New: 98,000+ skills indexed from GitHub repos with 100+ stars · every skill safety-checkedBrowse top skillsTop skills
Esc to closeBrowse all skills
Submit a skillBrowse skills
Submit a skillBrowse skills

Agent skill

Raw Photo Lightroom Preset

by Automaat in Automaat/lightroom-mcp

A skill your agent uses for RAW photo culling, Lightroom Classic or Camera Raw editing, reference-style matching, closed-loop Lightroom MCP adjustments, lighting-cluster preset creation, XMP…

MITAuto-check passedAgent Workflows

Install Raw Photo Lightroom Preset

skills CLI
$ npx skills add Automaat/lightroom-mcp --skill raw-photo-lightroom-preset -a claude-code

Project install by default; add -g for ~/.claude/skills/.

GitHub CLI
$ gh skill install Automaat/lightroom-mcp raw-photo-lightroom-preset --agent claude-code

Project scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).

Manual copy
$ git clone --depth 1 https://github.com/Automaat/lightroom-mcp.git skills-src && mkdir -p .claude/skills && cp -r skills-src/skills/raw-photo-lightroom-preset .claude/skills/raw-photo-lightroom-preset && rm -rf skills-src

Use ~/.claude/skills/ instead of .claude/skills for a personal install. The folder must contain SKILL.md.

Claude Code skills documentation · loads skills from .claude/skills/

Facts

Skill name
raw-photo-lightroom-preset
GitHub stars
130
Token cost
~1.2k tokens
SKILL.md length
557 words
Files
8 (incl. scripts, references)
Skills in repo
1
Repo updated
First seen
Licence
MIT

At a glance

A skill your agent uses for RAW photo culling, Lightroom Classic or Camera Raw editing, reference-style matching, closed-loop Lightroom MCP adjustments, lighting-cluster preset creation, XMP…

  • Works in 5 steps: Read references/workflow.md for every… → Read references/style-library.md before… → If Lightroom MCP tools are available and… → …
  • RAW photo culling
  • SKILL.md covers Core rules, Choose the route, Closed-loop route and Manual-preview route, plus 2 more sections
  • Runs Python scripts from its folder; calls python

What it does

Raw Photo Lightroom Preset is an agent skill from Automaat/lightroom-mcp. Use for RAW photo culling, Lightroom Classic or Camera Raw editing, reference-style matching, closed-loop Lightroom MCP adjustments, lighting-cluster preset creation, XMP fallback generation, NEF/DNG/TIFF preview workflows, or Chinese requests about matching previous edits. Prefer Lightroom-rendered before/after feedback when Lightroom MCP tools are available.

Its SKILL.md is about 1.2k tokens, which your agent loads only when the skill is triggered. The skill folder holds 11 other files, including scripts and reference files (for example `agents/openai.yaml`, `references/lightroom-mcp.md` and `references/style-library.md`).

It sits in Agent Workflows, covering MCP servers. It works with Model Context Protocol. The repository describes itself as: MCP server for Adobe Lightroom Classic. The licence is MIT.

When your agent uses it

  • RAW photo culling
  • Lightroom Classic
  • Camera Raw editing
  • Reference-style matching

Example prompts

  • “/raw-photo-lightroom-preset”

Requirements

  • Python 3

Workflow steps

5 steps, taken from the first numbered list in SKILL.md.

  1. Read references/workflow.md for every shoot.
  2. Read references/style-library.md before choosing a style or reference direction.
  3. If Lightroom MCP tools are available and Lightroom Classic is running, also read references/lightroom-mcp.md and use the closed-loop route.
  4. Otherwise use Lightroom/Camera Raw neutral previews and the manual-preview route. State that Lightroom-side feedback is unavailable.
  5. If provenance is missing or ambiguous, stop color work and mark the affected item 未分類.

What it can do on your machine

Read from SKILL.md and the folder at commit b977acb. It shows what the files ask for, not the result of running them.

  • Tool permissions

    Pre-approves nothing: there is no allowed-tools line, so your agent's usual permission prompts apply.

    From allowed-tools in the SKILL.md frontmatter.

  • Runs code

    Ships 1 file in scripts/ (Python), which the agent can run.

    Shell commands in SKILL.md call:

    • python

    From the folder's file list and the shell code blocks in SKILL.md.

  • Network

    No URLs in SKILL.md.

    From URLs in SKILL.md, links to its own repository left out.

