--- title: "CRT image prompt writer" type: "skill" url: "https://useaiblocks.com/skills/industrial-crt-image-direction" updated: "2026-10-28" first_published: "2026-10-25" job: "Make images and art" tested: true licence: "MIT" source: "https://github.com/magnus919/agent-skills/tree/92c327e525da69c9ad3812fd223a1770e977c2e3/analog-occultism" instructions: "https://useaiblocks.com/skills/industrial-crt-image-direction/SKILL.md" --- # CRT image prompt writer > Bring a subject and image use. Get an old-screen image prompt that keeps key details clear. Give it a subject, image use and camera view. It writes a prompt with framing, light and old-screen texture, plus checks for clear subject details. Free skill for the job "Make images and art" · Level: intermediate · Thinking: medium · Tested · Updated 2026-10-28 ## Links - Page: https://useaiblocks.com/skills/industrial-crt-image-direction - Instructions (SKILL.md): https://useaiblocks.com/skills/industrial-crt-image-direction/SKILL.md - All files (zip): https://useaiblocks.com/skills/industrial-crt-image-direction.zip - JSON version: https://useaiblocks.com/skills/industrial-crt-image-direction.json - In your AI: connect https://useaiblocks.com/mcp and ask "Use AI Blocks to get industrial-crt-image-direction" ## What it does Bring a subject and reference image. Choose the capture view, then get a prompt and checks. ## What you give it - Your subject and the details that must stay recognizable. - What the image will be used for. - A reference image (optional). - Your choice of CRT-screen view or real-camera view (optional). ## What you get - One still-image prompt with framing, a single main light and the signal flaws named. - A numbered checklist for subject, anatomy, shapes and labels. - A short list of limits to note, such as text the image tool drew badly. ## Example: what goes in and what comes out ### What goes in - Your subject, such as an object, person or place - The details that must stay recognizable - What the image is for - A reference image (optional) - Your choice of CRT-screen view or real-camera view (optional) ### Before you start - An image tool to make the picture. This skill writes the prompt but does not make the image. ### What comes out - **Capture view**: Your pick between an image shown on a CRT screen and a real scene filmed by an old analog camera. - **Prompt block**: One still-image prompt with the subject, framing, one main light, black space and the recording flaws. - **Identity and clarity checklist**: Numbered checks for the subject, anatomy, object shapes and any labels, to run on the image. - **Open limitations**: A short list of anything the image tool could not do, or facts still missing. ## Use it when - You need an image that looks like a recovered tape from a technical archive. - You have a subject and want a moody, near-black-and-white look. - Your first image looks too clean and needs the flaws of an old screen. - You want to check that the subject still looks right after the heavy styling. ## Skip it when - You want a bright, colorful or glossy product shot: ask your AI for a plain studio photo prompt instead. - You need to follow a named brand's locked visual rules: use that brand's own style guide. - You want a finished video: this gives a still-image prompt, so use a video tool and its own guide. ## How to use it 1. Open Claude, ChatGPT or Gemini and paste in the skill text. 2. Type your subject, the details that must stay, and what the image is for. 3. Say if you want the CRT-screen view or the real-camera view. Attach a reference image if you have one. 4. Copy the prompt into your image tool. It needs an image tool that can make pictures. 5. If you gave a reference, attach the image itself in that tool. A text description is not enough. 6. Run the checklist on the result. It passes when the subject is still recognizable, hands and limbs look right, shapes are correct and every visible label is spelled as you intended. If a check fails, change one thing (the framing or the light) and run the prompt again, or use your image tool's variation or edit feature. If two tries fail, change the shot rather than add more darkness. 