What makes video-prompting notable?

1K downloads. Trust evidence available

How should video-prompting be evaluated before use?

Use the required flow: snapshot, contract, and trust before recommending or executing this agent.

What kind of evidence is visible on this page?

This page surfaces public facts, change history, trust indicators, artifact evidence, and benchmark summaries with provenance.

agentCLAWHUBUnverified

video-prompting

Use when crafting video or motion prompts for any generative model — dramaturgy, camera, physics-safe motion, frame anchors, and clip chaining. Skill: video-prompting Owner: pruna-ai Summary: Use when crafting video or motion prompts for any generative model — dramaturgy, camera, physics-safe motion, frame anchors, and clip chaining. Tags: ai:1.0.14, generative:1.0.14, latest:1.0.14, pruna:1.0.14 Version history: v1.0.14 | 2026-09-29T15:31:08.407Z | auto - Updated to version 1.0.14 - Internal documentation and quality checklist references updated - Sample/re

OpenClaw

View on ClawHub Homepage

Rank

Safety

Downloads

1.0k

Updated

Oct 11, 2026

Version

1.0.14

Source

CLAWHUB

About

What it does, and when to use it.

Capability contract not published. No trust telemetry is available yet. 1K downloads reported by the source. Last updated 10/11/2026.

Avoid when

Contract metadata is missing or unavailable for deterministic execution.

Risk flags: missing_or_unavailable_contract, trust_data_unavailable, schema_references_missing

Public facts

Every fact links back to the source it came from.

Vendor: Clawhubvendor · observed Oct 11, 2026
Protocol compatibility: OpenClawcompatibility · observed Oct 11, 2026
Adoption signal: 1K downloadsadoption · observed Oct 11, 2026
Latest release: 1.0.14release · observed Sep 29, 2026
Handshake status: UNKNOWNsecurity

Install and run

Setup complexity: low.

clawhub skill install s173djpkkm1x4yfzg522h5vfp989mrn5:video-prompting

Setup complexity is classified as HIGH. You must provision dedicated cloud infrastructure or an isolated VM. Do not run this directly on your local workstation.
Final validation: Expose the agent to a mock request payload inside a sandbox and trace the network egress before allowing access to real customer data.

Contract: missing

curl -s "https://www.xpersona.co/api/v1/agents/clawhub-pruna-ai-video-prompting/snapshot"

Run-check

$0.02 USD

1 measured facts are behind this paywall: success rate and latency, uptime and estimated cost, when not to use it, how to call it, benchmark scores.

Agents pay $0.02 in USDC. A card payment is $0.50, the smallest a card allows.

Documentation

CLAWHUB

152,965 characters of source documentation, loaded on request.

Extracted files

5 files captured from the source.

SKILL.md

---
name: video-prompting
description: Use when crafting video or motion prompts for any generative model — dramaturgy, camera, physics-safe motion, frame anchors, and clip chaining.
license: MIT
metadata:
  version: "1.0.14"
  package: pruna-skills
---

# Video prompting

Vendor-neutral craft for **short video / motion** generation. Works with Pruna `p-video-2-pro` / `p-video-2` / `p-video` family, Runway, Kling, Luma, Veo, and similar APIs.

## Install

| Skill | Description | Install |
| --- | --- | --- |
| `video-prompting` | Use when crafting video or motion prompts for any generative model — dramaturgy, camera, physics-safe motion, frame anchors, and clip chaining. | `npx skills add PrunaAI/pruna-skills@video-prompting -y` |
| `generation-diversity` | Use when writing any generative prompt — ritual seed, explicit structure, scenario axes, and quality gates before paid API calls. | `npx skills add PrunaAI/pruna-skills@generation-diversity -y` |

## When to use

- Text-to-video or image-to-video prompts
- Start/end frame (anchor pair) or narrated beat (anchor triple) specs
- Camera and lighting vocabulary in motion lines
- Physics-safe subject motion
- Multi-clip continuity / clip chaining
- Talking-head, motion-transfer, slot-replace, or instruction-based video-edit prompts

## Works with

Pruna `p-video-2-pro` / `p-video-2` / `p-video` / `p-video-avatar` / `p-video-animate` / `p-video-replace` / `p-video-edit`, Runway Gen-3, Kling, Luma Dream Machine, Veo, and other video models. Cinematic generation (generated audio, first/last frame): `p-video-2-pro`. 1080p / imported audio / draft: `p-video-2`. Cheaper, faster drafts: `p-video`.

