docx4imgs

从 Word 文档中提取所有图片并保存到指定目录。当用户提到 Word 提取图片、docx 抠图、Word 取图时使用。

Quality

81%

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

Quality

Content

80%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.

A compact, actionable skill body with a clean parameter table and executable example. Its main weakness is the absence of any validation/verification step for a batch extraction operation, which caps workflow clarity.

Suggestions

Add a brief verification step after extraction, e.g. check that the generated subdirectory is non-empty or report the count of images saved, so the batch operation has an explicit checkpoint.

Remove the redundant '使用示例' section (or differentiate it with a second variant) since it duplicates the '调用方式' code block.

Note basic failure handling, such as what happens when word_path is missing or the document contains no images.

Dimension	Reasoning	Score
Conciseness	The body is lean with no concept over-explanation, but the '调用方式' and '使用示例' sections repeat nearly identical code and the blockquote restates the description. Not a 5 because of this redundant example; not a 3 because most content earns its place.	4 / 5
Actionability	Provides a complete, copy-paste ready import-and-call example plus a full parameter table with types, required flags, and defaults. Not a 4 because the guidance is fully executable with no missing key details for the single common case.	5 / 5
Workflow Clarity	The single action (call docx4imgs with two paths) is unambiguous, but extracting all images is a batch operation with no validation or verification step (e.g., confirming images were saved). The rubric's batch-operation cap at 3 applies and takes precedence over the simple-skill exception; not a 2 because the call sequence is clear and coherent.	3 / 5
Progressive Disclosure	The body is under 50 lines, has no external references, and is organized into clearly labeled sections (功能描述, 调用方式, 参数说明, 返回值, 使用示例, 原始函数). Per the simple-skill note this merits a 5; not a 4 because sectioning is clean and complete.	5 / 5
	Total	17 / 20 Passed

Description

82%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 clearly communicates a single purpose and provides explicit, natural-language trigger phrases in third person. It is concise and well-targeted, with only minor room to add a file extension for fuller trigger coverage.

Dimension	Reasoning	Score
Specificity	Names the domain (Word documents) and two concrete actions (extract all images, save to a specified directory), but offers no broader coverage of related operations. Not a 4 because it does not list several specific actions; not a 2 because it does name the domain plus concrete actions rather than minimal/generic ones.	3 / 5
Completeness	Explicitly states what it does ('提取所有图片并保存到指定目录') and when to use it ('当用户提到…时使用') with concrete trigger phrases. Not a 4 because the 'when' is explicit and specific rather than merely present-but-could-be-more-explicit.	5 / 5
Trigger Term Quality	Includes natural user phrases ('Word 提取图片', 'docx 抠图', 'Word 取图') with synonym variation. Not a 5 because it lacks an explicit file extension like .docx and a few common phrasings; not a 3 because coverage goes beyond a single relevant keyword to multiple natural synonyms.	4 / 5
Distinctiveness Conflict Risk	Targets a clear niche (image extraction from Word) with distinct, image-specific triggers (抠图/取图/提取图片), minimizing overlap with generic docx skills. Not a 4 because the triggers are tightly scoped to this single purpose with minimal conflict risk.	5 / 5
	Total	17 / 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: CoderWanFeng/python-office
Path: skills/word/docx4imgs/SKILL.md
Commit: dd6fe56

Reviewed: 1 day 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.