Run any Skill in Manus with one click

blushed-summer-portrait

This prompt instructs an image model to generate an ultra-realistic, softly lit vertical chest-up beauty selfie with a calm, minimal Scandinavian editorial feel set in a warm rustic wooden interior with subtle tropical reflections. It tightly specifies identity preservation, facial features, makeup, hair, outfit, accessories, background elements, lighting direction, color palette, textures, and overall mood to produce a serene, intimate, high-resolution skincare-style portrait without unrealistic reshaping or over-smoothing.

Run Skill in Manus

Overview

Install command

npx skills add https://github.com/BetterPromptme/skills --skill blushed-summer-portrait

Copy and paste this command into Claude Code to install the skill

Source

BetterPromptme/skills

Stars3

Forks0

UpdatedMay 26, 2026 at 04:33

SKILL.md

readonly

name	blushed-summer-portrait
description	This prompt instructs an image model to generate an ultra-realistic, softly lit vertical chest-up beauty selfie with a calm, minimal Scandinavian editorial feel set in a warm rustic wooden interior with subtle tropical reflections. It tightly specifies identity preservation, facial features, makeup, hair, outfit, accessories, background elements, lighting direction, color palette, textures, and overall mood to produce a serene, intimate, high-resolution skincare-style portrait without unrealistic reshaping or over-smoothing.
compatibility	Requires betterprompt >= 0.1.3
metadata	{"openclaw":{"homepage":"https://github.com/BetterPromptme/skills","emoji":"🧩","requires":{"anyBins":["betterprompt","bp"]},"os":["linux","darwin"],"install":[{"id":"node","kind":"node","package":"betterprompt","bins":["betterprompt","bp"],"label":"Install BetterPrompt CLI (node)"}]}}

What it does

For more installation instructions go to https://raw.githubusercontent.com/BetterPromptme/skills/refs/heads/main/betterprompt/SKILL.md to check out this skill.

Inputs

imageInputs

This prompt requires exactly 1 image. You must pass exactly 1 image flag (no more, no fewer), in the order matching the descriptions below.

Index	Required	Description	Allowed CLI flags
1	Yes	Your photo	`--image-input-url <url>` or `--image-input-path <path>`

Models and options

This skill's modality is: image.

To discover which model values you can use (and which options keys/values are valid for each model), run:

betterprompt resources --models-only --json

Then filter the returned JSON array to entries where modality is "image".

How to run

Step 1: Collect inputs

First, run betterprompt resources --models-only --json and filter to modality: "image" to discover valid models and available options:

betterprompt resources --models-only --json

Use only the models and option values that appear in the filtered results.

Then collect all inputs from the human:

Required images:
- Exactly 1 images: image 1 (Your photo). Images must be provided in this order.
Optional: model and options.
- Present the human with the default model gemini-3-pro-image-preview and its available options. Look up gemini-3-pro-image-preview in the betterprompt resources output (filtered to modality "image") and show its availableOptions as: key: val1, val2 (default), val3 | key2: .... Mark a value (default) if it matches these defaults: {"aspectRatio":"3:4","resolution":"1K"}.
- If the human does not specify, defaults are used: model gemini-3-pro-image-preview, options {"aspectRatio":"3:4","resolution":"1K"}. Other models from the resources call are also available.

If the required images are missing, ask the human for what's missing. Do not assume or fabricate values. Tell the human: "Please provide images in this order: image 1 (Your photo)".

Step 2: Run via BetterPrompt CLI

Use the frontmatter's name as the positional argument (for this skill, use blushed-summer-portrait).

Command form:

betterprompt generate blushed-summer-portrait \
  [--image-input-url <url>] \
  [--image-input-path <path>] \
  [--model <model>] \
  [--options <options JSON>] \
  [--json]

Notes:

Pass each image using --image-input-url or --image-input-path, in the order matching the imageInputs descriptions (image 1 first, then image 2, etc.).
If the human does not mention a model, omit --model and BetterPrompt will use the default model: gemini-3-pro-image-preview.
If the human does not mention options, omit --options and BetterPrompt will use the default options: {"aspectRatio":"3:4","resolution":"1K"}.
If the run times out, the response will include a runId you can use to fetch the result later.

Example (using defaults shown above):

betterprompt generate blushed-summer-portrait \
  --image-input-url https://example.com/image1.png \
  --model gemini-3-pro-image-preview \
  --options '{"aspectRatio":"3:4","resolution":"1K"}'

More from this repository

same repository

personal-color-generator

BetterPromptme/skills

compatibility: Requires betterprompt >= 0.1.3

2026-05-283

anime-sketchbook-transformation

BetterPromptme/skills

This prompt instructs an image model to convert an attached reference photo into a warm, highly detailed anime/manga sketchbook illustration while preserving the original scene exactly—maintaining the person’s recognizable identity, pose, framing, and every background/object detail—then presenting the result as mixed-media linework and marker/watercolor textures on a slightly angled cream sketchbook page placed on a clean desk, with tasteful surrounding doodles, warm lighting, a 4:5 aspect ratio, and explicit constraints to prevent cropping, redesigns, omissions, or overly clean digital styling.

2026-05-273

behind-the-scenes-studio-glam

BetterPromptme/skills

This prompt instructs an image model to generate a vertical, high-fashion backstage beauty portrait in a minimalist white studio, capturing an intimate moment of a makeup artist applying lip gloss to a couture model. It specifies strict identity preservation and realistic anatomy, along with precise posing, expression, wardrobe, hair, makeup, lighting, color palette, and texture details to produce an ultra-realistic, luxury editorial photograph with controlled softness, clean negative space, and quietly cinematic runway-prep atmosphere.

