Agent skill · Testing & QA

still-image-retouching-finishing

Provider-independent still-image post-production skill for RAW/rendered intake, nondestructive development, exposure, white balance, tone, color, ICC proofing, masking, repair, compositing, truthful retouching by genre, generative disclosure, sharpening, noise, resampling, variants, metadata, export, QA, rights, and ethical finishing. Use when an agent must plan, perform, direct, or review still photography retouching and finishing for print, web, social, archive, publication, or client delivery; do not use for image-generation APIs, video grading, or campaign-specific production strategy.

Calesthio43,316★ · +2,384/wk · 2 repos on radarProfile →
claude-codecodexcopilotcursorMIT
Install
npx skills add calesthio/generative-media-skills --skill still-image-retouching-finishing --agent claude-code

Same command for any agent — swap --agent for codex, cursor, copilot.

Facts
Files in the skill folder: 2
SKILL.md size: 35 KB
Bundled scripts: none
Path: skills/production/post-production/still-image-retouching-finishing/SKILL.md
Open the folder on GitHub →
Where it comes from
Stars: 112 · +8 this week
Language: Python
Read our review of the source →

Weekly change comes from our own snapshots, not the repository page — it measures attention, not adoption.

Review
written from the skill's own SKILL.md · Aug 5, 2026

What it does

Finishes still images by guiding decisions on development, color, metadata, output, and review for RAW, rendered, or composite sources. It covers nondestructive development, color-managed finishing, retouching, and export, including generative-disclosure considerations and QA/archival packaging. It also prescribes how to handle metadata, rights, and provenance and specifies acceptable tools and output considerations.

How it works

It defines a workflow from intake to delivery:

  • Intake and triage: classify asset type (RAW, rendered, layered, composite, or scan) and collect delivery/use requirements, then classify asset for editing.
  • Development order: ingest/preserve, interpret profiles and metadata, fix defects, establish neutral exposure, shape tone/color, localize with masks, perform retouch/repair, proof and generate variants, then QA/deliver.
  • Color and ICC decisions: explicitly decide working color space per stage (e.g., RAW development in high-gamut internal pipeline; layered work in a compatible RGB space like ProPhoto RGB, Adobe RGB, or sRGB depending on output).
  • Intake and triage: start by clarifying truth boundaries and destination; ensure metadata, rights, and provenance considerations are captured.
  • The skill emphasizes documented grounded facts about color management, metadata standards (EXIF, IPTC, XMP, C2PA), and ethical guidelines.

When to use it

Use when an agent must plan, perform, direct, or review still photography retouching and finishing for print, web, social, archive, publication, or client delivery. Do not use for image-generation APIs, video grading, or campaign-specific production strategy.

What it can touch

The skill supports tool-agnostic workflows; explicit tools mentioned include Lightroom, Camera Raw, Capture One, Darktable, RawTherapee, Affinity Photo, Photoshop, GIMP, and related DAM/RIP/workflow tools. It includes intents around embedding profiles, metadata, and export recipes, but does not mandate a single software.

Caveats

It notes the need to disclose generative interventions, provenance data, and AI-related disclosures; it references rights metadata standards (IPTC, XMP, C2PA, Content Credentials) and cautions that AI-related fields do not automatically satisfy all client or legal requirements. It emphasizes that soft proofing is dependent on equipment and conditions and that output sharpening is destination-specific. It also cautions against using the skill for generation or campaign strategy.

From the SKILL.md

# Still Image Retouching and Finishing This skill is for finishing existing still images. It assumes there is a captured, scanned, rendered, or composited source image and that the agent's job is to make production decisions about development, retouching, color, metadata, output, and review. It is tool-agnostic: Lightroom, Camera Raw, Capture One, Darktable, RawTherapee, Affinity Photo, Photoshop,

More from generative-media-skills
All skills →
About this skill
What does the still-image-retouching-finishing skill do?

Provider-independent still-image post-production skill for RAW/rendered intake, nondestructive development, exposure, white balance, tone, color, ICC proofing, masking, repair, compositing, truthful retouching by genre, generative disclosure, sharpening, noise, resampling, variants, metadata, export, QA, rights, and ethical finishing. Use when an agent must plan, perform, direct, or review still photography retouching and finishing for print, web, social, archive, publication, or client delivery; do not use for image-generation APIs, video grading, or campaign-specific production strategy.

How do I install it?

Run `npx skills add calesthio/generative-media-skills --skill still-image-retouching-finishing --agent claude-code` — it drops the skill into your project so the agent can pick it up. Swap the --agent value for codex, cursor or copilot if you use one of those.

Where does this skill come from?

From calesthio/generative-media-skills, a repository with 112 stars. We read it straight from the repository tree rather than a submitted listing, so what you see here is what is actually published.

Is a popular skill a good skill?

Not necessarily. Stars measure attention, not adoption — a repository can trend for a week and be abandoned. That is why we show the weekly change from our own snapshots next to the total, instead of a single flattering number.

Keep going