pdf

PDF document processing and manipulation. Tools: Python (PyPDF2, pdfplumber, reportlab), CLI tools. Capabilities: text extraction, table extraction, form filling, merge/split documents, create PDFs, add annotations, watermarks, page manipulation. Actions: extract, create, merge, split, fill, annotate PDFs. Keywords: PDF, text extraction, table extraction, form fill, PDF form, merge PDF, split PDF, create PDF, reportlab, PyPDF2, pdfplumber, annotation, watermark, page rotation, PDF metadata, bookmarks, OCR. Use when: extracting text/tables from PDFs, filling PDF forms, merging/splitting documents, creating PDFs programmatically, adding annotations/watermarks, processing PDFs at scale.

Quality

82%

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

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.

A highly actionable, code-dense guide with excellent copy-paste examples and good section structure. Its main weaknesses are missing validation checkpoints on batch/destructive operations and dangling references to non-existent files (reference.md, forms.md).

Suggestions

Add validation/verify steps after batch and destructive operations (e.g., confirm merged page count, verify encrypted PDF opens, check split files are valid) to lift workflow clarity above the cap.

Create the referenced reference.md and forms.md files (or point to the existing scripts/ helpers) so the navigation links actually resolve.

Consolidate the repeated merge/split/rotate recipes across pypdf, qpdf, and pdftk into one primary method with alternatives noted briefly, to reduce redundancy.

Dimension	Reasoning	Score
Conciseness	The body is almost entirely executable code with brief comments and assumes Claude's competence, but merge/split/rotate are shown redundantly across pypdf, qpdf, and pdftk, which could be trimmed — placing it at score-4 rather than the lean score-5.	4 / 5
Actionability	Copy-paste-ready, executable snippets cover the common cases (extract text/tables, merge, split, create, watermark, encrypt, OCR) plus concrete CLI commands, matching the score-5 anchor.	5 / 5
Workflow Clarity	Operations are presented as standalone recipes rather than sequenced workflows, and batch/destructive operations (split into one-page files, merge multiple PDFs, encrypt) lack any validation or verify-fix-retry checkpoint; per the rubric this caps workflow_clarity at 3.	3 / 5
Progressive Disclosure	Sectioning is reasonable and references to reference.md/forms.md are clearly signaled one level deep, but those referenced files do not exist in the bundle (no references/ directory; only scripts/ exists), so navigation is broken and the promised detail is missing — falling to score-3.	3 / 5
	Total	15 / 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, comprehensive description that clearly states capabilities and explicit 'Use when' triggers, with good keyword coverage. The only weakness is a keyword-stuffed format and the absence of the '.pdf' file extension and 'PDFs' plural in the trigger terms.

Suggestions

Weave the keywords into natural prose rather than a comma-stuffed 'Keywords:' list; the current format reads as SEO padding rather than natural language.

Add the '.pdf' file extension and 'PDFs' to the trigger terms to reach full coverage per the rubric's score-5 anchor.

Trim the redundant 'Actions:' field, which restates capabilities already enumerated under 'Capabilities:'.

Dimension	Reasoning	Score
Specificity	The description lists many concrete actions — 'text extraction, table extraction, form filling, merge/split documents, create PDFs, add annotations, watermarks, page manipulation' — giving comprehensive coverage matching the score-5 anchor.	5 / 5
Completeness	It explicitly answers both 'what' (Capabilities/Actions) and 'when' ('Use when: extracting text/tables from PDFs, filling PDF forms, merging/splitting documents...') with concrete trigger phrases, matching the score-5 anchor.	5 / 5
Trigger Term Quality	Keywords include natural phrases users say ('merge PDF', 'split PDF', 'form fill', 'PDF form', 'OCR', 'watermark') plus synonyms, but it omits the '.pdf' file extension and 'PDFs' that the score-5 anchor calls out, and the keyword list is mechanically stuffed rather than woven naturally.	4 / 5
Distinctiveness Conflict Risk	The description carves a clear PDF-only niche with distinct triggers (PDF forms, merge/split, OCR, watermarks), making conflict with other skills minimal per the score-5 anchor.	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: samhvw8/dot-claude
Path: skills/document-skills/pdf/SKILL.md
Commit: 28c7616

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.