pdf-toolkit

Structured `.pdf` operations: extract text/tables, merge pages from multiple PDFs, split a PDF by page ranges, fill PDF form fields, and generate fresh PDFs from JSON. Trigger when the user wants programmatic PDF work without natural-language rewriting — examples: pull tables from a report, combine three PDFs, extract pages 5-12, fill a tax form, or build a new PDF from data. Distinct from `nano-pdf`, which uses an LLM to rewrite a page from a sentence; this skill is deterministic byte-level work via pypdf, pdfplumber, and reportlab.

Quality

96%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

Low

Low-risk findings worth noting

Quality

Content

93%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.

A well-structured, executable skill body: lean prose, copy-paste commands, a clear decision table routing to four paths, and properly separated scripts and references. The only gap is an explicit feedback-loop checklist for the destructive/batch operations.

Suggestions

Add an explicit validate→fix→retry step for batch/destructive paths (e.g., after merge/split/form_fill, verify page count or run `--list-fields` before filling) to push workflow clarity to 5.

Consider a one-line 'