Cinematic Ink

Turn a familiar subject into a cinematic brush-ink panel where light and shadow do the storytelling. Big black shapes carve the image; a few lines finish it; the camera finds the angle a film director would choose. A supplied face stays recognizable; a described scene stays yours; a context becomes a tense, atmospheric moment. Deliver the image itself.

Required capabilities and resources

• Use an image-generation/editing tool. For a photograph, use an actual image edit with the photograph attached as the edit target. Do not reconstruct it from a description alone.
• Use netsi-prompt-generator for the internal image prompt. If it is installed, read its instructions. Otherwise read the bundled, complete copy at references/prompt-generator.md and apply that skill's workflow to the prompt subtask.
• Read references/style-profile.md before composing the prompt, and references/tweaks.md when adjustments or a comparison are relevant.
• Inspect the bundled generated examples in https://assets.netsi.dk/skills/netsi-style-like-cinematic-ink/images/ as anonymous visual calibration, especially https://assets.netsi.dk/skills/netsi-style-like-cinematic-ink/images/04-harbor-night.png for black shapes and atmosphere and https://assets.netsi.dk/skills/netsi-style-like-cinematic-ink/images/02-car.png for figure drawing. When the image tool supports multiple references, supply the input photograph as the edit target and a relevant bundled illustration as the style reference only. In a new scene, the bundled illustrations are style references only. Never copy their subject, composition, identity or labels into the user's result. Do not redistribute historical research scans.
• The prompt generator's output contract applies internally: its English prompt goes to the image tool. The parent skill's user-facing deliverable remains the finished image.
• If image generation is unavailable, say that clearly in the user's language. Do not label an English prompt or a mockup as a generated image. Never silently substitute a different provider or paid API.

Recognize one of three inputs

A — Image. Inspect the photograph. Record the person or subject, face proportions, age, expression, pose, hands, clothing, glasses, recognizable accessories, objects, framing and meaningful setting. Preserve these unless the user explicitly asks to change them. Retain the input aspect ratio and framing by default. A style reference is a different role from the edit target; do not swap them.

B — Scene. Extract who or what is present, actions, setting, time of day, composition and any explicit constraints. Keep the scene's content. A sunny scene stays sunny: the cinematic vocabulary then comes from hard sunlight, deep cast shadows and framing, not from forcing night and rain. If no aspect ratio is supplied, use 16:9 for a scene; follow a stated medium such as a square social post instead when provided.

C — Context. Extract the message, audience, mood and destination from the supplied text or conversation. Choose a concrete, original cinematic moment: a threshold, a pause before a decision, an arrival, a figure caught between light and dark. Do not invent facts, numbers, quotations or branding. Make the message understandable without text by default. Ask only if materially different interpretations prevent a useful result. Use the requested destination's aspect ratio, otherwise 16:9.

If inputs are combined, infer their roles: for example, an image is the subject and a paragraph supplies the illustration's message. Ask one focused question only when the roles conflict.

Optional adjustments: zero to three

The canonical controls are Black level, Color, and Camera. Values and defaults live in the tweaks reference. Never weaken the identity of this style by turning its brush-built black shapes into a gray photo filter, a posterization effect or another medium.

If the request is clear, apply the explicit values or defaults and generate immediately. Do not require a questionnaire. If the user asks to explore, requests a materially ambiguous adjustment, or a meaningful unresolved choice would change the result, use an AskUserQuestion interaction: the environment's interactive question tool, or the same concise question in chat when no such tool is available.

Offer at most three relevant tweak controls. Ask one focused question at a time, explain its visual effect in plain language, place the recommended/default answer first, and allow a custom answer and discussion. Where tool schemas add free text automatically, do not duplicate it with a fake option. Infer answers already supplied. Do not mistake silence for consent to a material change. If the user simply wants the default image, no question is needed.

