pdf-reader

Use this skill when the user wants to read, parse, or extract data from PDF files — text, tables, images, or metadata.

Quality

88%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

Passed

No findings from the security scan

Quality

Content

83%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.

A concise, highly actionable reference skill with copy-paste code for every common PDF task. Its main weakness is workflow clarity: batch and disk-writing operations lack validation checkpoints and the OCR-vs-extract decision flow is left implicit rather than sequenced.

Suggestions

Add a short decision workflow at the top: check is_text_pdf() first, then branch to direct extraction or ocr_pdf() for scanned files, with a verify step confirming extracted output is non-empty before reporting success.

For batch operations like extract_images and tables_to_csv, add validation feedback (e.g., assert saved file count > 0, or log a warning if a page yields no tables) so failures surface early.

Note external system dependencies explicitly where they matter (e.g., tesseract binary for pytesseract, poppler for pdf2image) so execution doesn't fail silently.

Dimension	Reasoning	Score
Conciseness	The body is almost entirely executable code with terse, task-named headers and no padding explaining PDFs or library mechanics; every token earns its place.	5 / 5
Actionability	Every section provides copy-paste-ready, complete Python functions covering the common cases (text, tables, fast text, page ranges, metadata, images, OCR, scanned-check, multi-column), plus a concrete library-per-task reference table.	5 / 5
Workflow Clarity	Batch/destructive-adjacent operations (extract_images, tables_to_csv, ocr_pdf) write many files or run heavy OCR with no validation checkpoints or feedback loops, and the natural decide-then-extract sequence (is it scanned? -> OCR vs extract) is left implicit; per the rubric cap, batch skills without validation cannot exceed 3.	3 / 5
Progressive Disclosure	No bundle files exist, so all content is inlined; the body (~133 lines) is above the simple-skill threshold but is well-organized into clear task sections plus a Quick Reference table, yielding good structure with only minor organization gaps.	4 / 5
	Total	17 / 20 Passed

Description

92%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.

A strong, specific description that clearly states both what the skill does and when to use it, with concrete actions and content types. Minor trigger-term gap: it lacks 'PDFs' (plural noun) and the '.pdf' extension that would round out keyword coverage.

Dimension	Reasoning	Score
Specificity	Enumerates concrete actions ('read, parse, or extract data') and four data types (text, tables, images, metadata), giving comprehensive coverage of the PDF domain.	5 / 5
Completeness	Explicitly answers 'when' ('Use this skill when the user wants to...') and 'what' (read/parse/extract PDF data across text, tables, images, metadata) with concrete trigger phrases.	5 / 5
Trigger Term Quality	Natural phrases like 'read/parse/extract data from PDF files' and named content types are present, but synonyms ('PDFs' plural noun) and the '.pdf' extension found in the score-5 anchor are missing.	4 / 5
Distinctiveness Conflict Risk	Tightly scoped to PDF files with specific content-type triggers, giving a clear niche with minimal overlap risk against non-PDF skills.	5 / 5
	Total	19 / 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: ProwlrBot/prowlr-marketplace
Path: skills/pdf-reader/SKILL.md
Commit: 32f0050

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.