h3-storyboard

h3-storyboard is a skill for Claude Code, Codex from phileiny/h3-storyboard-skill. It costs 114 tokens per session (35,193 once invoked), scanned A, original, MIT.

A skill that turns a script into shot lists for MiniMax H3, a video-generation model. It breaks scenes into short shots and describes timing, emotional beats, facial expressions, and acting direction.

In plain words
What is it for?
It is for planning H3 video shots, directing character expressions, setting beat timings, and improving wooden or unclear performances.
Why use it?
It helps prevent too many emotional changes from being packed into one shot, which can make the generated performance look flat or frozen.

Skill for Claude CodeCodex

Written for no agent in particular: nothing here depends on one.

Good fit It is for planning H3 video shots, directing character expressions, setting beat timings, and improving wooden or unclear performances.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/phileiny/h3-storyboard-skill/h3-storyboard
Install

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.

Any agent
npx skills add phileiny/h3-storyboard-skill --skill h3-storyboard
Clone the repo
git clone --depth 1 https://github.com/phileiny/h3-storyboard-skill

Made for: Claude Code, Codex.

Wrote 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.

agentmods badge for h3-storyboard

README.md
[![agentmods](https://agentmods.dev/badge/skills/phileiny/h3-storyboard-skill/h3-storyboard/github.svg)](https://agentmods.dev/skills/phileiny/h3-storyboard-skill/h3-storyboard)
Your own site
<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.

agentmods 80×15 button for h3-storyboard

Your own site · 80×15
<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>
Per session 114 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 35,193 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe. Third-party audits
  • NVIDIA SkillSpector pass 7 Sept 2026
How audits are shown
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce 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

Measured 1mo ago against content hash 9a9f43181567, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

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.

skills/h3-storyboard/SKILL.md · 1,991 lines

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。

Read the full file on GitHub · 1,991 lines

Files

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.

Changes

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.

  1. 1mo ago Changed · +29 lines 9a9f43181567
  2. 1mo ago Changed · +28 lines f3611f919dac
  3. 1mo ago Changed · +132 lines 00596cf8266e
  4. 1mo ago Changed · +248 lines c919ce50d249
  5. 1mo ago Changed · +801 lines 259e7b6cd697
  6. 2mo ago First seen · 753 lines · 114 tokens per session scan A 21580ba97556

Subscribe to this mod's changes

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.

Related

h3-storyboard compared with skills from other repositories

h3-storyboard next to 6 skills from other repositories
ModTypeStarsLast pushLicenceScanTokensWorks with
h3-storyboardphileiny/h3-storyboard-skillSkill1901mo agoMITA114Claude Code, Codex
imagegenopenai/codexSkill133kyesterdayApache-2.0A113Codex
playwright-climicrosoft/playwrightSkill99kyesterdayApache-2.0A19Claude Code
local-ai-agentsmicrosoft/ai-agents-for-beginnersSkill79k4d agoMITA200Claude Code, Codex
systematic-debuggingobra/superpowersSkill313k3d agoMITA21Claude Code
next-cache-components-adoptionvercel/next.jsSkill143kyesterdayMITA95Claude Code
next-partial-prefetching-adoptionvercel/next.jsSkill143kyesterdayMITA103Claude Code