Name: ocr-web-service
Rating: 55.2 (1 reviews)
Author: membranedev

Blog Docs Log in Get started

ocr-web-service

OCR Web Service integration. Manage Documents. Use when the user wants to interact with OCR Web Service data.

Quality

62%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

Passed

No findings from the security scan

Fix and improve this skill with Tessl

tessl review fix ./skills/ocr-web-service/SKILL.md

Quality

Content

67%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 highly actionable, with executable Membrane CLI commands and a clear connect-to-run workflow that includes state-based validation checkpoints. Its main weakness is conciseness — an unnecessary intro explaining OCR and a duplicated action-list command — plus slightly inconsistent step numbering.

Suggestions

Cut the introductory paragraph explaining what OCR is and who uses it; Claude already knows this, so start directly with how to use the integration.

Reconcile the step numbering into a single coherent sequence (1. Install, 2. Authenticate, 3. Connect, 4. Wait for READY, 5. Discover actions, 6. Run) instead of mixing 'Step 2' and '1b' references.

Add one concrete OCR action example (a real action run with sample --input) so users see the end-to-end happy path without placeholders.

Dimension	Reasoning	Score
Conciseness	The body is mostly efficient with executable CLI commands, but the opening paragraph explains what OCR is and who uses it ('OCR Web Service is a tool that converts images of text into machine-readable text. Developers and businesses use it...') — a concept Claude already knows — and the 'Popular actions' section repeats the action-list command, fitting 'mostly efficient but includes some unnecessary explanation or could be tightened'.	3 / 5
Actionability	Concrete, copy-paste-ready CLI commands cover the common cases (login, connection ensure/get, action list/run, request with a flag table), but there is no concrete OCR action example and CONNECTION_ID remains a placeholder, fitting 'mostly executable guidance; concrete code or commands with minor gaps'.	4 / 5
Workflow Clarity	The connect-to-run sequence is clear with state-based checkpoints (READY/BUILDING/CLIENT_ACTION_REQUIRED/CONFIGURATION_ERROR) and polling feedback, but the numbering is inconsistent (references 'Step 2' and '1b' without a coherent numbered master sequence), fitting 'clear sequence with most checkpoints present; minor validation gaps'.	4 / 5
Progressive Disclosure	It is a single, well-organized file with clear section headers and only a one-level external docs link (no nested references, no bundle files present), but at ~140 lines it is longer than the under-50-line simple-skill case that earns a 5, fitting 'good structure; most content appropriately placed; minor organization gaps'.	4 / 5
	Total	15 / 20 Passed

Description

57%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 answers both 'what' and 'when' and names a distinct niche, but its action vocabulary is generic ('Manage Documents') and its trigger terms miss the natural synonyms (OCR, text extraction, scanned images) users would actually say. Strengthening the action list and trigger phrases would move it from adequate to strong.

Suggestions

Replace the generic 'Manage Documents' with concrete OCR actions, e.g. 'Extract text from scanned documents, PDFs, and images; run OCR via the OCR Web Service API.'

Expand the 'Use when...' clause with natural trigger phrases users say: 'Use when the user wants to OCR an image, extract text from scanned documents/PDFs, or convert images to text.'

Keep third person and add file/extension cues (e.g. .png, .jpg, scanned PDF) to improve distinctiveness against generic document skills.

Dimension	Reasoning	Score
Specificity	The description names the domain ('OCR Web Service') but only offers one minimal, generic action ('Manage Documents'), fitting the 'names the domain but actions are minimal or generic' anchor rather than the 1-2 concrete actions of a 3.	2 / 5
Completeness	It states a 'what' ('OCR Web Service integration. Manage Documents.') and a 'when' ('Use when the user wants to interact with OCR Web Service data.'), but the 'when' trigger is generic rather than concrete, fitting 'both what and when; when could be more explicit or specific' rather than the fully concrete 5.	4 / 5
Trigger Term Quality	Relevant keywords appear ('OCR Web Service', 'Documents', 'interact with OCR Web Service data') but common natural synonyms users would say — 'OCR', 'extract text', 'image to text', 'scanned documents' — are missing, matching the 'some relevant keywords but missing common variations' anchor.	3 / 5
Distinctiveness Conflict Risk	The explicit 'OCR Web Service integration' framing gives a clear niche with minimal conflict risk, though the generic 'Manage Documents' wording leaves minor overlap with other document/OCR skills, matching 'mostly distinct; minor overlap risk'.	4 / 5
	Total	13 / 20 Passed

Validation

93%

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 — 15 / 16 Passed

Validation for skill structure

Criteria	Description	Result
frontmatter_unknown_keys	Unknown frontmatter key(s) found; consider removing or moving to metadata	Warning

	Total	15 / 16 Passed

Repository: membranedev/application-skills
Path: skills/ocr-web-service/SKILL.md
Commit: f484c82

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.