ai21.net
語言

任務分派主題動態短片

示範影片

任務分派主題動態短片 — 1

提示詞

You're directing a 20-second animated short about the Claude Haiku 5.5 release. You're the director, the art department, the animator, the sound designer and the QA team, and you have real tools to call.

I'm giving you the idea, the tools and the quality bar. Everything else, from the beats to the look to the jokes, is yours to design. I trust your taste more than a beat sheet I could write. Your capabilities are far beyond what you assume, so work like it: plan carefully, push the craft, and use the tools and the time this deserves. Spend generously where it improves the film and economically everywhere else.

Final output: `out/level3.mp4`, 1920×1080, 30fps, exactly 20.0 seconds, with voices, music and sound design. At the end, you'll also save your process as a reusable skill.

---

## 1. The idea

**Opus is overloaded with work it shouldn't be doing.** It's buried in small, repetitive tasks: summaries, classifications, lookups, compactions. Then it has a realization: it can hand all of that to Haiku. It calls Haiku, Haiku arrives fast and clears the pile, and Opus is finally free to do the hard, important work it's built for.

That's the premise. How you tell it is up to you: the staging, gags, rhythm, camera, character beats, what the eureka moment looks like, how Haiku arrives, and how the delegation plays out. Sonnet can appear if it earns its place.

**Fixed points:**
- 20.0 seconds, 16:9.
- Opus and Haiku are characters in the same family as the Claude character.
- The film must read with the sound off.
- The ending respects reality: Haiku takes the volume, and Opus keeps the hard thinking. Anthropic says Opus 5.5 and Sonnet 5.5 remain the better choice for complex agentic coding, so Haiku is never shown replacing Opus.

---

## 2. Style reference

The reference is Jake Moran's "Animated agent session story": https://www.prompt-motion.com/jake11moran-a269c4. It was made with this skill: https://github.com/heygen-com/hyperframes-community-skills/tree/master/skills/session-story. Read the skill, including its references on motion and the room.

Take from it:
- The hand-drawn watercolour-on-paper look.
- A cozy room as a world.
- Cartoon blocks with faces as characters.
- Physical paper props that carry the story (paper planes as tasks).
- A score that's cued to every action.

Don't copy it. Use it as a starting point and push it further: richer staging, better acting from the characters, more cinematic camera, and a stronger hook. It should look like it belongs to the same family, made by someone who studied it closely.

---

## 3. Facts (lock these before any creative work)

Fetch https://www.anthropic.com/claude-haiku-5-5 and write `facts.json`: every claim you might use, each with the exact supporting sentence from the page. Only claims in `facts.json` may appear on screen or in dialogue.

This is a story first, so use one or two facts at most, woven into the world rather than presented as slides. For example, a price tag being re-stamped, or Haiku's speed shown rather than stated. The film must end on a card with **Claude Haiku 5.5**.

---

## 4. Audience and hook

The audience is AI and developer Twitter/X: people who use Claude every day and know the model names and the jokes about them. Before writing the treatment:
- **Research:** spend a little time on how people currently talk about Opus, Sonnet and Haiku, and what's being said about this launch. Find one or two references or running jokes this audience would recognize and enjoy. Use them only if they fit the story naturally. Never use real people or brand logos.
- **The hook:** the first second has to work as a still frame on a busy timeline. Someone scrolling should instantly see "a character drowning in work" and want to see what happens.
- **Text on screen:** this is motion design that tells a story, not a lyric video. Use text sparingly and only where it adds something: a beat the picture can't carry alone, the fact stamp, and the end card. Integrate it into the world (painted, stamped, written in marker) rather than overlaying it.

---

## 5. Tools

The keys are in `.env`. Pick the best tool for each job, and tell me which you chose and why.

| Tool | Key | Use it for |
|---|---|---|
| Web search and fetch | — | Source page, style reference, audience research |
| Higgsfield (connector) | — | Image generation; call `models_explore` first to pick the best model for flat illustrated characters. Also music or sound effects if its audio models are the best fit. |
| GPT Image (OpenAI) | `OPENAI_API_KEY` | A second image model. Test both on the same prompt and keep whichever matches the style better. |
| ElevenLabs | `ELEVENLABS_API_KEY` | Character voices, sound effects, and music (Eleven Music) |
| Remotion | — | The film itself |
| ffmpeg + Python | — | Audio analysis, frame extraction, checks |
| Subagents | — | Parallel research and independent review |

---

## 6. Order of work

### Step 1: Treatment
Write `treatment.md`:
- Your take on the story in one paragraph.
- The beat sheet with timings.
- What happens in each shot: camera, acting, the gag.
- Where the music hits.
- What each character says.
- Which fact appears and how.
- Why this version is the strongest way to tell it.

