CtrlK
BlogDocsLog inGet started
Tessl Logo

pdf

当用户需要对PDF文件进行任何操作时,请使用此技能。包括从 PDF 中读取或提取文本/表格、合并多个 PDF、拆分 PDF、旋转页面、添加水印、创建新PDF、填写PDF表单、加密/解密 PDF、提取图片,以及对扫描版 PDF 进行 OCR 使其可搜索。如果用户提到 .pdf 文件或要求生成 PDF,请使用此技能。

66

Quality

80%

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

71%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 code across all major PDF tasks and is reasonably concise, but it loses points for missing validation feedback loops on destructive/batch operations and for pointing to FORMS.md and REFERENCE.md files that are not present in the bundle.

Suggestions

Add explicit validation/verification steps to batch and destructive workflows (e.g., after merging or splitting, verify the output PDF opens and has the expected page count) to lift workflow clarity above 3.

Either provide the referenced FORMS.md and REFERENCE.md files or remove/fix the broken references, since the body repeatedly directs readers to files that do not exist in the bundle.

Trim redundant summary content (the '概述' paragraph and the '快速参考' table largely restate the per-section examples) to push conciseness toward 5.

DimensionReasoningScore

Conciseness

Mostly efficient code blocks with brief intros and no padding of basic PDF/library concepts; minor trimmable redundancy (the '概述' summary and '快速参考' table partly restate the section content), so it sits at anchor 4 rather than 5.

4 / 5

Actionability

Fully executable, copy-paste-ready code for pypdf, pdfplumber, reportlab, qpdf, pdftotext, and pytesseract covering the common cases, matching the anchor-5 example.

5 / 5

Workflow Clarity

Operations are sequenced but batch/destructive tasks (merge, split, encrypt, OCR) lack explicit validation checkpoints or validate→fix→retry feedback loops, which the rubric caps at 3.

3 / 5

Progressive Disclosure

The body clearly signals one-level-deep references to FORMS.md and REFERENCE.md and splits advanced content out, but neither referenced file actually exists in the bundle (only scripts/ is present), so navigation breaks and it cannot score above 3.

3 / 5

Total

15

/

20

Passed

Description

90%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 comprehensive and well-structured, clearly covering a wide range of PDF operations with strong natural trigger terms. The only weakness is the second-person voice ('请使用此技能') which the rubric penalizes on specificity.

DimensionReasoningScore

Specificity

Lists multiple concrete actions (读取/提取文本表格, 合并, 拆分, 旋转, 水印, 创建, 填表单, 加密/解密, 提取图片, OCR) for comprehensive coverage, but reduced from 5 to 4 because the second-person voice ('请使用此技能') triggers the rubric's -1 specificity penalty.

4 / 5

Completeness

Explicitly answers both 'what' (extensive action list) and 'when' ('当用户需要对PDF文件进行任何操作时...请使用此技能' and '如果用户提到 .pdf 文件或要求生成 PDF'), with concrete trigger phrases.

5 / 5

Trigger Term Quality

Comprehensive natural keyword coverage including PDF文件, PDF表单, 扫描版 PDF, and the .pdf file extension, matching the anchor-5 example.

5 / 5

Distinctiveness Conflict Risk

Clear PDF-specific niche with distinct triggers and minimal conflict risk with other skills.

5 / 5

Total

19

/

20

Passed

Validation

93%

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

Validation15 / 16 Passed

Validation for skill structure

CriteriaDescriptionResult

metadata_version

'metadata.version' is missing

Warning

Total

15

/

16

Passed

Repository
agentscope-ai/QwenPaw
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.