  • Credentials

    Names no API keys, tokens, secrets or passwords.

    From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.

Context cost

Raw Photo Lightroom Preset loads about 1.2k tokens when it runs, and up to ~5.7k if it reads all its reference files. Until then it costs about 97 tokens; SKILL.md has 557 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it
~97
When it runs · the whole SKILL.md, loaded when a task matches
~1.2k
With references · SKILL.md plus every file in references/, read only if the agent opens them
~5.7k

Estimates: characters ÷ 4, the usual rule of thumb; real counts depend on the model's tokenizer. Scripts and assets cost tokens only if the agent reads them.

Safety

Auto-check passed

The automated check found no risky patterns in SKILL.md.

Automated static check — not a guarantee. Review scripts before installing. It scans the text of SKILL.md for risky patterns (piping downloads into a shell, reading credential files, hidden Unicode, destructive commands); the scripts in this folder are not scanned.

SKILL.md

The full file from Automaat/lightroom-mcp at commit b977acb, republished under its MIT licence (© Automaat). 557 words, ~1,249 tokens.

Download SKILL.mdSave it as .claude/skills/raw-photo-lightroom-preset/SKILL.md (or your agent's skills folder). This skill also uses 7 other files; get the full folder from GitHub.
name
raw-photo-lightroom-preset
description
Use for RAW photo culling, Lightroom Classic or Camera Raw editing, reference-style matching, closed-loop Lightroom MCP adjustments, lighting-cluster preset creation, XMP fallback generation, NEF/DNG/TIFF preview workflows, or Chinese requests about matching previous edits. Prefer Lightroom-rendered before/after feedback when Lightroom MCP tools are available.

RAW Photo Lightroom Preset v2

Core rules

  • Judge color only from RAW files rendered by Lightroom/Camera Raw. Use ordinary camera JPGs only for composition, focus, and expression triage.
  • Preserve originals and the user's master edit. Do not move, rename, delete, overwrite, or batch-edit photos unless the user asks.
  • Treat a preset as a reusable starting point, not a finished edit.
  • Separate technical correction from creative style. Never guess 30-50 sliders at once.
  • Prefer a closed loop: inspect Lightroom state, render, adjust a small pass, render again, compare, then continue.
  • Do not claim Lightroom import, visual fidelity, or manual QA passed unless it was actually performed.

Choose the route

  1. Read references/workflow.md for every shoot.
  2. Read references/style-library.md before choosing a style or reference direction.
  3. If Lightroom MCP tools are available and Lightroom Classic is running, also read references/lightroom-mcp.md and use the closed-loop route.
  4. Otherwise use Lightroom/Camera Raw neutral previews and the manual-preview route. State that Lightroom-side feedback is unavailable.
  5. If provenance is missing or ambiguous, stop color work and mark the affected item 未分類.

Closed-loop route

Use one representative RAW per lighting cluster first.

  1. Capture the current photo metadata and develop settings.
  2. If the user has an approved historical look, list presets and read it with get_develop_preset. Use UUID or folder/scope to avoid duplicate-name ambiguity.
  3. Export a baseline JPEG from Lightroom into a new empty review folder.
  4. Apply one bounded pass at a time:
    • technical correction;
    • tonal shape;
    • color correction;
    • creative look;
    • detail/noise.
  5. Export and inspect after each pass. Compare against the baseline and any user-approved reference image.
  6. When the fork tools are available, create uniquely versioned checkpoints with create_develop_preset and diff them against the approved look with compare_develop_presets.
  7. Keep a checkpoint log of settings and rendered files. Stop when the remaining difference needs masks, crop, healing, AI Denoise, or subjective user choice.
  8. Ask for approval on representative before/after results before copying settings across a cluster.
  9. Export an accepted custom/checkpoint preset with export_develop_preset; never overwrite an existing destination. Import it into Lightroom before claiming compatibility. Use Lightroom's UI for a visible canonical preset when needed. The bundled generator remains a fallback for a verified global-setting subset.
Show full SKILL.md (189 more words)Show less

Manual-preview route

Require Lightroom/Camera Raw exports with recorded provenance. Classify lighting clusters, choose representative files, propose style direction, and get user agreement before generating presets. Keep exposure, white balance, skin, local edits, and denoise as per-image follow-up unless the evidence supports a shared adjustment.

