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.
npx skills add jianshuo/claude-skills --skill wjs-explaining-tv-slanggit clone --depth 1 https://github.com/jianshuo/claude-skillsWrote 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.
[](https://agentmods.dev/skills/jianshuo/claude-skills/wjs-explaining-tv-slang)<a href="https://agentmods.dev/skills/jianshuo/claude-skills/wjs-explaining-tv-slang"><img src="https://agentmods.dev/badge/skills/jianshuo/claude-skills/wjs-explaining-tv-slang/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.
<a href="https://agentmods.dev/skills/jianshuo/claude-skills/wjs-explaining-tv-slang"><img src="https://agentmods.dev/badge/skills/jianshuo/claude-skills/wjs-explaining-tv-slang.svg" alt="Reviewed on agentmods" width="80" height="20"></a>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.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00182 | $0.01940 |
| Opus 5.5 | $0.00073 | $0.00776 |
| Sonnet 5.5 | $0.00036 | $0.00388 |
| Haiku 4.5 | $0.00018 | $0.00194 |
Grade A, and why
wjs-explaining-tv-slang 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 6d 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.
How it starts
The opening of the file, as written. The whole thing — 116 lines — stays where its author put it; the contents beside it link to each section on GitHub.
美剧口头语解释器
核心原则
查字典给的是字面意思，看剧要懂的是这句话在那一刻干了什么——是在挖苦、撒娇、认怂、还是装傻。
裸模型解释口语常犯四个错，这个 skill 逐一钉住：
| 坑 | 表现 | 对策 |
|---|---|---|
| 只给字面义 | "I'm good" 译成「我很好」，其实是「不用了谢谢」 | 必填「实际在干什么」一栏 |
| 不讲语气分量 | 把冒犯级的词当普通口语教给用户 | 必填语气/冒犯度 + 能不能用 |
| 编造剧集台词 | 张冠李戴「这是老友记 S3E5 的台词」 | 出处没核实就标「示意」，要具体集数先 WebSearch |
| 翻译腔例句 | 中文对应说法生硬 | 给中文此情此景会怎么说，不是逐词翻 |
输入形态
- 单个词/短语：
"I'm down"、"no cap"、"that's on me" - 一句台词 + 剧名（最好有上下文）：「绝命毒师里 Jesse 一直说 yo, bitch」
- 截图：读图里的字幕，先确认识别出的原句再解释
- SRT / 字幕文件：批量扫，挑出口语/俚语/梗（跳过普通词汇），按出现顺序逐条用「速查格式」，最后给一张汇总表
- 用户没给剧名/上下文时不要先问——先按最常见用法解释，末尾提一句「如果是在某个具体场景里，告诉我剧名和前后台词，可能有别的意思」
输出格式（单条完整版）
用中文。按下面顺序，每节短而具体；不适用的节直接省略，别硬凑。
## "That's what she said"
**一句话**：把对方刚说的一句正经话，故意曲解成黄色双关的接梗。
### 1. 字面 vs 实际
- 字面：那是她说的
- 实际：「你这话听着有点黄啊」——一种低级但无害的冷笑话接茬
### 2. 为什么这么说（来源/逻辑）
词源、比喻逻辑、语法省略了什么、从哪个圈子/年代流行起来、有没有著名出处（核实过才写剧名+季集）。
讲清「为什么这几个词能表达这个意思」，让人以后能举一反三。
### 3. 语气与分量
| 维度 | 评级 |
|---|---|
| 正式度 | 很随意 / 随意 / 中性 / 正式 |
| 冒犯度 | 无 / 轻微 / 粗口 / 冒犯（会得罪人）/ 禁忌（别碰） |
| 情绪 | 调侃 / 讽刺 / 真诚 / 不耐烦 / 撒娇 … |
| 地域/人群 | 美式/英式/黑人英语 AAVE/青少年/职场/南方… |
| 时代感 | 现在常用 / 有点过时（像「给力」）/ 老派 / 网络新词 |
### 4. 你能不能用
- ✅ 可以：朋友之间、…
- ⚠️ 小心：…
- ❌ 别用：面试、对长辈、…（以及**非母语者说出来的效果**——有些词母语者说是好笑，外国人说就尴尬）
### 5. 中文怎么说
给 2–3 个**此情此景中国人会怎么说**的对应说法，标出最贴的那个。
如有字幕组常见误译，单列「⚠ 常见误译：…」。
### 6. 例句
3 句，覆盖不同场景（朋友/职场/恋人/家人…），每句英文 + 自然中文，
其中至少一句展示**语调/重音**怎么放（大写或加粗重读词）。