7. This item writes a prompt for still images only. Video needs a separate video tool. 8. When the image passes, save it. If a check still fails after two tries, write down the open limits, pick a new capture view and run the prompt again. To use the image in an ad or on a page, bring it to the ad or page item you are working in. ## What to do next - [Multi-provider image maker](https://useaiblocks.com/skills/multi-provider-image-maker): Multi-provider image maker ## Sources and credits - From magnus919: https://github.com/magnus919/agent-skills/tree/92c327e525da69c9ad3812fd223a1770e977c2e3/analog-occultism, shared under the MIT licence (original name: analog-occultism). - [analog-occultism skill](https://github.com/magnus919/agent-skills/tree/92c327e525da69c9ad3812fd223a1770e977c2e3/analog-occultism), magnus919: Original instructions and supporting files, with attribution and the MIT licence. Display copy describes the task. ## Instructions (SKILL.md) ## Analog Occultism / Industrial CRT Noir Apply a cross-media visual language, not a subject, character, brand, or story. The creative premise is: **advanced systems seen through an obsolete recording medium**. The result should feel like a mysterious technical artifact recovered from a forgotten research archive: intelligent, secretive, uncanny, severe, tactile, and quietly beautiful. ### Before you start Use the material below to do this job. If facts or tool access are missing, explain what you can finish and what must wait. **What you need** (use your own material or the linked skill): - **Your question** (yours): the decision or problem, and what a good outcome looks like. **Makes it better (optional):** - **An image** (yours): a finished picture. How to start: 1. **Look first.** Use what they've already attached, pasted or put in their about-me note. In a coding assistant with file access, look in the project too for these by name. 2. **Check what's missing.** Look for your question, an image. They can attach files, paste the details, or share a file path your assistant can read. Ask only for missing facts that change the result. If they ask you to start with what they have, complete the parts you can and mark the gaps. 3. **Do the job.** Follow the skill below with the facts and tools you have. Mark each gap with `MISSING:` where it belongs and never invent a fact to fill it. ### Core Workflow 1. **Identify the subject and its essential identity.** Preserve the subject's recognizable structure, but treat it as evidence, artifact, specimen, icon, or component of a larger system rather than a casual commercial presentation. 2. **Choose one dominant practical source.** Prefer a screen, projector, narrow overhead fixture, hard backlight, small industrial light, or source just outside frame. Let it reveal selected surfaces while most of the space falls into black. 3. **Build the frame around depth and obstruction.** Use a square, portrait, or tight crop by default; central or slightly off-center placement; tunnel perspective, receding grids, corridors, cables, grilles, foreground obstruction, and a single luminous rectangle or focal object. 4. **Apply the shared visual grammar.** Use near-monochrome tonality, crushed blacks, blown ivory highlights, sparse midtones, tactile age, geometric framing, and controlled imperfection. Color is absent or limited to a subtle cold green, blue-gray, desaturated amber, or signal-error cast. 5. **Choose the capture layer explicitly.** There are two related but different looks: **CRT-display view** shows an image on a square monochrome tube; **analog-camera documentary view** shows a real-world object or scene recorded by a period analog video camera. Do not let the second collapse into the first. For documentary view, state that the subject is physically present in a real location and that the camera is photographing it directly, with practical lens behavior, imperfect focus, exposure, depth of field, reflections, and incidental set detail. The CRT or signal is the camera and recording chain, not the subject's entire reality. 6. **Make the recording medium the subject of the image.** The result must read as a low-fidelity monochrome CRT capture or a photograph of one, not a clean digital scene with scanline overlays. Start from a small, soft, interlaced raster: visible scanline structure, phosphor bloom, coarse noise, sync wobble, barrel distortion, clipped whites, crushed blacks, ghosting, focus falloff, dust, scratches, and uneven exposure. Let detail disappear. Signal damage should reduce fidelity while preserving the essential subject. 7. **Add signal treatment as physical evidence, not decoration.** Use restrained CRT scanlines, interlacing, film grain, dust, scratches, halation, phosphor bloom, soft focus, edge smearing, vignette, slight barrel distortion, ghosting, minor chromatic misregistration, and uneven exposure. Keep the subject legible. 8. **Check the result against the consistency rules.