nexu-io/openmotion / library/design/skills/chat-motion-overlay
chat-motion-overlay
VerifiedGenerate configurable chat motion overlays from a transcript or screenshot, including plain bubble scenes, app-style chat containers, optional device frames, preset or uploaded avatars, nickname display rules, and transparent-video-ready Remotion bundles. Use when Codex needs to create reusable short-form chat clips for Douyin, demo videos, story reenactments, social-message proof scenes, or embeddable alpha overlays for Hyperframe and Remotion workflows.
| File | Kind | Size |
|---|---|---|
| SKILL.md | skill md | 4.7 KB |
| agents/openai.yaml | config | 315 B |
| assets/examples/chat-transcript.txt | markdown | 273 B |
| assets/examples/config-wechat-phone.json | config | 363 B |
| assets/remotion-template/package.json | manifest | 689 B |
| assets/remotion-template/remotion.config.ts | script | 180 B |
| assets/remotion-template/src/chatSpec.ts | script | 426 B |
| assets/remotion-template/src/components/types.ts | script | 1.1 KB |
| assets/remotion-template/src/index.ts | script | 105 B |
| assets/remotion-template/tsconfig.json | config | 307 B |
| references/config-schema.md | markdown | 2.2 KB |
| references/input-format.md | markdown | 2.9 KB |
| references/output-modes.md | markdown | 1.6 KB |
| references/question-strategy.md | markdown | 2.5 KB |
| references/test-matrix.md | markdown | 6.5 KB |
| references/test-report.md | markdown | 7.1 KB |
| scripts/build_chat_overlay_spec.py | script | 10.4 KB |
| scripts/prepare_chat_overlay_bundle.py | script | 4.4 KB |
| scripts/run_test_matrix.py | script | 21.5 KB |
references/question-strategy.md
View on GitHub# Question Strategy
Use this policy when the user triggers `$chat-motion-overlay` without enough detail.
## Principle
Ask only for decisions that materially change the result. Infer the rest.
## Default Behavior
- Infer `container=wechat` when the user says "微信聊天" or gives a WeChat-like screenshot.
- Infer `avatarMode=preset` when no avatar preference is given.
- For screenshot inputs, use visible avatars to help count and group participants, but use preset render avatars unless the user asks for custom or screenshot-derived avatars.
- Infer `deviceFrame=iphone-dynamic-island` only when the user explicitly asks for a phone frame or the prior context strongly implies phone mockup output.
- Infer `nicknameMode=hidden` for one-to-one chat clips unless the user asks to preserve identity or the content is clearly a group chat proof scene.
- Infer `deliveryFormat=mov` when the user says they want to use the result in editing software or says "透明视频片段".
## When To Ask
Ask when any of these are missing and would significantly change the output:
1. Container style
2. Avatar source
3. Device frame presence
4. Delivery format
5. Nickname display mode
## Preferred User-Facing Questions
### Delivery format
Ask:
- `MOV(透明背景,可直接导入剪映 / PR / FCP 叠加)`
- `WebM(透明背景,适合网页 / 浏览器播放)`
- `Remotion 工程(适合继续编辑和拼装)`
- `Hyperframe 工程(适合作为模块继续复用)`
- `JSON 数据(适合程序处理 / 自定义渲染)`
- `预览图 / 预览工程(适合先确认效果)`
Do not ask with internal terms such as `mov-alpha`, `json-spec`, or `hyperframe-ready`.
### Container style
Ask:
- `纯对话气泡`
- `微信`
- `Telegram`
- `Messenger`
### Avatar source
Ask:
- `预设头像`
- `上传头像`
- `部分角色上传头像`
For screenshot inputs, phrase the default clearly:
- `默认用预设头像(更稳定)`
- `我提供头像图片`
- `尝试从截图裁头像(可能不准)`
### Device frame
Ask:
- `不加手机边框`
- `iPhone 灵动岛边框`
### Nickname mode
Ask:
- `不显示昵称`
- `首次出现时显示昵称`
- `每条消息都显示昵称`
## Question Limits
- Ask at most 3 items in one turn.
- If more than 3 items are missing, ask for the highest-impact ones first:
1. delivery format
2. container style
3. avatar source
## If The User Does Not Care
If the user responds with "随便", "默认就行", or equivalent:
- continue with defaults
- list the chosen defaults briefly in the result
Related skills
| Skill | Stars | Updated | Works with | Status | Install |
|---|---|---|---|---|---|
| reverse-engineer-anythingmorluto/reaReverse engineer native, managed, Electron/JavaScript, packaged, firmware, and browser targets with REA, and build agent environments (AgentEnv bundles) of web applications from a live instance or a capture, and of Linux desktop apps with a task from a request. Use shipped-artifact or requested runtime evidence to explain features, compare versions, decompile code, or guide a reconstruction. Skip REA for ordinary source-repository architecture analysis. | Stars: 472k | Updated | Claude CodeCodex | Verified | Install |
| diagnosing-superpowersobra/superpowersUse when a superpowers session went wrong and your human partner wants to know why — repeated work, ignored plans, stumbles, poor results, a skill that didn't fire, "it took too long", "why is it so expensive", "what is it doing" — or wants to build a bug report for the superpowers maintainers, for the current session or a past one identified by id or path, on any harness. | Stars: 322k | Updated | Claude CodeCodex | Verified | Install |
| dispatching-parallel-agentsobra/superpowersUse when facing 2+ independent tasks that can be worked on without shared state or sequential dependencies | Stars: 322k | Updated | Claude CodeCodex | Verified | Install |
| executing-plansobra/superpowersUse when executing an implementation plan in the current session as the implementer yourself — your human partner chose inline execution, or no subagent tool is available | Stars: 322k | Updated | Claude CodeCodex | Verified | Install |