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.

2.48x

Quality

80%

Does it follow best practices?

Impact

97%

2.48x

Average score across 10 eval scenarios

Securityby

Passed

No findings from the security scan

The canonical home for this skill is pdf in anthropics/skills

Quality

Content

68%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 and reasonably concise, with executable examples across the main PDF tasks. Its weaknesses are missing validation for batch/destructive operations and a broken progressive-disclosure structure where the promised reference files are absent and the provided scripts bundle is orphaned.

Suggestions

Create the referenced reference.md and forms.md (or remove/redirect the references) so the signaled detail files actually exist and are navigable.

Link the existing scripts/ form-filling scripts (e.g., fill_fillable_fields.py, fill_pdf_form_with_annotations.py, check_fillable_fields.py) from the body or forms.md so the bundle is discoverable.

Add output validation checkpoints after batch/destructive operations (e.g., verify merged PDF page count equals sum of inputs, confirm encrypted file reopens with the password) to lift workflow clarity above the cap.

Dimension	Reasoning	Score
Conciseness	The body is code-forward and does not explain concepts Claude already knows, but the "Next Steps" section redundantly re-lists reference.md and forms.md already named in the Overview, which could be trimmed.	4 / 5
Actionability	Every section provides copy-paste-ready executable code or commands (pypdf, pdfplumber, reportlab, qpdf, pdftotext, OCR, watermark, encryption) covering the common cases.	5 / 5
Workflow Clarity	Recipes are individually clear but batch/destructive-ish operations (merging multiple PDFs, splitting into many files, encrypting) have no output validation checkpoints, triggering the workflow-clarity cap at 3.	3 / 5
Progressive Disclosure	The body signals reference.md and forms.md for advanced features and form filling, but neither file exists in the bundle, and the actual scripts/ bundle (form-filling scripts) is never referenced from the body, so the navigation is broken.	2 / 5
	Total	14 / 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.

The description is strong: it names concrete capabilities, gives an explicit third-person trigger clause, and scopes the skill cleanly to PDF work. The only gap is missing the ".pdf" extension and "PDFs" synonym for full trigger-term coverage.

Dimension	Reasoning	Score
Specificity	"extracting text and tables, creating new PDFs, merging/splitting documents, and handling forms" lists multiple concrete actions with comprehensive coverage, matching the score-5 anchor.	5 / 5
Completeness	It states a clear "what" (extract/create/merge-split/forms) and an explicit "when" trigger ("When Claude needs to fill in a PDF form or programmatically process, generate, or analyze PDF documents at scale"), satisfying both halves with concrete trigger phrases.	5 / 5
Trigger Term Quality	Natural terms like "PDF", "PDF form", and "PDF documents" give good coverage, but the description omits the ".pdf" file extension and the "PDFs" synonym that the score-5 anchor expects.	4 / 5
Distinctiveness Conflict Risk	The PDF-specific niche and "When Claude needs to...fill in a PDF form or...process PDF documents at scale" triggers carve a clear scope with minimal overlap with other skills.	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: Intelligent-Internet/ii-agent
Path: src/ii_agent/agents/skills/builtin/pdf/SKILL.md
Commit: 28563d6

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.