pdf

Comprehensive PDF manipulation toolkit for extracting text and tables, creating new PDFs, merging/splitting documents, and handling forms. When Claude needs to fill in a PDF form or programmatically process, generate, or analyze PDF documents at scale.

2.48x

Quality

74%

Does it follow best practices?

Impact

97%

2.48x

Average score across 10 eval scenarios

Securityby

Low

Low-risk findings worth noting

Fix and improve this skill with Tessl

tessl review fix ./examples/skills/claude_skills/pdf/SKILL.md

The canonical home for this skill is pdf in anthropics/skills

Quality

Content

65%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.

Highly actionable with comprehensive executable examples, but it is over-long for the token budget and repeatedly references reference.md and forms.md that are not present in the bundle. Adding validation steps and ensuring the referenced files exist would lift the weakest dimensions.

Suggestions

Create the referenced reference.md and forms.md files (or remove/fix the citations) so navigation is not broken.

Add explicit validation/verification steps (e.g., check page counts after merge/split, verify the encrypted file opens) for batch and destructive operations to exceed the workflow-clarity cap of 3.

Trim boilerplate read/write snippets and basics Claude already knows (metadata printing, rotate) to improve token efficiency.

Dimension	Reasoning	Score
Conciseness	Mostly efficient with concrete code, but it explains basic operations Claude already knows (extract metadata, rotate pages, simple OCR loops) and repeats boilerplate read/write patterns across many near-duplicate snippets; could be tightened.	3 / 5
Actionability	Code and commands are executable and copy-paste ready across the common cases (merge, split, extract, create, OCR, watermark), with a quick-reference table summarizing best tools.	5 / 5
Workflow Clarity	Operations are grouped by task but there are no validation/verification checkpoints for destructive or batch operations (splitting, encrypting, watermarking), which the rubric caps at 3.	3 / 5
Progressive Disclosure	The body repeatedly points to reference.md and forms.md for advanced features, but those referenced files do not exist in the bundle (no references/ dir, no reference.md/forms.md), so the navigation is broken rather than well-signaled.	3 / 5
	Total	14 / 20 Passed

Description

83%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.

A strong, specific description that covers concrete PDF actions and an explicit use-when clause in third person. It would reach the top level with a tighter 'Use when...' trigger phrase and explicit synonyms/extensions like '.pdf'.

Suggestions

Add an explicit parallel 'Use when...' clause with natural user phrasing (e.g., 'Use when the user mentions PDFs, forms, or .pdf files').

Include file extensions and synonyms ('PDFs', '.pdf') to broaden trigger-term coverage.

Dimension	Reasoning	Score
Specificity	Names multiple concrete actions — 'extracting text and tables, creating new PDFs, merging/splitting documents, and handling forms' — matching the comprehensive-coverage anchor.	5 / 5
Completeness	Both 'what' (toolkit operations) and 'when' ('When Claude needs to fill in a PDF form or programmatically process, generate, or analyze PDF documents at scale') are present, but the 'when' trigger phrasing could be more explicit and parallel to the anchor's 'Use when...' form.	4 / 5
Trigger Term Quality	Good natural keywords (PDF, forms, documents) but is missing synonyms and file extensions like 'PDFs' and '.pdf' that anchor 5 expects.	4 / 5
Distinctiveness Conflict Risk	Scoped clearly to PDF-specific operations with distinct triggers, minimal overlap risk with other skills.	5 / 5
	Total	18 / 20 Passed

Validation

100%

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 — 16 / 16 Passed

Validation for skill structure

No warnings or errors.

Repository: modelscope/ms-agent
Path: examples/skills/claude_skills/pdf/SKILL.md
Commit: ea7da5c

Reviewed: 2 days 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.