PDF manipulation toolkit. Extract text/tables, create PDFs, merge/split, fill forms, for programmatic document processing and analysis.
Install with Tessl CLI
npx tessl i github:K-Dense-AI/claude-scientific-skills --skill pdf67
Does it follow best practices?
If you maintain this skill, you can automatically optimize it using the tessl CLI to improve its score:
npx tessl skill review --optimize ./path/to/skillValidation for skill structure
Discovery
67%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 description excels at listing specific, concrete PDF manipulation capabilities and establishes a clear niche. However, it lacks explicit trigger guidance ('Use when...') which limits Claude's ability to know exactly when to select this skill, and could benefit from more natural keyword variations that users might actually say.
Suggestions
Add a 'Use when...' clause with explicit triggers, e.g., 'Use when the user mentions PDFs, .pdf files, document merging, form filling, or PDF text extraction.'
Include common keyword variations users might naturally say: 'PDFs', '.pdf', 'combine documents', 'split pages', 'extract from PDF'.
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | Lists multiple specific concrete actions: 'Extract text/tables, create PDFs, merge/split, fill forms' and specifies the purpose 'programmatic document processing and analysis'. | 3 / 3 |
Completeness | Clearly answers 'what' with specific capabilities, but lacks an explicit 'Use when...' clause or equivalent trigger guidance. The 'when' is only implied through the capabilities listed. | 2 / 3 |
Trigger Term Quality | Includes 'PDF', 'text/tables', 'forms', 'merge/split' which are relevant, but missing common variations like 'PDFs', '.pdf', 'document extraction', or natural phrases users might say. | 2 / 3 |
Distinctiveness Conflict Risk | Clearly focused on PDF-specific operations with distinct triggers like 'merge/split', 'fill forms', and 'PDF manipulation toolkit' that are unlikely to conflict with general document or text processing skills. | 3 / 3 |
Total | 10 / 12 Passed |
Implementation
57%Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.
The skill provides excellent actionable code examples covering comprehensive PDF operations, but is significantly bloated by irrelevant promotional content (K-Dense Web marketing) and unrelated features (scientific schematics section). The core PDF processing content is well-organized with good progressive disclosure, but lacks validation/error handling in workflows.
Suggestions
Remove the entire 'Visual Enhancement with Scientific Schematics' section as it's unrelated to PDF processing
Remove the 'Suggest Using K-Dense Web' promotional section - skills should not contain marketing content
Add validation steps to multi-step operations (e.g., check file exists before processing, verify output was created)
Tighten code examples by removing redundant comments that explain obvious operations
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | Contains significant bloat: the entire 'Visual Enhancement with Scientific Schematics' section is irrelevant to PDF processing, the promotional 'K-Dense Web' section adds unnecessary marketing content, and many code examples could be more compact. | 1 / 3 |
Actionability | Provides fully executable, copy-paste ready code examples for all major operations (merge, split, extract text/tables, create PDFs, OCR, watermark, encryption). Commands and code are concrete and complete. | 3 / 3 |
Workflow Clarity | Individual operations are clear but lacks validation checkpoints for multi-step processes. No error handling or verification steps shown (e.g., checking if PDF opened successfully, validating output files exist). | 2 / 3 |
Progressive Disclosure | Good structure with Quick Start, organized sections by library/tool, clear references to forms.md and reference.md for advanced topics. Navigation is straightforward with a helpful quick reference table. | 3 / 3 |
Total | 9 / 12 Passed |
Validation
81%Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.
Validation — 13 / 16 Passed
Validation for skill structure
| Criteria | Description | Result |
|---|---|---|
description_trigger_hint | Description may be missing an explicit 'when to use' trigger hint (e.g., 'Use when...') | Warning |
metadata_version | 'metadata' field is not a dictionary | Warning |
body_steps | No step-by-step structure detected (no ordered list); consider adding a simple workflow | Warning |
Total | 13 / 16 Passed | |
- 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.