ocr

Extract text from images using Tesseract OCR

Quality

68%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

Low

Low-risk findings worth noting

Fix and improve this skill with Tessl

tessl review fix ./examples/skill/skills/ocr/SKILL.md

Quality

Content

82%Weight 40%Scale 1-5

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

The body is an efficient, highly actionable single-purpose skill with concrete executable commands and clear structure. The main improvements are removing minor duplication and adding a light output-quality verification hint.

Dimension	Reasoning	Score
Conciseness	The body is largely lean with executable commands and tables, but the opening line restates the description and the Capabilities bullets partially duplicate the Parameters section, leaving minor trim opportunities.	4 / 5
Actionability	Provides fully executable, copy-paste-ready commands ("python3 scripts/ocr.py image.png text.txt --lang eng+chi_sim") covering the common cases including language, preprocessing, JSON output, and URL input.	5 / 5
Workflow Clarity	The single action (run the OCR script with arguments) is unambiguous and well-illustrated; no explicit output verification is given, but the operation is non-destructive and single-purpose, so it sits just below the simple-skill top anchor.	4 / 5
Progressive Disclosure	Well-organized sections with real one-level-deep references to scripts/ocr.py and scripts/ocr_url.py (verified present); the languages table and formats list are inline rather than split out, a minor organization gap.	4 / 5
	Total	17 / 20 Passed

Description

53%Weight 40%Scale 1-5

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 names a concrete action with a clear niche, but it omits any explicit "Use when..." trigger guidance, which limits completeness and natural-term coverage. Adding a trigger clause would lift the two capped dimensions.

Suggestions

Append a trigger clause, e.g. "Use when the user needs to OCR an image, read text from a screenshot or scan, or convert an image to text."

Add common natural synonyms and file extensions (scan, read text, .png, .jpg, .tiff) to improve trigger-term coverage.

Optionally note the URL variant capability to broaden distinctiveness without inflating the description.

Dimension	Reasoning	Score
Specificity	Names the domain (images) and one concrete action ("Extract text from images using Tesseract OCR"), matching the anchor for naming a domain plus 1-2 concrete actions without being comprehensive.	3 / 5
Completeness	Provides a clear "what" (extract text from images via Tesseract) but no "Use when..." trigger clause; per guidelines a missing explicit trigger caps completeness at 3.	3 / 5
Trigger Term Quality	Includes relevant keywords ("text", "images", "OCR", "Tesseract") but misses common natural variations users say ("scan", "read text from image", image file extensions like .png/.jpg).	3 / 5
Distinctiveness Conflict Risk	"Extract text from images using Tesseract OCR" carves a clear OCR niche with distinct triggers and only minor overlap risk with related image skills.	4 / 5
	Total	13 / 20 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
Path: examples/skill/skills/ocr/SKILL.md
Commit: 9f7e561

Reviewed: ~16 hours 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.