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.

1.31x

Quality

78%

Does it follow best practices?

Impact

95%

1.31x

Average score across 8 eval scenarios

Securityby

High

Do not use without reviewing

Fix and improve this skill with Tessl

tessl review fix ./resources/example-skills/pdf/SKILL.md

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

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 body is highly actionable with complete executable examples and clean organization, but it loses points for missing validation steps on batch/destructive operations and, more severely, for referencing REFERENCE.md and FORMS.md that are absent from the bundle, which undermines its progressive-disclosure structure.

Suggestions

Add verification steps to batch/destructive operations — e.g., after splitting, assert each output PDF opens and has one page; after encrypting, confirm PdfReader reports is_encrypted before trusting the result.

Either include the referenced FORMS.md and REFERENCE.md files in the bundle or inline the essential content they would contain, so the 'see X.md' navigation pointers resolve to real files.

Trim redundant inline comments in code blocks (e.g. '# Read a PDF', '# Extract text') to tighten token efficiency, since the surrounding headers already convey the intent.

Dimension	Reasoning	Score
Conciseness	Mostly efficient — each section leads with executable code rather than explaining PDF concepts — but it pads several blocks with redundant comments ('# Read a PDF', '# Extract text') and repeats similar library boilerplate, so a few tokens could be trimmed.	2 / 3
Actionability	Every task is backed by fully executable, copy-paste-ready Python or shell commands with concrete library calls (pypdf, pdfplumber, reportlab, qpdf, pdftotext), matching the anchor for specific examples that are copy-paste ready.	3 / 3
Workflow Clarity	Operations are organized by task with a useful Quick Reference table, but destructive/batch operations like splitting all pages, OCR, and encryption have no validation or verification steps, which caps workflow clarity at 2 per the rubric's feedback-loop guidance.	2 / 3
Progressive Disclosure	The body repeatedly points to REFERENCE.md and FORMS.md for advanced features, but those files are not present in the bundle — the navigation signals to files that do not exist, leaving the structure effectively broken at one level deep.	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 strong across the board: it enumerates concrete PDF capabilities, provides natural trigger terms, explicitly states both what it does and when to use it, and is clearly scoped to PDFs with little conflict risk. No meaningful weakness; suggestions are not warranted.

Dimension	Reasoning	Score
Specificity	Lists many concrete actions — 'reading or extracting text/tables', 'combining or merging', 'splitting PDFs apart', 'rotating pages', 'adding watermarks', 'filling PDF forms', 'encrypting/decrypting', 'extracting images', and 'OCR' — matching the anchor that lists multiple specific concrete actions.	3 / 3
Completeness	Explicitly answers both what it does (the enumerated operations) and when to use it via 'Use this skill whenever the user wants to do anything with PDF files' and 'If the user mentions a .pdf file or asks to produce one, use this skill', matching the top anchor with explicit triggers.	3 / 3
Trigger Term Quality	Covers natural terms a user would say — 'PDF files', 'PDFs', '.pdf file', 'PDF forms' — plus task verbs like merge/split/OCR, giving good coverage of common variations; not merely technical jargon.	3 / 3
Distinctiveness Conflict Risk	Scoped tightly to PDF files with PDF-specific triggers, so it is unlikely to fire for non-PDF document skills; it has a clear niche with distinct triggers.	3 / 3
	Total	12 / 12 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: eigent-ai/eigent
Path: resources/example-skills/pdf/SKILL.md
Commit: 9d0a169

Reviewed: about 9 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.