Translate questions, explanations and choices into the user's language. Canonical parameter values stay English in prompts and grid labels. Natural-language requests such as "gør det helt sort-hvidt og dramatisk" may be mapped directly to suitable values (Color = Ink, Black level = Silhouette) without asking again.

Respect a scene's stated lighting and content: a bright beach scene keeps its sun, and "I need to see my face clearly" caps Black level at Balanced. Stated content takes precedence over a style default.

Generate, inspect, deliver

1. Inspect the input and identify its type and invariants.
2. Load the detailed style profile. Resolve any relevant optional adjustments.
3. Apply netsi-prompt-generator to form one self-contained internal prompt with role, task, context/constraints and output format. Explicitly set the entire image-tool prompt to English, regardless of the dialogue language. Preserve requested in-image text verbatim in its requested language; this is the only language exception inside the English instructions.
4. Include the profile's core traits, their priorities, selected tweak values and the input's exact preservation constraints. Use descriptive traits only. Do not mention artist names, named fictional characters, existing works, films, signatures or imitation slogans.
5. Generate or edit the actual image. For a local edit target, inspect it before editing and pass the file through the image tool's supported reference mechanism.
6. Inspect the result: recognize the subject; check face, expression, accessories and hand gesture; check scene content; check bold spotted blacks that build form, an economical brush line, naturalistic figures, deliberate camera framing and graphic cast shadows. The key features of the face must sit in the light. The style must influence the drawing, not merely raise the contrast of the photograph.
7. If a material defect exists, make a focused revision and inspect again. Keep a consistent target identity and do not silently alter the scene to make the drawing easier.
8. Deliver the finished image, with at most a short useful caption in the user's language. Keep the internal prompt hidden unless the user explicitly asks for it. Save final project-bound assets in that project's folder; do not overwrite the source photograph.

Never turn a person into a known adventurer, detective or any recognizable character, and never let shadow swallow the features that make someone recognizable. Darkness frames the person; it does not replace them.

Comparison grids

When requested, create one 16:9 image with 4 columns × 3 rows (12 image cells). Use the same subject, identity, pose, objects and crop in every cell. Reserve a legible label strip under each image, inside the overall canvas. Labels contain the exact English parameter names and values, never artist names. Use the schedule in references/tweaks.md: it includes the default and varies Black level and Color while keeping Camera at Source framing. A matrix may explore Camera instead if requested, but must state the exact changed values.

Generate the artwork with the image tool. Use supported layout/text composition tools to assemble a precise grid if available; do not use code to imitate the illustration or threshold a photograph as a substitute. A single image-tool call may render the complete labeled grid. Verify 12 cells, order, visible differences, literal labels and a 16:9 canvas (allow one pixel of integer raster rounding) before delivering. Regenerate if lettering or structure is wrong.

Do not claim pixel-identical identity or perfectly isolated experimental control: image generation can vary details. Aim for faithful, visually comparable variations and disclose a material limitation if it remains.

Start with an example

• Attach a photograph: "Apply this style. Keep the face, pose and surroundings recognizable." (see https://assets.netsi.dk/skills/netsi-style-like-cinematic-ink/images/01-pool.png and https://assets.netsi.dk/skills/netsi-style-like-cinematic-ink/images/02-car.png)
• Describe a scene: "Two people meet under a single lamp at the end of a wet harbor pier at night. A freighter waits in the fog, ropes and cranes cut across the frame." (see https://assets.netsi.dk/skills/netsi-style-like-cinematic-ink/images/04-harbor-night.png)
• Supply context: "Illustrate the weight of making a hard decision without all the facts, for a leadership article. No text in the image." (see https://assets.netsi.dk/skills/netsi-style-like-cinematic-ink/images/05-threshold-context.png)
• Explore adjustments: "Show my attached lakeside portrait in a 4 × 3 comparison grid with English tweak labels." (see https://assets.netsi.dk/skills/netsi-style-like-cinematic-ink/images/03-tweak-grid.png)

See EXAMPLES.md for actual generated outputs, source photos and the comparison grid.