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.mdQuality
Discovery
75%Based on the skill's description, can an agent find and select it at the right time? Clear, specific descriptions lead to better discovery.
This is a solid description that clearly communicates scope and boundaries, with explicit 'Use when' guidance and helpful exclusions (no OCR, no docx) that reduce conflict risk. Its main weakness is limited trigger term coverage—it could include more natural user phrasings—and the specificity could be improved by listing additional concrete actions beyond just 'extract text'.
Suggestions
Add more natural trigger terms users would say, such as '.pdf', 'parse PDF', 'get text from a PDF', 'read a PDF file'
Consider listing additional specific actions if applicable (e.g., 'extract text, read page content, pull paragraphs from PDF files') to improve specificity
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | Names the domain (text extraction from document files) and specifies a key action (read/extract text), but only describes one core action rather than listing multiple specific concrete actions. The parenthetical clarification about text-based PDF and exclusions adds useful specificity. | 2 / 3 |
Completeness | Clearly answers both 'what' (straightforward text extraction from document files, text-based PDF only, no OCR or docx) and 'when' ('Use when you just need to read/extract text from binary documents'). The explicit 'Use when' clause with trigger guidance is present. | 3 / 3 |
Trigger Term Quality | Includes some relevant keywords like 'text extraction', 'PDF', 'read/extract text', 'binary documents', but misses common user variations like '.pdf', 'parse PDF', 'get text from', 'pull content from'. The term 'binary documents' is somewhat technical and not what users would naturally say. | 2 / 3 |
Distinctiveness Conflict Risk | The description carves out a clear niche by specifying text-based PDF only, excluding OCR and docx, and emphasizing 'straightforward' extraction. This makes it clearly distinguishable from OCR skills, docx processing skills, or more complex document analysis tools. | 3 / 3 |
Total | 10 / 12 Passed |
Implementation
77%Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.
A functional skill with good actionability — concrete, executable code examples cover the main use cases well. The main weakness is redundancy between the Quick Start and Basic Usage sections, which wastes tokens without adding value. The skill could be tightened by merging duplicate sections and removing information Claude already knows (like what scanned PDFs are).
Suggestions
Merge the 'Quick Start' and 'Basic Usage' sections to eliminate the near-duplicate PdfReader code examples.
Remove explanations of concepts Claude already knows, such as what scanned PDFs are and why they don't yield text.
Remove the 'Future' note about DOCX/XLSX support — it adds no actionable value.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | The content is mostly efficient but has redundancy — the 'Quick Start' and 'Basic Usage' sections show nearly identical code. The 'Common Issues' section and requirements are useful but the 'Future' note is unnecessary filler. Some explanations like 'Scanned PDFs without OCR won't extract text' are things Claude already knows. | 2 / 3 |
Actionability | The skill provides fully executable, copy-paste ready Python code and CLI commands. Multiple usage patterns are covered (all pages, specific pages, output to file) with concrete examples. | 3 / 3 |
Workflow Clarity | This is a simple, single-purpose skill (text extraction from PDF). The single action is unambiguous — read PDF, extract text. There are no destructive or batch operations requiring validation checkpoints, so the clear presentation is sufficient. | 3 / 3 |
Progressive Disclosure | The content references a script at `scripts/extract_pdf_text.py` but no bundle files are provided to verify its existence. The structure is reasonable with sections progressing from quick start to details, but the content is somewhat monolithic — the basic usage and quick start overlap, and there's no separation of reference material into supporting files. | 2 / 3 |
Total | 10 / 12 Passed |
Validation
100%Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.
Validation — 11 / 11 Passed
Validation for skill structure
No warnings or errors.
- Repository
- YPares/agent-skills
- Commit
84b1da5
- Reviewed
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.