What makes image-prompting notable?

1K downloads. Trust evidence available

How should image-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

image-prompting

Use when crafting still-image prompts for any generative model — composition, identity sheets, edits, try-on, and photoreal personas. Skill: image-prompting Owner: pruna-ai Summary: Use when crafting still-image prompts for any generative model — composition, identity sheets, edits, try-on, and photoreal personas. Tags: ai:1.0.14, generative:1.0.14, latest:1.0.14, pruna:1.0.14 Version history: v1.0.14 | 2026-09-29T15:29:43.858Z | auto - Bumped version to 1.0.14 in SKILL.md metadata. - Removed the redundant skill-card.md file. - No functional or doc

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:image-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-image-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

150,762 characters of source documentation, loaded on request.

Extracted files

5 files captured from the source.

SKILL.md

---
name: image-prompting
description: Use when crafting still-image prompts for any generative model — composition, identity sheets, edits, try-on, and photoreal personas.
license: MIT
metadata:
  version: "1.0.14"
  package: pruna-skills
---

# Image prompting

Vendor-neutral craft for **still-image** generation and editing. Works with Pruna `p-image` family, Flux, Midjourney, Ideogram, Stable Diffusion, and similar APIs.

## Install

| 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` |
| `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

- Writing photo generation prompts
- Building character identity / turnaround sheets
- Surgical edits (change/keep discipline)
- Virtual try-on garment prompts
- Photoreal or stylized persona plates for avatars

## Works with

Pruna `p-image` (simple quick photos), `p-image-ideogram` (controlled photo generation — text, JSON, hex/bbox), `p-image-edit` / `p-image-try-on` / `p-image-upscale`, Flux, Midjourney, Ideogram, SDXL, and other still models.

## When NOT to use

Use a different skill instead:

| 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` |
| `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` |
| `pruna-api` | Use before any Pruna or Replicate HTTP call — credentials, upload/poll/download, parallel batches, and agent safety. | `npx skills add PrunaAI/pruna-skills@pruna-api -y` |
| `p-image` | Use when someone explicitly wants the fastest, cheapest photo generation — mood boards, bulk panels, or quick iterations — not when controlled photoreal or in-image text is needed. | `npx skills add PrunaAI/pruna-skills@p-image -y` |

## Guide habit

In the **first reply**, name `` `image-prompting` `` in backticks. When aspect, resolution, or media source are open, open intake → **`generation-diversity`** clarification intake. For Pruna still calls, cite the reading order: `generation-diversity` (ritual + **still-image prompt flow** reference) → golden rules → model-specific reference below.

## Before generating

1. Follow `generation-diversity` first — for `p-image-ideogram` / `p-image` / `p-image-edit`, run **still-image prompt flow** (brief lock → ritual → draft → fidelity check).
2. **[Prompt golden rules](./references/

_meta.json

{
  "ownerId": "kn7cagwf7q3t0cxrgteb7xk0bh81j0eb",
  "slug": "image-prompting",
  "version": "1.0.14",
  "publishedAt": 1790695783858
}

references/character-turnaround-sheet.md

# Character turnaround sheet (`p-image` → I2V)

Reusable identity plates before scene stills and video. Use when the brief needs the **same character** across multiple shots, not a one-off hero.

Talking-head cast ledgers and voice locks stay in avatar-multi-scene prompt-templates (`avatar-multi-scene`) and [realistic-persona-showcase.md](./realistic-persona-showcase.md). This page is the **visual turnaround** handoff.

**Sources:** patterns adapted from [Square-Zero-Labs/video-prompting-skill](https://github.com/Square-Zero-Labs/video-prompting-skill) (Apache-2.0); rewritten for Pruna.

## Handoff order

```text
1. Character turnaround sheet  (p-image or multi-panel edit)
2. Scene stills                (p-image-edit from sheet / hero)
3. Video                       (p-video pair/triple — motion only)
```

Do not invent a new face in step 2. Lock identity from the sheet (or a single approved hero plate) and change only pose, camera, wardrobe state, or background beat.

## Sheet types

| Type | When | Prompt focus |
|------|------|--------------|
| **Turnaround** | Stylized or invented characters | Front, 3⁄4, profile, back — same outfit, neutral studio |
| **Expression row** | Performance / avatar prep | Same face + lighting; **distinct** emotions; include open-mouth for lip-sync |
| **Photoreal identity** | Real-person consistency | Same person photographed repeatedly; keep asymmetry, pores, age cues |
| **Wardrobe update** | Outfit change only | Same face/session framing; change clothes only |

## Turnaround prompt skeleton

```text
Character turnaround sheet of [named character], [age/build/species], wearing [exact outfit].
Four panels on one image: front view, three-quarter view, side profile, back view.
Identical face and costume in every panel. Neutral seamless studio backdrop #c8c8c8,
even softbox lighting, no story background, no props that change between panels.
[render style — e.g. documentary photoreal / cel-shaded anime]. Exact same character in every panel.
```

