Skip to main content
skill CX Codex

portrait-enhancement — Claude Code skill: setup and features

Automates AI-driven portrait retouching with each::sense. It adjusts lighting, removes blemishes, smooths skin texture, and adds background blur via agent prompts.

Install into Claude Code · Skills CLI (Vercel) All methods and platforms ↓
npx skills add eachlabs/skills --skill portrait-enhancement -a claude-code
Open on GitHub

What portrait-enhancement does

The skill connects your coding agent to the eachsense/beta model via https://eachsense-agent.core.eachlabs.run/v1/chat/completions. It handles skin cleanup while retaining natural pores, whitens teeth, enhances iris reflections, adjusts harsh shadows, and simulates shallow depth-of-field blur.

Requests operate in one of two modes. The max profile generates high-grade output suited for print or client delivery, taking more processing time. For rapid iterations or batch work, the eco profile completes faster at good quality. The HTTP client timeout must be configured for at least 10 minutes.

Without setting the EACHLABS_API_KEY environment variable, all requests fail immediately. Processing relies on remote each::sense servers, so local hardware does not run the model.

What it helps with

  • eliminate blemishes and scars without wiping away skin pores
  • soften harsh sunlight and deep facial shadows
  • simulate optical background bokeh behind the subject
  • whiten teeth naturally while avoiding flat white tones

Example prompts for the agent

  • Smooth the skin in this portrait naturally, keeping fine details around the eyes.
  • Add a soft bokeh blur to the background while keeping the hair outline crisp.
  • Fix harsh midday lighting on this photo by adding gentle studio fill light.

How to install portrait-enhancement

1Skills CLI (Vercel)

npx skills add eachlabs/skills --skill portrait-enhancement -a claude-code

2Manually: put the files in place

~/.claude/skills/portrait-enhancement/SKILL.md

Copy the whole skill folder; for one project use .claude/skills/portrait-enhancement/

Step by step, with commands for each platform: How to install skills in Claude Code: five ways

Questions about portrait-enhancement

How to install portrait-enhancement in Claude Code?

Run npx skills add eachlabs/skills --skill portrait-enhancement -a claude-code. The skill definition will be placed in ~/.claude/skills/portrait-enhancement/SKILL.md.

What does portrait-enhancement do?

It directs portrait retouching jobs to each::sense AI. The tool smooths skin, whitens smiles, sharpens eyes, fixes bad lighting, and adds lens-style background blur.

What is the difference between max and eco modes?

The max mode delivers top quality for final assets at a slower pace. The eco mode prioritizes generation speed for previews and bulk drafts.

Similar skills

All skills for AI and ML →

From the same set36

image-to-video Turns still photos into short videos with each::sense: subtle motion, cinemagraphs, camera pushes. Handy when all you have is one image. CX Codex +1 521installs eachlabs-video-generation Creates new videos from text prompts, source images, or motion references via the EachLabs API. Useful when your agent needs to generate animations, speaking avatars, or scene transitions. CX Codex +1 491installs flyer-design-generation Builds flyer layouts and promo leaflets through the each::sense API. Prepares designs formatted for physical printing or social media posting. CX Codex +1 490installs meta-ad-creative-generation This skill generates images and video for Facebook and Instagram ads: feed, Stories, Reels, carousels. Useful when you need creatives sized for Meta placements. CX Codex +1 467installs packaging-design-generation This skill turns a product description into packaging artwork with each::sense AI — boxes, labels, jars, coffee bags. Useful before a designer gets involved. CX Codex +1 444installs anime-avatar-generation Creates anime avatars and character art with each::sense AI. Use it to restyle photos, make chibi portraits, or design full-body characters. CX Codex +1 427installs object-removal Sends image URLs to each::sense AI to erase unwanted people, wires, text overlays, and blemishes from photographs. CX Codex +1 415installs video-watermark A skill that stamps logos or text onto video and strips existing watermarks. Runs through each::sense AI over HTTP. CX Codex +1 402installs

Project sponsors

Companies that keep this analytics open
Gold sponsor

Impressions, clicks and code copies — open statistics. We keep the numbers public for the same reason NeBlask itself is public. Become a sponsor