gooseworks-ai/goose-skills / skills/video/video-production-harness
video-production-harness
VerifiedFull video production sequence with script review, actual ingredient choices, controlled generation, editing, evidence-based quality review, polish, captions and delivery. A host binding supplies project storage, authentic approvals, provider access and billing.
references/genres/chat-ui.md
View on GitHub# Chat UI
A story told as a phone chat, or a question answered in an AI chat. Routing rows are named as in the shot-routing guide.
## Shot list skeleton
1. 0-1.2 s framed phone; the first message is sent by 1.2 s.
2. Hook: the photo or line the chat is about.
3. Banter: quick replies, typing dots before each received text.
4. Reveal: the product or offer in a message.
5. About 0.6 s pause, the last message, about 0.6 s hold.
6. 0.3 s crossfade to a static end card, 2.5-3.5 s.
For AI chat, first inspect the actual app and its current interaction; question entry, thinking, tool use and reply presentation follow that app rather than this card's timing examples.
## Ground the depicted app
Use current screenshots, a screen recording, official documentation or an authorized browser session to verify the app's layout, sender roles, input syntax, connector/tool indicators and CTA. Save the source and checked behavior with the scene. A reference ad sets the storytelling, not another app's commands or UI. Do not invent mentions, slash commands, a separate tool sender or an installation step. If an essential behavior cannot be verified, resolve it before building that scene. Render actual product outputs when a scene claims to show them; a mock card is not evidence the product made an ad.
## Routing rows
Chat screen · Kinetic type / motion card · Music · End card.
## Pacing
- 7-14 messages over 15-45 s; reactions 0.25-0.45 s apart, sentences 0.6-0.9 s, typing dots about 0.7 s.
- AI chat: question at most 16 words; answer 40-75 words at about 7 words/s; 11.5-21 s.
## Nearest template
`imessage` (AI chat: `chatgpt`)
## Top 5 failures and fixes
- Flicker at scene joins → record one continuous take; the only cut is to the end card.
- Sound on typing or thinking dots → keep them silent; sound only when a message lands.
- The AI chat looks like another app → follow the verified app behavior, including tool attribution and reply roles; do not reuse another app's loading or mention convention.
- An attached screenshot looks generated → rebuild the real app's layout, colours and type in HTML.
- The end card drifts or fakes the logo → static card, real logo; star ratings only with brand proof.
Related skills
| Skill | Stars | Updated | Works with | Status | Install |
|---|---|---|---|---|---|
| receiving-code-reviewobra/superpowersUse when receiving code review feedback, before implementing suggestions, especially if feedback seems unclear or technically questionable - requires technical rigor and verification, not performative agreement or blind implementation | Stars: 323k | Updated | Claude CodeCodex | Verified | Install |
| requesting-code-reviewobra/superpowersUse when completing tasks, implementing major features, or before merging to verify work meets requirements | Stars: 323k | Updated | Claude CodeCodex | Verified | Install |
| using-git-worktreesobra/superpowersUse when starting feature work that needs isolation from current workspace or before executing implementation plans - ensures an isolated workspace exists via native tools or git worktree fallback | Stars: 323k | Updated | Claude CodeCodex | Verified | Install |
| verification-before-completionobra/superpowersUse when about to claim work is complete, fixed, or passing, before committing or creating PRs - requires running verification commands and confirming output before making any success claims; evidence before assertions always | Stars: 323k | Updated | Claude CodeCodex | Verified | Install |