ocr

Extract text from images using Tesseract OCR

Quality

48%

Does it follow best practices?

Impact

Pending

No eval scenarios have been run

Securityby

Advisory

Suggest reviewing before use

Optimize this skill with Tessl

npx tessl skill review --optimize ./examples/skill/skills/ocr/SKILL.md

Quality

Discovery

32%

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 functional but minimal, clearly identifying the core capability (OCR with Tesseract) but lacking explicit trigger guidance and comprehensive keyword coverage. The absence of a 'Use when...' clause significantly limits Claude's ability to know when to select this skill over alternatives.

Suggestions

Add a 'Use when...' clause with explicit triggers like 'Use when the user wants to extract text from images, screenshots, scanned documents, or mentions OCR, image-to-text, or reading text from pictures.'

Include common file format triggers users might mention: '.png', '.jpg', '.jpeg', '.tiff', 'screenshot', 'scanned document', 'photo of text'

Expand the action list to be more specific: 'Extract text from images, process scanned documents, convert screenshots to editable text using Tesseract OCR'

Dimension	Reasoning	Score
Specificity	Names the domain (images, OCR) and one action (extract text), but doesn't list multiple concrete actions like handling different image formats, batch processing, or output options.	2 / 3
Completeness	Describes what it does (extract text from images) but completely lacks a 'Use when...' clause or any explicit trigger guidance for when Claude should select this skill.	1 / 3
Trigger Term Quality	Includes 'images', 'Tesseract', and 'OCR' which are relevant keywords, but misses common variations users might say like 'scan', 'read text from picture', 'image to text', '.png', '.jpg', or 'screenshot'.	2 / 3
Distinctiveness Conflict Risk	Mentioning 'Tesseract OCR' specifically helps distinguish it from other text extraction tools, but 'extract text from images' could overlap with other image processing or document extraction skills.	2 / 3
	Total	7 / 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 skill provides clear, actionable commands for OCR text extraction with good coverage of common use cases. However, it includes some unnecessary reference material (language codes, format lists) that Claude already knows, and lacks validation/error handling guidance for when OCR produces poor results.

Suggestions

Remove or significantly trim the language codes table and supported formats list - Claude knows these

Add validation guidance: how to check OCR quality, handle low-confidence results, or retry with preprocessing if output is poor

Move installation instructions to a separate SETUP.md file since they're one-time setup, not operational guidance

Dimension	Reasoning	Score
Conciseness	The content is mostly efficient but includes some unnecessary sections like the full language table and supported formats list that Claude already knows. The capabilities section is somewhat redundant given the usage examples.	2 / 3
Actionability	Provides fully executable bash commands with clear examples covering basic usage, language options, preprocessing, and URL handling. All commands are copy-paste ready with concrete file paths and flags.	3 / 3
Workflow Clarity	This is a simple single-command tool, but lacks validation guidance. No mention of how to verify OCR success, handle errors, or check output quality. For a tool that can produce poor results on low-quality images, some validation guidance would help.	2 / 3
Progressive Disclosure	Content is reasonably organized with clear sections, but everything is inline in one file. The installation section and language table could be referenced externally. No links to additional resources or advanced documentation.	2 / 3
	Total	9 / 12 Passed

Validation

100%

Warnings & errors only

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: 50ef2f3

Reviewed: 5 days ago

Table of Contents

Discovery Implementation Validation

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.