prompt-expander
Skill0 starsChanged 2 months agoMITView on GitHub
Use when someone hands you a rough video idea, logline or one-liner and wants a full cinematic prompt, when writing or polishing a Gemini Omni Flash / Google Flow prompt, or when planning a conversational edit of an existing clip. Turns "a lonely astronaut finds a flower" into a complete, generation-ready prompt by deciding every dimension a clip can express.
In this repository9 other files it gives its agents.
- cinematographySkill
- dialogue-and-voiceSkill
- identity-and-likenessSkill
- multiclip-continuitySkill
- seedance-promptingSkill
- veo-flow-promptingSkill
- veo-prompt-lintSkill
- viral-short-scriptSkill
- wan-3-promptingSkill
The file
We split this skill into the rules it gives an agent
6 rules. About 0 are common, 6 are distinctive, and 0 are very specific to this project.
≈0
Common · estimate
Many files like this have a rule of this kind.
≈6
Distinctive · estimate
This author's own choices. Worth a look.
0
Very specific
Tied to their project's names, files or tools. Probably skip.
- Common
- Distinctive
- Very specific
- Distinctive: line 38
Read the reference for any axis you are unsure how to fill.
- Distinctive: line 50
Use the defaults table for anything unspecified.
- Distinctive: line 56
Add a timestamp breakdown only if there are genuinely 2–3 beats.
- Distinctive: line 77
State the defaults you used in the Levers list: Never silently bury a consequential choice.
- Distinctive: line 82
Default to assuming and proceeding, noting it in Levers.
- Distinctive: line 91
Use the surgical rule from the audio reference §B1:
≈ “Common” is an estimate: at least 1 in 5 of the 364,980 skill files we read have a rule of the same kind, not the same words. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.
Files
Prompt expander
Turn a rough idea into a complete, generation-ready cinematic prompt — by deliberately deciding every dimension a clip can express, then writing only the relevant choices as natural prose.
Written against Gemini Omni Flash in Google Flow (~10s clips with synced audio; accepts text + reference image/audio/video; supports multi-turn conversational editing). The dimension model transfers to any video generator; the mechanics in §B of the audio reference are Omni-specific.
When to use: someone hands you a logline and wants it "expanded" · you are writing or polishing a Flow prompt · you want to edit an existing clip (use the Editing path, not full expansion).
The dimensions — think through ALL of them
For every prompt, consciously decide each axis, then keep only what serves the idea:
| # | Dimension | Reference |
| 1 | Subject — who/what, 5–8 specific descriptors | subject-action-continuity.md |
| 2 | Action / physics — one beat, strong verbs, secondary motion | same |
| 3 | Setting — location, era, weather, depth layers | same |
| 4 | Camera — shot size, angle, movement, lens | visual-language.md |
| 5 | Light & colour — setup, time of day, palette, film stock | same |
| 6 | Style & mood — visual style, tone word, atmosphere | same |
| 7 | Audio — dialogue / SFX / ambient / music, or explicit silence | audio-and-mechanics.md |
| 8 | Beat — the single emotional moment the clip delivers | subject-action-continuity.md |
Read the reference for any axis you are unsure how to fill. Do not paste the menus into the prompt — choose a few options and write prose.
Workflow
- Parse the idea: pull out subject, action, setting, and any stated mood, genre or audio.
- Classify: a fresh generation, or an edit of an existing clip? An edit goes to the Editing path below.
- Fill the gaps: for each of the 8 dimensions, choose options that fit the mood. Use the defaults table for anything unspecified.
- Respect the constraints (audio reference §B5): one beat per ~10s · always specify audio · phrase exclusions positively · do not rely on rendered on-screen text · keep references to a few.
- Write the prompt as flowing prose in this order: camera → subject → action → setting → light/style → audio. Add a timestamp breakdown only if there are genuinely 2–3 beats.
- Lint the result —
veo-prompt-lint— and fix any ERRORs. If that is unavailable, self-check against the Common mistakes list below. - Present three things: the prompt block, a short Levers list of the assumptions you made so they can be tweaked, and 1–2 suggested conversational edits for iterating.
Sensible defaults (when the user is silent)
| Axis | Default |
| Style | photorealistic, cinematic |
| Camera | slow push-in, eye-level, 50mm, shallow depth of field |
| Light | motivated natural light matched to the setting's time of day |
| Motion | 24fps real-time, natural real-world physics |
| Audio | matching ambient bed + one tied SFX; no dialogue unless implied |
| Aspect | 16:9 (9:16 if "shorts / vertical / phone" is implied) |
| Beat | one clear reveal or reaction |
State the defaults you used in the Levers list. Never silently bury a consequential choice.
Ask vs. assume
Default to assuming and proceeding, noting it in Levers. Ask only when a choice is both consequential and genuinely ambiguous — almost always one of: realistic vs. animated/stylised, dialogue vs. silent, vertical vs. widescreen. Bundle those questions; do not drip them one at a time.
Editing path (an existing clip)
Use the surgical rule from the audio reference §B1:
- One change per turn. Isolate a single dimension; verify before the next edit.
- Freeze-list: name explicitly what stays.
Change <X>. Keep the camera, subject, location, timing, and audio identical. - Batch changes as a numbered list, ending with the same freeze line.
- Remember: editing the spoken audio of a clip is currently restricted.
Worked example
Idea: "a lonely astronaut finds a flower on a dead planet"
Expanded prompt:
Slow push-in, low-angle medium shot on a weathered astronaut in a scuffed white EVA suit, cracked gold visor reflecting a dim red sun, kneeling on cracked ochre desert rock. He slowly reaches a trembling gloved hand toward a single impossible blue flower pushing up through the dust; grit drifts in the low gravity. Vast empty rust-coloured plain stretches to a hazy horizon behind him, distant dust devils. Bleak desaturated palette with one vivid blue accent, harsh low sunlight, 35mm film grain, melancholic and awestruck. Ambient: faint wind and the hiss of suit air. SFX: soft servo whir as his hand moves. No dialogue, no music.
Levers: photorealistic (could go painterly) · 16:9 (could be 9:16) · silent (could
add a breath or VO) · single push-in (could add a [00:06-00:10] insert close-up on the
flower).
Suggested edit: Change the flower from blue to glowing bioluminescent teal. Keep
the camera, subject, location, timing, and audio identical.
Common mistakes
- Pasting whole menu tables into the prompt — pick a few options, write prose.
- Forgetting audio → the model invents unwanted speech.
- Cramming a multi-scene story into 10 seconds — one beat.
- "no people / no text" phrasing → flip it positive ("a deserted street", "a clear sky").
- "locked tripod" → use "static shot".
The reference menus
| File | Covers |
visual-language.md | Shot sizes, angles, camera movements, lenses and optics, composition, motion feel, lighting setups, time of day, colour temperature, palettes and grading, film stock, visual styles, mood, texture |
subject-action-continuity.md | Subject descriptor slots (people, creatures, objects), action verbs and pacing, physics cues, setting layers, continuity and multi-shot sequencing, emotional beats |
audio-and-mechanics.md | Dialogue, SFX, ambient, music, sync, the silence gotcha — plus Omni Flash mechanics: conversational editing, reference inputs, exclusions, timestamps, constraints |
Does it work?
Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.
No reviews yet
People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.
- It worked
- Partly
- It didn't
Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.
Your trail
Files you open will collect here, so you can find them again.
Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.
Now do this for your own.
Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.

