gooseworks-ai/goose-skills / skills/video/render-chatgpt-chat
render-chatgpt-chat
VerifiedAssemble a ChatGPT chat-reveal video ad from a thread + timeline JSON — one continuous Playwright recording of a ChatGPT mobile chat (user types with the iOS keyboard up → taps send → keyboard slides down + header cluster swaps in one beat → one gray loading dot → the assistant answer streams in word-by-word) crossfaded into a designed end card, with subliminal ChatGPT SFX and an optional ducked music bed. FREE assembly (Playwright + ffmpeg); the recipe supplies the per-brand thread + timeline + end-card config and gates the paid music call to its own capability. The ChatGPT sibling of render-imessage-chat. Use for the chatgpt-chat format.
| File | Kind | Size |
|---|---|---|
| SKILL.md | skill md | 9.3 KB |
| assets/sfx/key-tap.wav | binary | 3.1 KB |
| assets/sfx/response-done.wav | binary | 13.9 KB |
| assets/sfx/send-tap.wav | binary | 7.8 KB |
| assets/sfx/stream-tick.wav | binary | 2.0 KB |
| scripts/config.example.json | config | 3.5 KB |
| scripts/end-card.template.html | other | 2.5 KB |
| scripts/mockup/generate.js | script | 16.3 KB |
| scripts/mockup/templates/chat.css | other | 16.6 KB |
| scripts/mockup/templates/icons.js | script | 11.5 KB |
| scripts/package.json | manifest | 320 B |
| scripts/record-chat.jsexecutable | script | 14.5 KB |
| scripts/render-end-card.jsexecutable | script | 6.2 KB |
| scripts/stitch.shexecutable | script | 6.6 KB |
| skill.meta.json | config | 229 B |
| tests/smoke-test.md | markdown | 2.4 KB |
scripts/config.example.json
View on GitHub{
"_comment": "Example config for render-chatgpt-chat. The recipe (DB) binds the brand's own thread + timeline + end-card here at remix time. The punchline is the STREAMED ASSISTANT ANSWER — the brand surfacing as the natural response to 'I just asked ChatGPT…'. thread + timeline drive record-chat.js; end_card + brand_name drive render-end-card.js. Keyframe rules: keyboard is up while the user types and slides down on the SAME t as send-tap; header cluster swaps in that same beat; ONE gray loading dot (never three); assistant message has stream:true so it reveals word-by-word. Worked example (a neutral meal-planning build, not any real brand). Creative fields — thread.messages[user-text].text, thread.messages[assistant].text, thread.keyboard.suggestions, the composer-type text in timeline, and any product image message — come from the recipe's choices (question_angle, asker, product_in_thread, music); never copy them as defaults.",
"brand_name": "ExampleBrand",
"width": 750,
"height": 1624,
"sfx": true,
"thread": {
"statusBar": { "time": "9:41" },
"header": {
"style": "plain-title",
"title": "ChatGPT",
"rightIcons": ["personPlus", "dottedCircle"],
"rightIconsAlt": ["edit", "more"]
},
"keyboard": { "layout": "qwerty-lower", "suggestions": ["I", "The", "I'm"], "state": "hidden" },
"messages": [
{ "type": "user-text", "id": "msg-user-1", "text": "what's the easiest way to plan a week of meals?", "popState": "pending" },
{ "type": "loading-dot", "id": "dot-1", "popState": "pending" },
{
"type": "assistant",
"id": "msg-assistant-1",
"stream": true,
"popState": "pending",
"feedback": false,
"text": "The simplest approach most people land on:\n\n* Pick 3-4 dinners you actually like\n* Batch one protein + one grain on Sunday\n* Let an app build the grocery list for you\n\nExampleBrand does all three in one tap — you pick the meals, it plans the week and orders the ingredients."
}
],
"composer": { "placeholder": "Ask ChatGPT" }
},
"timeline": [
{ "t": 0.0, "kind": "keyboard-show" },
{ "t": 0.5, "kind": "composer-type", "text": "what's the easiest way to plan a week of meals?", "dur_sec": 2.6 },
{ "t": 3.3, "kind": "send-tap" },
{ "t": 3.3, "kind": "pop", "target": "msg-user-1" },
{ "t": 3.3, "kind": "composer-clear" },
{ "t": 3.3, "kind": "header-swap", "value": "alt" },
{ "t": 3.3, "kind": "keyboard-hide" },
{ "t": 3.3, "kind": "send-state", "value": "streaming" },
{ "t": 3.65, "kind": "loading-dot-show", "target": "dot-1" },
{ "t": 4.2, "kind": "loading-dot-hide", "target": "dot-1" },
{ "t": 4.2, "kind": "pop", "target": "msg-assistant-1" },
{ "t": 4.25, "kind": "stream-words", "target": "msg-assistant-1", "dur_sec": 6.5, "wps": 7 },
{ "t": 4.6, "kind": "scroll-to", "target": "msg-assistant-1", "dur_ms": 300 },
{ "t": 11.0, "kind": "send-state", "value": "active" }
],
"end_card": {
"bg": "#ffffff",
"fg": "#111111",
"cta_bg": "#111111",
"cta_fg": "#ffffff",
"star_color": "#f5b301",
"wordmark_text": "EXAMPLEBRAND",
"logo_svg": "",
"stars": 5,
"proof_text": "Meal planning in one tap",
"trust_trio": [
{ "label": "Pick your\nmeals", "icon": "check" },
{ "label": "Auto grocery\nlist", "icon": "gift" },
{ "label": "Ready in\nminutes", "icon": "bolt" }
],
"cta_text": "Plan my week",
"dwell_sec": 2.5
}
}
Related skills
| Skill | Stars | Updated | Works with | Status | Install |
|---|---|---|---|---|---|
| finishing-a-development-branchobra/superpowersUse when implementation is complete, all tests pass, and you need to decide how to integrate the work | Stars: 322k | Updated | Claude CodeCodex | Verified | Install |
| systematic-debuggingobra/superpowersUse when encountering any bug, test failure, or unexpected behavior, before proposing fixes | Stars: 322k | Updated | Claude CodeCodex | Verified | Install |
| test-driven-developmentobra/superpowersUse when implementing any feature or bugfix, before writing implementation code | Stars: 322k | Updated | Claude CodeCodex | Verified | Install |
| skill-creatoranthropics/skillsCreate new skills, modify and improve existing skills, and measure skill performance. Use when users want to create a skill from scratch, edit, or optimize an existing skill, run evals to test a skill, benchmark skill performance with variance analysis, or optimize a skill's description for better triggering accuracy. | Stars: 198k | Updated | Claude CodeCodex | Verified | Install |