ocr

Extract text from images using Tesseract OCR

Quality

—

Does it follow best practices?

Impact

—

No eval scenarios have been run

Securityby

Advisory

Suggest reviewing before use

Quality

Content

85%

Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.

The body is highly actionable and well-structured: executable commands reference real scripts, the single-task workflow is unambiguous, and references stay one level deep. The main weakness is mild redundancy between the language/format lists that could be consolidated.

Dimension	Reasoning	Score
Conciseness	It is lean and free of explanations of concepts Claude already knows, but the Common Languages table and the repeated image-format lists (Capabilities, Supported Image Formats, and the --lang examples) introduce redundancy that could be tightened.	2 / 3
Actionability	All examples are fully executable, copy-paste ready commands referencing real scripts (scripts/ocr.py, scripts/ocr_url.py) with specific flags, matching the "fully executable; copy-paste ready" anchor.	3 / 3
Workflow Clarity	This is a simple single-task skill with unambiguous invocation for both local and URL flows; per the scoring notes a single-purpose skill with a clear, unambiguous action can score 3, and no destructive/batch validation checkpoint is required here.	3 / 3
Progressive Disclosure	The body is a clear overview that signals one-level-deep references to real bundle files (scripts/ocr.py, scripts/ocr_url.py) directly in code blocks, with no nested references and well-organized sections, matching the "clear overview with well-signaled one-level-deep references" anchor.	3 / 3
	Total	11 / 12 Passed

Description

50%

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 concrete and technically precise but minimal: it states one action and names the engine, with no trigger guidance and limited keyword coverage. Adding a "Use when..." clause and broader natural terms would raise completeness and trigger quality.

Suggestions

Add a "Use when..." clause, e.g. "Use when the user wants to OCR an image, scan, or screenshot, or extract text from an image file."

Broaden trigger terms to include natural phrasings like "scan", "screenshot", "read text from image", and common formats (.png, .jpg).

Mention multiple concrete actions (e.g., plain-text and JSON output, preprocessing) to improve specificity.

Dimension	Reasoning	Score
Specificity	It names a concrete action ("Extract text from images") and the specific engine ("Tesseract OCR"), but lists only a single action rather than multiple specific actions, so it does not reach the comprehensive anchor of 3.	2 / 3
Completeness	It clearly states what the skill does but provides no "Use when..." or equivalent trigger guidance for when Claude should invoke it, which per the guidelines caps completeness at 2.	2 / 3
Trigger Term Quality	"images" and "Tesseract OCR" are natural terms a user might say, but common variations like "scan", "screenshot", "image text", "read text from image", or format names (".png") are missing, matching the "some relevant keywords" anchor.	2 / 3
Distinctiveness Conflict Risk	The OCR/Tesseract niche is fairly distinct, but the terse description lacks explicit triggering language that sharpens it, so it could still overlap with general image-handling skills.	2 / 3
	Total	8 / 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 — 16 / 16 Passed

Validation for skill structure

No warnings or errors.

Repository: trpc-group/trpc-agent-go
Commit: 737835b

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.