Safe XMP fallback

Use scripts/generate_xmp_preset.py only after style direction is agreed:

powershell
python scripts/generate_xmp_preset.py --list-styles
python scripts/generate_xmp_preset.py --list-modifiers
python scripts/generate_xmp_preset.py --style graduation-bright-natural --name "Graduation Bright Natural" --output "Graduation_Bright_Natural.xmp"
python scripts/generate_xmp_preset.py --style graduation-documentary --modifier low-light-noise-controlled --name "Graduation Documentary Low Light" --output "Graduation_Documentary_Low_Light.xmp"

The generator:

  • accepts only .xmp output;
  • refuses existing output unless --force is explicit;
  • refuses paths that look like RAW/JPG sidecar XMP files, even with --force;
  • writes atomically;
  • validates known Camera Raw keys, types, and ranges;
  • emits point curves as RDF sequences;
  • omits Profile, White Balance, and lens settings unless explicitly requested;
  • uses ASCII metadata by default; use --allow-unicode-metadata only when the target Lightroom setup has been tested.

Use --unsafe-set KEY=VALUE only for controlled research against a Lightroom-exported golden fixture. Never use it for routine delivery.

Validation levels

Report these separately:

  • Parser-level: XML is well formed.
  • Generator-level: CLI, safety checks, schema validation, and tests pass.
  • Lightroom import-level: the target Lightroom version imports the XMP and exposes the expected fields.
  • Visual fidelity-level: Lightroom-rendered output matches the intended/reference look.

Only the last two require real Lightroom validation.

© Automaat, MIT. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file

Files

SKILL.md and 7 other files (scripts, references) in skills/raw-photo-lightroom-preset of Automaat/lightroom-mcp.

  • SKILL.md
  • agents/openai.yaml
  • references/lightroom-mcp.md
  • references/style-library.md
  • references/styles.json
  • references/workflow.md
  • scripts/generate_xmp_preset.py
  • tests/test_generate_xmp_preset.py

Open the folder on GitHubat commit b977acb

Compare with similar skills

Raw Photo Lightroom Preset next to the 5 skills that share the most tags, products or categories with it. Stars are the repository's; “used in” counts other GitHub owners with a copy.

Raw Photo Lightroom Preset compared with similar skills
SkillStarsUsed inTokensAuto-checkLicenceRepo updated
Raw Photo Lightroom Preset this skillAutomaat/lightroom-mcp130—~1.2kAutomated safety check: PassMIT
MCP Server Builderanthropics/skills180k63 repos~2.3kAutomated safety check: PassApache-2.0
MCP Server BuildershareAI-lab/learn-claude-code78k4 repos~1.2kAutomated safety check: PassMIT
MCP Integration for Pluginsanthropics/claude-plugins-official38k11 repos~3.1kAutomated safety check: PassApache-2.0
Crush Configurationcharmbracelet/crush29k—~3.7kAutomated safety check: PassCustom licence
Context Mode Output Sandboxmksglu/context-mode26k—~4.1kAutomated safety check: PassCustom licence

Similar skills

  • MCP Server Builder

    anthropics/skills

    Official

    Guides the design and implementation of Model Context Protocol servers in TypeScript or Python, from tool naming and error messages to evaluation.

    180k GitHub starsUsed in 63 repos~2.3k tokens
    Agent WorkflowsAuto-check passed

  • MCP Server Builder

    shareAI-lab/learn-claude-code

    Walks through building MCP servers in Python or TypeScript that expose tools, resources and prompts to Claude, with templates, registration and testing.

    78k GitHub starsUsed in 4 repos~1.2k tokens
    Agent WorkflowsAuto-check passed

  • MCP Integration for Plugins

    anthropics/claude-plugins-official

    Official

    Explains how to bundle Model Context Protocol servers in a Claude Code plugin, covering config files, stdio, SSE, HTTP and WebSocket server types, and authentication.

    38k GitHub starsUsed in 11 repos~3.1k tokens
    Agent WorkflowsAuto-check passed

  • Crush Configuration

    charmbracelet/crush

    Explains how to configure the Crush coding agent with crushrc or crush.json, covering providers, models, LSPs, MCP servers, hooks, permissions and config precedence.

    29k GitHub stars~3.7k tokensUpdated today
    Agent WorkflowsAuto-check passed

  • Context Mode Output Sandbox

    mksglu/context-mode

    Routes large command, file, API and browser output through context-mode tools so only the needed result enters the agent's context, instead of dumping it via Bash.

