# Mirror Message Cinematic Bathroom Thriller > This prompt instructs an image generator to create a photorealistic, tense cinematic bathroom scene using an uploaded portrait as the main subject, dressed in a simple school-uniform outfit, framed through a dirty mirror under harsh fluorescent lighting. The resulting image is a medium, shallow–depth-of-field photograph where the subject’s reflection and the red lipstick message on the mirror are sharp, while a menacing Joker figure appears behind them in the mirror slightly out of focus, with strict constraints to preserve realism, coherent reflections/lighting, and exclude extra text, logos, or stylized rendering. - Skill: `majiayu000/mirror-message-cinematic-bathroom-thriller` (Agent Skill, multi-file: 2 files) - Install (CLI): `npx skillmds add majiayu000/mirror-message-cinematic-bathroom-thriller` - Raw SKILL.md: https://api.skillmd.com/api/skills/majiayu000/mirror-message-cinematic-bathroom-thriller/raw - Safety review: pending - Works with: Claude Code, Claude.ai, OpenAI Codex - Category: AI & ML - Author: majiayu000 (https://skillmd.com/u/majiayu000) - Updated: 2026-09-09 - Page: https://skillmd.com/skills/majiayu000/mirror-message-cinematic-bathroom-thriller --- ## What it does This prompt instructs an image generator to create a photorealistic, tense cinematic bathroom scene using an uploaded portrait as the main subject, dressed in a simple school-uniform outfit, framed through a dirty mirror under harsh fluorescent lighting. The resulting image is a medium, shallow–depth-of-field photograph where the subject’s reflection and the red lipstick message on the mirror are sharp, while a menacing Joker figure appears behind them in the mirror slightly out of focus, with strict constraints to preserve realism, coherent reflections/lighting, and exclude extra text, logos, or stylized rendering. > Requires the **betterprompt** CLI to run. For installation and general CLI usage, refer to the `betterprompt` skill in your skill list or if not yet available in skill list, install via `npx skills add https://github.com/BetterPromptme/betterprompt/skills --skill betterprompt` ## Inputs ### textInputs Pass each text input using `--input =` flags. | Variable key | Required? | Description | Defaults | | --- | ---: | --- | --- | | `outfit` | Optional | Describe the outfit the subject wears | `white button-down shirt, rolled sleeves, dark red striped tie, grey pleated skirt” or “white shirt with rolled sleeves, dark red striped tie, charcoal trousers,...` | ### 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 | Upload one clear portrait photo of the subject. | `--image-input-url ` or `--image-input-base64 ` or `--image-input-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: ```bash 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: ```bash 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: - Optional text inputs (use defaults if not provided by the human): - `outfit` (default: `white button-down shirt, rolled sleeves, dark red striped tie, grey pleated skirt” or “white shirt with rolled sleeves, dark red striped tie, charcoal trousers,...`) - Required images: - **Exactly 1** images: image 1 (Upload one clear portrait photo of the subject.). Images must be provided in this order. - Optional: model and options. - Present the human with the default model **`gemini-2.5-flash-image-preview`** and its available options. Look up `gemini-2.5-flash-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: `{}`. - If the human does not specify, defaults are used: model `gemini-2.5-flash-image-preview`, options `{}`. 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 (Upload one clear portrait photo of the subject.)"**. ### Step 2: Run via BetterPrompt CLI Use the frontmatter's `skillVersionId` as the positional argument (for this skill version, use `019a0a98-9642-77cf-8774-07c2797b33bd`). Command form: ```bash betterprompt generate 019a0a98-9642-77cf-8774-07c2797b33bd \ [--input =] \ [--image-input-url ] \ [--image-input-base64 ] \ [--image-input-path ] \ [--model ] \ [--options ] \ [--json] ``` Notes: - Pass each text input as a separate `--input =` flag. - Pass each image using one of `--image-input-url`, `--image-input-base64`, 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-2.5-flash-image-preview`**. - If the human does **not** mention options, **omit** `--options` and BetterPrompt will use the default options: **`{}`**. - If the run times out, the response will include a `runId` you can use to fetch the result later. Example (using defaults shown above): ```bash betterprompt generate 019a0a98-9642-77cf-8774-07c2797b33bd \ --input 'outfit=white button-down shirt, rolled sleeves, dark red striped tie, grey pleated skirt” or “white shirt with rolled sleeves, dark red striped tie, charcoal trousers,...' \ --image-input-url https://example.com/image1.png \ --model gemini-2.5-flash-image-preview \ --options '{}' ```