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-segmentgit 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-segment)<a href="https://agentmods.dev/skills/kezd088/100x-skill-tiktok/100x-segment"><img src="https://agentmods.dev/badge/skills/kezd088/100x-skill-tiktok/100x-segment/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-segment"><img src="https://agentmods.dev/badge/skills/kezd088/100x-skill-tiktok/100x-segment.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 | $0.00118 | $0.02349 |
| Opus 5 | $0.00059 | $0.01175 |
| Sonnet 5 | $0.00024 | $0.00470 |
| Haiku 4.5 | $0.00012 | $0.00235 |
Grade A, and why
100x-segment 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.
How it starts
The opening of the file, as written. The whole thing — 118 lines — stays where its author put it; the contents beside it link to each section on GitHub.
100x-segment
一句话定位
输入一段 TikTok/UGC 口播脚本纯文本（英语或西语），输出三层独立叠加的切分结果： L1 段落逻辑（10 模块 + 7 原型）、L2 镜头目的预判、L3 行内气口标记。属于 100x 体系 "1 分段"这一步。
何时触发
用户说：
- "帮我分段" / "这条脚本怎么分段" / "拆一下这条口播文案" / "这段哪里该喘气"
- "segment this script" / "break this voiceover into beats"
- 或直接给一段口播脚本纯文本，要求"按模块拆" / "标一下气口" / "这段应该怎么切"
输入
最小输入（类别 A，硬性必填）：source_text——一段口播脚本/文案纯文本。本
skill 不接视频文件/视频帧，只吃文本（详见 workflow.md Phase 1）。
类别 B（软性输入）：无——source_text 本身已包含分段所需的全部信号，不需要
额外补卖点/受众/语气才能开始工作（和 100x-persona 结构一致，和
100x-search-query 不同，详见 workflow.md"类别 B 说明"）。
语言范围（v1 明确边界，非降级）：language 从 source_text 自动判定，只接受
英语或西语；判定为其他语言或英西混排到无法判定主语言时直接拒绝，不猜、不代做。
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）： 本仓目前没有可作为上游的产品画像/选题材料类 skill 产出。
输出
结构见 schema.json：source_text/language/archetype（7 原型 A-G，单一或
"主+辅"复合如 "G+E"）/segments[]（每项含 segment_id/module[10 枚举]/
raw_text/text_annotated[压了 ‖强气口·弱气口的行内标记版本]）/shots[]
（每项含 shot_id/segment_refs[]/shot_purpose[7 枚举标准定义]）/meta。可选再渲染一张人类可读的 Markdown 段落表。
核心约束（4 条公理，详见 axioms.md）
segments[].module锁 10 枚举（11 模块去掉贯穿全文的 Localization）+archetype锁 7 原型格式（单一或"主+辅"两个不同字母）- 气口是行内标记，只加不减——
text_annotated去掉‖/·后必须与raw_text逐字相同，不许删词/加词/改词 - 气口强弱判据已锁死（转折连词开头>句末标点/破折号>逗号分号，一口气 EN 14 词/
ES 16 音节强制切分），按固定优先级判定，不可自由发挥（已知局限：EN
so同时有"转折/因果连词"和"程度副词/强调词"（so much/so many）两种用法， 纯关键词匹配区分不了，只排除了"so much"/"so many"这个最常见搭配，其他 强调用法仍可能被误判成转折连词、强制要求强气口——这条是硬性 fail 判据 而不是软性 warning，误判代价比下面这条更高；填充词后接、价格数字前不标 气口这两条是启发式关键词匹配，不是真语义判断，like的介词/填充词歧义 会造成一定误报率，只做 warning 不 fail，见axioms.md公理3 TODO；句末 标点判据用固定、非穷举的缩写词典（a.m./p.m./Mr.等）排除常见缩写 句点，已在真实英语语料上确认修好这几个具体缩写，但词典之外的缩写仍会 误判为句末；另外，句末标点与下一词零空格粘连（漏打空格）目前只对!/?判定为缺失气口，.出于避免和缩写/小数点冲突的考虑仍要求真实空白字符， 零空格粘连的.暂不触发判据，均见axioms.md公理3 TODO） shots[].shot_purpose锁 7 枚举标准定义，且必须完整 覆盖segments[]（引用完整性 + 零孤儿，已知局限：本 skill 纯文本输入，shots[]只预判镜头目的，不含time_bucket/visual_description/camera_language/audio_plan——这些字段依赖实际视频画面，不在本 skill 范围内）
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 25 KB
- evals/example-01-energy-staged-timeline.json 4.5 KB
- evals/example-02-night-drink-secret-reveal.json 3.8 KB
- evals/example-03-knee-conditional-pain.json 3.7 KB
- metadata.json 5.7 KB
- package-lock.json 2.4 KB
- package.json 873 B
- schema.json 7.9 KB
- scripts/validate.js 35 KB runs code
- sources.md 5.7 KB
- workflow.md 16 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.
- 12d ago First seen · 118 lines · 118 tokens per session scan A 7b7f7c75ea34
100x-segment is a skill published in the GitHub repository kezd088/100x-skill-tiktok (8 stars, last pushed 16d ago), licensed MIT. It adds 118 tokens to every session and 2,349 once invoked, about $0.0006 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…
chat-pet-sprite-creation
Use when creating or changing VS Code chat pet sprite art, sprite sheets, state animations, eye treatments, Stable/Insiders variants, or pet transitions under src/vs/workbench/contrib/chat/browser/widget/media/chatPet.
cpu-profile-analysis
Analyze V8/Chrome CPU profiles (.cpuprofile) and DevTools trace files (Trace-.json). Use when: profiling performance, investigating slow functions, comparing code paths, finding bottlenecks, analyzing timeToRequest, understanding call trees from sampling profiler data, analyzing layout/paint/rendering, investigating…
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…