claude

image-production

Claude Code plugin for image editing, batch operations, format conversion, and filesystem organisation of image libraries — bucket by resolution, aspect ratio, orientation, format, EXIF capture time, camera, and dedupe duplicates / near-duplicates.

23 on GitHubby Daniel Rosehillv2.4.0MITupdated 3 days ago

Not in a marketplace yet, so it loads for one session with --plugin-dir.

Plugin image-production in danielrosehill/Claude-Image-Production-Plugin. Commands read from the repo's manifest — 2 days ago.

What it installs

Skills (29)

  • ai-graphics

    Generate AI graphics (banners, illustrations, hero images, social cards, characters, etc.) on fal, or Replicate if asked, choosing a cost-effective model per use case. Use when the user asks to create, generate, or make an image, banner, illustration, graphic, or artwork, or to redraw a reference im

  • auto-deskew

    Use when the user wants to automatically straighten a tilted image — scanned documents, phone-captured pages, photographed receipts, or slightly off-axis photos. Detects the dominant skew angle and rotates the image to vertical/horizontal, optionally cropping the resulting transparent triangles. Use

  • auto-tone

    Use when the user wants automatic tonal correction — fix flat/washed-out / underexposed / low-contrast images by stretching levels, normalising contrast, and gamma-correcting to a neutral midtone. Implements auto-level (per-channel histogram stretch), auto-gamma (midtone correction), and a combined

  • auto-white-balance

    Use when the user wants to automatically correct the white balance of an image (or batch) — neutralise colour casts from indoor lighting, mixed light, underwater shots, scans, or uncalibrated cameras. Implements gray-world (default), white-patch (per-channel auto-level), and a combined mode via Imag

  • batch-set-copyright

    Batch-stamp copyright, artist, and rights information on all images in a directory. Use when you need to quickly add copyright metadata to a photo library before distribution or archival — a convenience wrapper around exiftool.

  • check-model-pricing

    Check what an image model costs on fal (default) or Replicate, search fal's library for a model, and review or update the preferred image models per use case. Use when asked "how much is this model", "what's cheapest for X", "check fal pricing", "review the fal library", "update our preferred models

  • convert-to-avif

    Use when the user wants AVIF output — modern web format with ~30% better compression than WebP at the same visual quality, and ~50% better than JPEG. Wraps `avifenc`. Companion to `convert-to-webp`. Best target for new web work; check browser support if delivering to ancient clients.

  • fast-resize

    Use when the user wants to resize a large batch of images (>500 files) where ImageMagick throughput is the bottleneck. Wraps libvips for 5–10× faster batch resize at lower memory. Falls back to ImageMagick if `vips` isn't installed. Same outputs as `batch-resize` — different engine.

  • fast-thumbnail

    Use when the user wants to generate thumbnails at scale — index views, contact sheets, web previews, or just shrinking a library to manageable sizes. Wraps `vipsthumbnail` for sub-second-per-image generation, much faster than ImageMagick on large batches.

  • from-jxl

    Decode JPEG XL images (.jxl) to PNG or JPEG. Use when you need to convert JXL files back to standard formats for compatibility, display, or further editing.

  • images-to-pdf

    Use when the user wants to combine a folder or list of images into a single PDF — typically on a standard paper size (A4 default) for digital printers, document-style sharing, or proof sheets. Modes - one-per-page (default; auto-orient portrait/landscape per image), multi-up (2/4/6/9 per page), as-i

  • install-deps

    Provision the plugin's tools — system binaries via the host package manager, Python tools into a plugin-owned uv venv at <data-dir>/venv/. Idempotent doctor — run before any command reports a missing dep. Never touches system Python or fights PEP 668.

  • new-project

    Create a new image project inside the user's registered image workspace. Use when the user says "new image project", "create an image project called X", "scaffold a new image set", or similar. Creates a project subfolder with source, working, exports, references layout and an optional git init.

  • new-workflow

    Scaffold a multi-touchpoint image workflow inside the registered image workspace — a structured pipeline with explicit human review gates and optional cloud-AI generation/edit steps (Fal nano-banana via MCP). Use when the user says "new image workflow", "scaffold a workflow", "set up an image pipeli

  • open-workspace

    Open the user's registered image workspace folder. Use when the user says "open my image workspace", "take me to my image workspace", or similar. Reads the path from workspace.json and opens a terminal there.

  • optimize-jpeg

    Use when the user wants to shrink JPEG files — losslessly with `jpegoptim` (~5–15% reduction, no re-encode) or with re-compression via `mozjpeg` (~10–15% better than libjpeg-turbo at the same visual quality). Web-prep workhorse for photo libraries.

  • optimize-png

    Use when the user wants to shrink PNG files in a batch — losslessly with `oxipng` (typical 20–40% reduction, byte-identical decode) or aggressively with `pngquant` (lossy palette quantisation, 60–80% reduction with near-imperceptible quality loss for web use). Web-prep workhorse.

  • pdf-extract-embedded-images

    Extract embedded JPEG and PNG images from a PDF at their native resolution, without rasterizing. Use when a PDF is primarily a wrapper around photos or images and you want to recover them at full quality without the page rendering overhead.

  • pdf-to-images

    Rasterize PDF pages to numbered image files (JPEG, PNG, or TIFF) at a specified resolution (DPI). Use when you need to convert PDF content to standalone images — one image per page — with optional page range selection.