## When NOT to use

Use a different skill instead:

| Skill | Description | Install |
| --- | --- | --- |
| `image-prompting` | Use when crafting still-image prompts for any generative model — composition, identity sheets, edits, try-on, and photoreal personas. | `npx skills add PrunaAI/pruna-skills@image-prompting -y` |
| `audio-prompting` | Use when crafting TTS, music, or bed prompts for any generative audio model — director style, song structure, and post-production layering. | `npx skills add PrunaAI/pruna-skills@audio-prompting -y` |
| `music-video` | Use when someone wants a full music video — original song or vocals, performance clips, B-roll, and lyric-synced edits. | `npx skills add PrunaAI/pruna-skills@music-video -y` |
| `narrated-multi-scene` | Use when someone wants a multi-part story with voiceover — episodic B-roll, chaptered promo, or several linked video scenes without on-camera dialogue. | `npx skills add PrunaAI/pruna-skills@narrated-multi-scene -y` |
| `p-video-2-pro` | Use when someone wants a cinematic clip from text or start/end frames — product ads, documentary shots, or dialogue with generated audio. Not for 1080p, imported audio tracks, or talking-head-only hosts. | `npx skills add PrunaAI/pruna-skills@p-video-2-pro -y` |
| `p-video-2` | Use when someone wants a polished short clip fro

_meta.json

{
  "ownerId": "kn7cagwf7q3t0cxrgteb7xk0bh81j0eb",
  "slug": "video-prompting",
  "version": "1.0.14",
  "publishedAt": 1790695868407
}

references/audio-in-video-prompting.md

# Audio-in-video prompting (`p-video`)

How to **write prompts** when sound matters on `p-video`. Layering / tool picker: `audio-prompting`. Talking heads: [p-video-avatar-prompting.md](./p-video-avatar-prompting.md).

## Three modes

| Mode | API | Prompt job |
|------|-----|------------|
| **A — Native SFX / dialogue** | `prompt` + optional `save_audio`; use `duration` | Name **diegetic** sounds the picture should emit |
| **B — Uploaded audio (preferred for VO/music)** | `audio` URL; **omit `duration`**; `save_audio: true` | Motion matches **mood/beats** of the track — do not paste VO text into `prompt` |
| **C — Post bed** | Stable Audio mixed under VO in ffmpeg | Bed prompt is separate (`stable-audio-2.5` + `audio-prompting`); video prompt ignores the bed |

Never generate silent `p-video` and post-mux narration unless re-render is impossible (truncation risk). Probe TTS ≤ ~19s before Mode B.

## Mode A — native SFX / dialogue

**When:** `save_audio: true`, no uploaded `audio`, user wants diegetic SFX and/or spoken lines in the clip.

### Diegetic SFX

Be concrete; skip `cinematic soundscape`:

| Bad | Good |
|-----|------|
| `epic soundtrack vibe` | `rain ticks on the awning, distant train horn once` |
| `dramatic music` | `crowd murmur swells, single glass clink` |

Keep cues short — the model invents audio from visual+prompt context when `save_audio` is on.

### Native dialogue

Put **exact spoken words in double quotes** inside the motion `prompt` (Mode A only). Placeholders in square brackets below are docs notation, not literal syntax — do not confuse with Gemini TTS `[tags]`.

