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-prompt-composegit 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-prompt-compose)<a href="https://agentmods.dev/skills/kezd088/100x-skill-tiktok/100x-prompt-compose"><img src="https://agentmods.dev/badge/skills/kezd088/100x-skill-tiktok/100x-prompt-compose/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-prompt-compose"><img src="https://agentmods.dev/badge/skills/kezd088/100x-skill-tiktok/100x-prompt-compose.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 | $0.00132 | $0.02292 |
| Opus 5 | $0.00066 | $0.01146 |
| Sonnet 5 | $0.00026 | $0.00458 |
| Haiku 4.5 | $0.00013 | $0.00229 |
Grade A, and why
100x-prompt-compose 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 — 120 lines — stays where its author put it; the contents beside it link to each section on GitHub.
100x-prompt-compose
一句话定位
输入一个提示词模板 id（或需求描述）+ 变量，输出逐字渲染、按目标模型（Veo/Seedance/ 即创）包装好的最终生成提示词。属于 100x 体系"提示词+模型"这一步，衔接上游人物/场景/ 搜索关键词类 skill 与下游 AI 生成模型。
何时触发
用户说：
- "帮我组装提示词" / "填个模板出提示词" / "这条视频用什么模型" / "生成视频提示词" / "选个模板配变量"
- "compose a video prompt" / "fill in this template" / "which model should I use for this" / "generate an AI video prompt"
- 或直接给一段产品/人设/场景描述，要求出一条能直接喂给图片/视频生成模型的提示词
输入
最小输入（类别 A，硬性必填）：template_id（14 个模板之一，见 templates.json）
或一段足以唯一匹配到某个模板的需求描述（品类+use_when场景，见 workflow.md
Phase 1 步骤 1）；该模板 variables[] 里 label 不含"(可选)"的变量必须全部给出
（不代猜、不编造具体外观/台词内容）。
软性补充（类别 B，缺失走降级，见 workflow.md Phase 1 步骤 2/4）：label 含
"(可选)"的变量；视频模板的 model 选择（缺失时问一次，仍未答复则默认
model_hint[0]）。
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）：
existing_refs_input（此前调用已建立的产品/人物锁编号，见公理 2）。
输出
结构见 schema.json：ComposedPromptBundle = template_id/category +
variables_used + rendered_body（逐字插值后的中文正文，已含 realism_suffix）+
reference_locks（产品/人物锁的建立或引用记录）+（视频模板）model + video_unit
（按模型包装后的最终提示词 + 时长）+ meta。可选再渲染一段人类可读摘要（模板名/
变量表/最终提示词）。
核心约束（4 条公理，详见 axioms.md）
- 最终提示词须逐字替换模板正文，不得意译删减——
rendered_body必须是templates.json对应模板 body 的逐字插值结果（含方括号占位展开），不是"意思对 就行"的自由改写 - 参考图编号引用须指向已声明的锁，不可虚指——产品/人物首次出现锁外观，后续必须写
"参考图N产品/人物"，N 必须真实存在于已建立的编号集合（已知局限：这里能验证的
只是"格式对不对"和"编号是否真实存在"，验证不了"首次锁定描述本身是否真的具体
（产品外观要素齐全 / 人物年龄+种族+性别+穿着+外貌五要素齐全）"——
persona: "a person"、product_lock: "a thing"这类空洞占位文字目前能通过校验，因为schema.json/scripts/validate.js都只查字符串非空+格式+编号存在性，不做语义 内容判断；评估过用最短长度等启发式去堵，但会同时误杀模板自身的合法短示例，故未 实现，如实记录在axioms.md公理 2"已知边界"段，仍完全依赖调用者按workflow.mdPhase 1 步骤 2"缺失时追问、不脑补"的纪律执行） - 场景变量禁止写光线词，光线由后缀统一控制——
scene/scenes/place/rooms类变量命中闭集光线词表即拒绝，天气词允许 - 视频按所选模型执行时长上限与禁词表，零容忍——veo 8.0s/seedance 10.0s + 各自
禁词表 + 结尾固定句；即创无专用来源材料，只校验叙事镜头分类，不做时长/禁词硬校验
（已知局限：当前暂未包含即创模型的专用公理材料，详见
sources.md）；已知局限（真实语料实测确认，非纸面假设）：veo/seedance 禁词表是纯词法的词边界匹配，分不清"作为 AI 套路形容词使用的 professional"（禁词表本意拦的对象，如"professional lighting"）和"作为说话人 真实职业身份如实描述的 professional"（比如把说话人真实职业如实翻译成英文后 含这个词）——如实描述真实身份也会被判 FAIL，只能换一个不撞词的同义词改写， 详见axioms.md公理 4"已知边界"段
What ships with it
15 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 22 KB
- evals/example-01-supplement-vial-lock.json 1.2 KB
- evals/example-02-testimonial-veo-reference-reuse.json 2.5 KB
- evals/example-03-cleaning-spray-seedance.json 2.4 KB
- evals/example-04-cta-part-generic.json 1.1 KB
- metadata.json 5.4 KB
- package-lock.json 2.4 KB
- package.json 988 B
- profiles/seedance.md 1.9 KB
- profiles/veo.md 3.0 KB
- schema.json 11 KB
- scripts/validate.js 40 KB runs code
- sources.md 3.7 KB
- templates.json 23 KB
- workflow.md 13 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 · 120 lines · 132 tokens per session scan A be0ead0614a3
100x-prompt-compose is a skill published in the GitHub repository kezd088/100x-skill-tiktok (8 stars, last pushed 16d ago), licensed MIT. It adds 132 tokens to every session and 2,292 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…
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…