show-dont-tell-skill

show-dont-tell-skill is a skill for Claude Code, Codex from Supreme-Ultimate/novel-to-script-team. It costs 36 tokens per session (3,987 once invoked), scanned A, original, MIT.

A script-editing method that changes stated emotions into visible actions, expressions, and images. The idea is known as “show, don’t tell”: the audience understands a feeling from what they see rather than being told its name.

In plain words
What is it for?
Use it to scan scripts for abstract emotion words, classify them, and replace them with specific actions or visual details.
Why use it?
It makes emotional moments easier to film and more concrete for viewers. It also reduces vague lines such as “she is sad” or “he is angry.”

Skill for Claude CodeCodex

Written for no agent in particular: nothing here depends on one.

Good fit Use it to scan scripts for abstract emotion words, classify them, and replace them with specific actions or visual details.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/supreme-ultimate/novel-to-script-team/show-dont-tell-skill
Install

Getting it into your agent

One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.

Any agent
npx skills add Supreme-Ultimate/novel-to-script-team --skill show-dont-tell-skill
Clone the repo
git clone --depth 1 https://github.com/Supreme-Ultimate/novel-to-script-team

Made for: Claude Code, Codex.

Wrote this? Show the measurements

A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.

agentmods badge for show-dont-tell-skill

README.md
[![agentmods](https://agentmods.dev/badge/skills/supreme-ultimate/novel-to-script-team/show-dont-tell-skill/github.svg)](https://agentmods.dev/skills/supreme-ultimate/novel-to-script-team/show-dont-tell-skill)
Your own site
<a href="https://agentmods.dev/skills/supreme-ultimate/novel-to-script-team/show-dont-tell-skill"><img src="https://agentmods.dev/badge/skills/supreme-ultimate/novel-to-script-team/show-dont-tell-skill/github.svg" alt="Measured on agentmods" height="20"></a>

Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.

agentmods 80×15 button for show-dont-tell-skill

Your own site · 80×15
<a href="https://agentmods.dev/skills/supreme-ultimate/novel-to-script-team/show-dont-tell-skill"><img src="https://agentmods.dev/badge/skills/supreme-ultimate/novel-to-script-team/show-dont-tell-skill.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 36 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 3,987 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
Origin original No closer match found in the catalogue.
Token cost

What it costs to keep this loaded

Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.

ModelPer sessionOnce invoked
Fable 5.1 $0.00036 $0.03987
Opus 5 $0.00018 $0.01994
Sonnet 5 $0.00007 $0.00797
Haiku 4.5 $0.00004 $0.00399

Measured 12d ago against content hash 6c24e752e550, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-11, from the pricing page.

Security

Grade A, and why

show-dont-tell-skill scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 12d ago.

A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.

Nothing flagged

None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.

skills/show-dont-tell-skill/SKILL.md · 406 lines

How it starts

The opening of the file, as written. The whole thing — 406 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Show Don't Tell 技能

必读

  1. ../../references/13-show-dont-tell-methodology.md
  2. ../../references/03-script-writing-standard.md
  3. ../../references/10a-action-dialogue-scenes.md

核心任务

将抽象情绪翻译为可拍摄的动作和画面,让观众通过看到的画面感受情绪,而不是被告知情绪。


执行流程

步骤1:扫描识别

扫描剧本,识别所有情绪形容词:

1.1 情绪形容词黑名单

参考 references/13-show-dont-tell-methodology.md 第一章,识别以下类型:

基础情绪类

  • 伤心、难过、悲伤、痛苦、心碎
  • 开心、高兴、快乐、兴奋、激动
  • 愤怒、生气、恼火、暴怒、愤恨
  • 害怕、恐惧、惊恐、紧张、不安
  • 惊讶、震惊、意外、诧异、惊愕

复杂情绪类

  • 失望、绝望、无助、无奈、迷茫
  • 尴尬、羞愧、内疚、后悔、自责
  • 嫉妒、羡慕、不甘、憋屈、委屈
  • 冷漠、麻木、疲惫、厌倦、无聊
  • 温柔、温暖、感动、心疼、怜惜

状态描述类

  • 紧张、焦虑、慌乱、不知所措
  • 犹豫、纠结、矛盾、挣扎、动摇
  • 坚定、果断、决绝、冷静、淡定
  • 疲惫、虚弱、无力、崩溃、绝望
1.2 允许的网文感情绪词

以下词可以保留(但必须配合具体动作):

  • 冷笑、嗤笑、冷哼、轻笑、讥笑
  • 眼神一冷、目光一沉、脸色一变
  • 嘴角上扬、眉头一挑、眼神闪烁
1.3 识别输出格式
## 情绪形容词清单

| 位置 | 原文 | 情绪类型 | 严重程度 |
|------|------|---------|---------|
| 第2场 第3行 | "她很伤心" | 伤心 | 高(直接使用黑名单词) |
| 第3场 第5行 | "他愤怒地说" | 愤怒 | 中(副词形式) |
| 第4场 第8行 | "她失望极了" | 失望 | 高(直接使用黑名单词) |

