Tactical Glam Outfit Filter · skill pública de Open Skill

Tactical Glam Outfit Filter

On the train platform, I keep thinking about how the city lights should land right on the beat drop. This gives my night-out set the tactical glam look I want. I start with one adult photo, then style the subject with a harness crop top, utility belt, thigh straps, and combat boots. **tips from me:** - choose black if you want the outfit to stay low-key under the street lights - pick 1 to 4 panels for different poses, from one confident pose to a mini photo set - keep the default 3:4 portrait ratio, or choose 2:3 or 9:16 for your layout - add a clear description if you want a specific outfit color or scene post what you make, especially if the beat drop lands right.

@AvaLindqvist

TryOn

0 0 3

https://d7qlwi7tl2u27.cloudfront.net/skill-covers/prod/4284954/2026-10-16/es2phas3.webp

# Tactical Glam Outfit Filter

Action-heroine ready. The woman in your photo gets a sleek tactical glam look with harness top, utility belt and combat boots, in your color and as a 1-4 panel photo set (still image).

## When to use

- The user wants the woman in their photo restyled in an action-heroine tactical glam outfit (harness crop top, utility belt, thigh straps, combat boots clothing filter)
- A variation on a previous result: another color or fabric

Not for: Video output (use a video skill).

## Inputs and gates

| Input | Required | Default | Gate |
|---|---|---|---|
| Photo | Yes | — | One adult with the face clearly visible. Ask for another photo if the face is tiny, blurred, heavily covered or in profile |
| Description | No | tuned default below | What the user wants; merged into the prompt |
| Color | No | `user-described outfit color (default black)` | user-described outfit color (default black) |
| Panels | No | `1 to 4 photo panels with different poses (default 1)` | 1 to 4 photo panels with different poses (default 1) |
| Ratio | No | `3:4 default` | 3:4 default; 2:3, 9:16 on request |

- If the person may be under 18, stop and decline politely. Real-person photos must be of adults the user has the right to use.
- Fashion, dark and horror themes are fine as stills; refuse explicit sexual content and anything sexualizing minors.

## Steps

1. Read `references/image-edit.md` for prompt structure.
2. **Identity read**: `recognize_image(image_url=<photo>, prompt='Describe this adult for identity preservation: face shape, eye shape and color, brows, nose, lips, skin tone, apparent age range, hair color and length, distinctive marks, glasses. One compact line.')`.
3. **Generate**: `generate_image(prompt=<PROMPT>, input_urls=[photo], model='i2i.hd', orientation='portrait', aspect_ratio='3:4', name='Tactical Glam Outfit Filter', entity_type='skill_generation')`. Merge the user's details and options into the template.
4. **Self-check, one retry**: look at the result. If a person photo was used and the face no longer reads as the same person, regenerate with the identity clause first. If someone glancing at it would not instantly see the intended change (it reads as a light filter, the old clothes or background remain, or the style is faint), regenerate once with the change described bigger and more concretely.
5. Reply in one or two sentences, e.g. "Done! Here's your tactical glam outfit filter. I can also try another color or fabric if you like." Results appear on the canvas; never paste URLs.

## Prompt templates

**PROMPT**

```text
The same adult from the reference: <identity line>. Same face structure, eyes, skin tone and recognizable likeness; no beautification or face reshaping. Intentional changes: the same adult woman wearing an action-heroine tactical glam outfit in <color>: harness crop top, utility belt, fitted shorts with thigh straps, fingerless gloves and combat boots, no weapons, confident action-movie fashion shoot, shown as <n> panel(s) with different poses if requested, tasteful, fully clothed. <user details and options>. The new outfit fully replaces the original clothes with a clearly different silhouette; real fabric texture, accurate fit and drape, styling and accessories; a setting and light that suit the outfit. Lighting and materials described concretely; composition suited to portrait 3:4. Photoreal unless the style says otherwise, fully clothed, no text unless requested.
```

Quality bar: Make the new outfit read as real fabric: bold silhouette change from the original clothes, named materials and textures, hero lighting, and a scene that suits the outfit (not the selfie background).

## Failure handling

- `success=false`: say what failed in one sentence; retry once only if transient; never invent links.
- The face changes: regenerate once with the identity clause first; then say so honestly.

## Examples

**Default**: the user says "use this pic" with a photo. Use color `user-described