Image Enhancer
Creative skill, available on Zeplik
Image Enhancer is a ready-to-run creative skill on Zeplik. Not for new images from scratch (use imagegen). Ask in plain language and Zeplik applies the skill's method for you inside the conversation, on whichever AI model you prefer.
The Image Enhancer skill loads automatically when your request matches it, or you can invoke it directly by typing /image-enhancer in any chat. It works with attachments, connectors, and any model that supports the task, so you get the same expert method every time without setting anything up.
What the Image Enhancer skill can do
- Diagnose sharpness, exposure, and composition problems in uploaded images
- Identify root causes like JPEG artifacts or low display scaling, not just symptoms
- Provide ordered, concrete fix steps tailored to web, slides, social, or print use
- Write a Hermes-native regeneration prompt when the original source is unrecoverable
Try these prompts on Zeplik
Pick a prompt to open it in the Zeplik app. If you are not signed in yet, your prompt is waiting for you the moment you do.
How the Image Enhancer skill works
/image-enhancer
The user uploads an image; you analyze what is wrong with it and deliver two things: concrete enhancement guidance they can apply, and -- when regeneration is the better path -- a precise Hermes-native image-generation prompt that reproduces the image with the problems fixed.
Workflow
- Ask for the image if it is not already attached. You need to see it to diagnose it.
- Analyze quality across these dimensions:
- Resolution and apparent pixelation (upscaled? screenshot of a screenshot?)
- Sharpness and focus (motion blur, soft focus, oversharpening halos)
- Compression artifacts (JPEG blocking, banding in gradients, ringing around text)
- Exposure and lighting (too dark, blown highlights, flat contrast, color cast)
- Composition and framing (awkward crop, clutter, no negative space, tilted horizon)
- Text legibility (for screenshots and UI captures)
- Diagnose the root cause, not just the symptom -- "this is a JPEG saved at low quality, re-export from the source as PNG" beats "sharpen it".
- Choose the fix path:
- Guidance path: the user has the source (a screenshot they can retake, a photo they can re-shoot, an export they can redo). Give specific, ordered steps: retake at 2x display scaling, re-export as PNG, crop to the subject, raise shadows, etc.
- Regeneration path: the source is gone or the image is generated/illustrative. Write a detailed regeneration prompt describing the image's subject, composition, style, and palette, with the defects explicitly corrected ("crisp edges, no compression artifacts, even soft lighting"), and generate it with Hermes-native image generation. State clearly that regeneration produces a new image, not a pixel-faithful restoration -- photos of real people, real products, or evidentiary screenshots should stay on the guidance path.
- Tailor to the destination. Ask or infer where the image will be used and adjust the target: web/blog (moderate size, sharp text), slides (large, high contrast, readable from distance), social (platform crop ratios, bold subject), print (highest resolution available, no upscaling tricks will save a tiny source).
Output format
## Image Assessment
[2-3 sentences: what the image is and the main quality issues]
## Issues Found
- [issue]: [cause] -> [severity for the intended use]
## Recommended Fixes
[Ordered, concrete steps the user can take]
## Regeneration Prompt [only when regeneration is appropriate]
[Complete prompt, ready to run, with defects corrected and invariants stated]
Tips
- Screenshots: the best "enhancement" is almost always retaking at higher display scaling with a clean window -- say so.
- Never promise pixel-faithful restoration of faces or fine text through regeneration.
- For social media, ask which platform; crop and contrast targets differ.
- If the image is actually fine for its intended use, say that instead of inventing fixes.
Usage
/image-enhancer $ARGUMENTS
How to use the Image Enhancer skill
Sign in to Zeplik
Create a free Zeplik account or sign in. New accounts start with free credits, so you can try the Image Enhancer skill right away.
Describe your creative task
Ask in plain language, or type /image-enhancer to invoke the skill directly. Zeplik recognizes the Image Enhancer skill and applies its method.
Review and refine the result
Zeplik returns a clear, structured answer. Ask follow-ups in the same chat to refine it or take the next step.
Source and credit
- Author
- davila7
- License
- MIT
Adapted from the open-source davila7/claude-code-templates project and tuned to run natively on Zeplik. View source on GitHub.
Frequently asked questions
- What is the Image Enhancer skill?
- Image Enhancer is a ready-to-run creative skill on Zeplik. Not for new images from scratch (use imagegen). Ask in plain language and Zeplik applies the skill's method for you inside the conversation, on whichever AI model you prefer.
- How do I use Image Enhancer on Zeplik?
- Sign in to Zeplik and ask in plain language, or type /image-enhancer in any chat to invoke it directly. The skill applies its method and returns a result you can refine in the same conversation.
- Which AI model does the Image Enhancer skill use?
- Any model you choose. Zeplik works across every model in one chat, so the Image Enhancer skill runs on your preferred model for the task.
- Where does the Image Enhancer skill come from?
- The Image Enhancer skill is adapted from the open-source davila7/claude-code-templates project (MIT) and tuned to run natively on Zeplik. The original source is linked on this page.
- How much does the Image Enhancer skill cost?
- Using the skill is free to start. You only spend Zeplik credits when the assistant runs, and new accounts begin with free credits.
Related creative skills
- 3D Web ExperiencesUse when building 3D on the web: Three.js, React Three Fiber, WebGL, Spline, scroll-driven 3D scenes. Not for 2D browser games (use develop-web-game) or non-3D artifacts (use web-artifacts-builder).
- AI Image GenerationWrite high-quality prompts for Black Forest Labs FLUX image models, covering text-to-image, image editing instructions, structured JSON scene prompts, exact hex colors, text rendering, and multi-reference composition. Use when the user is generating or editing images with FLUX or asks for an image generation prompt and names FLUX or BFL. Not for diagram or chart requests, and not general prompt engineering for language models.
- Algorithmic Art StudioUse when the user asks for generative or algorithmic art made with code — p5.js sketches, flow fields, particle systems, seeded randomness with interactive parameter exploration. Trigger: "generative art", "creative coding", "make art with code". Not for photorealistic image generation (use flux-imaging).
- Game Development StudioUse when designing or building games in engines like Unity, Godot, or Unreal -- mechanics, GDScript, ECS/DOTS, game systems, performance. Not for browser games built in chat (use develop-web-game).
- Image Generation StudioUse to help CRAFT and refine an image prompt (composition, style, lighting, negative space, targeted revisions). You do NOT generate images from this skill -- Zeplik's native image pipeline handles generation automatically. Prompt-craft guidance only.
- Meme MakerUse when the user wants a meme made -- 'make a meme about deploying on friday', 'drake meme comparing tabs and spaces', 'this-is-fine meme for our launch'. Builds classic-template meme images via URL plus text formats. Not for AI image generation (use flux-imaging) or Slack GIFs (use slack-gif-creator).
More on Zeplik
Try Image Enhancer on Zeplik
Every model, one chat. Bring the Image Enhancer skill into your next conversation and let the assistant do the work.