    26k GitHub stars~4.1k tokensUpdated today
    Agent WorkflowsAuto-check passed

  • Warp GUI to Agent CLI Migration

    warpdotdev/warp

    Migrates the compatible subset of settings and global file-based MCP servers from the Warp desktop app into Warp Agent CLI without exposing credentials or state.

    65k GitHub starsUsed in 1 repo~2.1k tokens
    Agent WorkflowsAuto-check passed

Works with

Categories

Questions about Raw Photo Lightroom Preset

What does Raw Photo Lightroom Preset do?

A skill your agent uses for RAW photo culling, Lightroom Classic or Camera Raw editing, reference-style matching, closed-loop Lightroom MCP adjustments, lighting-cluster preset creation, XMP…. Raw Photo Lightroom Preset is an agent skill from Automaat/lightroom-mcp. Use for RAW photo culling, Lightroom Classic or Camera Raw editing, reference-style matching, closed-loop Lightroom MCP adjustments, lighting-cluster preset creation, XMP fallback generation, NEF/DNG/TIFF preview workflows, or Chinese requests about matching previous edits.

When should I use Raw Photo Lightroom Preset?

Raw Photo Lightroom Preset fits situations like: RAW photo culling; lightroom Classic; camera Raw editing; reference-style matching.

How do I install Raw Photo Lightroom Preset in Claude Code?

Run `npx skills add Automaat/lightroom-mcp --skill raw-photo-lightroom-preset -a claude-code`. Or copy the skill folder (skills/raw-photo-lightroom-preset in Automaat/lightroom-mcp) into .claude/skills/raw-photo-lightroom-preset in your project. Claude Code loads it when a task matches its description.

How do I install Raw Photo Lightroom Preset in Codex?

Run `npx skills add Automaat/lightroom-mcp --skill raw-photo-lightroom-preset -a codex`. Or copy the skill folder (skills/raw-photo-lightroom-preset in Automaat/lightroom-mcp) into .agents/skills/raw-photo-lightroom-preset in your project. Codex loads it when a task matches its description.

Can I use Raw Photo Lightroom Preset in Cursor, Gemini CLI or GitHub Copilot?

Cursor, Gemini CLI, GitHub Copilot and OpenCode also load SKILL.md folders. With the skills CLI, run `npx skills add Automaat/lightroom-mcp --skill raw-photo-lightroom-preset -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/raw-photo-lightroom-preset, .gemini/skills/raw-photo-lightroom-preset, .github/skills/raw-photo-lightroom-preset and .opencode/skills/raw-photo-lightroom-preset in your project.

What does Raw Photo Lightroom Preset need to run?

Going by SKILL.md and its folder, Raw Photo Lightroom Preset needs Python for the scripts in its folder and the command-line tools its instructions call (python). Our summary lists: Python 3.

Does Raw Photo Lightroom Preset access the network?

SKILL.md contains no URLs. Any network use would come from the scripts or tools the agent runs. This is read from the text; nothing was executed.

Is Raw Photo Lightroom Preset safe to install?

Our automated static check of SKILL.md found no risky patterns, such as piping downloads into a shell, reading credential files or hidden Unicode. It is not a guarantee. The check reads SKILL.md only: the scripts in the folder are not scanned, so read them before running anything.

What licence does Raw Photo Lightroom Preset use?

Raw Photo Lightroom Preset is published under the MIT licence (the repository's licence). It allows redistribution, so the full SKILL.md is shown on this page.

How many tokens does Raw Photo Lightroom Preset use?

About 1.2k tokens (SKILL.md is roughly 5k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full. Its references folder adds about 4.4k tokens, read only when the agent opens those files.

What are the alternatives to Raw Photo Lightroom Preset?

Skills that share tags, products or a category with Raw Photo Lightroom Preset: MCP Server Builder (anthropics/skills, 180k stars), MCP Server Builder (shareAI-lab/learn-claude-code, 78k stars), MCP Integration for Plugins (anthropics/claude-plugins-official, 38k stars) and Crush Configuration (charmbracelet/crush, 29k stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains Raw Photo Lightroom Preset?

Automaat (a GitHub user) maintains it in Automaat/lightroom-mcp, which has 130 GitHub stars. The repository was last updated on October 10, 2026.

Source: Automaat/lightroom-mcp on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.