Write two or three distinct treatments, then pick one and explain why.

### Step 2: Style bible
Write `style/bible.md`:
- Palette: 6 colours maximum, with hex values and a reason for each.
- Ink line rules: weight, and the "boiling" redraw jitter.
- Watercolour and paper texture.
- Lighting.
- Type: local font files only.
- Character design rules for Opus and Haiku: size ratio, shapes, how each one moves, and their expression set.

### Step 3: Key art (images as the base, no video generation)
The generated images are your key frames and design references. You are the in-betweener. Generate:
1. **Style frames:** 3 options of the world. Pick one.
2. **Character sheets:** Opus and Haiku, each with front, three-quarter and side views and their full expression set. Use the chosen style frame as a reference so everything shares one world.
3. **Key poses:** one image per key pose in your treatment (roughly 6–10), each built from the character sheets and the style frame, matching the camera and composition of the shot.

Put everything on one contact sheet.

**Stop and wait for my approval** before building anything.

The images are references. The final film is drawn in code to match them, and generated images never appear on screen. Trace the shapes, poses, proportions and composition from the key art into SVG, and animate between them.

### Step 4: Audio first
The film's timing comes from the audio.
1. **Voices:** audition at least 2 ElevenLabs voices per character. Opus should feel warm, low and deliberate. Haiku should feel quick, bright and eager. Generate each line separately, with 2 takes, and keep the best delivery.
2. **Music:** generate a track that fits your treatment, about 22s long, with its structure matching your beats: for example, a drop when Haiku arrives. If the generated track won't land on your beats, trim and offset it with ffmpeg rather than changing the picture.
3. **Sound effects:** a sound for every physical action. Paper, whooshes, impacts, the lightbulb, stamps.
4. **Timing map:** detect the music's beat onsets and write `timing.json`. It holds every beat time, the drop frame, each voice line's start and end frames, and every key action snapped to the nearest beat. All animation timing reads from `timing.json`, with nothing hardcoded.
5. Play me the audio-only mix before building the picture.

### Step 5: Build in Remotion
- **Components:** one per character, prop and set piece. Story beats live as data in `story.json`.
- **Drawing:** watercolour fills via SVG turbulence and displacement filters, a multiply-blended paper texture, and boiling ink lines.
- **Motion craft:** anticipation before every big action, follow-through after, squash and stretch, springs for landings, arcs for every moving object, and no linear easing.
- **Acting:** the characters have to perform. Give them readable poses, holds where the audience needs to read a face, and timing that's funny.
- **Mouths:** mouth shapes driven by the voice track's loudness. They must be still when the character is silent.
- **Camera:** push-ins, a whip or a shake where it helps. Motivate every camera move.
- **Mix:** music, voices and sound effects on separate layers. Duck the music under dialogue.

---

## 7. Verification loops (do not skip any)

1. **Key-pose match:** at every key pose, render the frame and compare it side by side with its key art. Write what differs and fix it.
2. **Sound-off read:** render a silent cut. A fresh subagent that has seen nothing else reviews a contact sheet at 2 frames per second and retells the story. If it can't, the staging failed. Fix it and repeat.
3. **Sync check:** list every catch, landing, stamp and dialogue line with its actual frame vs its `timing.json` target. Everything must be within 1 frame.
4. **Fact check:** every word on screen and in dialogue, matched to `facts.json`. Cut anything unmatched.
5. **Technical:** duration exactly 20.0s, stereo audio, peaks below −1 dBFS, no unintended dead air.
6. **Director's review:**
- Watch the whole film at least twice as frames.
- Write a brutal critique as the most demanding motion designer you know: what feels assembled, what's slow, what doesn't land.
- Fix the top 3 issues, then review again.
- Only then hand it over, with a 10-frame contact sheet.

