read-bin-docs
Straightforward text extraction from document files (text-based PDF only for now, no OCR or docx). Use when you just need to read/extract text from binary documents.
84
76%
Does it follow best practices?
Impact
100%
2.04xAverage score across 3 eval scenarios
Passed
No known issues
Optimize this skill with Tessl
npx tessl skill review --optimize ./read-bin-docs/SKILL.mdEvaluation results
100%
45%Academic Paper Text Indexer
pypdf extraction script
Uses pypdf library
0%
100%
Correct import statement
0%
100%
PdfReader instantiation
0%
100%
extract_text method
0%
100%
Output file flag
100%
100%
Page range support
100%
100%
Comma-separated pages support
100%
100%
1-indexed page numbers
100%
100%
Stdout fallback
100%
100%
100%
50%Portable PDF Extraction for CI/CD Pipeline
uvx dependency-free invocation
Uses uvx invocation
0%
100%
Correct uvx syntax
0%
100%
pypdf as the dependency
0%
100%
PDF argument passed
100%
100%
Output flag usage
100%
100%
Pages flag documented
100%
100%
No pre-install required
0%
100%
Output flag documented in USAGE.md
100%
100%
Invokes provided script
100%
100%
100%
58%PDF Text Quality Diagnostic Tool
layout-aware encoding handling
Uses pypdf library
0%
100%
Correct import pattern
0%
100%
Layout-aware extraction
0%
100%
extract_text called
0%
100%
PdfReader pages iteration
0%
100%
Scanned PDF limitation
100%
100%
No OCR claim
100%
100%
No docx support
100%
100%
Per-page reporting
100%
100%
Encoding mitigation in notes
50%
100%
- Repository
- YPares/agent-skills
- Commit
aed1afb
- 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.