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.

Quality

78%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

High

Do not use without reviewing

Fix and improve this skill with Tessl

tessl review fix ./configs/microservice/bff-service/configs/agent-skills/anthropics/pdf/SKILL.md

Quality

Content

57%

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

The content is highly actionable with strong executable examples but suffers from significant verbosity and repetition, and it relies on three referenced files (REFERENCE.md, FORMS.md, BEST_PRACTICES.md) that are absent from the bundle, breaking progressive disclosure.

Suggestions

Create or restore the missing REFERENCED files (REFERENCE.md, FORMS.md, BEST_PRACTICES.md) or remove the references and inline only the essential content; broken links fail progressive disclosure.

Consolidate the repeated drawString-vs-Paragraph warning and CIDFont 'no font file needed' points into a single section to cut length and redundancy.

For destructive or batch operations (e.g. form filling, merging), add explicit validation checkpoints so multi-step workflows have feedback loops.

Dimension	Reasoning	Score
Conciseness	The body is very long and repeats the same guidance multiple times — the drawString-vs-Paragraph warning appears in three places and the 'CIDFont needs no font file' point is restated throughout — so it is mostly efficient but could be tightened considerably.	2 / 3
Actionability	Provides numerous executable, copy-paste-ready examples across pypdf, pdfplumber, reportlab, pytesseract, and qpdf/pdftotext, with concrete commands and complete code rather than pseudocode.	3 / 3
Workflow Clarity	The body is structured as a reference catalog rather than sequenced multi-step workflows, and the one path that delegates to a process (form filling via FORMS.md) has no validation checkpoints described inline and references a missing file.	2 / 3
Progressive Disclosure	The body references REFERENCE.md, FORMS.md, and BEST_PRACTICES.md, but none of these files exist in the bundle, so the monolithic SKILL.md fails to offload detail and its navigation points are broken.	1 / 3
	Total	8 / 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.

The description is specific, complete, and trigger-rich, clearly stating both what the skill does and when to invoke it with natural user-facing keywords. It is a strong, low-conflict description.

Dimension	Reasoning	Score
Specificity	Lists many concrete actions including 'reading or extracting text/tables', 'merging multiple PDFs', 'splitting PDFs apart', 'rotating pages', 'adding watermarks', 'filling PDF forms', and 'OCR on scanned PDFs', matching the anchor for listing multiple specific concrete actions.	3 / 3
Completeness	Explicitly answers both what ('reading or extracting text/tables... OCR on scanned PDFs') and when ('Use this skill whenever the user wants to do anything with PDF files', 'If the user mentions a .pdf file or asks to produce one'), with an explicit trigger clause.	3 / 3
Trigger Term Quality	Covers natural terms users would say — 'PDF files', 'PDFs', '.pdf file', 'PDF forms', 'scanned PDFs' — giving good coverage rather than technical jargon.	3 / 3
Distinctiveness Conflict Risk	The PDF niche is clearly bounded with distinct triggers tied to .pdf files and PDF operations, making it unlikely to conflict with other skills.	3 / 3
	Total	12 / 12 Passed

Validation

87%

Warnings & errors only

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

Validation — 14 / 16 Passed

Validation for skill structure

Criteria	Description	Result
skill_md_line_count	SKILL.md is long (613 lines); consider splitting into references/ and linking	Warning
relative_links	Relative link issues: 1 missing	Warning

	Total	14 / 16 Passed

Repository: UnicomAI/wanwu
Path: configs/microservice/bff-service/configs/agent-skills/anthropics/pdf/SKILL.md
Commit: f618458

Reviewed: about 14 hours ago

Table of Contents

Discovery Implementation Validation

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.