ocr
Extract text from images using Tesseract OCR
61
52%
Does it follow best practices?
Impact
Pending
No eval scenarios have been run
Advisory
Suggest reviewing before use
Optimize this skill with Tessl
npx tessl skill review --optimize ./examples/skill/skills/ocr/SKILL.mdQuality
Discovery
40%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 concise and identifies a clear niche (Tesseract OCR on images), giving it good distinctiveness. However, it lacks a 'Use when...' clause, lists only a single action, and misses common user-facing trigger terms like 'scan', 'image to text', or file extensions.
Suggestions
Add a 'Use when...' clause with explicit triggers, e.g., 'Use when the user wants to extract or read text from images, screenshots, scanned documents, or mentions OCR.'
Include natural trigger term variations such as 'image to text', 'scan text', 'read text from picture', '.png', '.jpg', '.tiff'.
List additional concrete capabilities if applicable, such as 'supports multiple languages, batch processing, or outputting structured text'.
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | Names the domain (images, OCR) and one action (extract text), but only describes a single capability rather than listing multiple concrete actions like supported formats, batch processing, or language options. | 2 / 3 |
Completeness | Describes what the skill does (extract text from images using Tesseract OCR) but completely lacks a 'Use when...' clause or any explicit trigger guidance, which per the rubric caps completeness at 2, and since the 'what' is also minimal, a score of 1 is appropriate. | 1 / 3 |
Trigger Term Quality | Includes relevant keywords like 'images', 'Tesseract', and 'OCR' that users might say, but misses common variations like 'scan text', 'read text from image', 'image to text', '.png', '.jpg', or 'optical character recognition'. | 2 / 3 |
Distinctiveness Conflict Risk | The mention of 'Tesseract OCR' and 'images' creates a clear, distinct niche that is unlikely to conflict with other skills. OCR from images is a well-defined task. | 3 / 3 |
Total | 8 / 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.
The skill provides clear, actionable CLI commands for OCR text extraction with good coverage of options and languages. Its main weaknesses are verbosity in areas Claude doesn't need (language tables, format lists, basic capability descriptions) and the absence of any validation/troubleshooting guidance for when OCR produces poor results. Trimming known-information sections and adding a brief error-handling note would significantly improve it.
Suggestions
Remove or drastically shorten the 'Capabilities', 'Common Languages', 'Supported Image Formats', and 'Dependencies' sections — Claude already knows these or can infer them from the usage examples.
Add a brief troubleshooting/validation section: how to check if output quality is poor, when to use --preprocess, and what to do if tesseract is not installed or a language pack is missing.
Consider moving the language code table and installation instructions to a separate reference file to keep SKILL.md focused on usage.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | The content includes some unnecessary sections like the language table, supported image formats list, and capabilities bullet points that Claude already knows or could infer. The installation section and dependencies are borderline useful but add bulk. However, the core usage examples are reasonably tight. | 2 / 3 |
Actionability | The skill provides fully executable, copy-paste ready bash commands with clear parameter explanations. Multiple concrete examples cover different use cases (basic, multi-language, preprocessing, JSON output, URL-based). The commands are specific and immediately usable. | 3 / 3 |
Workflow Clarity | This is essentially a single-tool skill with clear command syntax, but it lacks any validation or error-handling guidance. There's no mention of what to do if OCR fails, how to verify output quality, or when preprocessing should be used vs. not. For a tool that can produce poor results on bad input, some validation guidance would be valuable. | 2 / 3 |
Progressive Disclosure | The content is organized with clear sections and headers, but it's somewhat monolithic — the language table and installation instructions could be in separate reference files. For a skill of this size (~80 lines of content), the inline approach is acceptable but not optimal. | 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
- trpc-group/trpc-agent-go
- Commit
0c1ec2b
- 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.