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-personagit 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-persona)<a href="https://agentmods.dev/skills/kezd088/100x-skill-tiktok/100x-persona"><img src="https://agentmods.dev/badge/skills/kezd088/100x-skill-tiktok/100x-persona/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-persona"><img src="https://agentmods.dev/badge/skills/kezd088/100x-skill-tiktok/100x-persona.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 | $0.00119 | $0.01870 |
| Opus 5 | $0.00060 | $0.00935 |
| Sonnet 5 | $0.00024 | $0.00374 |
| Haiku 4.5 | $0.00012 | $0.00187 |
Grade A, and why
100x-persona 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 — 99 lines — stays where its author put it; the contents beside it link to each section on GitHub.
100x-persona
一句话定位
输入一段脚本/文案纯文本,输出"谁来讲"(人物)+ "在哪讲"(场景,独立实体,非人物附属 字段)+ 两者如何与脚本原句绑定,三者都能逐字回指原文。属于 100x 体系 L2 创意生成层, 对应"3.1 人物×场景"这一步。
何时触发
用户说:
- "给这条脚本配个人设" / "这条脚本谁来讲比较合适" / "这个人设怎么定"
- "这个场景怎么设定" / "这条广告适合什么场景拍" / "这条脚本在哪拍合适"
- "who should deliver this script" / "what persona fits this product"
- "what setting fits this ad" / "where should this be filmed"
- 或直接给一段脚本文案,要求"配人物和场景" / "assign a character and setting"
输入
最小输入(类别 A,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。
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-segment 产出的 segments[](若存在,pairings[].segment_ref 可回填,缺失时
整个字段省略,靠 script_span_quote 独立定位)。
输出
结构见 schema.json:PersonaSceneBundle = source_script(原文回显,供证据核对)+
personas(人物 map,独立实体)+ scenes(场景 map,独立实体,与 personas 平级,
不是人物的字符串字段)+ pairings(人物×场景×脚本原句的绑定表)+ meta。可选再渲染
一张人类可读的 Markdown 摘要(人物列表 / 场景列表 / pairing 对照表)。
核心约束(4 条公理,详见 axioms.md)
- 场景是独立实体,靠 ID 引用,不是人物的内嵌字段——
personas/scenes是两个平级 map,pairings[]里的persona_ref/scene_ref必须真实存在于对应 map(引用完整性) - 人物的权威/受众依据必须是原文逐字子串,不许臆造——
authority_evidence_quote/audience_pain_quote/script_span_quote都要能在source_script里逐字找到。 已知局限(不是隐藏缺陷):逐字子串只能证明"这句话原文有",证明不了"这句话在 人物字段里的语义方向没被反着用"——比如摘一句自我怀疑的话("如果你不信我")反着当 权威锚点,也是合法子串。当前机制包含一层闭集自我怀疑短语检测(命中即要求人工披露, 见axioms.md公理2),但反讽/引用-驳斥框架类反转仍检测不到,这是字符串匹配的 天花板,详见axioms.md公理2"机制天花板与缓解措施"段 - 场景须具体到微观坐标,不许写泛地点——闭集泛化词表拒收 + 至少 2 件具体道具
- 人物与场景零孤儿,建了必须被至少一个 pairing 引用——不为了"看起来矩阵齐全"堆砌
三阶段流程
详见 workflow.md:Phase 1 人物反推(扫描脚本里的 Authority/Pain 信号,逐字摘取证据句)
→ Phase 2 场景建模(每个场景线索独立建实体 + 与人物/脚本原句绑定 + 零孤儿自检)→
Phase 3 输出(组装 JSON,公理 1-4 全过)。
独立调用保证
类别 A(source_script)缺失 → 固定拒绝话术追问,不代猜、不接视频文件替代。类别 C
(上游 100x-segment 产出)缺失 → 静默跳过,绝不要求用户先跑其他 skill。
禁用词
让我 / 希望 / 或许 / 大概 / 可能 / 也许 / 让我们;AI 客服味(as an AI / I'd be happy to /
feel free to);不编造脚本原文没有的资质/认证/见证/效果数据;不写死任何客户品类词典;
micro_coordinate 不使用闭集泛化词(见 axioms.md 公理 3:某处/随便/某个地方/TBD/
somewhere/anywhere 等)。
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 14 KB
- evals/example-01-sleep-gummies.json 3.1 KB
- evals/example-02-resistance-band.json 3.3 KB
- evals/example-03-waist-wrap-staged-timeline.json 3.2 KB
- metadata.json 5.7 KB
- package-lock.json 2.5 KB
- package.json 482 B
- schema.json 9.9 KB
- scripts/validate.js 21 KB runs code
- sources.md 3.8 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.
- 12d ago First seen · 99 lines · 119 tokens per session scan A bc118f1b0c71
100x-persona is a skill published in the GitHub repository kezd088/100x-skill-tiktok (8 stars, last pushed 16d ago), licensed MIT. It adds 119 tokens to every session and 1,870 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…