graphical-abstract-wizard
Generate graphical abstract layout recommendations based on paper abstracts
63
45%
Does it follow best practices?
Impact
96%
2.28xAverage score across 3 eval scenarios
Passed
No known issues
Optimize this skill with Tessl
npx tessl skill review --optimize ./scientific-skills/Academic Writing/graphical-abstract-wizard/SKILL.mdEvaluation results
96%
68%Graphical Abstract for Computational Biology Paper
Correct script usage and output structure
Script entry point
0%
60%
Abstract input method
0%
100%
Output to file
0%
100%
Key Concepts section
70%
100%
Visual Elements section
80%
100%
Layout Blueprint section
100%
100%
AI Art Prompts section
40%
100%
Midjourney v6 aspect ratio
0%
100%
Midjourney v6 version flag
0%
100%
Midjourney style raw flag
0%
100%
Dependency install
0%
100%
Without context: $0.7419 · 3m 24s · 34 turns · 40 in / 11,309 out tokens
With context: $0.6507 · 1m 39s · 26 turns · 149 in / 5,169 out tokens
100%
68%Automate Graphical Abstract Data Extraction for Design Pipeline
JSON output structure for integration
Script entry point
100%
100%
JSON format flag
0%
100%
abstract_summary key
0%
100%
key_concepts key
100%
100%
visual_elements key
100%
100%
layout_blueprint key
0%
100%
ai_prompts key
0%
100%
midjourney nested key
0%
100%
dalle nested key
0%
100%
Midjourney v6 flags in JSON
0%
100%
Keys documented
100%
100%
Without context: $0.4317 · 1m 49s · 23 turns · 26 in / 6,555 out tokens
With context: $0.4485 · 1m 4s · 21 turns · 144 in / 3,130 out tokens
94%
28%Visual Style Comparison for Conference Proceedings
Style options and stdin input
Script entry point
100%
62%
minimal style flag
100%
100%
colorful style flag
100%
100%
Output to file with -o flag
100%
100%
output_minimal.md present
100%
100%
output_colorful.md present
100%
100%
Midjourney aspect ratio
0%
100%
Midjourney version flag
0%
100%
Dependency install in script
0%
70%
Without context: $0.9724 · 3m 44s · 34 turns · 37 in / 12,167 out tokens
With context: $0.4936 · 1m 14s · 22 turns · 145 in / 3,672 out tokens
- Repository
- aipoch/medical-research-skills
- Commit
4a48721
- Evaluated
- Agent
- Claude Code
- Model
- Claude Sonnet 4.6
Table of Contents
Is this your skill?
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.