pdf

Comprehensive PDF manipulation toolkit for extracting text and tables, creating new PDFs, merging/splitting documents, and handling forms. When Claude needs to fill in a PDF form or programmatically process, generate, or analyze PDF documents at scale.

Quality

90%

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

80%

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

The content is lean and highly actionable, dominated by executable code for distinct PDF tasks. Its weaknesses are missing validation steps for batch operations and broken/unsurfaced progressive disclosure — the referenced reference.md and forms.md are absent while the real scripts/ bundle is ignored.

Suggestions

Add verification steps after batch/destructive operations (e.g. after splitting, confirm the expected number of output files exist and open with PdfReader; after merging, assert the page count equals the sum of inputs).

Fix progressive disclosure: either create the referenced reference.md and forms.md, or update the links to point to the actual scripts/ files (e.g. fill_pdf_form_with_annotations.py, fill_fillable_fields.py) so the existing bundle is discoverable.

Move the detailed per-library recipe catalog into reference.md, keeping SKILL.md as a concise overview with a quick-start and one-level-deep pointers, to reduce inline length and redundancy with the Quick Reference table.

Dimension	Reasoning	Score
Conciseness	The body is almost entirely executable code and commands with no concept explanations Claude already knows (no "what is a PDF" prose), so every token earns its place.	3 / 3
Actionability	Each task is given as complete, copy-paste-ready code or commands (e.g. the pypdf merge, qpdf split, pdfplumber table extraction), matching the score-3 anchor.	3 / 3
Workflow Clarity	Tasks are presented as standalone snippets with no validation checkpoints for batch/destructive operations (split, merge, encrypt, watermark), which the rubric caps at 2.	2 / 3
Progressive Disclosure	The body signals reference.md and forms.md, but those files do not exist while the provided scripts/ bundle (form-filling scripts) is never referenced, so structure exists but navigation is broken and content that could be externalized is inline.	2 / 3
	Total	10 / 12 Passed

Description

100%

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 strong: it enumerates concrete capabilities, uses natural trigger terms, and includes an explicit "When Claude needs to..." usage clause. It is clearly scoped to PDF processing and unlikely to fire for the wrong skill.

Dimension	Reasoning	Score
Specificity	"extracting text and tables, creating new PDFs, merging/splitting documents, and handling forms" lists multiple specific concrete actions, matching the score-3 anchor.	3 / 3
Completeness	It states what the skill does (extract/create/merge/split/forms) and gives an explicit "When Claude needs to..." trigger clause, answering both what and when.	3 / 3
Trigger Term Quality	Natural user terms are well covered — "PDF", "PDF form", "PDF documents", "forms", "text and tables" — closely matching the score-3 example ("PDF files, PDFs, forms, document extraction").	3 / 3
Distinctiveness Conflict Risk	The PDF-manipulation niche is clear with distinct triggers ("fill in a PDF form", "process, generate, or analyze PDF documents"), making conflict with other skills unlikely.	3 / 3
	Total	12 / 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: quran/quran.com-frontend-next
Path: .agents/skills/pdf/SKILL.md
Commit: aff1a03

Reviewed: 2 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.