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.
92
82%
Does it follow best practices?
Impact
95%
1.31xAverage score across 8 eval scenarios
Passed
No known issues
Quality
Discovery
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.
This is a strong skill description that comprehensively lists specific PDF operations, includes natural trigger terms users would use, and explicitly states both what the skill does and when to use it. The only minor issue is the use of second person ('Use this skill') rather than third person voice, but the description is otherwise excellent in specificity, completeness, and distinctiveness.
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | The description lists numerous specific concrete actions: reading/extracting text and tables, combining/merging, splitting, rotating pages, adding watermarks, creating new PDFs, filling forms, encrypting/decrypting, extracting images, and OCR on scanned PDFs. | 3 / 3 |
Completeness | Clearly answers both 'what' (extensive list of PDF operations) and 'when' with explicit triggers: '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.' | 3 / 3 |
Trigger Term Quality | Includes strong natural keywords users would say: 'PDF files', '.pdf file', 'merging', 'splitting', 'rotating pages', 'watermarks', 'filling PDF forms', 'OCR', 'scanned PDFs', 'extracting text/tables', 'encrypting/decrypting'. Good coverage of common variations and use cases. | 3 / 3 |
Distinctiveness Conflict Risk | Clearly scoped to PDF files with distinct triggers (.pdf, PDF-specific operations like OCR, watermarks, form filling). Unlikely to conflict with other document-processing skills due to the explicit PDF focus. | 3 / 3 |
Total | 12 / 12 Passed |
Implementation
64%Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.
This is a solid, actionable PDF processing guide with excellent executable code examples covering a wide range of operations. Its main weaknesses are the lack of validation/verification steps in workflows (especially for multi-step operations like merging or watermarking) and the somewhat verbose inline content that could benefit from better progressive disclosure to referenced files. The ReportLab subscript/superscript warning is a good example of adding genuinely useful, non-obvious knowledge.
Suggestions
Add validation steps after key operations (e.g., verify output PDF opens correctly, check page count after merge, confirm text extraction is non-empty) to improve workflow clarity.
Move detailed library-specific code examples (reportlab creation, advanced table extraction) into REFERENCE.md and keep only the most common operations (read, merge, extract text/tables) inline to improve conciseness and progressive disclosure.
Add brief error handling guidance for common failure modes (e.g., encrypted PDFs failing to read, missing tesseract for OCR, corrupt PDF files).
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | The skill is fairly comprehensive but includes some redundancy (e.g., the Quick Start section overlaps with the pypdf section, and some code patterns are repetitive). The content is mostly efficient but could be tightened—for instance, the metadata extraction and some simpler examples don't add much beyond what Claude already knows about these libraries. | 2 / 3 |
Actionability | All code examples are fully executable, copy-paste ready, and cover a wide range of PDF operations with specific imports, complete code blocks, and concrete command-line examples. The quick reference table provides an excellent at-a-glance mapping of tasks to tools. | 3 / 3 |
Workflow Clarity | While individual operations are clearly presented, there are no validation checkpoints or error-handling steps. For operations like merging, watermarking, or encryption, there's no guidance on verifying the output PDF is valid or handling failures. The OCR workflow lacks a check for tesseract availability. | 2 / 3 |
Progressive Disclosure | The skill references REFERENCE.md and FORMS.md appropriately, and the structure with sections is reasonable. However, the main file is quite long with extensive inline code examples that could be split into separate reference files, and no bundle files were provided to verify the referenced files exist. | 2 / 3 |
Total | 9 / 12 Passed |
Validation
100%Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.
Validation — 11 / 11 Passed
Validation for skill structure
No warnings or errors.
- Repository
- douglasvought/wiggle-skills
- Commit
b27906e
- Reviewed
Table of Contents
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.