vector-text-fixer
Fix garbled text in PDF/SVG vector graphics for final editing in AI. Detect, replace and repair garbled text in vector graphic files while maintaining original formatting and layout.
62
Quality
51%
Does it follow best practices?
Impact
70%
5.00xAverage score across 3 eval scenarios
Passed
No known issues
Optimize this skill with Tessl
npx tessl skill review --optimize ./scientific-skills/Data analysis/vector-text-fixer/SKILL.mdQuality
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.
The description effectively communicates a specific, niche capability for repairing garbled text in vector graphics with good distinctiveness. However, it lacks an explicit 'Use when...' clause and could benefit from additional natural trigger terms that users might actually say when encountering this problem.
Suggestions
Add an explicit 'Use when...' clause, e.g., 'Use when users mention garbled, corrupted, or unreadable text in PDF or SVG files, or when preparing vector graphics for editing in Adobe Illustrator.'
Include additional natural trigger terms users might say: 'corrupted text', 'broken characters', 'font encoding issues', 'unreadable text', '.pdf', '.svg', 'Illustrator'.
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | Lists multiple specific concrete actions: 'Detect, replace and repair garbled text in vector graphic files while maintaining original formatting and layout.' Also mentions the purpose 'for final editing in AI.' | 3 / 3 |
Completeness | Clearly answers 'what' (detect, replace, repair garbled text in vector files) but lacks an explicit 'Use when...' clause. The 'when' is only implied through the problem description rather than explicitly stated. | 2 / 3 |
Trigger Term Quality | Includes relevant terms like 'PDF', 'SVG', 'vector graphics', 'garbled text', but missing common variations users might say like 'corrupted text', 'broken characters', 'font issues', 'encoding problems', or file extensions like '.pdf', '.svg'. | 2 / 3 |
Distinctiveness Conflict Risk | Very specific niche: 'garbled text in PDF/SVG vector graphics' is a distinct problem domain unlikely to conflict with general PDF processing or SVG editing skills. The focus on text repair in vector formats creates clear differentiation. | 3 / 3 |
Total | 10 / 12 Passed |
Implementation
35%Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.
This skill is overly verbose with significant boilerplate that doesn't help Claude perform the task. While it provides some concrete CLI and API examples, it reads more like product documentation than actionable instructions. The core repair workflow lacks validation steps and the extensive metadata sections (Risk Assessment, Security Checklist, Lifecycle Status) waste tokens on information Claude doesn't need.
Suggestions
Remove boilerplate sections (Risk Assessment, Security Checklist, Evaluation Criteria, Lifecycle Status, Prerequisites) that don't provide actionable guidance for the repair task
Add explicit validation workflow: how to verify repairs succeeded, handle partial failures, and iterate on blocks requiring manual review
Move detailed parameter tables, JSON schemas, and dependency lists to separate reference files, keeping only essential quick-start content in SKILL.md
Replace the Features/Supported Scenarios descriptive sections with a concise 'When to use' one-liner and jump straight to usage examples
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | Extremely verbose with extensive boilerplate sections (Risk Assessment, Security Checklist, Evaluation Criteria, Lifecycle Status) that add no actionable value. The Features section explains what the tool does rather than how to use it, and much content is redundant or obvious to Claude. | 1 / 3 |
Actionability | Provides concrete CLI commands and Python API examples that are copy-paste ready, but the code examples reference a hypothetical 'scripts/main.py' and 'VectorTextFixer' class without showing actual implementation. The examples show usage patterns but not executable repair logic. | 2 / 3 |
Workflow Clarity | The tool usage is clear for simple cases, but lacks validation checkpoints for the repair workflow. No guidance on verifying repairs worked correctly, handling partial failures, or iterating on problematic blocks. The 'requires manual review' output suggests a workflow that isn't documented. | 2 / 3 |
Progressive Disclosure | Content is reasonably organized with clear sections, but everything is in one monolithic file. The extensive parameter tables, JSON schemas, and dependency lists could be split into reference files. No links to external documentation for advanced topics. | 2 / 3 |
Total | 7 / 12 Passed |
Validation
90%Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.
Validation — 10 / 11 Passed
Validation for skill structure
| Criteria | Description | Result |
|---|---|---|
frontmatter_unknown_keys | Unknown frontmatter key(s) found; consider removing or moving to metadata | Warning |
Total | 10 / 11 Passed | |
- Repository
- aipoch/medical-research-skills
- Commit
ca9aaa4
- 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.