CtrlK
BlogDocsLog inGet started
Tessl Logo

yj-ocr-parser

文档解析技能,用于解析PDF文档和图片(jpg/png/jpeg)并将其转换为Markdown格式输出。支持标题层级、表格(HTML格式)、公式(LaTeX格式)、图片(链接形式)等复杂内容的解析。当用户提到"解析PDF"、"文档解析"、"PDF转Markdown"、"提取PDF内容"、"解析文档"、"文档内容提取"、"PDF内容识别"、"图片解析"、"图片转文字"、"识别图片内容"等场景时使用此技能。即使用户只是要求读取或查看PDF/图片文件内容,也应考虑使用此技能。

75

Quality

92%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

SecuritybySnyk

High

Do not use without reviewing

SKILL.md
Quality
Evals
Security

Quality

Content

85%

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

The body is actionable and well-structured with executable curl examples and a clear validation/error-handling workflow. Its main weakness is redundancy: supported formats and scenario triggers are restated across multiple sections and partly duplicate the description.

Suggestions

Consolidate the supported-format list (pdf/jpg/jpeg/png; not SVG/gif/bmp) into one section and reference it elsewhere instead of repeating it in 使用步骤, 执行流程, and 注意事项.

Trim the 适用场景 section, since its trigger terms largely duplicate the description's use-when clause; keep only scenarios not already covered.

Merge 使用步骤 and 执行流程 into a single numbered workflow to remove overlap between the two step lists.

DimensionReasoningScore

Conciseness

Mostly task-specific with no concept-overexplaining, but the supported-format list (pdf/jpg/jpeg/png) and the scenario list repeat across 使用步骤, 执行流程, 注意事项, and 适用场景 overlaps the description.

2 / 3

Actionability

Provides a complete executable curl command, a parameter table, the response JSON structure, per-code error handling, and two copy-paste examples (report.pdf, photo.jpg).

3 / 3

Workflow Clarity

执行流程 is a clearly numbered sequence with format validation (steps 1-2), a missing-variable feedback branch (step 3), and explicit error-code → user-message mapping (step 6: 200/400/429/500).

3 / 3

Progressive Disclosure

A single self-contained SKILL.md (~115 lines) with well-organized sections and no bundle files; per the simple-skills note, clear organization warrants top score with no external references needed.

3 / 3

Total

11

/

12

Passed

Description

100%

Based on the skill's description, can an agent find and select it at the right time? Clear, specific descriptions lead to better discovery.

A high-quality description: concise, third-person, with concrete capabilities, rich natural trigger terms, and explicit use-when guidance. It cleanly answers both what the skill does and when Claude should invoke it.

DimensionReasoningScore

Specificity

Names the domain (PDF/图片 → Markdown) and multiple concrete actions: heading hierarchy, tables as HTML, formulas as LaTeX, images as links. Third-person voice ("解析") throughout.

3 / 3

Completeness

Explicitly states what it does (parse PDF/图片 to Markdown) and when to use it ("当用户提到…等场景时使用此技能"), with an extra "even if just reading" clause, satisfying both what and when.

3 / 3

Trigger Term Quality

Lists many natural trigger phrases a user would say ("解析PDF"、"文档解析"、"PDF转Markdown"、"图片解析"、"图片转文字"、"识别图片内容" etc.), giving strong keyword coverage.

3 / 3

Distinctiveness Conflict Risk

A clear OCR/document-parsing niche with distinct triggers (PDF/图片 to Markdown), unlikely to conflict with other skills.

3 / 3

Total

12

/

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
UnicomAI/wanwu
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.