video-prompting
Base craft for AI video prompts inside Palmier Pro across Seedance, Kling, MiniMax H3/Hailuo, Grok, and Veo. Assigns @Image/@Video/@Audio authority, locks identity and screen geography, then stages timed shots. Use for generate_video multimodal prompts, precise video edits, or cinematic AI video beyond simple UGC talking-head beats. For UGC selfie-then-animate prefer ugc-photo-prompts then ugc-video-prompts. Specialized siblings: character-pipeline, cinematic-motion, motion-graphics, podcast-ad.
palmier-io · Static checks on file
Installation
Read the source and dependencies before running a command. Copying does not install or execute anything.
npx skills add palmier-io/palmier-skills --skill video-promptingAbout this skill
name: video-prompting description: Base craft for AI video prompts inside Palmier Pro across Seedance, Kling, MiniMax H3/Hailuo, Grok, and Veo. Assigns @Image/@Video/@Audio authority, locks identity and screen geography, then stages timed shots. Use for generate_video multimodal prompts, precise video edits, or cinematic AI video beyond simple UGC talking-head beats. For UGC selfie-then-animate prefer ugc-photo-prompts then ugc-video-prompts. Specialized siblings: character-pipeline, cinematic-motion, motion-graphics, podcast-ad.
Video Prompting
Write a production brief, not a vibe paragraph. Models fail when every asset competes for identity, motion, camera, and style.
Core rule
Assign authority before action. Every reference gets one job and an explicit boundary on what it must not control. Then: lock continuity → place screen geography → time the shot → light/sound → short negatives.
When to use which skill
| Need | Skill |
|---|---|
| Multimodal / cinematic / edit prompts | this skill |
| Face consistency across stills → video | character-pipeline |
| Documentary handheld / density maps | cinematic-motion |
| Overheard two-person podcast ad | podcast-ad |
| UGC talking-head / product selfie | ugc-photo-prompts → ugc-video-prompts |
| Assemble / caption finished clips | ugc-editing |
| Kinetic titles / flat glass UI / H3 product journey promos | motion-graphics |
Session gates
get_timeline— ifcanGenerateis false, ask user to sign in / subscribe.list_modelsforimage/video/audio— ids and caps drift.- Propose prompt + model + duration + aspect (+ refs). Wait for confirmation — paid, not undoable.
- Fire
generate_*; do not busy-poll. Ready whenget_media({ ids })has nogenerationStatus. Onfailed, report and ask before retry. - Organize with
folder(e.g.Hero/Sheets,Hero/Takes).
Reference wiring
| Tool argument | Prompt tags | Typical job |
|---|---|---|
startFrameMediaRef / endFrameMediaRef | implied first/last frame | Image-to-video anchors |
referenceImageMediaRefs | @Image1… (some Kling: @Element1) | Identity, wardrobe, product, scene |
referenceVideoMediaRefs | @Video1… | Motion timing, camera rhythm |
referenceAudioMediaRefs | @Audio1… | Voice, lip-sync audio, music timing |
generate_image → referenceMediaRefs | model-specific | Still identity lock |
Declare authority when multiple refs are passed:
@Image1 defines identity and wardrobe only. Ignore its background.
@Video1 defines motion timing and camera only. Do not inherit its people or location.
@Audio1 defines <Character>'s voice timbre and delivery only.
Never: “use all references to make the same scene.”
Prompt architecture
Stable truth first; time second; polish last.
[REFERENCE USE] — what each @ImageN / @VideoN / @AudioN controls + ignores
[IDENTITY LOCKS] — count, face, hair, wardrobe, props, voice ownership
[SCENE] — place, time of day, dramatic goal, emotional turn
[DIALOGUE] — exact quoted lines, speakers, delivery + voice pins
[SCREEN GEOGRAPHY] — who/what is left/right/front before anyone moves
[SHOT LIST] — time ranges: framing, action, dialogue, end state
[ACTING] — posture, gaze, gesture, emotional progression
[LIGHT / IMAGE] — light, palette, texture, lens, DoF
[CAMERA] — sizes, move rules, axis, transitions
[SOUND] — ambience, dialogue clarity, music rule
[NEGATIVES] — only the failure modes that matter
Length vs start frame: with startFrameMediaRef alone and simple motion, keep the prompt short (camera + action + speech/SFX) — do not re-describe the still. With multi-ref / timed performance / edits, use the full architecture.
Continuity + shot timing
Lock subject count, face/hair/wardrobe, prop ownership, screen direction, voice ownership. Place people before they move.
Treat duration as an editorial budget (list_models → durations). One primary beat per range: establish → escalate → resolve. Prefer one beat per generate_video call; assemble on the timeline. If dialogue rushes, shorten lines — do not cram two turns into one short clip.
Model routing
Confirm ids/caps via list_models before firing. Default stack for these skills:
| Stage | Prefer | How |
|---|---|---|
| Iterate | seedance-2-mini, MiniMax H3 (hailuo-03), or Flux 3 draft | Mini / H3 as normal generates. Flux 3: draft: true (720p preview; supportsDraft must be true). |
| Final | seedance-2, MiniMax H3 (hailuo-03), or FLUX Enhance | Seedance / H3: full-quality generate (ask before Seedance 1080p/4K). Flux 3 finals are not upscale_media — only enhance a completed draft. |
Flux 3 draft → enhance (not upscale)
- Iterate:
generate_video({ model: "flux-3", draft: true, … }) - When
get_mediashows the draft ready andcanEnhanceDraft: true, final:generate_video({ enhanceDraftMediaRef: "<draftId>" })alone — no prompt/model/inputs. Keeps motion; renders FLUX.3 at 1080p. - Do not use
upscale_mediafor this path. Enhance only works on Flux 3 drafts (canEnhanceDraft); other models have no enhance step.
| Other goals | Prefer | Notes |
|---|---|---|
| Synced spoken dialogue | Kling V3/O3, or Grok | Quoted line; pin voice every beat |
| Stills / sheets | grok-imagine, gpt-image-2, or seedream-v5-pro | Best of multi-room podcast bakeoff; see character-pipeline / podcast-ad |
| Avoid as default | Veo | Content-checker failures common |
Precise editing
- Master — source /
@Video1owns timeline, subjects, camera, audio. - Changes — exact subject/object/region/line/time only.
- Preserve — identity, occlusion, eyelines, camera, dialogue, ambience, duration.
Text and titles
Most video models cannot render reliable readable t
Read the complete source ↗