**统计**:
- 情绪形容词总数:12个
- 剧本总字数:3500字
- 情绪形容词密度:3.4个/1000字(超标,目标 ≤ 2个/1000字)

步骤2:情绪分类

对每个识别出的情绪形容词,判断情绪类型:

情绪类型 子类型 翻译策略
伤心/难过 轻度、中度、重度 使用克制动作(咬唇、低头、转身)
愤怒/生气 压抑、爆发、冷怒 使用爆发动作(站起、摔、握拳)
害怕/恐惧 紧张、恐惧、惊恐 使用防御动作(后退、颤抖、攥衣角)
惊讶/震惊 意外、震惊、难以置信 使用中断动作(停住、愣住、掉落)
失望/绝望 失望、心灰意冷、绝望 使用放弃动作(垂眼、垂手、放下)
尴尬/羞愧 尴尬、羞愧、内疚 使用回避动作(躲闪、低头、转身)
犹豫/纠结 犹豫、纠结、举棋不定 使用重复动作(反复、来回、悬停)
冷漠/麻木 冷漠、麻木、无动于衷 使用机械动作(机械点头、无反应)

步骤3:动作化翻译

参考 references/13-show-dont-tell-methodology.md 第二章的翻译表,为每个情绪提供3个改写方案:

3.1 翻译输出格式
## 改写建议

### 位置:第2场 第3行

**原文**:

※ 她很伤心,眼泪止不住地流下来。


**问题**:
1. 直接使用情绪形容词"伤心"
2. "眼泪止不住"太直白,缺乏层次
3. 缺乏具体动作和环境细节

**改写方案1(推荐)**:

※ 她低头盯着手机屏幕,拇指悬在发送键上方,颤抖着,最终还是删掉了整段文字。 △ 她咬紧下唇,眼眶泛红,但强忍着没让泪水落下。

- 景别:特写(手机屏幕)+ 中景(咬唇、眼眶)
- 优点:克制、有层次、有具体动作
- 情绪传达:通过"删掉文字"和"强忍"传达伤心

**改写方案2**:

※ 她靠在墙上,缓缓滑坐到地上,双手抱住膝盖,把脸埋进臂弯里。 △ 她的肩膀微微颤抖,但没有发出任何声音。

- 景别:全景(滑坐)+ 中景(肩膀颤抖)
- 优点:视觉冲击力强,孤独感明显
- 情绪传达:通过"滑坐"和"埋脸"传达伤心

**改写方案3**:

※ 她站在窗前,看着外面的雨,手指在玻璃上画了一个圈,又慢慢抹掉。 △ 她深吸一口气,闭上眼睛,眼角有泪痕。

- 景别:侧面中景(窗前)+ 特写(泪痕)
- 优点:有环境细节(雨),有象征动作(画圈抹掉)
- 情绪传达:通过"雨"和"抹掉"传达伤心

**推荐理由**:
方案1最符合短剧节奏,动作具体、克制、有层次,且符合"可控剧本三问"(人物≤2、动作简单、情绪段落清晰)。

Read the full file on GitHub · 406 lines

Changes

What this file has done since we first saw it

Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.

  1. 12d ago First seen · 406 lines · 36 tokens per session scan A 6c24e752e550

Subscribe to this mod's changes

show-dont-tell-skill is a skill published in the GitHub repository Supreme-Ultimate/novel-to-script-team (165 stars, last pushed 4mo ago), licensed MIT. It adds 36 tokens to every session and 3,987 once invoked, about $0.0002 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.

Related

Other skills, from other repositories

webgl-holographic-foil

A self-contained WebGL2 hero: thin-film interference over a crushed-foil surface whose palette shifts with the viewing angle; move the cursor to tilt the film.

nexu-io/open-design · 41 tokens

general-video

Author or edit a custom HyperFrames composition when no specialized workflow fits, or when BRIEF.md sets flow: companion. Use for longer or multi-scene pieces, brand and sizzle reels, montages, static loops, static title cards, footage remixes, and freeform builds. Use motion-graphics instead for a short unnarrated…

heygen-com/hyperframes · 92 tokens

html-ppt-hermes-cyber-terminal

OpenDesign + BYOK: choosing and wiring your own model, hands-on — cost, quality, and the routing decision. Built as a decision-grade AI literacy deck for engineers, IT, applied-AI teams.

nexu-io/open-design · 53 tokens

html-ppt-taste-brutalist

16:9 HTML deck in tactical-telemetry / CRT-terminal taste. Deactivated-CRT charcoal slides, white-phosphor monospace, hazard-red accent, scanline overlay, ASCII syntax, density over decoration. Distilled from Leonxlnx/taste-skill brutalist-skill (Tactical Telemetry mode).

nexu-io/open-design · 78 tokens

chengfeng-check-updates

An environment manager for a video-editing system. It checks whether its skills and runtime—the software needed to run them—are installed and compatible.

Agentchengfeng/chengfeng-videocut-skills · 120 tokens

diagnostic-stem-delivery

Audio production with diagnostic analysis, timecode parsing from documents, and verified export workflow.

HKUDS/OpenSpace · 23 tokens