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

76%

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 ./src/ii_agent/settings/skills/builtin/pdf/SKILL.md

Quality

Content

61%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 executable examples throughout, but the body inlines content that should live in referenced files, those referenced files (reference.md, forms.md) are missing, and the real scripts/ bundle is orphaned. Batch/destructive operations also lack validation checkpoints.

Suggestions

Create the referenced reference.md and forms.md (or fix the links to point at files that exist), and add a section that points into the scripts/ bundle for form filling so the orphaned scripts are discoverable.

Move the bulk of the library/CLI reference into reference.md and keep SKILL.md as a lean overview with a quick-start and a navigation table, trimming the redundant merge/split/rotate variants and the Quick Reference table.

Add validation/verification checkpoints to batch and destructive operations (e.g., verify merged page count after merge, confirm split files open, verify encryption by reopening with the password).

Dimension	Reasoning	Score
Conciseness	Prose is lean and avoids over-explaining concepts Claude already knows, but the body inlines a comprehensive ~290-line guide (merge/split/rotate shown three ways across pypdf, qpdf, and pdftk, plus a redundant Quick Reference table) that the description itself says belongs in reference.md, so it could be tightened.	3 / 5
Actionability	Fully executable, copy-paste-ready code and commands cover the common cases — merge, split, extract text/tables, create PDFs, OCR, watermark, extract images, and password protection.	5 / 5
Workflow Clarity	Each task shows a rough sequence via its code, but batch/destructive operations (merge, split, encrypt, OCR) have no validation or verification checkpoints, so workflow clarity is capped at 3 per the rubric.	3 / 5
Progressive Disclosure	References to reference.md and forms.md are clearly signaled but neither file exists in the bundle, and the actual scripts/ bundle (form-filling scripts) is never referenced from the body, so navigation is broken and bulk content is inlined.	2 / 5
	Total	13 / 20 Passed

Description

92%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 concretely states capabilities and gives an explicit 'When Claude needs to…' trigger. The only gap is the absence of the '.pdf' extension and a richer synonym set in the trigger terms.

Dimension	Reasoning	Score
Specificity	Lists multiple concrete actions — 'extracting text and tables, creating new PDFs, merging/splitting documents, and handling forms' — giving comprehensive coverage of the toolkit's capabilities.	5 / 5
Completeness	Explicitly answers both what ('extracting text and tables, creating new PDFs, merging/splitting documents, and handling forms') and when ('When Claude needs to fill in a PDF form or programmatically process, generate, or analyze PDF documents at scale').	5 / 5
Trigger Term Quality	Good natural keyword coverage ('PDF form', 'PDF documents', 'forms', 'new PDFs', 'extracting text and tables') but missing the '.pdf' file extension and a fuller synonym set, so it falls short of the comprehensive anchor.	4 / 5
Distinctiveness Conflict Risk	Clearly scoped to a PDF-manipulation niche with distinct triggers ('PDF form', 'PDF documents at scale'), giving minimal overlap risk with other skills.	5 / 5
	Total	19 / 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: Intelligent-Internet/ii-agent
Path: src/ii_agent/settings/skills/builtin/pdf/SKILL.md
Commit: 28563d6

Reviewed: 5 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.