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.

1.31x

Quality

90%

Does it follow best practices?

Impact

95%

1.31x

Average score across 8 eval scenarios

Securityby

Passed

No findings from the security scan

Quality

Content

80%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 content is lean and highly actionable with broad executable coverage, but its batch and destructive workflows lack validation checkpoints and its progressive disclosure is undermined by references to missing files plus orphaned scripts that are never navigated to.

Suggestions

Add validation/verification checkpoints to batch and destructive workflows — e.g., after merge/split verify the output page count matches the inputs, and after encryption confirm the file reopens with the password before considering the task done.

Resolve the broken references: either create the referenced REFERENCE.md and FORMS.md, or replace those pointers with links to the actual bundle (e.g., the scripts/fill_pdf_form_with_annotations.py and related scripts in scripts/).

Surface the existing scripts/ bundle from the body — add a short section or table entry listing scripts like extract_form_field_info.py, fill_fillable_fields.py, and convert_pdf_to_images.py so the form-filling and image workflows point to real, usable files.

Dimension	Reasoning	Score
Conciseness	The body is code-forward with almost no concept padding — it assumes Claude knows what a PDF/library is and reserves prose for a genuinely non-obvious gotcha (the Unicode subscript/superscript black-box warning), so every section earns its tokens.	5 / 5
Actionability	Provides copy-paste-ready executable examples across pypdf, pdfplumber, reportlab, pdftotext, qpdf, pdftk, OCR, watermarking, and encryption, covering the common cases with complete code and commands rather than pseudocode.	5 / 5
Workflow Clarity	Batch operations (merging multiple PDFs, splitting into per-page files) and the encryption/overwrite workflows present a clear open→process→write sequence but include no validation or verification checkpoints, triggering the rubric's cap-at-3 rule for batch/destructive work without validation.	3 / 5
Progressive Disclosure	Section structure and a Quick Reference table are well organized and references are clearly signaled, but the body points to REFERENCE.md and FORMS.md that do not exist in the bundle while the eight real scripts/ files are never linked, leaving references broken and the existing bundle undiscoverable.	3 / 5
	Total	16 / 20 Passed

Description

100%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 exemplary: it enumerates comprehensive concrete capabilities, supplies natural trigger terms with the .pdf extension, and explicitly states both what the skill does and when to use it. No vague fluff or over-claims are present.

Dimension	Reasoning	Score
Specificity	Lists many concrete actions — 'reading or extracting text/tables', 'combining or merging', 'splitting PDFs apart', 'rotating pages', 'adding watermarks', 'filling PDF forms', 'encrypting/decrypting', 'extracting images', 'OCR on scanned PDFs' — giving comprehensive coverage that exceeds the score-5 anchor example.	5 / 5
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 concrete-trigger-phrases anchor exactly.	5 / 5
Trigger Term Quality	Covers natural terms and synonyms — 'PDF files', 'PDFs', 'PDF forms', and the '.pdf file' extension — matching the comprehensive-coverage anchor that calls for synonyms plus the file extension.	5 / 5
Distinctiveness Conflict Risk	Occupies a clear PDF-only niche with concrete PDF-specific triggers and the '.pdf' extension cue, giving minimal overlap with other skills as the score-5 anchor requires.	5 / 5
	Total	20 / 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: ZHangZHengEric/Sage
Path: app/skills/pdf/SKILL.md
Commit: df00b92

Reviewed: 4 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.