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-localizegit 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-localize)<a href="https://agentmods.dev/skills/kezd088/100x-skill-tiktok/100x-localize"><img src="https://agentmods.dev/badge/skills/kezd088/100x-skill-tiktok/100x-localize/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-localize"><img src="https://agentmods.dev/badge/skills/kezd088/100x-skill-tiktok/100x-localize.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 | $0.00150 | $0.02389 |
| Opus 5 | $0.00075 | $0.01195 |
| Sonnet 5 | $0.00030 | $0.00478 |
| Haiku 4.5 | $0.00015 | $0.00239 |
Grade A, and why
100x-localize 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 — 121 lines — stays where its author put it; the contents beside it link to each section on GitHub.
100x-localize
一句话定位
输入一段源文案（任意源语言），输出墨西哥西语默认本地化版本——不是逐字翻译，而是主动 压缩长度、贴合真实语料的实际强度分布。属于 100x 体系 L2 创意生成层，对应"2c 投放语 本地化"这一步。
何时触发
用户说：
- "投放语本地化" / "本地化成西语" / "翻译成西语文案" / "改写成墨西哥西语" / "这条文案怎么本地化"
- "localize this ad copy" / "translate this script into Spanish" / "adapt this for the Spanish market" / "Mexican Spanish localization"
- 或直接给一段源文案（源语言任意，通常是英语或中文文案），要求出西语本地化版本
输入
最小输入（类别 A，硬性必填）：source_script——完整源文案纯文本（源语言任意）。
本 skill 不接视频/音频文件，只吃文本。
软性补充（类别 B，均有明确默认值，见 workflow.md Phase 1）：target_region
（默认 "mx"，仅接受 mx/generic-latam，其余值降级为 generic-latam 并在
meta.warnings 记录）、register_profile（默认 "default"，贴合真实语料强度，
不是保守档，见"核心约束"公理 2）。
上游可选产出（类别 C，缺失静默跳过，不阻塞，也绝不要求用户先跑别的 skill）：
100x-persona 的人物/场景卡片、100x-search-query 的搜索词结果。
输出
结构见 schema.json：source_script（原文回显）+ target_region + register_ profile + localized_script（西语本地化产出）+ meta（必填：generated_by、
warnings；可选信息字段：compression_ratio）。
核心约束（4 条公理，详见 axioms.md）
- 压缩公理：西语产出字符数不得超过源文案字符数的 1.10 倍（也不得低于 0.5
倍）——基于参考语料的转写长度分布校准，西语表达同等信息量天然较长，逐字直译会系统性超出口播时长
预算，必须主动压缩改写，不是逐字翻译（1.10/0.5 这两个具体数字是工程判断，
详见
axioms.md公理 1） - 语域强度默认公理：默认贴合真实语料实际强度分布，07 号规范文件（
07_西语口播风格规范.md）§5 的保守禁语清单降级为 可选档profiles/compliance-conservative.md，不是默认（该文件 §1 自己声明"不是 从库内西语爆款样本归纳出的实战结论"，本 skill 因此不把它的保守建议当作默认必须 遵守的验证结论） - 人称一致公理：全篇统一
tú称呼，不得混入usted/vosotros（已知局限： 当前只支持mx/generic-latam两个target_region，不支持西班牙正式usted/vosotrosregister 或阿根廷vos变位——这是范围限制，请求这类地区会 被降级到generic-latam并提示，不会假装支持。另外参考语料存在实际出现usted且与tú混用的情况——这条公理是本 skill 对 自己产出设的质量线，不是对真实语料现状的描述，见axioms.md公理 3。当前机制已覆盖 全大写/去重音/零宽不可见字符插入/组合重音符号插入这四类绕过手法（手写校验层 对公理 2/3 做不可见字符 + 组合重音符号双重归一化，公理 4 的权威词族检测同样 做不可见字符剥离），仍有的已知残留缺口：schema.json层面的 ajvpattern仍然没有预处理能力（JSON Schema 规范 结构限制），且手写层的不可见字符码点列表（6 个）不是 Unicode 格式字符类别 的穷举，见axioms.md公理 2/3/4 的 TODO） - 防臆造权威声称公理：不得引入源文案没有的权威/认证类声称（闭集词族：FDA/
Harvard/OMS/临床验证类表述）——已知局限：这只能拦住闭集词族内的关键词层面新增
（已对去重音、大小写混合、逐字母加点缩写等书写变体做归一化，仍无法拦住
编造一个不在闭集里的虚构机构名/人名），见
axioms.md公理 4
What ships with it
12 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 18 KB
- evals/example-01-energy-focus-drink.json 1.2 KB
- evals/example-02-sleep-gummies-conservative.json 1.5 KB
- evals/example-03-doorframe-resistance-band.json 1.4 KB
- metadata.json 7.5 KB
- package-lock.json 2.4 KB
- package.json 816 B
- profiles/compliance-conservative.md 3.6 KB
- schema.json 10 KB
- scripts/validate.js 39 KB runs code
- sources.md 6.3 KB
- workflow.md 9.7 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 · 121 lines · 150 tokens per session scan A 171b4396b1a8
100x-localize is a skill published in the GitHub repository kezd088/100x-skill-tiktok (8 stars, last pushed 15d ago), licensed MIT. It adds 150 tokens to every session and 2,389 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
chinese-documentation
A Chinese technical-documentation style guide covering spacing, punctuation, numbers, terminology, and links when Chinese and English appear together.
azure-ai-translation-text-py
Azure AI Text Translation SDK for real-time text translation, transliteration, language detection, and dictionary lookup. Use for translating text content in applications. Triggers: "text translation", "translator", "translate text", "transliterate", "TextTranslationClient".
harden
Improve interface resilience through better error handling, i18n support, text overflow handling, and edge case management. Makes interfaces robust and production-ready. Use when the user asks to harden, make production-ready, handle edge cases, add error states, or fix overflow and i18n issues.
seedance-vocab-ja
This skill should be used when the user asks for Japanese Seedance 2.0 prompt wording, Japanese cinematic vocabulary, or translation of camera, lighting, action, VFX, audio, and production terms into Japanese.
asc-subscription-localization
Bulk-localize subscription, subscription-group, and in-app purchase display names across App Store locales using asc, including API 4.4.1 version-scoped v2 resources. Use when filling or updating subscription/IAP names and descriptions without App Store Connect UI work.
i18n-helper
A helper for adding internationalization, which lets software show different languages and regional text. It finds user-visible text written directly in code and moves it into language files.