---

## 8. Package it as a skill

Save the full pipeline as `.claude/skills/launch-film/SKILL.md`, so that next time *"Make a launch film for [URL] about [idea]"* is enough.

The skill should include:
- The fact lock
- The treatment process
- The style bible as a reference file
- The key-art process with both image models
- Voice auditions
- Music and sound effects
- The timing map
- The reusable Remotion components
- Every verification loop

---

## Approval gates
1. `facts.json` and the chosen treatment
2. Style bible, character sheets and key poses → **wait for my approval**
3. Audio-only mix and `timing.json`
4. Final film, contact sheet and critique
5. Skill

Keep a task list throughout. At each gate, show me the work, not a description of it.

中文翻譯

你正在執導一部 20 秒的動畫短片,主題是 Claude Haiku 5.5 的發佈。你同時是導演、美術部門、動畫師、音效設計師和 QA 團隊,而且你有真實可用的工具可以調用。

我給你想法、工具和質量標準。其餘的一切,從節拍到視覺風格再到笑點,都由你來設計。比起我自己能寫出的節拍表,我更相信你的品味。你的能力遠遠超出你自己的假設,所以就按這個水準去工作:仔細規劃,把工藝推到極致,用好工具,也用好這件事值得投入的時間。凡是能提升影片的地方就大方投入,其餘地方則精打細算。

最終輸出:`out/level3.mp4`,1920×1080,30fps,精確 20.0 秒,包含配音、音樂和音效設計。最後,你還要把你的流程保存成一個可複用的 skill。

---

## 1. 想法

**Opus 被大量本不該它做的工作壓垮了。** 它埋沒在瑣碎重複的任務裏:摘要、分類、查詢、壓縮。然後它意識到:它可以把這些統統交給 Haiku。它調用 Haiku,Haiku 迅速趕到,清空了積壓,Opus 終於騰出手來做它生來就該做的、困難而重要的工作。

這就是前提。怎麼講由你決定:場面調度、搞笑橋段、節奏、鏡頭、角色節拍、靈光一現的時刻長什麼樣、Haiku 怎麼登場,以及這次任務委派如何展開。如果 Sonnet 配得上出場,它可以出現。

**固定要點:**
- 20.0 秒,16:9。
- Opus 和 Haiku 是與 Claude 角色同屬一個家族的角色。
- 影片在靜音狀態下也必須看得懂。
- 結尾要尊重現實:Haiku 承擔數量,Opus 保留硬核思考。Anthropic 說,在複雜的 agentic coding 上,Opus 5.5 和 Sonnet 5.5 仍然是更好的選擇,所以絕不能讓 Haiku 取代 Opus。

---

## 2. 風格參考

參考作品是 Jake Moran 的 “Animated agent session story”:https://www.prompt-motion.com/jake11moran-a269c4。它是用這個 skill 做的:https://github.com/heygen-com/hyperframes-community-skills/tree/master/skills/session-story。讀一讀這個 skill,包括裏面關於動效和房間的參考。

從中借鑑:
- 手繪水彩紙感。
- 以一個溫馨的房間作爲世界。
- 帶面孔的卡通積木作爲角色。
- 推動敘事的實體紙道具(紙飛機代表任務)。
- 每個動作都有對應的配樂提示。

不要照抄。把它當作起點,再往前推:更豐富的調度、更好的角色表演、更有電影感的鏡頭,以及更強的鉤子。它應該看起來同出一門,而且是一個仔細研究過參考的人做的。

---

## 3. 事實(在任何創作之前先鎖定)

抓取 https://www.anthropic.com/claude-haiku-5-5,寫出 `facts.json`:你可能用到的每一條說法,都要附上頁面上精確的支撐句。只有 `facts.json` 裏的說法才能出現在畫面或對白裏。

這首先是一個故事,所以最多用一兩條事實,把它們織進世界裏,而不是像放幻燈片一樣擺出來。比如,一個被重新蓋章的價籤,或者把 Haiku 的速度“演”出來,而不是“說”出來。影片必須以一張寫有 **Claude Haiku 5.5** 的卡片收尾。

