ocr

Extract text from images using Tesseract OCR

Quality

52%

Does it follow best practices?

Impact

—

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

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 identifies a clear niche (Tesseract OCR for image text extraction) which makes it distinctive, but it is too terse. It lacks a 'Use when...' clause and misses common user trigger terms like 'scan', 'image to text', or file extensions, reducing its effectiveness for skill selection among many options.

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 user-facing trigger terms and file extensions such as 'image to text', 'scan text', 'read text from photo', '.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 but completely lacks a 'Use when...' clause or any explicit trigger guidance, which per the rubric caps completeness at 2, and the 'what' itself is also minimal, warranting a score of 1.	1 / 3
Trigger Term Quality	Includes relevant keywords like 'images', 'Tesseract', and 'OCR', but misses common user variations such as 'scan text', 'read text from image', 'image to text', '.png', '.jpg', or 'screenshot'.	2 / 3
Distinctiveness Conflict Risk	The mention of 'Tesseract OCR' creates a clear niche that is unlikely to conflict with other skills; OCR via Tesseract is a distinct and specific capability.	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.

This skill provides clear, actionable CLI commands for OCR text extraction with good coverage of options (languages, preprocessing, formats, URLs). Its main weaknesses are the lack of validation/error-handling workflows (e.g., what to do when OCR quality is poor) and some redundant sections that could be trimmed. The content is well-structured but could benefit from a feedback loop for accuracy improvement.

Suggestions

Add a validation/troubleshooting workflow: e.g., 'If output is garbled: 1. Try --preprocess, 2. Check image resolution (minimum 300 DPI recommended), 3. Verify correct --lang flag'

Remove the 'Capabilities' and 'Supported Image Formats' sections — the capabilities are evident from the usage examples, and formats are already implied

Add a brief error-handling note for common failures (Tesseract not installed, unsupported image, empty output)

Dimension	Reasoning	Score
Conciseness	The skill includes some unnecessary sections like 'Capabilities' (which just restates what the commands do), the 'Supported Image Formats' section (already mentioned in Capabilities), and the 'Dependencies' section which is somewhat redundant given the Installation section. The language table is useful but could be trimmed. Overall mostly efficient but has padding.	2 / 3
Actionability	Provides fully executable, copy-paste ready commands for all use cases including basic OCR, multi-language, preprocessing, JSON output, and URL-based OCR. Installation commands are concrete and platform-specific. Parameters are clearly documented.	3 / 3
Workflow Clarity	The skill presents individual commands clearly but lacks any workflow sequencing or validation steps. For OCR tasks where accuracy matters, there's no guidance on verifying output quality, handling failures (e.g., Tesseract not installed, poor image quality), or a feedback loop like 'if accuracy is low, try --preprocess and re-run.'	2 / 3
Progressive Disclosure	The content is reasonably organized with clear sections, but everything is inline in one file. The language table and installation instructions could be referenced externally. However, with no bundle files provided, the lack of external references is somewhat justified. The structure is flat but navigable.	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: b22744d

Reviewed: 3 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.