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

87%

Does it follow best practices?

Impact

100%

2.04x

Average score across 3 eval scenarios

Securityby

Passed

No known issues

Quality

Content

85%

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

A clean, actionable, well-organized skill body with executable code and a properly referenced bundle script. The main weakness is redundancy between the Quick Start and Basic Usage sections, which inflates tokens without adding new capability.

Suggestions

Collapse the Quick Start snippet and the 'Basic Usage' loop into a single canonical example to remove the near-duplicate PdfReader code blocks.

Trim the conversational lead-in ('Need to extract text from a PDF? Use this Python snippet:') to a bare heading+code block for tighter token efficiency.

Dimension	Reasoning	Score
Conciseness	The body is mostly lean and free of concepts Claude already knows, but the Quick Start snippet and the 'Basic Usage' section are near-duplicate PdfReader extraction examples, and three code blocks repeat the same core operation — matching anchor 2 ('mostly efficient but could be tightened') rather than the every-token-earns-its-place bar of anchor 3.	2 / 3
Actionability	It provides fully executable Python and bash (uvx invocation plus the script CLI with --output and --pages flags) that is copy-paste ready with specific examples, matching anchor 3.	3 / 3
Workflow Clarity	This is a simple single-purpose skill whose single action (extract PDF text) is unambiguous from the Quick Start; per the simple_skills scoring note, workflow clarity scores 3 when the action is clear and well-organized, and text extraction is read-only so no destructive/batch validation checkpoint is required to cap the score.	3 / 3
Progressive Disclosure	Content is organized into clear sections (Quick Start, Basic Usage, Specific Pages, Using the Script, Requirements, Common Issues) and the bundle script scripts/extract_pdf_text.py — verified to exist — is referenced one level deep and clearly signaled, matching anchor 3 and the simple_skills allowance for well-organized sections.	3 / 3
	Total	11 / 12 Passed

Description

90%

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

A concise, well-scoped description that clearly states both capability and trigger conditions, with explicit boundaries that reduce conflict risk. Its only gap is specificity: it names a single action rather than enumerating the concrete operations the skill supports.

Suggestions

Name the concrete operations the skill supports (e.g., 'extract all text, extract specific pages, or run command-line extraction from PDFs') to lift specificity from one action to multiple concrete actions.

Consider adding the natural term '.pdf' / 'PDFs' to broaden trigger coverage for users who reference the file extension directly.

Dimension	Reasoning	Score
Specificity	The description names a concrete domain and action — "text extraction from document files (text-based PDF only for now)" — but lists only a single action (extraction), which matches anchor 2 ('Names domain and some actions, but not comprehensive') rather than anchor 3's requirement of multiple specific concrete actions.	2 / 3
Completeness	It explicitly answers both "what" (text extraction from text-based PDFs) and "when" via an explicit "Use when you just need to read/extract text from binary documents" trigger clause, matching anchor 3 and satisfying the guideline that an explicit Use-when clause avoids the cap at 2.	3 / 3
Trigger Term Quality	It surfaces several natural terms a user would actually say — "text extraction", "document files", "text-based PDF", "read/extract text", "binary documents" — giving good coverage rather than the sparse single-keyword case of anchor 2.	3 / 3
Distinctiveness Conflict Risk	The explicit scoping "text-based PDF only for now, no OCR or docx" carves a clear niche and rules out adjacent skills (OCR, docx), matching anchor 3's 'clear niche with distinct triggers; unlikely to conflict' rather than the broader overlap of anchor 2.	3 / 3
	Total	11 / 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 — 16 / 16 Passed

Validation for skill structure

No warnings or errors.

Repository: YPares/agent-skills
Commit: ac633fa

Reviewed: 5 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.