  • read-metadata

    Read and display EXIF, IPTC, XMP, and other metadata from images as structured JSON. Use when you need to inspect image metadata without modifying it — opposite of scrub-metadata, which removes metadata.

  • scrub-metadata

    Strip EXIF / IPTC / XMP metadata from images using exiftool. Use when the user wants to remove identifying metadata (GPS, camera, timestamps, thumbnails) from a single image, a folder, or a recursive tree before sharing or publishing. Supports preview, backup-first, whitelist of fields to keep (e.g.

  • set-metadata

    Write EXIF, IPTC, and XMP metadata tags to image files. Use when you need to add or update metadata like artist name, copyright, description, keywords, or GPS coordinates on individual images.

  • svg-to-raster

    Use when the user wants to rasterize SVG files — convert SVG to PNG, PDF, or PostScript at a chosen resolution. Wraps CairoSVG (Python, in the plugin venv). Single file or batch. Companion to `vectorize` (other direction).

  • to-jxl

    Convert images to JPEG XL format (.jxl) with quality presets (lossless, visually lossless, or web). Use when you want optimal compression for photo archival or long-term storage, especially from JPEG originals where lossless transcoding preserves the original bitstream at smaller file size.

  • transcode-jpeg-to-jxl-lossless

    Losslessly transcode JPEG files to JPEG XL, preserving the original JPEG bitstream while achieving ~20% file size reduction. Use when archiving JPEG photo libraries where the goal is smaller files without re-compression artifacts.

  • upscale-image

    Use when the user wants to AI-upscale images 2× / 3× / 4× — recovering detail in low-res sources, prepping small photos for print, enlarging AI-generated images. Wraps `upscayl-bin` (the CLI bundled with Upscayl) with its model library; falls back to standalone `realesrgan-ncnn-vulkan` if Upscayl is

  • vectorize

    Use when the user wants to trace a raster image (PNG/JPEG) into an SVG vector — useful for logos, line art, diagrams, and stylized illustrations. Wraps `vtracer` (Rust-backed, via Python wheel in the plugin venv). Companion to `svg-to-raster` (other direction).

  • web-ready

    Use when the user wants to take a folder of images (any mix of HEIC, RAW, PNG, JPEG, TIFF, WebP) and produce a web-ready set — EXIF stripped, resized to a sensible max dimension, encoded in modern formats (AVIF + WebP, with JPEG fallback), and optimised for size. End-to-end orchestrator. Mirrors `au

  • workspace-setup

    Register or create the user's image production workspace — a folder on disk where they keep image projects. Use on first run, or when the user says "set up my image workspace", "register my image workspace", "change my image workspace path", or similar. Persists the path so other skills (open-worksp

Slash commands (19)

  • /image-production:apply-filters
  • /image-production:batch-resize
  • /image-production:bg-removal
  • /image-production:compress-images
  • /image-production:convert-to-webp
  • /image-production:crop-images
  • /image-production:dedupe
  • /image-production:group-by-camera
  • /image-production:group-by-time
  • /image-production:images-here
  • /image-production:install-gimp-plugin
  • /image-production:organize-by-aspect-ratio
  • /image-production:organize-by-format
  • /image-production:organize-by-orientation
  • /image-production:organize-by-resolution
  • /image-production:scrub-small-images
  • /image-production:separate-photos-and-video
  • /image-production:setup-workspace

    Register or create the image production workspace folder

  • /image-production:sort-media
View source on GitHub blog.danielrosehill.com

Similar plugins

Harness Adobe's creative AI-powered tools to edit images, automate design workflows, and bring creative visions to life — from background removal to vectorization and professional retouching.

26 skills · 1 MCP server

anthropics/claude-plugins-official 47,076

Adobe

claude

Brings together Adobe Creative Cloud tools for images, vectors, design, and video. Edit multiple assets at once, adapt for different platforms, and complete multi-step creative workflows for polished results.

26 skills · 1 MCP server

anthropics/knowledge-work-plugins 35,601

Generate and edit AI images and videos from inside Claude Code through one remote MCP server. Nano Banana 2, GPT Image 2.5, Seedream 4.5, Flux 2 Pro and Z-Image for stills; Veo, Kling, Seedance, Grok Imagine and MiniMax for clips. quote_generation prices any call before you spend, and failed generations are refunded automatically. OAuth via /mcp; no API key to paste.

1 MCP server

davepoon/buildwithclaude 3,741

Generate and edit raster images through any OpenAI-compatible image API, with model discovery, reference-image editing, masks, and provider configuration support.

1 skill

hashgraph-online/awesome-codex-plugins 1,566

Brief-led image generation, editing, review, and bounded multi-model orchestration with current Gemini image models. Requires Claude Code 2.1.199+, Python 3.11+ with python3 on PATH, and Linux, macOS, or WSL for generation.

1 skill · 2 agents · 1 MCP server

AgriciDaniel/banana-claude 1,213

Generate or edit images via two backends: Google Gemini (gemini-3-pro-image) or any OpenAI-compatible endpoint (gpt-image-2, dall-e-3)

1 skill

FradSer/dotclaude 596

Maintain image-production?

This page updates itself from your repo. Add the badge to your README, or get it Featured to pin it above the organic results with a followed link to your site.

claude & codex pluginslisted