CtrlK
BlogDocsLog inGet started
Tessl Logo

pdf

Use this skill whenever the user wants to do anything with PDF files. This includes reading or extracting text/tables from PDFs, combining or merging multiple PDFs into one, splitting PDFs apart, rotating pages, adding watermarks, creating new PDFs, filling PDF forms, encrypting/decrypting PDFs, extracting images, and OCR on scanned PDFs to make them searchable. If the user mentions a .pdf file or asks to produce one, use this skill.

68

Quality

82%

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

65%

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 and commands, but it repeats tool variants redundantly, omits validation for batch operations, and its progressive-disclosure links point to missing files while existing bundle scripts go unreferenced.

Suggestions

Add validation/verification checkpoints after batch or destructive operations — e.g., reopen and check page counts after split/merge, confirm encryption by reopening with the password — so workflows include explicit feedback loops.

Fix broken progressive disclosure: either create the referenced REFERENCE.md and FORMS.md, or repoint the form-filling guidance to the existing scripts/ files (fill_pdf_form_with_annotations.py, fill_fillable_fields.py, extract_form_field_info.py, etc.), which are currently orphaned.

Reduce redundancy by choosing one primary approach each for merge, split, and rotate (e.g., pypdf) and mentioning qpdf/pdftk only as brief alternatives, and consider folding the quick-reference table into the section headings to avoid duplicated content.

DimensionReasoningScore

Conciseness

The body is code-forward without explaining library concepts Claude already knows, but it repeats the same operations across pypdf, qpdf, and pdftk (merge/split/rotate) and duplicates that material in a quick-reference table, so it could be tightened rather than every token earning its place.

2 / 3

Actionability

Provides fully executable, copy-paste-ready Python (pypdf, pdfplumber, reportlab) and concrete CLI commands (pdftotext, qpdf, pdfimages) with specific flags, matching the 'fully executable code/commands' anchor.

3 / 3

Workflow Clarity

Each task's steps are clear and unambiguous, but batch/destructive operations (splitting all pages, merging, encrypting, watermarking every page) include no validation or verification checkpoints, capping the score at 2 per the rubric's batch-operation rule.

2 / 3

Progressive Disclosure

Sections are well organized and reference detail files one level deep, but the referenced REFERENCE.md and FORMS.md do not exist while the actual form-filling scripts in scripts/ are never referenced from the body, breaking navigation.

2 / 3

Total

9

/

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 strong description: it enumerates concrete PDF capabilities, gives natural trigger terms, and explicitly states both what it does and when Claude should use it, all within a clearly distinct PDF niche.

DimensionReasoningScore

Specificity

Lists many concrete actions — '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…OCR' — matching the 'lists multiple specific concrete actions' anchor.

3 / 3

Completeness

Explicitly states what it does (the operation list) and when to use it via '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,请使用此技能', satisfying both what and when with explicit triggers.

3 / 3

Trigger Term Quality

Covers natural user terms including 'PDF文件', '.pdf 文件', 'PDF表单', and '生成 PDF', matching the 'good coverage of natural terms' anchor (PDF files, PDFs, forms, .pdf).

3 / 3

Distinctiveness Conflict Risk

Scoped to a clear PDF-only niche with distinct triggers (.pdf files, specific PDF operations), making it unlikely to fire for unrelated skills.

3 / 3

Total

12

/

12

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.