drpedapati/sciclaw/imagemagick

Claude Code and agent skill by drpedapati/sciclaw

Trust tier 3
  • community
Source check pending

Checking that the SKILL.md file is still in the repository.

Use this skill whenever scientific image assets need deterministic preprocessing (resize, crop, convert, DPI normalization, montage/contact sheets) using ImageMagick 7 `magick`.

Install

npx vskill@latest install drpedapati/sciclaw/imagemagick

SKILL.md

ImageMagick Skill

Use this skill for reproducible image preparation in manuscript and presentation workflows.

Primary CLI: magick (ImageMagick 7)

When to Use

Use this skill when a task involves:

  • converting image formats (png, jpg, tiff, webp, pdf pages to images)
  • resizing or cropping figures for publication constraints
  • setting or normalizing DPI / pixel density
  • trimming whitespace around plots/diagrams
  • generating contact sheets / montages for quick review
  • applying deterministic preprocessing before OCR or document export

Core Rules

  1. Always write to a new output path; do not overwrite originals unless explicitly requested.
  2. Prefer deterministic commands with explicit size, density, and quality values.
  3. Log command and output artifact path in the manuscript/project notes when results support claims.
  4. Standardize on magick command syntax (not legacy convert) for portability in sciClaw.

Quick Recipes

1) Resize to max width while preserving aspect ratio
bash
magick input.png -resize 1600x output-1600w.png
2) Normalize whitespace and add consistent border
bash
magick input.png -trim +repage -bordercolor white -border 20 output-trimmed.png
3) Convert with explicit quality
bash
magick input.tif -quality 92 output.jpg
4) Set DPI metadata for journal pipelines
bash
magick input.png -units PixelsPerInch -density 300 output-300dpi.png
5) Crop exact region
bash
magick input.png -crop 1200x900+100+80 +repage output-crop.png
6) Build contact sheet for fast visual QA

Always quote paths with spaces. Prefer an explicit font (or omit -label if fonts fail). Do not use ../ — set working directory to the image folder and write the sheet in-place. Prefer python-pptx / the pptx skill for slide decks; montage is for QA contact sheets only.

bash
magick montage figure-*.png -font DejaVu-Sans -label '%f' -tile 4x -geometry 600x600+8+8 contact-sheet.png
# Fallback font path on data3/Ubuntu if the name does not resolve:
# magick montage ... -font /usr/share/fonts/truetype/dejavu/DejaVuSans.ttf ...
# No-label fallback:
# magick montage figure-*.png -tile 4x -geometry 600x600+8+8 contact-sheet.png
7) First page of PDF to PNG for preview/review
bash
magick -density 300 manuscript.pdf[0] -quality 95 manuscript-page1.png

Scientific Workflow Patterns

Figure normalization batch
bash
mkdir -p normalized
for f in figures/*.png; do
base="$(basename "$f" .png)"
magick "$f" -trim +repage -resize 1800x -units PixelsPerInch -density 300 "normalized/${base}-norm.png"
done
OCR pre-processing
bash
magick scan.jpg -colorspace Gray -auto-level -sharpen 0x1.0 -density 300 scan-ocr-ready.png

Validation Checklist

  • Output files exist and are non-empty.
  • Pixel dimensions match requested constraints.
  • DPI metadata is set when required by downstream tools.
  • No source files were mutated unintentionally.

Failure Handling

  • If magick is missing: install ImageMagick (brew install imagemagick).
  • If policy/security errors occur on PDF operations: prefer working on image exports first, then re-run with simpler options.
  • If results look oversharpened or lossy: reduce aggressive filters and keep a lossless intermediate (.png or .tif).

Interoperability Notes

  • Pair with pandoc-docx and docx-review when preparing manuscript-ready figures.
  • Pair with pdf skill for PDF extraction/assembly workflows.
  • Pair with explainer-site and beautiful-mermaid when polishing visual assets for web explainers.

Security

  • Security scanPassed, 95 of 100Pattern checks on the skill's files.
  • Model reviewPassed

Quality evaluation

  • Task evaluationNot runNo evaluation yet. Run one in Skill Studio.

Source

Popularity

Repository stars
87
Repository forks
16
7-day trend score
22

Stars and forks are for the whole GitHub repository, not this skill alone. Not refreshed yet.

Works with

Any agent vskill installs to: 56 targets in all. These 39 have a page on this site.

  • Claude Code
  • Cursor
  • GitHub Copilot
  • Windsurf
  • Codex
  • Gemini CLI
  • Cline
  • Amp
  • Roo Code
  • Goose
  • Continue
  • Kilo Code
  • Junie
  • Trae
  • OpenHands
  • Qwen Code
  • AI Agent
  • Tabnine Chat
  • Sourcegraph Cody
  • Amazon Q
  • Firebase Genkit
  • Sweep
  • Devin
  • Phind
  • Mentat
  • Claude Desktop
  • Aider
  • GPT Pilot
  • Plandex
  • bolt.new
  • v0
  • Replit Agent
  • Anse
  • TypingMind
  • BetterChatGPT
  • LibreChat
  • Warp AI
  • Pieces
  • Fig AI
Embed badge
vskill VERIFIED badge
[![vskill VERIFIED](https://verified-skill.com/api/v1/skills/drpedapati/sciclaw/imagemagick/badge)](https://verified-skill.com/skills/drpedapati/sciclaw/imagemagick)

Something wrong with this skill or its page? Tell us.