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.

2.04x

Quality

76%

Does it follow best practices?

Impact

100%

2.04x

Average score across 3 eval scenarios

Securityby

Passed

No known issues

Optimize this skill with Tessl

npx tessl skill review --optimize ./read-bin-docs/SKILL.md

Quality

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 description is functional and well-scoped, clearly communicating both what the skill does and when to use it, with helpful boundary conditions (no OCR, no docx). Its main weakness is that it describes only a single action (text extraction) and could include more natural trigger terms users might use. The explicit limitations actually help with distinctiveness by clearly delineating this skill from more capable document processing tools.

Suggestions

Add more natural trigger term variations such as '.pdf', 'parse PDF', 'get text from a PDF', or 'read PDF content' to improve matching.

Consider listing any additional specific capabilities beyond basic extraction (e.g., 'extract text page-by-page, retrieve metadata') to strengthen specificity.

Dimension	Reasoning	Score
Specificity	Names the domain (text extraction from documents) and specifies a key constraint (text-based PDF only, no OCR or docx), but only describes one action (extract text) rather than listing multiple concrete capabilities.	2 / 3
Completeness	Clearly answers both 'what' (straightforward text extraction from text-based PDFs) and 'when' ('Use when you just need to read/extract text from binary documents'), with explicit scope limitations (no OCR, no docx).	3 / 3
Trigger Term Quality	Includes some natural terms like 'text extraction', 'PDF', 'read', 'extract text', and 'binary documents', but misses common user variations like '.pdf', 'parse PDF', 'get text from PDF', or 'read PDF content'.	2 / 3
Distinctiveness Conflict Risk	The explicit constraints (text-based PDF only, no OCR, no docx) and the narrow scope (just text extraction, not form filling or merging) create a clear niche that is unlikely to conflict with broader document processing or OCR skills.	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 solid, actionable skill for PDF text extraction with executable code examples and useful CLI commands. The main weakness is redundancy between the Quick Start and Basic Usage sections, which repeat nearly identical code. The reference to a bundled script that isn't provided slightly undermines progressive disclosure.

Suggestions

Remove the 'Basic Usage' section or merge it with Quick Start to eliminate the duplicate PdfReader code snippet.

Include the referenced `scripts/extract_pdf_text.py` in the bundle, or remove the reference if the script doesn't exist yet.

Dimension	Reasoning	Score
Conciseness	The content is mostly efficient but has redundancy — the basic usage section repeats nearly the same code as the quick start. The 'Common Issues' section and requirements are useful but the duplicate code examples waste tokens.	2 / 3
Actionability	Provides fully executable Python code snippets and concrete CLI commands with various flag options. The examples are copy-paste ready and cover multiple use cases (all pages, specific pages, output to file).	3 / 3
Workflow Clarity	This is a simple, single-purpose skill (text extraction) with no destructive or multi-step operations requiring validation checkpoints. The single action is unambiguous and the troubleshooting section addresses common failure modes.	3 / 3
Progressive Disclosure	The content references `scripts/extract_pdf_text.py` but no bundle files are provided, making the reference unverifiable. The structure is reasonable with sections progressing from quick start to details, but the inline content could be tighter with the script details potentially in a separate file.	2 / 3
	Total	10 / 12 Passed

Validation

100%

Warnings & errors only

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: d2b7dff

Reviewed: about 20 hours ago

Table of Contents

Discovery Implementation Validation

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.