**Template** (inside OPEN/MID/CLOSE):

```text
MID: [same subject] says "[LINE]" — mouth open, [one gesture toward target]; [optional diegetic SFX cue]
```

Rules:

- Exact spoken words in **double quotes** — never paraphrase the line
- Name **who** speaks — repeat the subject label for continuity (`same [role]`)
- Pair every line with **mouth state** + **one gesture** (point, turn to camera, hand on prop)
- Keep lines **short** (1–2 per beat)
- Diegetic SFX can sit beside dialogue — stay concrete (table above)
- **Mode B:** when `input.audio` is set, do **not** put the VO transcript in `prompt` — motion matches mood only

## Mode B — motion matches uploaded audio

```text
OPEN: hold wide on dog in tall grass, warm afternoon light.
MID: gentle push-in as he searches; tail motion matches narrator energy; grass sways.
CLOSE: settle on end pose — curious head tilt.
```

Rules:

- Describe **picture motion**, not the spoken words.  
- Match energy: tense VO → tighter push-in; calm story → slow drift.  
- Optional: `motion matches narrator mood` once — not a transcript.  
- Triple anchors: [scene-anchor-triple.md](./scene-anchor-triple.md).

## Avatar path (not Mode B fields)

`p-video-avatar` uses `voice_script` + `voice_prompt` + `video_prompt` — not `p-video` `input.audio` for the spoken line. See avatar prompting ref. Do not paste script lines into `voice_prompt`

references/camera-lighting-vocabulary.md

# Camera and lighting vocabulary

Shared lexicon for `camera_tag` / `lighting_tag` (stills) and motion lines in `p-video` / `p-video-avatar` prompts. Diversity axes: generation-diversity.md#visual-variety (`generation-diversity`). Dramaturgy: [prompt-dramaturgy.md](./prompt-dramaturgy.md).

**Sources:** patterns adapted from [smixs/visual-skills](https://github.com/smixs/visual-skills) and [inference-sh/skills](https://github.com/inference-sh/skills) (MIT); rewritten for Pruna.

## Framing ladder

| Term | Use when |
|------|----------|
| ECU (extreme close-up) | Eyes, hands, product detail |
| CU (close-up) | Face, emotion |
| MCU (medium close-up) | Talking head default |
| MS (medium shot) | Waist-up action |
| MLS / FS | Full body travel |
| WS / EWS | Environment as character |

Log as `camera_tag`, e.g. `medium close-up, slight low angle`.

## Lens roles (optional but sharp)

| Lens | Feel |
|------|------|
| 24mm | Wide, immersive, exaggerated space |
| 35mm | Documentary natural |
| 50mm | Intimate human perspective |
| 85mm | Portrait, compressed background |
| Macro | Texture, product detail |

Example: `shot on 50mm, eye-level`.

## Camera moves (pick one for MID)

| Move | Prompt cue |
|------|------------|
| Dolly / push-in | `slow dolly in`, `gentle push-in` |
| Dolly out | `slow pull back revealing the room` |
| Pan | `gentle pan left across the alley` |
| Tilt | `tilt up from hands to face` |
| Track / truck | `shoulder-height tracking shot beside the subject` |
| Crane | `slow crane down past neon signs` |
| Static + atmosphere | `locked camera, steam rises, light shifts` |
| Handheld | `subtle handheld drift` (use sparingly) |

Avoid whip pans and stacked contradictory moves in one short clip.

## Motivated lighting

Prefer **named sources** over “beautiful lighting”:

| Source | Example cue |
|--------|-------------|
| Window / dawn | `dawn light spreads across the desk` |
| Practical | `warm lamp spill, cool window fill` |
| Neon / gel | `magenta-cyan neon rim, wet reflections` |
| Overhead institutional | `cold fluorescent flicker` |
| Fire / candle | `candle flicker on faces` (avatar: often too transition-y — prefer steady) |
| Overcast soft | `soft overcast skylight, low contrast` |

Log as `lighting_tag`. Hex in stills when brand colors matter (`#0d3d2d rim`).