---

## 4. 受衆與鉤子

受衆是 AI 和開發者 Twitter/X:每天都用 Claude、熟悉模型名字以及關於它們的梗的人。在寫闡述稿之前:
- **調研:** 花一點時間看看現在大家怎麼談論 Opus、Sonnet 和 Haiku,以及關於這次發佈都有哪些說法。找一兩個這個受衆能認出來並會心一笑的典故或常駐梗。只有當它們能自然融入故事時才用。絕不要使用真實人物或品牌 logo。
- **鉤子:** 第一秒必須在繁忙的信息流裏作爲一張靜止畫面就成立。刷到的人應該一眼看出“一個被工作淹沒的角色”,並想知道接下來會發生什麼。
- **畫面上的文字:** 這是用動態設計講故事,不是歌詞視頻。文字要剋制,只在能加分的地方使用:畫面單獨承載不了的一個節拍、事實印章,以及片尾卡。把文字融進這個世界(畫上去、蓋上去、用馬克筆寫上去),而不是直接疊在畫面上。

---

## 5. 工具

密鑰都在 `.env` 裏。爲每項工作挑選最合適的工具,並告訴我你選了什麼、爲什麼。

| 工具 | 密鑰 | 用途 |
|---|---|---|
| 網頁搜索與抓取 | — | 來源頁面、風格參考、受衆調研 |
| Higgsfield(連接器) | — | 圖像生成;先調用 `models_explore`,爲扁平插畫角色挑選最合適的模型。如果它的音頻模型最合適,也可用於音樂或音效。 |
| GPT Image(OpenAI) | `OPENAI_API_KEY` | 第二個圖像模型。用同一個提示詞測試兩者,保留更貼合風格的那個。 |
| ElevenLabs | `ELEVENLABS_API_KEY` | 角色配音、音效和音樂(Eleven Music) |
| Remotion | — | 影片本身 |
| ffmpeg + Python | — | 音頻分析、抽幀、檢查 |
| Subagents | — | 並行調研與獨立審閱 |

---

## 6. 工作順序

### 第 1 步:闡述稿
寫出 `treatment.md`:
- 用一段話講你對這個故事的處理。
- 帶時間點的節拍表。
- 每個鏡頭裏發生什麼:鏡頭、表演、笑點。
- 音樂在哪些點落下。
- 每個角色說什麼。
- 哪條事實出現,以及怎麼出現。
- 爲什麼這個版本是講這個故事最有力量的方式。

寫兩到三個不同的闡述稿,然後選一個,並解釋原因。

### 第 2 步:風格聖經
寫出 `style/bible.md`:
- 色板:最多 6 種顏色,給出十六進制值和每種顏色的理由。
- 墨線規則:粗細,以及“沸騰”式的重繪抖動。
- 水彩與紙張紋理。
- 燈光。
- 字體:僅使用本地字體文件。
- Opus 和 Haiku 的角色設計規則:體型比例、形狀、各自的運動方式,以及表情組。

### 第 3 步:主視覺(以圖像爲基礎,不用視頻生成)
生成的圖像是你的關鍵幀和設計參考。你來當中間畫師。生成:
1. **風格幀:** 3 個世界的方案。選一個。
2. **角色設定圖:** Opus 和 Haiku,各含正面、四分之三側面和側面視圖,以及完整表情組。用選定的風格幀作爲參考,讓所有內容共享同一個世界。
3. **關鍵姿勢:** 闡述稿裏的每個關鍵姿勢一張圖(大約 6–10 張),每張都基於角色設定圖和風格幀構建,並與該鏡頭的機位和構圖匹配。

