Fix garbled text in PDF/SVG vector graphics for final editing in AI. Detect, replace and repair garbled text in vector graphic files while maintaining original formatting and layout.
62
51%
Does it follow best practices?
Impact
70%
5.00xAverage score across 3 eval scenarios
Passed
No known issues
Optimize this skill with Tessl
npx tessl skill review --optimize ./scientific-skills/Data analysis/vector-text-fixer/SKILL.mdJSON export for editable workflow
Uses scripts/main.py
0%
100%
Export-JSON flag used
0%
100%
file_info section present
0%
100%
repair_data section present
0%
100%
text_elements or text_blocks list
0%
100%
original_text field in elements
0%
100%
confidence field in elements
0%
100%
suggested_fix or user_editable field
20%
100%
is_garbled flag present
50%
100%
Without context: $0.1715 · 47s · 9 turns · 14 in / 3,442 out tokens
With context: $0.7285 · 2m 22s · 31 turns · 165 in / 7,218 out tokens
Batch folder processing
Uses scripts/main.py
0%
75%
Batch flag used
0%
0%
Output folder specified
0%
0%
fixed_ prefix on outputs
0%
0%
All input files processed
100%
100%
Dependencies installed
0%
100%
Summary report produced
100%
100%
Without context: $0.2798 · 1m 7s · 15 turns · 19 in / 4,485 out tokens
With context: $0.7536 · 2m 9s · 30 turns · 63 in / 7,385 out tokens
Python API integration with repair level control
Imports VectorTextFixer
0%
100%
Uses fix_svg or fix_file method
0%
100%
Repair level set to minimal
0%
0%
Does NOT use aggressive level
100%
100%
Reads result success field
0%
100%
Accesses garbled block info
0%
100%
Installs dependencies
0%
0%
Produces output artifact
60%
100%
Without context: $0.2551 · 1m 4s · 13 turns · 16 in / 3,880 out tokens
With context: $0.7937 · 2m 34s · 31 turns · 127 in / 8,221 out tokens
ca9aaa4
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.