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 kezd088/100x-skill-tiktok --skill 100x-exaggerategit clone --depth 1 https://github.com/kezd088/100x-skill-tiktokWrote 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/kezd088/100x-skill-tiktok/100x-exaggerate)<a href="https://agentmods.dev/skills/kezd088/100x-skill-tiktok/100x-exaggerate"><img src="https://agentmods.dev/badge/skills/kezd088/100x-skill-tiktok/100x-exaggerate/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/kezd088/100x-skill-tiktok/100x-exaggerate"><img src="https://agentmods.dev/badge/skills/kezd088/100x-skill-tiktok/100x-exaggerate.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
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 | $0.00136 | $0.02771 |
| Opus 5 | $0.00068 | $0.01385 |
| Sonnet 5 | $0.00027 | $0.00554 |
| Haiku 4.5 | $0.00014 | $0.00277 |
Grade A, and why
100x-exaggerate 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 11d 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 — 127 lines — stays where its author put it; the contents beside it link to each section on GitHub.
100x-exaggerate
一句话定位
输入一段脚本/文案纯文本，输出"怎么夸张"（夸张技法+强度）+ "怎么反差"（反差类型+两端 锚点），每条都逐字回指脚本原句，强度按市场+帽度天花板校准。属于 100x 体系 L2 创意生成层， 对应"3.3 夸张/反差"这一步。
何时触发
用户说：
- "帮这条脚本加点夸张" / "这里怎么做反差" / "这段有点平，怎么更抓人" / "加个前后对比"
- "这条脚本的钩子不够冲击" / "怎么让这句话听起来更夸张但别太假"
- "make this script more dramatic" / "add a before/after contrast" / "how do I exaggerate this without it looking fake" / "what's the contrast angle here"
- 或直接给一段脚本文案，要求"设计夸张点和反差点" / "design exaggeration and contrast beats for this"
输入
最小输入（类别 A，硬性必填）：source_script——完整脚本/文案纯文本。本 skill 不接
视频文件，只吃文本（与 100x-persona 同一约束）。
软性补充（类别 B，缺失走三级降级，见 workflow.md Phase 1）：hat_level
（blackhat/grayhat/whitehat）+ market（自由文本，如"美区"/"US"/"西语区"/
"通用"）。两者都缺失时，hat_level 内联推断为 grayhat，market 按保守默认处理
（emotion_reaction_hyperbole 技法按美区市场对待），不追问用户，meta.warnings
如实记录推断过程——详见 axioms.md 公理 3、workflow.md Phase 1。
上游可选产出（类别 C）：本 skill 不声明任何依赖上游 skill 产出的字段——如果用户
已跑过 100x-persona/100x-search-query 并附带产出，可在 rationale 里顺带引用，
但 schema.json 完全不含 persona_ref/scene_ref 一类的跨 skill 引用字段，比
100x-persona 的可选 segment_ref 更彻底解耦。
输出
结构见 schema.json：ExaggerationContrastBundle = source_script（原文回显）+
meta（hat_level/market/校准说明/warnings）+ exaggeration_beats[]（夸张点，
每条含 technique 闭集枚举 + label_cn + intensity + 逐字锚点）+ contrast_beats[]
（反差点，每条含 contrast_type 闭集枚举 + label_cn + 两端逐字锚点）。可选再渲染
一张人类可读的 Markdown 摘要（夸张点列表 + 反差点列表）。
核心约束（4 条公理，详见 axioms.md）
- 夸张手法（5 种）与反差类型（4 种）必须选自闭集枚举，不许自创新词——枚举本身取自 创意桥段词典的 L1 桥段/画面类型 + 参考语料信号频次，不是拍脑袋定的
- 每条夸张点/反差点的锚点必须是脚本原句的逐字子串，不许编造——与
100x-persona证据引文公理同一机制 - 夸张强度受市场+帽度天花板校准，不是越夸张越好——直接吸收词典-06 自带的美区市场
夸张强度校准提醒（具体措辞不逐字引用，见
axioms.md公理 3），但这条限制只对emotion_reaction_hyperbole（情绪反应夸张）这一个技法生效，不笼统限制其余 4 种 技法（已知局限：天花板表本身的三档数值化是本次原创判断，只在英西两个市场的保健品 类目语料上验证过；meta.market命中美区的判定目前是分段后做整段精确匹配，不做真正 的中英文分词，识别不了"美国市场"这类别名嵌在更长复合词、且前后没有任何分隔符的写法 ——v1.1 已修正一个更严重的反向问题：分段前的整串子串匹配曾对Russia/Australia/Belarus/"南美国家"这类与美区无关的市场字符串产生假阳性；v1.2 又修正了另一个方向 的问题：v1.1 的分段符号不含连字符-/&，导致"美区-通用"/"US & Canada"这类用连字符 或&组合多个市场值的写法被漏判为不命中美区，市场天花板被静默放开，现已把-/&也纳入分段符号——但"完全无分隔符的复合词"这一类仍未解决，见axioms.md公理 3、 TODO） - 反差两端必须有真实落差，不许同一句话充当两端——直接对应词典-06 Type D 画面对
