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

75%

Does it follow best practices?

Impact

100%

2.04x

Average score across 3 eval scenarios

Securityby

Passed

No findings from the security scan

Fix and improve this skill with Tessl

tessl review fix ./read-bin-docs/SKILL.md

Quality

Content

81%Weight 40%Scale 1-5

Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.

The body is highly actionable with executable Python and CLI examples backed by a real script, and its single-task workflow is clear for a simple read-only skill. The main weakness is redundant duplicate snippets that hurt conciseness and organization.

Suggestions

Remove the duplicate PdfReader loop — keep one canonical example in Quick Start and have 'Basic Usage' reference it or show only the variant (specific pages).

Drop or relocate the 'Future' note; it is non-actionable padding that does not help Claude execute the task.

Make the script path consistent across sections (the body references both extract_pdf_text.py and scripts/extract_pdf_text.py).

Dimension	Reasoning	Score
Conciseness	The Quick Start snippet and the 'Basic Usage' snippet are near-duplicate PdfReader loops, and the 'Future' note is non-actionable padding — anchor 3, could be tightened rather than anchor 4.	3 / 5
Actionability	Provides fully executable, copy-paste-ready Python and CLI invocations (uvx, --output, --pages 1-5 / 1,3,5) backed by a real bundled script covering the common cases — anchor 5.	5 / 5
Workflow Clarity	A simple single-purpose, read-only skill with an unambiguous single action; the simple-skill exception applies and no destructive/batch validation cap is triggered — anchor 5.	5 / 5
Progressive Disclosure	Well-organized sections with the bundled script referenced one level deep, but the duplicated code between Quick Start and Basic Usage is a minor organization gap — anchor 4, not 5.	4 / 5
	Total	17 / 20 Passed

Description

70%Weight 40%Scale 1-5

Based on the skill's description, can an agent find and select it at the right time? Clear, specific descriptions lead to better discovery.

The description clearly conveys the skill's narrow purpose (text extraction from text-based PDFs) and includes an explicit 'Use when...' trigger with helpful boundary exclusions. It is slightly held back by limited action variety and trigger-term breadth.

Suggestions

Add 1-2 more concrete actions (e.g., 'extract specific pages', 'save extracted text to a file') to lift specificity from 3 toward 4-5.

Broaden trigger terms with synonyms/extensions users actually say, such as 'PDFs' and '.pdf files'.

Make the 'when' clause more concrete by naming user cues, e.g. 'Use when the user mentions PDFs, .pdf files, or wants text from binary documents.'

Dimension	Reasoning	Score
Specificity	Names the domain ('text extraction from document files') and one concrete action ('read/extract text') with explicit scope narrowing, but does not list several distinct actions — matching anchor 3, not 4.	3 / 5
Completeness	Provides a clear 'what' (text-based PDF extraction, no OCR/docx) and an explicit 'Use when...' trigger, but the 'when' could name concrete user cues like 'when the user mentions PDFs' — anchor 4, not 5.	4 / 5
Trigger Term Quality	Includes natural terms users would say ('PDF', 'text extraction', 'binary documents', 'read/extract text') but misses common synonyms like 'PDFs' or '.pdf', fitting anchor 4.	4 / 5
Distinctiveness Conflict Risk	Explicit exclusions (no OCR, no docx) carve a distinct niche, but the trigger phrase 'binary documents' is somewhat broad, leaving minor overlap risk — anchor 4.	4 / 5
	Total	15 / 20 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 — 16 / 16 Passed

Validation for skill structure

No warnings or errors.

Repository: YPares/agent-skills
Path: read-bin-docs/SKILL.md
Commit: e9d2149

Reviewed: 3 days 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.