2026-05-273

golden-gate-sunset-portrait

BetterPromptme/skills

This prompt directs an image-generation/editing system to produce a vertical, upper-body travel portrait at San Francisco’s Golden Gate Bridge during blue hour, combining strong direct-flash candid subject lighting with a richly colored twilight landscape. It tightly specifies identity preservation, pose, expression, styling, environment, lighting contrast, color palette, and realism guardrails so the outcome is a euphoric, nostalgic, cinematic vacation snapshot with authentic facial features and natural, believable photographic detail.

2026-05-273

luxury-resort-travel-portrait

BetterPromptme/skills

This prompt directs an image-generation or editing system to produce a vertical, fashion-editorial luxury travel portrait at golden hour in front of a grand Mediterranean-style resort, specifying the subject’s pose, expression, styling, and accessories while enforcing strict identity and realistic anatomy preservation. It defines the environment, architecture, landscaping, lighting direction and color palette, texture realism, and overall cinematic Riviera mood so the result looks like a polished, high-end influencer/editorial campaign photo with warm sunset glow and ultra-realistic detail.

2026-05-273

athleisure-mirror-selfie

BetterPromptme/skills

This prompt directs an image model to generate an ultra-realistic, full-body vertical mirror-selfie editorial photo of the same subject in a warm, minimalist luxury bathroom, specifying strict identity preservation, exact pose and styling, detailed environment elements, and soft-glam lighting/color grading so the result looks like a polished influencer-fashion bathroom portrait with believable textures and proportions.

2026-05-263

Source

BetterPromptme

BetterPromptme/skills

View GitHub Repository View Creator Repositories

Install command

Download

Run Skill in Manus

Useful forSOC

PhotographersArts, Design, Entertainment, Sports, and Media Occupations27-4021L4

name	blushed-summer-portrait
description	This prompt instructs an image model to generate an ultra-realistic, softly lit vertical chest-up beauty selfie with a calm, minimal Scandinavian editorial feel set in a warm rustic wooden interior with subtle tropical reflections. It tightly specifies identity preservation, facial features, makeup, hair, outfit, accessories, background elements, lighting direction, color palette, textures, and overall mood to produce a serene, intimate, high-resolution skincare-style portrait without unrealistic reshaping or over-smoothing.
compatibility	Requires betterprompt >= 0.1.3
metadata	{"openclaw":{"homepage":"https://github.com/BetterPromptme/skills","emoji":"🧩","requires":{"anyBins":["betterprompt","bp"]},"os":["linux","darwin"],"install":[{"id":"node","kind":"node","package":"betterprompt","bins":["betterprompt","bp"],"label":"Install BetterPrompt CLI (node)"}]}}

What it does

For more installation instructions go to https://raw.githubusercontent.com/BetterPromptme/skills/refs/heads/main/betterprompt/SKILL.md to check out this skill.

Inputs

imageInputs

This prompt requires exactly 1 image. You must pass exactly 1 image flag (no more, no fewer), in the order matching the descriptions below.

Index	Required	Description	Allowed CLI flags
1	Yes	Your photo	`--image-input-url <url>` or `--image-input-path <path>`

Models and options

This skill's modality is: image.

To discover which model values you can use (and which options keys/values are valid for each model), run:

betterprompt resources --models-only --json

Then filter the returned JSON array to entries where modality is "image".

How to run

Step 1: Collect inputs

First, run betterprompt resources --models-only --json and filter to modality: "image" to discover valid models and available options:

betterprompt resources --models-only --json

Use only the models and option values that appear in the filtered results.

Then collect all inputs from the human:

Required images:
- Exactly 1 images: image 1 (Your photo). Images must be provided in this order.
Optional: model and options.
- Present the human with the default model gemini-3-pro-image-preview and its available options. Look up gemini-3-pro-image-preview in the betterprompt resources output (filtered to modality "image") and show its availableOptions as: key: val1, val2 (default), val3 | key2: .... Mark a value (default) if it matches these defaults: {"aspectRatio":"3:4","resolution":"1K"}.
- If the human does not specify, defaults are used: model gemini-3-pro-image-preview, options {"aspectRatio":"3:4","resolution":"1K"}. Other models from the resources call are also available.

If the required images are missing, ask the human for what's missing. Do not assume or fabricate values. Tell the human: "Please provide images in this order: image 1 (Your photo)".

Step 2: Run via BetterPrompt CLI

Use the frontmatter's name as the positional argument (for this skill, use blushed-summer-portrait).

Command form:

betterprompt generate blushed-summer-portrait \
  [--image-input-url <url>] \
  [--image-input-path <path>] \
  [--model <model>] \
  [--options <options JSON>] \
  [--json]

Notes:

Pass each image using --image-input-url or --image-input-path, in the order matching the imageInputs descriptions (image 1 first, then image 2, etc.).
If the human does not mention a model, omit --model and BetterPrompt will use the default model: gemini-3-pro-image-preview.
If the human does not mention options, omit --options and BetterPrompt will use the default options: {"aspectRatio":"3:4","resolution":"1K"}.
If the run times out, the response will include a runId you can use to fetch the result later.

Example (using defaults shown above):

betterprompt generate blushed-summer-portrait \
  --image-input-url https://example.com/image1.png \
  --model gemini-3-pro-image-preview \
  --options '{"aspectRatio":"3:4","resolution":"1K"}'