visa-doc-translate

将签证申请文件（图像）翻译成英文，并创建包含原文和译文的双语 PDF。

Quality

46%

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 ./skills/visa-doc-translate/SKILL.md

Quality

Content

57%

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

The body is well-structured with a clear six-step workflow, concrete commands, and tidy sectioning. Its main weaknesses are redundant guideline/example restatements, a described-but-not-provided PDF-generation script, and missing validation checkpoints for the OCR-to-PDF pipeline.

Suggestions

Add an explicit validation checkpoint, e.g. verify OCR produced non-empty text before translating, and confirm the PDF file exists on disk before reporting completion.

Provide an executable PDF-generation script (or a complete code skeleton using PIL/reportlab) rather than describing the layout in prose, to lift actionability.

Trim the redundant '重要指南' and '输出示例' sections that restate the numbered workflow and the auto-confirm instruction.

Dimension	Reasoning	Score
Conciseness	The body is mostly efficient with concrete commands and ordered steps, but the '重要指南' and '输出示例' sections restate earlier instructions (e.g. '不要在每个步骤都请求用户确认', re-listing the OCR/translate/PDF steps), adding redundancy that keeps it from the lean score-3 anchor.	2 / 3
Actionability	It gives concrete commands (sips, pip install) and named libraries (PIL, reportlab, EasyOCR) but the PDF-generation step describes the desired script rather than providing executable code, and the OCR section gives imports without a complete extraction routine — incomplete per the score-2 anchor.	2 / 3
Workflow Clarity	The six-step sequence is clearly ordered, but for an image-processing/generation pipeline there is no explicit validation that OCR succeeded or that the PDF was produced before reporting; per the feedback-loops note this caps workflow clarity at 2.	2 / 3
Progressive Disclosure	It is a single self-contained ~110-line SKILL.md with well-organized sections and no external bundle files; per the simple-skills note this scores 3 without needing separate references.	3 / 3
	Total	9 / 12 Passed

Description

35%

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 clearly states what the skill does — translate visa-application document images to English and produce a bilingual PDF — in concise third person. It is missing any explicit 'Use when' trigger guidance and natural user-facing keywords, which cap both completeness and trigger-term quality.

Suggestions

Add an explicit trigger clause, e.g. 'Use when translating visa application documents (images) into English for submissions to countries requiring certified translations.'

Include natural trigger terms users would say such as 'visa translation', 'translate document for visa', or 'bilingual PDF'.

Optionally enumerate a couple more concrete actions (e.g. OCR extraction, image rotation/HEIC conversion) to lift specificity toward a 3.

Dimension	Reasoning	Score
Specificity	It names the domain and two concrete actions — '翻译成英文' (translate into English) and '创建包含原文和译文的双语 PDF' (create a bilingual PDF) — but stops short of listing multiple specific actions like the score-3 anchor.	2 / 3
Completeness	It answers 'what' (translate visa-application images to English and produce a bilingual PDF) but has no 'Use when...' clause or equivalent explicit trigger, which per the guidelines caps completeness at 2.	2 / 3
Trigger Term Quality	The description is a capability statement with no natural trigger phrases a user would say (e.g. 'translate visa documents', 'bilingual PDF for visa application'), matching the score-1 anchor of no natural keywords.	1 / 3
Distinctiveness Conflict Risk	The visa-application-document niche is reasonably specific and unlikely to conflict broadly, but without explicit trigger terms it could overlap with general document-translation skills, matching the 'somewhat specific but could overlap' anchor.	2 / 3
	Total	7 / 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: xu-xiang/everything-claude-code-zh
Path: skills/visa-doc-translate/SKILL.md
Commit: dfbf946

Reviewed: 13 minutes 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.