pdf

Use this skill whenever the user wants to do anything with PDF files. This includes reading or extracting text/tables from PDFs, combining or merging multiple PDFs into one, splitting PDFs apart, rotating pages, adding watermarks, creating new PDFs, filling PDF forms, encrypting/decrypting PDFs, extracting images, and OCR on scanned PDFs to make them searchable. If the user mentions a .pdf file or asks to produce one, use this skill.

Quality

86%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

High

Do not use without reviewing

Quality

Content

72%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 examples and clean organization, but it omits validation checkpoints for destructive/batch operations and its file references do not align with the actual bundle contents.

Suggestions

Add validation/verification steps for sensitive and batch operations—e.g., verify a merge produced the expected page count, confirm decryption succeeded, or check split outputs before proceeding.

Resolve the reference mismatch: either provide REFERENCE.md and FORMS.md, or replace those pointers with links to the existing scripts/ files (e.g., fill_fillable_fields.py, extract_form_field_info.py) that already cover form handling.

Reduce redundancy by presenting merge/split/rotate once with a preferred tool and noting alternatives briefly, rather than fully duplicating examples across pypdf, qpdf, and pdftk.

Dimension	Reasoning	Score
Conciseness	Mostly efficient code-driven prose with little concept explanation, but several operations (merge/split/rotate) are shown redundantly across pypdf, qpdf, and pdftk, adding tokens that could be trimmed.	4 / 5
Actionability	Copy-paste-ready, executable Python and shell examples cover the common PDF tasks (merge, split, extract text/tables, create, rotate, watermark, OCR, encrypt) with specific, complete snippets.	5 / 5
Workflow Clarity	Operations are well-organized and a Quick Reference table aids task-to-tool mapping, but sensitive/batch operations (encrypt/decrypt, merge, split) lack validation or verification checkpoints, capping the score at 3 per rubric guidance.	3 / 5
Progressive Disclosure	References to REFERENCE.md and FORMS.md are clearly signaled one level deep, but those files are not present in the bundle while the actual scripts/ files (form-related) are never referenced from the body, leaving structure misaligned with the real bundle.	3 / 5
	Total	15 / 20 Passed

Description

100%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 is comprehensive, concrete, and well-triggered, explicitly covering both capabilities and clear activation conditions with natural synonyms and the .pdf extension.

Dimension	Reasoning	Score
Specificity	Lists many concrete actions—reading/extracting text/tables, merging, splitting, rotating, watermarking, creating, filling forms, encrypting/decrypting, extracting images, and OCR—giving comprehensive coverage of the PDF domain.	5 / 5
Completeness	Explicitly answers 'what' with a detailed capability list and 'when' with concrete triggers ('whenever the user wants to do anything with PDF files', 'If the user mentions a .pdf file or asks to produce one').	5 / 5
Trigger Term Quality	Covers natural terms and synonyms including 'PDF files', 'PDFs', 'PDF forms', 'scanned PDFs', and the '.pdf' file extension, matching comprehensive anchor coverage.	5 / 5
Distinctiveness Conflict Risk	Scoped clearly to PDF files with distinct triggers and explicit file-extension guidance, minimizing overlap with other skills.	5 / 5
	Total	20 / 20 Passed

Validation

93%

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 — 15 / 16 Passed

Validation for skill structure

Criteria	Description	Result
metadata_version	'metadata.version' is missing	Warning

	Total	15 / 16 Passed

Repository: agentscope-ai/QwenPaw
Path: src/qwenpaw/agents/skills/pdf-en/SKILL.md
Commit: 2094e07

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.