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 phileiny/h3-storyboard-skill --skill h3-storyboardgit clone --depth 1 https://github.com/phileiny/h3-storyboard-skillWrote 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/phileiny/h3-storyboard-skill/h3-storyboard)<a href="https://agentmods.dev/skills/phileiny/h3-storyboard-skill/h3-storyboard"><img src="https://agentmods.dev/badge/skills/phileiny/h3-storyboard-skill/h3-storyboard/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/phileiny/h3-storyboard-skill/h3-storyboard"><img src="https://agentmods.dev/badge/skills/phileiny/h3-storyboard-skill/h3-storyboard.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 | $0.00114 | $0.35193 |
| Opus 5.5 | $0.00046 | $0.14077 |
| Sonnet 5.5 | $0.00023 | $0.07039 |
| Haiku 4.5 | $0.00011 | $0.03519 |
Grade A, and why
h3-storyboard 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 1mo 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 — 1,991 lines — stays where its author put it; the contents beside it link to each section on GitHub.
H3 分鏡與表演
minimax-h3 那份 skill 教你怎麼把已經想好的東西寫成 H3 格式。
這份教你怎麼想——劇本怎麼拆成鏡頭、情緒怎麼變成模型演得出來的動作。
官方和社群的 skill 都停在翻譯層,沒有人做這段(instann/minimax-h3-director
把「自動拆鏡」列在 roadmap,還沒做)。下面全部是實拍歸納出來的,
每一條都標了驗證狀態。
零之二、⭐⭐⭐ 寫每一顆之前:先問【這顆要呈現什麼】,再決定構圖,最後才寫內容
構圖不是「內容寫完之後順手決定的東西」。它是第一個決定,因為它決定了其他東西演不演得出來。
✗ 常見的寫法(也是最容易失敗的)
內容 → 表演 → 對白 → ……最後順手填一個景別
結果:景別永遠是最中性的那個(置中、平視、正面),
而中性構圖 = 訪談感、證件照感 —— 它不會傳達任何情緒強度
✅ 正確的順序
① 這一顆在戲裡要達成什麼?(一句話,用觀眾的感受寫,不是用動作寫)
「讓人覺得這是他這輩子最高的一刻」而不是「他抬頭看大家」
② 什麼構圖能達成它? ← 機位高度、景別、人在畫面裡的位置、前景、視線方向
③ 然後才寫表演、光、對白、道具
為什麼這個順序不能顛倒
表演 臉佔畫面 1/7 時,「下眼瞼微抬」無處可畫 → 先有景別,表情才有地方發生
特徵 體格、骨相在遠景會被抹平 → 先有景別,幾何描述才守得住
情緒 「高光時刻」「被排除在外」「他一個人」這些都是【構圖講的】,不是表情講的:
仰角=主導 俯角=被壓 置中=中性 偏置+前方留空=有去向
前景有人=被包圍 背景空曠=孤立
光 先知道機位在哪,才知道光從哪來;反過來寫一定會打架
⭐ 一句話:先決定觀眾要「感覺到什麼」,再決定他們「從哪裡看」,最後才決定畫面裡「發生什麼」。
⚠️ 檢查的方法也要跟著改:驗收一顆鏡頭時,先問「它有沒有達成它在戲裡的目的」, 再問「它有沒有照分鏡拍出來」。後者是檢查表,前者才是導演。 一顆可以完全照分鏡拍出來,而完全沒有達成目的 —— 那時要改的是構圖,不是提示詞的細節。
一、🔴 第一定律:一顆鏡頭裝不下太多節拍
在一顆鏡頭裡塞太多表情節拍,模型會往「平均運動」收斂,把它們全部抹平。 寫了睜眼、揚眉、咬下唇,畫面上什麼都沒發生——而且不會有任何報錯。
三個版本的對照實驗,同一顆震驚戲、同一顆 seed、同樣的臉部節拍:
| 鏡頭結構 | 對白 | 情緒峰值的 PSNR | 結果 | |
|---|---|---|---|---|
| A | 一顆 7 秒特寫,9 個節拍 | 無 | 37–42 dB | 臉完全沒動 |
| B | 拆成三顆 2–3 秒,各一個主節拍 | 無 | 22–23 dB | 表情全部到位 |
| C | 同 B | 加 <d> |
19 dB | 表演幅度再大一些 |
