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 huangrichao2020/pretty-skills --skill cinema-dna-21x9x3git clone --depth 1 https://github.com/huangrichao2020/pretty-skillsWrote 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/huangrichao2020/pretty-skills/cinema-dna-21x9x3)<a href="https://agentmods.dev/skills/huangrichao2020/pretty-skills/cinema-dna-21x9x3"><img src="https://agentmods.dev/badge/skills/huangrichao2020/pretty-skills/cinema-dna-21x9x3/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/huangrichao2020/pretty-skills/cinema-dna-21x9x3"><img src="https://agentmods.dev/badge/skills/huangrichao2020/pretty-skills/cinema-dna-21x9x3.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 | $0.00182 | $0.01118 |
| Opus 5 | $0.00091 | $0.00559 |
| Sonnet 5 | $0.00036 | $0.00224 |
| Haiku 4.5 | $0.00018 | $0.00112 |
Grade A, and why
cinema-dna-21x9x3电影感三联 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 13d 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.
What it actually says
cinema-dna-21x9x3 电影感三联
一句话定位
电影感 = 镜头/光线/空间/叙事 4 个判断先成立，不堆提示词。3 张 21:9 横向 triptych 叙事图（建立世界/建立关系/留下余韵）+ 现场摄影 5+ 参数 + Anti-AI 纪律 + 光学缺陷。matrix_generate_image × 3 + PIL 拼接即可落地。
5 步核心工作流
| 步 | 动作 | 关键 |
|---|---|---|
| 1 | 任务分析 | 主题 / 类型 / 受众 / 3 镜头角色分配 |
| 2 | 镜头方案 | Shot 1 建立世界（24-28mm）→ Shot 2 建立关系（32-50mm）→ Shot 3 留下余韵（50-85mm） |
| 3 | 光线 + 色彩脚本 | 选胶片介质（35mm/16mm/VHS/MiniDV 等 7 选 1）+ 光源 + 色彩身体 |
| 4 | 空间组织 | 5+ 摄影参数（焦段/机位/距离/比例/遮挡/空间轴/光源/焦点/视线/信息位置） |
| 5 | 输出完整 prompt + matrix_generate_image × 3 + PIL 拼接 | Triptych 比例 1.25:0.9:0.85（强调首镜头）+ 8px 黑色间隔 |
与同类方法对比
| 维度 | 普通 AI 配图 | cinema-dna | scroll-world | dashiai-ppt |
|---|---|---|---|---|
| 输出形式 | 1 张竖图 + AI 套词 | 3 张 21:9 横向叙事 | 2N-1 段视频 | 22 幕讲解 |
| 核心 | "电影感滤镜" | 镜头成立的原因 | seam frame-identical | 横屏适配 |
| 工具 | matrix_generate_image | matrix_generate_image × 3 + PIL | matrix_gen_videos + ffmpeg | matrix_generate_image + PIL |
| 适用 | 配图随手出 | 高级感主题 | 品牌沉浸 landing | 演讲/汇报 |
| 不适用 | 高品质场景 | 纯科普/数据/长文 | 静态图 | 视频/动画 |
详细文档
content.md· 9 段深度方法论（建立世界/建立关系/留下余韵/现场摄影/Anti-AI/光学缺陷/Triptych 节奏/导演转译/Mavis 适配/工具对比）images/· 15 张 cinema-dna 自带 example + 1 张 triptych 示范prompts/· 9 段出图 prompt（含 triptych 拼接示意）cinema-dna-21x9x3电影感三联讲解.pdf· PDF 讲解版锦绣/· 3 张 triptych example + cover + 融合 md
关键参考
- 原项目：dacnay816y62-hub/cinema-dna-21x9x3 · 39 stars
- SKILL.md 771 行（含 v3/v4 全部硬规则 + 14 张 example + 2 份 references）
- 14 张 triptych example（hotel-pink-ritual / venice-palace / journey-west / 等）
沉淀版本
v1.0 · 2026-07-22
What ships with it
39 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.
- cinema-dna-21x9x3电影感三联讲解.pdf 667 KB
- content.md 9.3 KB
- images/blue-sea-large-ship-triptych.png 9156 KB
- images/cabaret-aftermath-triptych.png 5402 KB
- images/courthouse-witness-triptych.png 5050 KB
- images/dumpling-shop-triptych.png 5760 KB
- images/eastern-palace-triptych.png 6204 KB
- images/examples/absurd-comedy-triptych.png 6940 KB
- images/examples/army-fisheye-first-person-triptych.png 9533 KB
- images/examples/blue-sea-large-ship-triptych.png 9156 KB
- images/examples/example-journey.png 6440 KB
- images/examples/example-venice.jpg 1812 KB
- images/examples/go-shadow-ink-triptych.png 5431 KB
- images/examples/green-girl-wide-aperture-triptych.png 6822 KB
- images/examples/industrial-ensemble-ledger-triptych.png 5795 KB
- images/examples/triptych-demo.png 18 KB
- images/examples/warm-narrative-overview.png 2172 KB
- images/green-water-memory-triptych.png 8146 KB
- images/hotel-pink-ritual-triptych.png 2250 KB
- images/journey-west-original-epic-triptych.png 6440 KB
- images/venice-palace-triptych.png 1812 KB
- manifest.json 2.0 KB
- prompts/p0_cover.md 1.1 KB
- prompts/p1.md 1.4 KB
- prompts/p2.md 1.5 KB
- prompts/p3.md 1.4 KB
- prompts/p4.md 1.5 KB
- prompts/p5.md 1.5 KB
- prompts/p6.md 1.6 KB
- prompts/p7.md 1.9 KB
- prompts/p8.md 3.0 KB
- prompts/README.md 1.0 KB
- README.md 4.5 KB
- 锦绣/cover-横屏.jpg 163 KB
- 锦绣/cover-竖屏.jpg 207 KB
- 锦绣/readme.md 2.9 KB
- 锦绣/slides/slide-1.jpg 2250 KB
- 锦绣/slides/slide-2.jpg 1812 KB
- 锦绣/slides/slide-3.jpg 6440 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.
- 13d ago First seen · 65 lines · 182 tokens per session scan A 875115288bbb
cinema-dna-21x9x3电影感三联 is a skill published in the GitHub repository huangrichao2020/pretty-skills (54 stars, last pushed yesterday), licensed MIT. It adds 182 tokens to every session and 1,118 once invoked, about $0.0009 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
cn-check
Install and run the Continue CLI (cn) to execute AI agent checks on local code changes. Use when asked to "run checks", "lint with AI", "review my changes with cn", or set up Continue CI locally.
story-long-write
A Chinese-language coaching workflow for creating a long online novel from the initial idea through the outline and chapter text. It starts by defining the intended emotion, then uses research and story-planning stages to guide writing.
story-import
A Chinese-language workflow for turning an existing novel into a structured writing project that can be continued later.
story-long-analyze
A structured process for deeply analysing a long online novel, starting with its opening three chapters and continuing chapter by chapter.
story-review
A review process for finding problems in a novel’s structure, characters, wording, and world rules. It can use several reviewers or one reviewer when others are unavailable.
story-short-write
A tool for writing complete short online novels, from the initial idea through the finished manuscript. It focuses on a single main emotional effect and usually uses first-person narration.