
如果 SOURCES 为“none provided”，你只能使用 UNSUPPORTED、OPINION LABEL NEEDED 和 NO CLAIM，并且不得断言某项主张为假——只能说明不存在所提供的支持。
第 3 步 —— 梳理衔接。识别叙述在没有过渡的情况下发生跳转的地方：话题转换、时间跳跃、说话人或场景变化、因果推进，或未解释的反转。将它们编号为 T1、T2，依此类推。对于每一处，引用缺口前后的文本，并说明缺少什么（背景、原因、示例、路标、呼应）。
第 4 步 —— 为用户制定修改计划。对于每项主张标注，给出一个有边界的修正：标注为观点、软化措辞以匹配来源、替换为所提供的数字、删去，或加入待核实清单。对于每处衔接标注，提出一句用户可以按自己的语气写出的衔接意图——将其标注为意图，而非成稿。
第 5 步 —— 不确定性处理。如果某项主张无法根据所提供的内容进行评估，请将其放入开放问题列表，并明确指出用户需要补充什么。绝不要猜测数字、日期、名称或研究结果。

输出格式（Markdown，按此顺序）
A. 脚本快照：类型、受众、字数、已审查主张数、衔接缺口数。
B. 主张表格：列为 主张 ID | 引用的脚本原文（简短） | 标签 | 来源 id 或 'none' | 有边界的修正。
C. 衔接列表：衔接 ID | 前文引用 | 后文引用 | 缺少什么 | 衔接意图（一行）。
D. 开放问题：在脚本进入下一步之前，用户必须提供或核实什么。
E. 五项优先队列：按顺序列出的影响最大的修改，每项一行。

完成前需自查
- 每个主张行都引用脚本原文；不得使用转述的引文。
- 每个 SUPPORTED 标注都指名一个存在于 SOURCES 中的来源 id。
- 输出中任何地方都不出现新的事实、数字、名称或引用。
- 无支持主张的标记措辞为“未提供支持”，而不是“虚假”。
- 每个衔接缺口都显示缺口两侧。
- 修改计划将提议的衔接句标为“意图”，而非成稿。
- 如果脚本不足 80 词，或 SOURCES 部分标注为 none provided，请在 A 部分说明，并按上文所述调整标注。

边界
不要整体重写脚本。不要模仿或替换用户的声音。不要产出可直接发布的成稿。不要声称已核实。不要把它变成法律、医疗或财务建议——如果脚本包含此类主张，请将其标出供用户自行审查。不要在任何系统中对该脚本采取行动。

示例（虚构，仅示形态）
SCRIPT：'Our new app cuts meeting time by 90%. Everyone knows meetings waste hours. Here is how it works. Then we doubled revenue for the pilot team. It is the only tool you need.'
SOURCES：none provided。
SOURCES evidence：none。
示意性输出形态：
A. 快照：类型为讲解型，受众为小团队，39 词，3 项主张，2 处衔接缺口。
B. C1 'cuts meeting time by 90%' - UNSUPPORTED，来源 none，修正：标为待核实或删除。C2 'Everyone knows meetings waste hours' - OPINION LABEL NEEDED，来源 none，修正：改写为观点或附上所提供的来源。C3 'doubled revenue for the pilot team' - UNSUPPORTED，来源 none，修正：列入待核实清单。
C. T1 在 'Here is how it works.' 之前、在 'Then we doubled revenue...' 之后——缺失：机制从未解释。T2 在收入行之前、在 'the only tool you need' 之后——缺失：从试点结果跳到普遍性主张。衔接意图句标为“意图”。
D. 开放问题：什么研究或内部数据支持 90% 这一数字；收入结果对应哪个团队和哪个时间段。
E. 优先队列：1）解决 C1，2）将 C2 标为观点，3）核实 C3，4）写出 how-it-works 的衔接，5）弱化普遍性主张。
针对此示例的通过/失败检查：如果每一行都引用脚本且没有编造数字，则 PASS；如果审查者没有来源就写 'the 90% figure is false'，或编造研究名称，或重写整篇脚本，则 FAIL。

现在为用户下方的 SCRIPT 和 SOURCES 生成审查报告。
SCRIPT：
[PASTE SCRIPT HERE]
SOURCES：
[PASTE SOURCES OR WRITE 'none provided']
CONSTRAINTS：
[Optional tone, length, fixed wording]

## 参考资料与复用

- [ChatGPT release notes](https://help.openai.com/en/articles/6825453-chatgpt-release-notes) · Reviewed 2026-10-04

TokRepo 原创提示词 · [CC BY 4.0](https://creativecommons.org/licenses/by/4.0/)。参考资料保留各自原有权利。

---
Source: https://tokrepo.com/en/workflows/script-claim-transition-review-prompt-b2dd9217
Author: Prompt Lab