"两端要有可感知落差"这一核心要求的机器化（具体措辞不逐字引用，见
axioms.md公理 4）（已知局限：只能拦"字面完全相同"，拦不住"语义重复但字面不同"的更隐蔽 退化，与100x-persona公理 3 TODO 同一类天花板，见axioms.md公理 4）
What ships with it
11 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
- axioms.md 24 KB
- evals/example-01-glow-serum-blackhat-us.json 3.9 KB
- evals/example-02-joint-formula-grayhat-generic.json 2.7 KB
- evals/example-03-sleep-gummies-whitehat.json 3.0 KB
- metadata.json 6.5 KB
- package-lock.json 2.4 KB
- package.json 828 B
- schema.json 9.5 KB
- scripts/validate.js 24 KB runs code
- sources.md 17 KB
- workflow.md 11 KB
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.
- 11d ago First seen · 127 lines · 136 tokens per session scan A 1a0d1f4f698e
100x-exaggerate is a skill published in the GitHub repository kezd088/100x-skill-tiktok (8 stars, last pushed 15d ago), licensed MIT. It adds 136 tokens to every session and 2,771 once invoked, about $0.0007 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 2026-08-31.
Other skills, from other repositories
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
local-ai-agents
Build local-first AI agents that run entirely on a developer workstation with Microsoft Foundry Local and Qwen function-calling models. Covers Small Language Models (SLMs), the OpenAI-compatible local endpoint, sandboxed local tools, local RAG with Chroma, local MCP servers, hybrid cloud/local routing, and the…
next-cache-components-adoption
Turn on Cache Components in a Next.js app and resolve the blocking routes it surfaces. Use when the user wants to enable, adopt, or migrate to Cache Components, flip the cacheComponents flag, work through a flood of blocking-prerender / instant validation errors, run the cache-components-instant-false codemod, or…
insight-error-page
Write or audit an insight-kind error page for the Next.js dev overlay. Use when creating a new errors/ .mdx page, auditing an existing one, or checking that a page matches the framework fix cards. Covers page structure, title alignment, FixCard cards with Copy prompt button, code snippets, terminology verification…
next-cache-components-optimizer
Drive a Next.js route to instant navigation by setting up an agentic loop, under Cache Components / PPR, on initial load (hard navigation) and client-side navigation (soft navigation). Encode the goal as a failing @next/playwright instant() e2e and work it to green, one verified route at a time; the shipped test then…
next-partial-prefetching-adoption
Turn on Partial Prefetching in a Next.js app and work through the insights it surfaces. Use when the user wants to enable or adopt Partial Prefetching, flip the partialPrefetching flag, opt routes in with export const prefetch = 'partial', audit Link prefetch={true} behavior, preserve existing prefetched UI with…