(PSNR 越低表示畫面變化越大。42 dB 等於凍結幀。)
A → B 是主因:拆鏡頭。 從 40 掉到 23,絕大部分的效果在這一步。 B → C 是加成:對白。 從 23 再到 19,有幫助但不是機制。
所以怎麼做
① 先數節拍。 一顆鏡頭超過兩三個表情節拍就要拆。
② 拆成 2–3 秒的短鏡頭,每顆一個主節拍。
③ 有台詞就寫進去(見下),沒有也能成立。
切鏡本身就是表演——觀眾在切點會自動重新讀取角色狀態, 所以拆開不只是為了讓模型執行得到,也是為了讓觀眾看得到。
驗證:2026-08-26,Ref2VA 243 幀,三版對照,seed 固定。 這是隔離過的:A→B 只改鏡頭結構,B→C 只改一句台詞。
旁證:B 站有支純本地實測是「統一首幀 · 10 種情緒 · 一支 6 秒一種情緒」, 同一個結論——一支只裝一種情緒。
⚠️ 這條管的是【臉】—— 大肢體動作的節拍密度上限高很多(2026-10-03,武俠測試)
徒手武打,雙人中遠景(兩人從頭到鞋入鏡)、107 幀、無剪點
一顆約 3 秒寫了 8–9 拍:直拳 → 閃 → 低踢 → 抬腿避 → 再一拳 → 格擋 → 側踢 → 被踢退三步 → 逼近
→ 4 份提示詞 × 2 seed,8 顆都照順序打出來,真速度、不是慢動作;動態量在整段動作期間一直維持高檔
⭐ 被平均掉的是【表情】那種小幅度、要像素才畫得出來的節拍;拳腳、重心轉移、被打退這類全身位移不會。 → 拆武打戲時不要套「兩三拍就拆」—— 一顆 3 秒塞滿招式是可行的,拆鏡的理由改成【換角度】而不是【節拍太多】。 ⚠️ partly:一個專案、一場戲、每份提示詞 2 seed;接觸(拳腳真的打到)沒有逐格驗。
What ships with it
1 file 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.
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.
- 1mo ago Changed · +29 lines 9a9f43181567
- 1mo ago Changed · +28 lines f3611f919dac
- 1mo ago Changed · +132 lines 00596cf8266e
- 1mo ago Changed · +248 lines c919ce50d249
- 1mo ago Changed · +801 lines 259e7b6cd697
- 2mo ago First seen · 753 lines · 114 tokens per session scan A 21580ba97556
h3-storyboard is a skill published in the GitHub repository phileiny/h3-storyboard-skill (190 stars, last pushed 1mo ago), licensed MIT. It adds 114 tokens to every session and 35,193 once invoked, about $0.0005 per session on Opus 5.5. 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.
h3-storyboard compared with skills from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| h3-storyboardphileiny/h3-storyboard-skill | Skill | 190 | 1mo ago | MIT | A | 114 | Claude Code, Codex |
| imagegenopenai/codex | Skill | 133k | yesterday | Apache-2.0 | A | 113 | Codex |
| playwright-climicrosoft/playwright | Skill | 99k | yesterday | Apache-2.0 | A | 19 | Claude Code |
| local-ai-agentsmicrosoft/ai-agents-for-beginners | Skill | 79k | 4d ago | MIT | A | 200 | Claude Code, Codex |
| systematic-debuggingobra/superpowers | Skill | 313k | 3d ago | MIT | A | 21 | Claude Code |
| next-cache-components-adoptionvercel/next.js | Skill | 143k | yesterday | MIT | A | 95 | Claude Code |
| next-partial-prefetching-adoptionvercel/next.js | Skill | 143k | yesterday | MIT | A | 103 | Claude Code |