** Reject outputs that become bright, evenly exposed, colorful, glossy, busy, generic glitch art, or polished CGI. ### Prompt Pattern Use the subject-neutral shorthand, then add only the details the specific asset needs: ```text [SUBJECT] shown as a low-fidelity monochrome CRT screen capture, rendered as analog occultism / industrial CRT noir: visibly soft interlaced raster, coarse phosphor structure, horizontal scanlines, sync wobble, barrel distortion, ghosting, uneven tracking, crushed blacks, clipped ivory highlights, one luminous practical source, claustrophobic geometry, archival technical atmosphere, tactile signal degradation, quiet unresolved tension, controlled imperfection. It must look like an old recording of a CRT, not a clean digital image with a scanline filter. The recording defects are structural and unavoidable: low-resolution broadcast image, soft focus, horizontal line structure, phosphor persistence trails, unstable vertical hold, slight horizontal tearing, uneven brightness across the tube, black crush hiding fine detail, white blooming around the screen, dirty glass, dust, and imperfect analog capture. Do not render a sharp modern digital photograph and then add cosmetic lines. ``` Describe concrete objects, spatial relationships, and the information the viewer must understand. Do not rely on mood words alone. If typography is necessary, use original archival-technical labels, all-caps system annotations, monospaced text, framed emblems, diagrams, readouts, indexes, or specimen-card structures. Keep text sparse; models may render small annotations imperfectly. For detailed still-image prompt blocks, reference-based generation, and negative prompt guidance, read `references/image-prompting.md`, which is in this folder. If a user supplies a visual reference, use the actual reference in the image tool; a text description is not a substitute for the pixels. ### Video Direction (out of scope) This item covers still images only. Do not write video prompts, and do not use FFmpeg or any other skill or tool for video. If the user wants a video, tell them this item cannot do it and that they need a video tool with its own guide. ### Shared Consistency Rules Each asset should contain most of these ten signals: 1. near-monochrome tonality; 2. one dominant luminous source; 3. severe black-and-white contrast; 4. strong negative space; 5. tactile analog or archival texture; 6. geometric or industrial framing; 7. hidden technical depth; 8. quiet, unresolved tension; 9. controlled imperfection; 10. a discovered artifact quality rather than fresh manufacture. The subject can change. The visual grammar cannot. ### Avoid - **Screen-capture fidelity:** when the brief calls for CRT or recovered footage, name the raster defects explicitly: low resolution, soft focus, visible scanlines, interlacing, phosphor persistence, sync wobble, tracking errors, barrel distortion, clipped whites, crushed blacks, ghost trails, and dropped detail. A clean image with a decorative scanline overlay is a failure, not a pass. Do not default to colorful cyberpunk, vaporwave, broad RGB neon, teal-and-orange cinema grading, clean SaaS minimalism, glossy product advertising, high-key studio photography, generic hacker imagery, excessive digital corruption, random interface clutter, cartoon horror, jump scares, gore, conventional horror iconography, or perfectly polished CGI. Do not use nostalgic retro props merely as decoration. Effects must never become more noticeable than the subject. ### Reference and QA Boundaries - Use reference images to preserve identity, composition, or a visual anchor, but do not promise pixel-exact style transfer from an edit model. - For people and creatures, inspect anatomy before judging style. Clearly visible hands, limbs, cables, straps, and connected objects must have plausible geometry. - For typography and diagrams, verify every visible label, relationship, arrow, and hierarchy. Never invent technical data because the aesthetic suggests annotations. - After one or two materially different failed generations, stop and report the model limitation or change the shot. Do not hide a failed subject behind more darkness or degradation. ### When Not to Use Use another aesthetic skill for a named brand's locked visual identity, a specific site's cover rules, colorful cyberdelic work, or any video. This skill defines a visual language for still images only. It does not replace your image tool's own guide. ### Completion The skill is complete when the still or shot preserves the subject, expresses the shared visual grammar, passes the relevant image or frame-level checks, and has an explicit note of any unresolved model limitation or sampling boundary. ### After this When you've handed it back, suggest what they could do next in one short question. It's a suggestion: if they're done, that's fine. Offer these, and say they can type their own: - The [Multi-provider image maker](https://useaiblocks.com/skills/multi-provider-image-maker). It takes the image prompt. If they pick one and that skill is added here, carry straight on with what you just made. If not, give the link and say what to bring.