Getting it into your agent
One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.
npx skills add Automaat/lightroom-mcp --skill raw-photo-lightroom-presetgit clone --depth 1 https://github.com/Automaat/lightroom-mcpWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/skills/automaat/lightroom-mcp/raw-photo-lightroom-preset)<a href="https://agentmods.dev/skills/automaat/lightroom-mcp/raw-photo-lightroom-preset"><img src="https://agentmods.dev/badge/skills/automaat/lightroom-mcp/raw-photo-lightroom-preset/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/skills/automaat/lightroom-mcp/raw-photo-lightroom-preset"><img src="https://agentmods.dev/badge/skills/automaat/lightroom-mcp/raw-photo-lightroom-preset.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
What it costs to keep this loaded
Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00074 | $0.01038 |
| Opus 5 | $0.00037 | $0.00519 |
| Sonnet 5 | $0.00015 | $0.00208 |
| Haiku 4.5 | $0.00007 | $0.00104 |
Grade A, and why
raw-photo-lightroom-preset scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 12d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 82 lines — stays where its author put it; the contents beside it link to each section on GitHub.
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
- Read
references/workflow.mdfor every shoot. - Read
references/style-library.mdbefore choosing a style or reference direction. - If Lightroom MCP tools are available and Lightroom Classic is running, also read
references/lightroom-mcp.mdand use the closed-loop route. - Otherwise use Lightroom/Camera Raw neutral previews and the manual-preview route. State that Lightroom-side feedback is unavailable.
- 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.
- Capture the current photo metadata and develop settings.
- 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. - Export a baseline JPEG from Lightroom into a new empty review folder.
- Apply one bounded pass at a time:
- technical correction;
- tonal shape;
- color correction;
- creative look;
- detail/noise.
- Export and inspect after each pass. Compare against the baseline and any user-approved reference image.
- When the fork tools are available, create uniquely versioned checkpoints with
create_develop_presetand diff them against the approved look withcompare_develop_presets. - Keep a checkpoint log of settings and rendered files. Stop when the remaining difference needs masks, crop, healing, AI Denoise, or subjective user choice.
- Ask for approval on representative before/after results before copying settings across a cluster.
- 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.
What ships with it
7 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
What this file has done since we first saw it
Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.
- 12d ago First seen · 82 lines · 74 tokens per session scan A a726bee7c32b
raw-photo-lightroom-preset is a skill published in the GitHub repository Automaat/lightroom-mcp (83 stars, last pushed 2d ago), licensed MIT. It adds 74 tokens to every session and 1,038 once invoked, about $0.0004 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other skills, from other repositories
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
local-ai-agents
Build local-first AI agents that run entirely on a developer workstation with Microsoft Foundry Local and Qwen function-calling models. Covers Small Language Models (SLMs), the OpenAI-compatible local endpoint, sandboxed local tools, local RAG with Chroma, local MCP servers, hybrid cloud/local routing, and the…
next-cache-components-adoption
Turn on Cache Components in a Next.js app and resolve the blocking routes it surfaces. Use when the user wants to enable, adopt, or migrate to Cache Components, flip the cacheComponents flag, work through a flood of blocking-prerender / instant validation errors, run the cache-components-instant-false codemod, or…
chat-pet-sprite-creation
Use when creating or changing VS Code chat pet sprite art, sprite sheets, state animations, eye treatments, Stable/Insiders variants, or pet transitions under src/vs/workbench/contrib/chat/browser/widget/media/chatPet.
cpu-profile-analysis
Analyze V8/Chrome CPU profiles (.cpuprofile) and DevTools trace files (Trace-.json). Use when: profiling performance, investigating slow functions, comparing code paths, finding bottlenecks, analyzing timeToRequest, understanding call trees from sampling profiler data, analyzing layout/paint/rendering, investigating…
insight-error-page
Write or audit an insight-kind error page for the Next.js dev overlay. Use when creating a new errors/ .mdx page, auditing an existing one, or checking that a page matches the framework fix cards. Covers page structure, title alignment, FixCard cards with Copy prompt button, code snippets, terminology verification…