CtrlK
BlogDocsLog inGet started
Tessl Logo

smart-ocr

Extract text from images and scanned documents using PaddleOCR - supports 100+ languages

52

Quality

57%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

SecuritybySnyk

Passed

No findings from the security scan

Fix and improve this skill with Tessl

tessl review fix ./.trae/openclaw-skills/smart-ocr/SKILL.md
SKILL.md
Quality
Evals
Security

Quality

Content

65%

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

The skill body is highly actionable with solid executable code, but it is a monolithic, somewhat verbose document that bundles reference material and multiple full examples inline without external references or validation checkpoints in its batch workflows.

Suggestions

Move the API/configuration reference and the three full worked examples into separate reference files (e.g., REFERENCE.md, EXAMPLES.md) and link to them from the overview to improve progressive disclosure.

Add explicit validation/feedback steps to batch and PDF workflows (e.g., check confidence thresholds, retry low-confidence regions, verify extracted text is non-empty before proceeding).

Trim redundant examples to one representative worked example in the main body to improve conciseness.

DimensionReasoningScore

Conciseness

The body is mostly efficient executable code rather than concept explanation, but it is padded with three full worked examples (business card, receipt, multilingual) and an exhaustive configuration-options listing that could be tightened; not a 1 because it avoids explaining basics Claude already knows.

2 / 3

Actionability

It provides concrete, executable, copy-paste-ready Python throughout, including initialization, result parsing, layout reconstruction, and PDF handling, with specific method calls and structure documentation.

3 / 3

Workflow Clarity

A simple usage sequence is present, but batch operations (batch_ocr) and PDF processing lack explicit validation checkpoints or error-recovery feedback loops, which per the guidelines caps workflow clarity at 2 for batch/risky operations.

2 / 3

Progressive Disclosure

No bundle files exist, so all API reference, configuration, and example content is inline in a single ~460-line file; it is well-organized into sections but content that would naturally be separate (API reference, examples) is not split out or signaled as references.

2 / 3

Total

9

/

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 clear and domain-specific but generic in execution: a single named action, no explicit usage triggers, and missing common keyword variations. It sits squarely at the middle anchor across all dimensions.

Suggestions

Add an explicit "Use when..." clause naming concrete triggers (e.g., OCR, scanned PDFs, screenshots, photos of text) to raise completeness and distinctiveness.

Broaden trigger terms to include "OCR", "PDF", "screenshots", and "photos" alongside "images and scanned documents".

Enumerate multiple concrete actions (e.g., extract text, recover layout, parse structured fields like receipts/cards) to improve specificity.

DimensionReasoningScore

Specificity

The description names a domain and one concrete action ("Extract text from images and scanned documents") but does not list multiple specific actions; it does not reach the level of enumerating several concrete capabilities like text/tables/forms/merge.

2 / 3

Completeness

It answers "what" (extract text from images/scanned documents via PaddleOCR) but provides no explicit "Use when..." trigger clause, which per the guidelines caps completeness at 2.

2 / 3

Trigger Term Quality

It includes some natural terms a user would say ("images", "scanned documents", "text") but omits common variations such as "OCR", "PDF", "screenshots", or "photos", and leans on the technical library name "PaddleOCR".

2 / 3

Distinctiveness Conflict Risk

OCR via PaddleOCR is a recognizable niche, but without explicit distinct trigger language it could still overlap with generic document or PDF skills, so it is not a clear 3.

2 / 3

Total

8

/

12

Passed

Validation

93%

Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.

Validation15 / 16 Passed

Validation for skill structure

CriteriaDescriptionResult

frontmatter_unknown_keys

Unknown frontmatter key(s) found; consider removing or moving to metadata

Warning

Total

15

/

16

Passed

Repository
huangruiteng/CS-Notes
Reviewed

Table of Contents

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.