Automatically assemble 6 sub-figures (A-F) into a high-resolution composite figure with aligned edges, unified fonts, and labels.
Install with Tessl CLI
npx tessl i github:aipoch/medical-research-skills --skill multi-panel-figure-assembler65
Does it follow best practices?
If you maintain this skill, you can automatically optimize it using the tessl CLI to improve its score:
npx tessl skill review --optimize ./path/to/skillValidation for skill structure
CLI figure assembly defaults
Script invocation
0%
100%
Six inputs provided
100%
100%
PIL/Pillow used
100%
100%
2x3 layout
100%
100%
DPI at least 300
100%
100%
Panel labels A-F
100%
100%
Topleft label position
100%
100%
Default padding 10px
0%
100%
Default border 2px
0%
100%
PNG output
100%
100%
Without context: $0.6375 · 2m 17s · 36 turns · 39 in / 7,531 out tokens
With context: $0.4044 · 1m 4s · 21 turns · 5,153 in / 3,017 out tokens
Programmatic assembly with custom layout and DPI
FigureAssembler class used
0%
100%
3x2 layout specified
66%
100%
600 DPI specified
100%
100%
Label size 36
23%
38%
DPI metadata in output
100%
100%
PIL/Pillow used
100%
100%
Uniform panel dimensions
100%
100%
LANCZOS resampling
100%
100%
Without context: $1.0739 · 4m 31s · 53 turns · 60 in / 12,741 out tokens
With context: $0.6541 · 1m 46s · 30 turns · 2,436 in / 5,681 out tokens
Custom styling parameters
scripts/main.py invoked
0%
100%
Hex background color
100%
100%
White label color
100%
100%
Bottom-right label position
100%
100%
20px padding
100%
100%
4px border
100%
100%
Output file produced
100%
100%
Without context: $0.7372 · 3m 5s · 41 turns · 95 in / 9,972 out tokens
With context: $0.5809 · 1m 36s · 28 turns · 5,437 in / 4,816 out tokens
Table of Contents
If you maintain this skill, you can claim it as your own. Once claimed, you can manage eval scenarios, bundle related skills, attach documentation or rules, and ensure cross-agent compatibility.