--- name: netsi-style-like-folk-satire description: >- Generate a finished image from an attached photograph, a described scene, or a context that needs illustration. Apply a warm folk-satire newspaper comic style: a bold, springy brush-and-pen contour, big expressive caricatured faces on long gangly bodies, a crowded small-town stage, spot blacks and flat Sunday-page colors, and a good-natured satirical point aimed at pomposity, red tape and self-importance, never at ordinary or poor people. Preserve recognizable people and source-image content. Offer up to three relevant optional style adjustments and generate a labeled comparison grid when requested. Use for friendly caricatures, social satire illustrations, small-town comic scenes, editorial cartoons with a kind heart, or /netsi-style-like-folk-satire. Image generation is required; a prompt alone is not the deliverable. metadata: version: "1.0.0" teaser: "You know the uncle who tells a story so well the whole table leans in, and somehow the pompous neighbor ends up the punchline, never you. This skill draws like that. Bold brush lines, big grinning faces and flat Sunday colors turn your photo, scene or idea into a finished caricature with a point. The trick: the joke always aims up, at red tape and puffed-up importance. You come out larger than life and still yourself." tags: - image-generation - illustration - style-transfer - creativity - design --- # Folk Satire Turn a familiar subject into a big-hearted newspaper caricature with a satirical wink. A supplied face stays recognizable and is exaggerated with affection; a described scene stays yours; a context becomes a small-town comic tableau with one clear point. The satire punches up: at bureaucracy, vanity, hype and self-importance. Ordinary people, rural life and modest circumstances are drawn with warmth and dignity. 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-folk-satire/images/` as anonymous visual calibration, especially `https://assets.netsi.dk/skills/netsi-style-like-folk-satire/images/04-ribbon-cutting.png` for the crowded small-town stage and `https://assets.netsi.dk/skills/netsi-style-like-folk-satire/images/02-car.png` for friendly caricature of a supplied face. 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. Caricature enlarges what is already characteristic (a smile, a beard, a jaw line, a gesture) and never adds flaws, mocks the body or makes the person look poor, dim or ridiculous. Retain the input aspect ratio 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, composition and any explicit constraints. Keep the scene's content. A scene that is not set in a small town keeps its setting: the folk vocabulary then appears through crowded bystanders, hand-built props and the comic staging, not by moving the location. 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 comic situation that makes the point visible: a pompous figure, an absurd institution, a gadget nobody asked for, and the sensible ordinary people around it. Aim the satire at the system or the vanity, not at a group of people. 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 **Caricature**, **Satire**, and **Color**. Values and defaults live in the tweaks reference. Never weaken the identity of this style by changing its springy brush contour to a generic filter 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 "bare en lille smule overdrevet" may be mapped directly to a suitable value (Caricature = Light) without asking again. Respect stated content: a request for "no politics" implies Satire = Warm, and a portrait for a birthday card implies a gentle Caricature. 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. If Satire is not Warm, choose the satirical target yourself from the subject or message, make sure it aims at an institution, a habit or a vanity, and describe it concretely in the prompt. Use descriptive traits only. Do not mention artist names, named fictional characters, existing works, 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 the springy brush contour, big expressive heads, spot blacks, flat Sunday colors and the crowded comic stage; check that the satirical point is readable and kind; check any requested lettering. The style must influence the drawing, not merely tint the photograph or enlarge the head with a lens effect. 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 an animal or a known cartoon character. Never use caricature to demean a real person's body, ethnicity, class, region, accent or disability. Do not draw stereotypes of rural, poor or uneducated people: no ragged clothes, missing teeth, bare feet, moonshine jugs or dim expressions as jokes. The person in the photo is the hero of the drawing, not its target. ## 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 Caricature and Satire while keeping Color at Sunday. A matrix may explore Color 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 recolor 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-folk-satire/images/01-pool.png` and `https://assets.netsi.dk/skills/netsi-style-like-folk-satire/images/02-car.png`. - Describe a scene: "A small-town mayor in a towering top hat proudly cuts the ribbon on a brand-new bridge that ends in mid-air, while a friendly crowd of neighbors politely tries not to laugh." See `https://assets.netsi.dk/skills/netsi-style-like-folk-satire/images/04-ribbon-cutting.png`. - Supply context: "Illustrate how a simple one-page form grows into a mountain of paperwork, for a newsletter header. No text in the image." See `https://assets.netsi.dk/skills/netsi-style-like-folk-satire/images/05-paperwork-mountain.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-folk-satire/images/03-tweak-grid.png`.