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), making it distinctive. However, it lacks a 'Use when...' clause and only describes a single action, limiting its effectiveness for skill selection among many options. Adding explicit trigger guidance and more capability details would significantly improve it.
Suggestions
Add a 'Use when...' clause with trigger terms like 'Use when the user wants to extract text from images, scan documents, read text from screenshots, or perform OCR on .png, .jpg, or .tiff files'.
Expand the capability list to include specific actions such as 'Extract text from images, recognize characters in scanned documents, convert image-based text to editable strings'.
Include common user-facing synonyms and file extensions like 'image to text', 'scan text', 'read text from photo', '.png', '.jpg', '.tiff'.
| 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. The combination of OCR-specific terminology makes it easily distinguishable. | 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 that are copy-paste ready, which is its strongest aspect. However, it includes unnecessary content like installation instructions, a language codes table, and a capabilities summary that inflate the token cost without adding much value for Claude. It also lacks any error handling guidance or validation steps for when OCR produces poor results.
Suggestions
Remove the Installation, Dependencies, Supported Image Formats, and Capabilities sections — Claude knows how to install packages and these waste tokens
Move the language codes table to a separate LANGUAGES.md reference file and link to it
Add a brief troubleshooting/validation section: e.g., 'If output is empty or garbled: try --preprocess, verify image is not corrupted, check language code matches content'
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | The content includes some unnecessary sections like the language table, supported image formats list, and dependencies/installation instructions that Claude already knows or can infer. The capabilities bullet list is also somewhat redundant given the usage examples. However, it's not egregiously verbose. | 2 / 3 |
Actionability | The skill provides fully concrete, copy-paste ready commands for all use cases including basic OCR, language selection, preprocessing, JSON output, and URL-based OCR. Parameters are clearly documented with defaults specified. | 3 / 3 |
Workflow Clarity | This is essentially a single-command tool, so complex workflows aren't needed. However, there's no guidance on what to do when OCR fails or produces poor results (e.g., try --preprocess, check image quality, try different languages). For a tool where accuracy varies, some validation/troubleshooting guidance would be valuable. | 2 / 3 |
Progressive Disclosure | The content is reasonably organized with clear sections, but the language table, installation instructions, and dependencies could be moved to a separate reference file. Everything is inline in a single document when some of it (especially the language codes table) would be better as a referenced resource. | 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
af8bd5f
- 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.