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 cclank/lanshu-awesome-ai-video-kit --skill kling-promptergit clone --depth 1 https://github.com/cclank/lanshu-awesome-ai-video-kitWrote 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/cclank/lanshu-awesome-ai-video-kit/kling-prompter)<a href="https://agentmods.dev/skills/cclank/lanshu-awesome-ai-video-kit/kling-prompter"><img src="https://agentmods.dev/badge/skills/cclank/lanshu-awesome-ai-video-kit/kling-prompter/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/cclank/lanshu-awesome-ai-video-kit/kling-prompter"><img src="https://agentmods.dev/badge/skills/cclank/lanshu-awesome-ai-video-kit/kling-prompter.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 | $0.00162 | $0.02469 |
| Opus 5 | $0.00081 | $0.01234 |
| Sonnet 5 | $0.00032 | $0.00494 |
| Haiku 4.5 | $0.00016 | $0.00247 |
Grade A, and why
kling-prompter 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 — 184 lines — stays where its author put it; the contents beside it link to each section on GitHub.
kling-prompter
Kling 3.0（可灵 3.0，快手）的三套主流写法：4 部分基础 / 5 层进阶 / 图生视频。
何时不用此 skill
- 复杂多镜头分镜叙事（>15s） → 用 seedance-storyboard
- 5/10/15 秒紧凑短片，对原生音频要求不高 → 用 happyhorse-prompter
- 已有 Seedance 提示词需修问题 → 用 seedance-debugger
三套写法决策树
你的需求是？
├── 5 秒短视频、单一场景 → 写法 1（4 部分基础公式）
├── 带剧情、带音频、多角色 → 写法 2（5 层进阶公式）★ Kling 强项
└── 已有参考图，只需动起来 → 写法 3（图生视频专用）★ Kling 强项
工作流程
步骤 1：判断写法
| 用户的需求关键词 | 写法 |
|---|---|
| 短视频、TikTok、抖音、循环、爆款、变身 | 写法 1（4 部分） |
| 对话、剧情、配音、CTA、广告、多角色 | 写法 2（5 层） |
| 这张图、参考这张照片、让它动起来 | 写法 3（图生视频） |
步骤 2：澄清缺失要素（必要时）
如果信息不够，问 2-3 个关键问题（不是全部）：
| 场景 | 必问的 2-3 项 |
|---|---|
| 短视频 | 主体（具体外观）、动作（动词+终点）、风格（电影感/动漫/赛博朋克） |
| 5 层剧情 | 角色（年龄+服装）、对话内容、要不要原生音频（音乐/音效/voiceover） |
| 图生视频 | 主体在图中做什么变化（不要再描述图本身）、镜头怎么动 |
步骤 3：按选定写法填充
写法 1：4 部分基础公式
[Subject - 具体视觉细节] [Action - 精确运动+终点] [Context - 3-5 环境元素] [Style - 镜头+灯光+氛围].
详细参考 methodology/09-kling-公式.md。
写法 2：5 层进阶公式（Kling 的看家本领）
强烈推荐用结构化格式，模型按层解析：
Scene: [地点 + 时间 + 氛围]
Characters: [每个角色的具体描述，age + 关键服装/外貌]
Action: [按时间顺序的步骤，体现因果与递进]
Camera: [镜头类型 → 运动 → 切换]
Audio & Style: [对话/音效/音乐 + 视觉风格]
⚠️ Audio & Style 这层是 Kling 的差异化卖点，一定要写！Seedance / HappyHorse 都做不到角色定向发声。
写法 3：图生视频专用
铁律：只描述运动，不重复图中已有的视觉信息。
❌ 不要写：A red sports car with chrome wheels on a wet road...（图已有）
✅ 直接写：The headlights blaze on and the engine roars to life. The rear tires spin...
步骤 4：6 条 Kling 写作守则自查
- 用 active verbs 替代笼统词（rockets / slams / erupts）
- 描述 时序流（开头 → 中间 → 结尾）
- 用 具体光源 代替 "dramatic lighting"
- 加 触感细节（grain / reflections / sweat / steam）
- 加 显式 endpoint（防 99% 卡死）：
then settles back / fades out - 幻想场景用 物理交互锚定（stone crumbles / torches flicker）
步骤 5：决定语言（中文还是英文）
| 场景 | 推荐语言 |
|---|---|
| 中式美学、武侠、汉服、中文台词 | 中文（Kling 中文理解最强） |
| 国际化、Hollywood 风、产品广告 | 英文 |
| 二者混合 | 选主导风格，不混用 |
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 · 184 lines · 162 tokens per session scan A bc295824c51a
kling-prompter is a skill published in the GitHub repository cclank/lanshu-awesome-ai-video-kit (392 stars, last pushed 3mo ago), licensed MIT. It adds 162 tokens to every session and 2,469 once invoked, about $0.0008 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 2026-08-30.
Other skills, from other repositories
shortfilm-prompt
Generate cinematic AI shortfilm prompts (works with Seedance 2.0, Xiaoyunque, Sora, Kling, Jimeng, Veo) using the 5-stage structure from Mx-Shell's Zombie Scavenger. Trigger when the user wants transformation sequences, multi-shot narrative shorts, weapon-charge/combat segments, emotional family/pet/farewell…
seedance-cinematic-film
Write photorealistic live-action cinematic Seedance 2.0 prompts for Higgsfield, built on five grounding pillars that stop AI drift and floaty motion. Use for "cinematic film prompt", "shot like a movie", realistic body movement, grounded motion, restrained emotional close-ups, driving scenes, fight choreography…
director-cinematography
Virtual director and cinematographer for AI-generated short videos using Higgsfield. Takes a script, scene, or creative idea and produces a shot-by-shot visual direction plan with ready-to-paste Higgsfield prompts — camera presets, lenses, lighting, color grading, and motion directives for every shot. Channels 11…
seedance-prompt-builder
Write production-ready Seedance 2.0 prompts (image, video, and motion/edit) for Higgsfield. Use this skill whenever the user wants a single Seedance prompt rather than a full shotlist — e.g. "make a Seedance prompt for X", "write me a video prompt", "restyle this clip", "turn my photo into a character sheet"…
cost-aware-llm-pipeline
A planning guide for choosing language models and managing the amount of conversation context used by an AI coding workflow. It groups tasks by complexity and gives rules for avoiding context overflow during long sessions.
higgsfield-seedance
Rewrites scene descriptions using professional cinematography language, structures prompts with a six-slot formula (camera + subject + action + setting + style + lighting), and diagnoses content filter rejections via a preflight linter. Use whenever the user asks for a Seedance 2.0 / Seedance Pro prompt, describes a…