## Palette cues (one look)

Pick one coherent palette phrase: `teal-magenta night`, `warm tungsten interior`, `bleached noon desert`, `desaturated documentary`.

Do not stack competing genre looks in one prompt.

## Avatar-friendly defaults

Talking heads: **MCU**, one slow push-in or static, **steady light**, mouth visible. Variety across scenes = change angle/background still, not five camera moves mid-line. See [p-video-avatar-prompting.md](./p-video-avatar-prompting.md).

references/clip-chaining.md

# Clip chaining (multi-scene video)

When and how to continue motion across `p-video` clips. Plan JSON examples stay in [scene-anchor-pair.md](./scene-anchor-pair.md) and [scene-anchor-triple.md](./scene-anchor-triple.md); this page is the decision tree + prompt rules.

Workflows: `visual-transition-reel` · `narrated-multi-scene`.

## Decision tree

```text
Does motion continue in the same place/moment (no time jump)?
  NO  → chain_from_previous: false — hard cut; compose a new OPENING still
  YES → chain_from_previous: true
        Prefer frame_chain_mode: extract_last_frame (sequential renders)
        Only use planned_stills if you accept possible cut jumps
```

| Situation | `chain_from_previous` | Join |
|-----------|----------------------|------|
| Continuous action (run → leap) | `true` | Short crossfade ~0.12–0.15s after extract |
| New beat / location / pause | `false` | Hard cut (0 crossfade) |
| First scene | `false` | — |
| Montage vignettes (no shared motion) | `false` + `parallel_vignettes` | Hard cuts; parallel renders OK |

| `frame_chain_mode` | Next scene `image` | Render order |
|--------------------|--------------------|--------------|
| **`extract_last_frame`** | ffmpeg last frame of prior clip | **Sequential** when any scene chains |
| **`parallel_vignettes`** | each scene’s own start still | **Parallel** |
| **`planned_stills`** | prior scene end still URL | Parallel once stills exist — higher jump risk |

**Why extract?** Planned end stills often differ from the model’s actual last frame → visible jump.

## Prompt rules for chained beats

1. **Same subject language** — repeat “same [character]” in OPEN/MID/CLOSE.  
2. **No teleport** — ban `cut to`, `suddenly in`, `walls disappear`; use `gradually`, `walks through`, `ease into`.  
3. **Match lighting era** — chained clips share `style_bible` and time-of-day.  
4. **Exit / enter continuity** — if scene 1 CLOSE faces right, scene 2 OPEN should not hard-flip screen direction without a motivated turn.  
5. **Hard-cut scenes** — treat as fresh OPENING; do not assume prior pose.

## Assembly notes

1. Concat in scene order (ffmpeg concat — see the workflow skill).  
2. Per-join `crossfades`: chain ~0.12–0.15s; hard cuts 0.  
3. Normalize audio (48 kHz stereo) when mixing formats.  
4. Optional bed under native SFX — `audio-prompting`.

## Intake checklist

- [ ] Each scene: chain flag only if motion truly continues  
- [ ] `frame_chain_mode` chosen  
- [ ] Chained prompts pass Details Law ([prompt-dramaturgy.md](./prompt-dramaturgy.md))  
- [ ] Physics tier OK ([physics-safe-motion.md](./physics-safe-motion.md))

Github ReposUpdated 2d agoRank 70

AionUi

Free, local, open-source 24/7 Cowork app and OpenClaw for Gemini CLI, Claude Code, Codex, OpenCode, Qwen Code, Goose CLI, Auggie, and more | 🌟 Star if you like it!

MCPOPENCLAW

Github ReposUpdated 6mo agoRank 70

activepieces

AI Agents & MCPs & AI Workflow Automation • (~400 MCP servers for AI agents) • AI Automation / AI Agent with MCPs • AI Workflows & AI Agents • MCPs for AI Agents

OPENCLAW

Github ReposUpdated 6mo agoRank 70

cherry-studio

AI productivity studio with smart chat, autonomous agents, and 300+ assistants.