Turns customer feedback into structured output
The source asks the model to group, classify, answer, or prioritize review feedback rather than treating every comment as an isolated case.
Beginnerfengzie
Mobazha Product Image Prompt
Mobazha Product Image Prompt is an ecommerce AI skill for fengzie, built for teams working with OpenClaw. Use it to turn a product brief into more consistent prompts…
- Views
- 0
- Installs
- 0
- Favorites
- 0
What this Skill does
Turn a product brief into more consistent prompts for studio, lifestyle, and campaign images. It uses a repeatable prompt structure rather than APIs or store integrations, making it accessible to operators who already use an image generator but need more controlled results.
What makes it different
Creates listing and search-content fields together
The source covers product or listing copy alongside SEO-related fields such as keywords, metadata, or image text when those fields are requested.
Install and get started
Installation command
- Copy and run the source-published installation command below.
- Inspect the installed files, permissions, and any source documentation before adding store data.
- Prepare accurate product materials, colors, dimensions, and reference photos.
openclaw skills install
@fengzie/mobazha-product-image-promptOriginal Skill.md
The complete source is shown below. Copy it from the top right to use it.
You are a product photography prompt engineer. Help the user write AI image-generation prompts using this structure: [Shot type] of [Subject] in [Setting], [Action/State]. [Style], [Composition], [Lighting], [Color], [Quality]. Rules: be specific about subject/material; use complete natural sentences, not keyword stacking; include who the image is for; if a result is 80% right, refine the prompt instead of re-rolling; never include recognizable third-party brand elements. Offer style presets: studio shot (white background, soft shadows, 45-degree angle, commercial style), lifestyle shot (product in use, natural light, shallow depth of field), and promotional graphic (campaign-ready composition). Ask for the product, target platform, and desired shot type.Get started
Starter prompts for the main use cases—copy and use them directly.
01Choose one shot type
Decide on studio, lifestyle, flat lay, or promotional composition before writing the prompt. Use this when the image has one clear business purpose and output format.
Show prompt and variablesHide prompt and variables
Choose one shot type
Decide on studio, lifestyle, flat lay, or promotional composition before writing the prompt. Use this when the image has one clear business purpose and output format.
Use the Skill above to help me with this task: Choose one shot type.
Task details: [TASK_DETAILS]
Constraints or policies to follow: [CONSTRAINTS]
Decide on studio, lifestyle, flat lay, or promotional composition before writing the prompt.
Return a practical result and clearly flag anything that needs human review.Replace these variables
[TASK_DETAILS]- The facts, context, or source material for this task.
[CONSTRAINTS]- Replace this placeholder with your verified store-specific information.
02Describe the product precisely
Specify material, color, form, setting, composition, lighting, and intended customer without adding unverified features. Use this when a reviewer could identify the correct SKU from the description.
Show prompt and variablesHide prompt and variables
Describe the product precisely
Specify material, color, form, setting, composition, lighting, and intended customer without adding unverified features. Use this when a reviewer could identify the correct SKU from the description.
Use the Skill above to help me with this task: Describe the product precisely.
Task details: [TASK_DETAILS]
Constraints or policies to follow: [CONSTRAINTS]
Specify material, color, form, setting, composition, lighting, and intended customer without adding unverified features.
Return a practical result and clearly flag anything that needs human review.Replace these variables
[TASK_DETAILS]- The facts, context, or source material for this task.
[CONSTRAINTS]- Replace this placeholder with your verified store-specific information.
03Generate a small set
Create a few variants and reject distorted labels, geometry, packaging, hands, or product details. Use this when no selected image changes a material product fact.
Show prompt and variablesHide prompt and variables
Generate a small set
Create a few variants and reject distorted labels, geometry, packaging, hands, or product details. Use this when no selected image changes a material product fact.
Use the Skill above to help me with this task: Generate a small set.
Task details: [TASK_DETAILS]
Constraints or policies to follow: [CONSTRAINTS]
Create a few variants and reject distorted labels, geometry, packaging, hands, or product details.
Return a practical result and clearly flag anything that needs human review.Replace these variables
[TASK_DETAILS]- The facts, context, or source material for this task.
[CONSTRAINTS]- Replace this placeholder with your verified store-specific information.
04Refine the closest result
Adjust one or two prompt elements at a time instead of restarting with unrelated wording. Use this when the next version fixes a named problem rather than merely looking different.
Show prompt and variablesHide prompt and variables
Refine the closest result
Adjust one or two prompt elements at a time instead of restarting with unrelated wording. Use this when the next version fixes a named problem rather than merely looking different.
Use the Skill above to help me with this task: Refine the closest result.
Task details: [TASK_DETAILS]
Constraints or policies to follow: [CONSTRAINTS]
Adjust one or two prompt elements at a time instead of restarting with unrelated wording.
Return a practical result and clearly flag anything that needs human review.Replace these variables
[TASK_DETAILS]- The facts, context, or source material for this task.
[CONSTRAINTS]- Replace this placeholder with your verified store-specific information.
Risks and operating notes
Treat review patterns as hypotheses to test
The instruction can group and prioritize feedback, but repeated wording is not proof of a product defect or customer-wide preference. Check the underlying sample before changing a product, policy, or campaign.
fengzie
ClawHub creator publishing practical prompt workflows for ecommerce product imagery and marketplace content.
Risk, permissions, and limitations
Review third-party permission scopes before providing store data. Never paste payment credentials, customer passwords, or unnecessary personal data into a model. Outputs must be checked by the operator responsible for the workflow.
Content checked:
No reviews yet.