CtrlK
BlogDocsLog inGet started
Tessl Logo

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。

72

Quality

88%

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

SKILL.md
Quality
Evals
Security

Quality

Content

87%

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

A tight, single-purpose API doc with executable code and a complete parameter table. Its one gap is the absence of any output verification for a batch extraction that writes files to disk.

Suggestions

Add a brief verification step after extraction, e.g. listing the generated subdirectory or reporting the count of images saved, so the batch write has an explicit checkpoint (this would lift workflow_clarity to 3).

Clarify in the parameter table what happens if img_path does not exist (auto-created vs. required) to remove ambiguity around the side-effecting subdirectory creation.

Note any failure behavior (e.g. what is returned or raised if the .docx has no images or is corrupted) to make the single action's error path actionable.

DimensionReasoningScore

Conciseness

The body is lean — a one-line description, a parameter table, and one code example — with no padding explaining what Word or docx is; every token earns its place per anchor 3.

3 / 3

Actionability

Provides a fully executable Python import and call with a complete parameter table (types, required flags, descriptions) and a copy-paste usage example, matching the anchor 3 example.

3 / 3

Workflow Clarity

The single call is unambiguous, but this batch/disk-writing operation (extracts all images and creates a subdirectory) lacks any verification step, which per the rubric caps workflow clarity at 2.

2 / 3

Progressive Disclosure

Under 50 lines with no external references needed, organized into clear labeled sections; per the rubric's simple-skill note, well-organized sections alone earn a 3, and no bundle files are missing.

3 / 3

Total

11

/

12

Passed

Description

90%

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, uses natural third-person trigger language, and clearly states both capability and when to invoke it. Its only weakness is modest action breadth — only two verbs — which keeps specificity at the middle anchor.

DimensionReasoningScore

Specificity

Names the domain (Word document images) and two concrete actions — "提取所有图片" and "保存到指定目录" — but does not enumerate multiple distinct actions, so it sits at anchor 2 rather than 3.

2 / 3

Completeness

Explicitly answers both what ("提取所有图片并保存到指定目录") and when ("当用户提到...时使用"), matching the anchor 3 example with an explicit Use-when trigger.

3 / 3

Trigger Term Quality

Lists three natural phrasings a user would actually say ("Word 提取图片、docx 抠图、Word 取图"), including the colloquial "抠图", giving good coverage of common variations.

3 / 3

Distinctiveness Conflict Risk

Targets a narrow niche (image extraction from .docx) with distinctive triggers like "docx 抠图", making it unlikely to fire for unrelated skills.

3 / 3

Total

11

/

12

Passed

Validation

100%

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

Validation16 / 16 Passed

Validation for skill structure

No warnings or errors.

Repository
CoderWanFeng/python-office
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.