### Expression sheet add-on

```text
Expression row below: neutral, warm smile, concerned frown, surprised open mouth ready to speak.
Each expression clearly different. Mouth visible in every panel. Same lighting and camera height.
```

### Photoreal identity sheet

```text
Photoreal identity reference sheet of the same person photographed repeatedly in a studio.
Preserve freckles, asymmetric smile, skin texture, and eye color exactly.
Front and three-quarter views, soft window light, plain backdrop, no beauty retouching.
```

## Rules

1. **Neutral backdrop** — no narrative locations on the sheet (story backgrounds come in scene stills).
2. **Exact same character** language every time — models drift identity without it.
3. **Distinct expressions** — “slightly different smiles” collapses; name emotion + mouth state.
4. **One `style_bible`** — append the same medium/palette lock used in downstream edits and video.
5. **Params outside prompt** — aspect ratio and model stay in A

references/p-image-edit-prompting.md

# p-image-edit prompting

Surgical edit prompts for `p-image-edit`. Shared still craft: [prompt-golden-rules.md](./prompt-golden-rules.md). Identity sheets: [character-turnaround-sheet.md](./character-turnaround-sheet.md).

## Core formula

```text
Change [specific thing]. Keep [identity / medium / lighting era] identical.
```

| Do | Don't |
|----|-------|
| `Change background to soft #e8e4dc gradient, keep subject identical` | `Make it better` |
| `Same woman, identical face and coat; turn torso 30° toward camera` | `Regenerate in a new pose` (prefer edit from locked URL) |
| Name which ref: `face from image 1, outfit from image 2` | Vague `combine these images` |

## Identity lock (required when subject continues)

Append when the person/product must survive the edit:

```text
same [subject], identical face/uniform, do not remove the person, do not change species or age
```

Prefer editing a locked photo or turnaround plate over running photo generation again.

## Typography edits

Change readable copy on a surface — not spoken dialogue (that is `p-video` Mode A). Full still rules: [prompt-golden-rules.md](./prompt-golden-rules.md) §5.

```text
Change [surface] text to "[EXACT STRING]" in [weight], [placement]. Keep subject and lighting identical.
```

Quote the exact string; name surface + placement. Do not use Gemini TTS `[tags]` here.

## Scene-anchor stills (pair / triple)

| Plan field | Prefix | Role |
|------------|--------|------|
| `edit_prompt` | `OPENING:` or `OPEN:` | Start composition |
| `last_frame_edit_prompt` | `CLOSING:` or `CLOSE:` | End composition — physically reachable from start |

Rules: `video-prompting` · `video-prompting`.

- Subject must appear in **both** stills when the beat follows that subject.
- Change only pose, camera, background beat, or prop state — not medium mid-scene.
- Append the shared `style_bible` to every edit.

## Multi-reference composition

Index refs by role:

```text
Use face and hair from image 1. Outfit from image 2. Place subject in the cafe interior from image 3.
Match lighting to image 3. Keep face identical to image 1.
```

Max 5 images on `p-image-edit`.

## Turbo

| Setting | When |
|---------|------|
| `turbo: true` (default) | Simple background / color / light tweaks |
| `turbo: false` | Hard identity preserves, multi-ref composites, scene-anchor CLOSING plates that drop subjects |

## Edit, don't re-roll

If the still is ~80% right, edit surgically. Regenerating the photo drifts identity and wastes the approved plate.

## Worked example — three-reference composite

User lock: face from portrait ref, navy blazer from product flat-lay, cafe interior from location still. Keep face identical.

```text
Use face and hair from image 1. Outfit from image 2 (navy blazer, white tee). Place subject seated at the window table from image 3.
Match warm afternoon lighting to image 3. Keep face identical to image 1; same woman, do not change age or species.
Change nothing except outfit and backgroun

references/p-image-edit-quality-checklist.md

# p-image-edit quality checklist

After each `p-image-edit` output is saved, **open the file and review it visually** against this checklist (agent vision review — see `generation-diversity`).

## Applies to

See the canonical mapping in `generation-diversity`.

## Edit intent and preservation

- Requested change is present and obvious.
- Locked regions remain stable (identity, product geometry, key wardrobe/details).
- "Change only X" constraints are respected; unrelated regions do not drift.

## Multi-image composition (when used)

- Source images blend coherently (lighting, scale, perspective).
- Subject edges are clean (no obvious cutout seams or ghosting).
- Final composition reads as one scene, not pasted layers.

## Technical and handoff checks

- Output dimensions and `aspect_ratio` match target use.
- Artifacts introduced by edit are absent (smears, repeated textures, malformed hands/faces).
- Result is ready for downstream `p-video` / `p-video-avatar`, or flagged for another pass.

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.