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。

77

Quality

96%

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

92%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.

The body is highly actionable with executable curl examples, a clearly sequenced and validated workflow, and good organization for a single-purpose skill. The main weakness is redundancy between the '使用步骤' and '执行流程' sections and the repeated curl block.

Suggestions

Merge '使用步骤' and '执行流程' into a single workflow section to eliminate heavy overlap and reduce tokens.

Show the curl command once and have the examples reference it (substituting only the file path/name) instead of restating the full command twice.

Consider trimming the duplicate format-support notes that recur across 适用场景, 使用步骤, 执行流程, and 注意事项 into a single authoritative statement.

DimensionReasoningScore

Conciseness

Mostly efficient and free of basic-concept padding, but '使用步骤' and '执行流程' overlap heavily and the curl command is restated in the examples section, adding avoidable tokens. Not a 3 because there is no genuine fluff and it assumes Claude's competence; not a 5 because the duplicated workflow/API blocks could be tightened.

4 / 5

Actionability

Provides fully executable copy-paste curl commands with the real endpoint, auth header, multipart fields, a complete JSON response shape, and two worked PDF/image examples covering the common cases.

5 / 5

Workflow Clarity

Clear sequenced workflow with explicit validation checkpoints (format/extension check, file-existence, token-presence check) and an error-feedback loop over response codes 200/400/429/500 with specific user guidance for each.

5 / 5

Progressive Disclosure

A single-purpose skill with no bundle files and well-organized sections (适用场景, 变量要求, API 调用, 执行流程, 注意事项, 示例); under the simple-skill guidance this warrants a top score.

5 / 5

Total

19

/

20

Passed

Description

100%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 is specific, trigger-rich, complete, and distinctive, answering both what the skill does and when to use it with concrete natural-language phrases and supported formats. Voice is appropriately third-person with no first/second-person drift.

DimensionReasoningScore

Specificity

Names the domain and multiple concrete actions — '标题层级、表格(HTML格式)、公式(LaTeX格式)、图片(链接形式)' — giving comprehensive, specific capability coverage rather than vague abstraction.

5 / 5

Completeness

Explicitly answers both what ('解析PDF文档和图片…转换为Markdown格式输出…支持标题层级、表格、公式、图片') and when ('当用户提到…场景时使用此技能'), with concrete trigger phrases.

5 / 5

Trigger Term Quality

Enumerates comprehensive natural user phrases including synonyms and file extensions — '解析PDF'、'PDF转Markdown'、'图片转文字'、'识别图片内容' — covering how users actually ask for this.

5 / 5

Distinctiveness Conflict Risk

Occupies a clear niche (PDF/image → Markdown OCR parsing) with distinct, specific triggers and minimal overlap risk with other skills.

5 / 5

Total

20

/

20

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.