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

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 body is highly actionable and token-efficient, but two areas hold it back: batch operations lack validation checkpoints, and the progressive-disclosure structure is undermined by references to missing files (reference.md, forms.md) while the real scripts/ bundle goes unlinked. Addressing these would lift the weakest dimensions.

Suggestions

Add verification checkpoints to batch/destructive operations — e.g. after splitting or encrypting, re-open the output with PdfReader and assert the expected page count / that it decrypts — to satisfy the workflow_clarity validation requirement.

Create the referenced reference.md and forms.md files (or remove the dangling references) and point the form-filling task at the actual scripts/ entries such as fill_fillable_fields.py and fill_pdf_form_with_annotations.py so navigation works.

Consolidate the repeated merge/split/rotate coverage across pypdf, qpdf, and pdftk (or move the alternatives into reference.md) to reduce redundancy and tighten the Quick Reference table accordingly.

Dimension	Reasoning	Score
Conciseness	The body is code-dense with minimal prose and does not re-explain concepts Claude already knows (no "what a PDF is" or "how libraries work" preamble), matching the score-3 lean-and-efficient anchor; it is above the score-2 case that includes unnecessary explanation.	3 / 3
Actionability	Every section provides complete, executable, copy-paste-ready code or commands (e.g. full pypdf merge/split blocks, qpdf/pdftotext command lines), matching the score-3 fully-executable anchor.	3 / 3
Workflow Clarity	Operations are presented as self-contained code blocks but multi-step/batch tasks (encrypt, split, OCR) lack any validation or verification checkpoints and there are no feedback loops, so per the rubric this is capped at 2 rather than reaching the score-3 explicit-validation anchor.	2 / 3
Progressive Disclosure	Sections are well organized and references are signaled one level deep ("see reference.md", "read forms.md"), but those referenced files do not exist and the actual scripts/ bundle (form-filling scripts) is never linked from the body, so navigation is broken — short of the score-3 easy-navigation anchor and above the score-1 monolithic case.	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 across all dimensions: it enumerates concrete capabilities, supplies natural trigger terms, and gives explicit when-to-use guidance tied to a clearly distinct PDF niche. No changes needed.

Dimension	Reasoning	Score
Specificity	Lists many concrete actions — "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" — matching the score-3 anchor for multiple specific concrete actions.	3 / 3
Completeness	Explicitly answers both what (the enumerated 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"), matching the score-3 anchor.	3 / 3
Trigger Term Quality	Uses natural terms a user would say — "PDF files", "PDFs", ".pdf file", "merge", "split", "forms", "OCR" — giving good coverage of common variations, matching the score-3 anchor.	3 / 3
Distinctiveness Conflict Risk	Occupies a clear PDF-processing niche with distinct triggers unlikely to conflict with other skills, matching the score-3 anchor; it is well above the score-2 "could still overlap" case.	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/scientific-agent-skills
Path: skills/pdf/SKILL.md
Commit: 757b63b

Reviewed: about 10 hours 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.