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

90%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

Low

Low-risk findings worth noting

Quality

Content

80%Weight 40%Scale 1-3

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

A dense, highly actionable recipe reference with lean code and no filler, but it offers no validation checkpoints for batch/destructive operations and its progressive-disclosure links point to files that are missing from the bundle.

Suggestions

Add verification steps to batch/destructive operations (e.g., after merge/split/encrypt, confirm page counts or open the output) to raise workflow clarity.

Either include the referenced reference.md and forms.md files in the bundle or remove/fix the broken lowercase links so progressive-disclosure navigation resolves.

De-duplicate the Quick Start text-extraction snippet against the pdfplumber section to tighten conciseness further.

Dimension	Reasoning	Score
Conciseness	The body is lean executable code with minimal prose and no concept-explanation fluff (no "PDF is a Portable Document Format…" intro); every section is a recipe, cleaner than the level-2 anchor that carries unnecessary opinion, though the Quick Start slightly duplicates the pdfplumber extract-text example.	3 / 3
Actionability	Fully executable, copy-paste-ready Python and shell snippets throughout (pypdf merge/split/rotate, pdfplumber tables, reportlab, qpdf, pdftotext), plus a Quick Reference table mapping tasks to tools — matching the executable-code anchor.	3 / 3
Workflow Clarity	Operations are presented as clear single-action recipes with a task-to-tool decision table, and the simple-skills note allows a high score for unambiguous single actions. However batch/destructive operations (merge many files, split, encrypt) lack any explicit validation checkpoints — verify output before proceeding — so workflow_clarity is capped at 2 per the destructive-operations guideline rather than reaching 3.	2 / 3
Progressive Disclosure	References to reference.md and forms.md are clearly signaled and one-level-deep, but those files are absent from the bundle (no references/ dir, no forms.md/reference.md), so the disclosed content is unreachable; this is better than a monolithic level-1 wall but cannot reach the level-3 "easy navigation" anchor.	2 / 3
	Total	10 / 12 Passed

Description

100%Weight 40%Scale 1-3

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, comprehensive description that clearly states both capabilities and explicit trigger conditions with natural user keywords. It is concise despite its breadth and occupies a distinct, low-conflict niche.

Dimension	Reasoning	Score
Specificity	Lists many concrete actions — "reading or extracting text/tables", "merging multiple PDFs", "splitting PDFs apart", "rotating pages", "adding watermarks", "filling PDF forms", "encrypting/decrypting", "extracting images", and "OCR" — matching the multi-action anchor rather than the single-action level 2.	3 / 3
Completeness	Explicitly answers both what (the action list) and when ("Use this skill whenever the user wants to do anything with PDF files" and "If the user mentions a .pdf file or asks to produce one, use this skill"), satisfying the explicit-trigger requirement; level 2 lacks an explicit when clause.	3 / 3
Trigger Term Quality	Covers natural terms users say — "PDF files", "PDFs", ".pdf file", "PDF forms" — giving good keyword coverage rather than just "Works with PDF files" at level 2.	3 / 3
Distinctiveness Conflict Risk	Scoped narrowly to PDF files with distinctive ".pdf"/"PDFs" triggers, unlikely to conflict with other skills; not the generic "Works with document files" level 2.	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: K-Dense-AI/claude-scientific-writer
Path: .claude/skills/document-skills/pdf/SKILL.md
Commit: 43aaecd

Reviewed: 18 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.