把所有內容彙總到一張總覽圖上。

**停下來,等我批準**,然後再開始搭建任何東西。

這些圖像只是參考。最終影片是用代碼繪製出來與它們匹配的,生成的圖像絕不會出現在屏幕上。把主視覺裏的形狀、姿勢、比例和構圖描摹成 SVG,然後在它們之間做動畫。

### 第 4 步:音頻優先
影片的時間節奏來自音頻。
1. **配音:** 每個角色至少試聽 2 個 ElevenLabs 聲音。Opus 應該溫暖、低沉、從容。Haiku 應該輕快、明亮、躍躍欲試。每句臺詞單獨生成,每條錄 2 遍,保留最好的一版演繹。
2. **音樂:** 生成一段符合你闡述稿的曲子,約 22 秒長,結構要與你的節拍對應:比如 Haiku 登場時來一個 drop。如果生成的曲子對不上你的節拍,就用 ffmpeg 裁剪和偏移它,而不是改畫面。
3. **音效:** 每個物理動作都要有聲音。紙張、呼嘯、撞擊、燈泡、蓋章。
4. **時間映射:** 檢測音樂的節拍起點,寫出 `timing.json`。它記錄每個節拍時間、drop 所在的幀、每句配音的起始與結束幀,以及每個吸附到最近節拍的關鍵動作。所有動畫的時間都從 `timing.json` 讀取,不得硬編碼。
5. 在搭建畫面之前,先放給我聽純音頻混音。

### 第 5 步:在 Remotion 中搭建
- **組件:** 每個角色、道具和場景單元各一個。故事節拍以數據形式存放在 `story.json` 裏。
- **繪製:** 通過 SVG 湍流和置換濾鏡實現水彩填充,正片疊底混合紙張紋理,以及沸騰的墨線。
- **運動工藝:** 每個大動作前有預備,動作後有跟隨,擠壓與拉伸,落地用彈簧,每個移動物體都走弧線,不使用線性緩動。
- **表演:** 角色必須真的在演。給他們清晰可讀的姿勢,在觀衆需要讀懂表情的地方留住,以及好笑的節奏。
- **嘴型:** 嘴型由配音軌道的響度驅動。角色沉默時嘴必須不動。
- **鏡頭:** 推鏡、甩鏡或震動,在有用的時候用。每一個運鏡都要有動機。
- **混音:** 音樂、配音和音效分軌。對白時把音樂壓低。

---

## 7. 驗證閉環(一個都不能跳過)

1. **關鍵姿勢匹配:** 在每個關鍵姿勢處渲染該幀,與對應的主視覺並排比較。寫下差異並修正。
2. **靜音可讀性:** 渲染一個無聲版本。讓一個全新的、沒看過任何其他內容的 subagent 以每秒 2 幀查看總覽圖,並複述故事。如果它複述不出來,就是調度失敗。修正後重來。
3. **同步檢查:** 列出每個接住、落地、蓋章和對白句的實際幀與 `timing.json` 目標幀。所有誤差必須在 1 幀以內。
4. **事實覈查:** 屏幕上和對白裏的每個字詞都要與 `facts.json` 對應。對不上的刪掉。
5. **技術:** 時長恰好 20.0 秒,立體聲,峯值低於 −1 dBFS,沒有意外的空白。
6. **導演審閱:**
- 以逐幀方式把整部影片至少看兩遍。
- 以你認識的最苛刻的動態設計師的身份寫一份毫不留情的批評:哪裏像是拼湊出來的,哪裏拖沓,哪裏沒打中。
- 修正最重要的 3 個問題,然後再次審閱。
- 到這時才交付,並附上一張 10 幀總覽圖。

---

## 8. 把它打包成一個 skill

把完整流程保存爲 `.claude/skills/launch-film/SKILL.md`,這樣下次只要說 *“爲 [URL] 做一部關於 [idea] 的發佈短片”* 就夠了。

這個 skill 應包含:
- 事實鎖定
- 闡述稿流程
- 作爲參考文件的風格聖經
- 使用兩個圖像模型的主視覺流程
- 配音試音
- 音樂與音效
- 時間映射
- 可複用的 Remotion 組件
- 每一個驗證閉環

---

## 審批關卡
1. `facts.json` 和選定的闡述稿
2. 風格聖經、角色設定圖和關鍵姿勢 → **等我批準**
3. 純音頻混音和 `timing.json`
4. 最終影片、總覽圖和批評意見
5. Skill

全程維護一份任務清單。每到一道關卡,給我看作品本身,而不是描述。

溯源

原作者
kelanoo
發佈日期
2026-10-08(由推文 ID 反解)
原始出處
查看原帖 ↗
收錄來源
zhuyansen/awesome-opus-5.5-video · 2108199183983497433 · 未聲明授權