### 7. 剧里的上下文
- 用户给了具体场景：解释这句在**这一刻**的作用——谁对谁说、关系、潜台词、笑点/张力在哪
- 没给：举一个典型剧情场景（标「示意场景」，不冒充真实剧集）
### 8. 怎么接话
对方这么说时，常见的 2–3 种回应（顺着接 / 怼回去 / 正经回应）。
### 9. 近义 / 变体 / 反义
- 近义：…（区别在哪）
- 变体：缩写、网络写法（如 "ngl"、"fr"）
- 容易混淆：长得像但意思不同的（如 "I'm down" vs "I'm feeling down"）
### 10. 发音
连读、吞音、重音位置，母语者实际听起来像什么（如 "gonna" /ˈɡʌnə/、"whaddaya"）。
### 💡 记忆钩子
一句话帮助记住，最好有画面感。
速查格式（批量/SRT 用）
每条一段：
**"I'm good"**（00:12:34）— 不用了谢谢（拒绝，不是「我很好」）· 随意 · 无冒犯
> 中文：不用啦｜例：Want some fries? — I'm good.
末尾汇总表：| 时间 | 原句 | 实际意思 | 冒犯度 |
事实纪律
- 出处必须可信：说「出自 XX 剧 SxEy」之前先 WebSearch 确认；查不到就只说「因 XX 剧流行」或干脆不提。
- 新词先查：2023 年后的网络俚语（Gen Z / Gen Alpha 用语、TikTok 梗）用 WebSearch 核实当前用法，Urban Dictionary 只作参考、取高票释义。
- 多义要摊开：一个词有多个常见意思（如 "sick" = 病了 / 酷毙了），列出来并说明怎么靠上下文区分。
- 不确定就说不确定：口语里的模糊地带直接标「这一点母语者之间也有分歧」。
- 粗口照样解释：用户是学语言，脏话、种族相关词要如实解释含义和分量，重点放在「为什么不能用、在剧里是什么效果」，不回避也不鼓励。
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.
- 6d ago First seen · 116 lines · 182 tokens per session scan A f287f0d138cd
wjs-explaining-tv-slang is a skill published in the GitHub repository jianshuo/claude-skills (135 stars, last pushed 3d ago), licensed MIT. It adds 182 tokens to every session and 1,940 once invoked, about $0.0007 per session on Opus 5.5. 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 2026-10-13.
Other skills, from other repositories
toolbox-talk-generator
Generate safety toolbox talks for construction crews. Create contextual safety briefings based on weather, work activities, and recent incidents. Support multiple languages.
nexus-content-multilingual
Multilingual and cultural bridge specialist for educational content. Use when you need educational translations, bilingual materials, or culturally-adapted content. Ensures translations preserve educational intent and cultural sensitivity rather than being literal word-for-word conversions.
understand-explain
Use when you need a deep-dive explanation of a specific file, function, or module in the codebase.
baoyu-comic
A tool for creating original educational comics that explain knowledge or ideas through multiple illustrated panels. It supports different art styles and tones and can create several comics in one batch.
ljg-read
A reading companion for books, articles, essays, papers, and news. It can translate English into Chinese, explain a text’s structure, annotate important ideas, and ask questions that deepen understanding.
extract-source-sample
Given the path to a finished content-goose ad-run folder, extract everything that defines that ad — recipe shot list, VO script, characters, voices, world, atom-skills, master mp4 — and emit a source-sample.json in the exact shape the upload-ad-sample skill writes to the Goose Ads library. Also links every character…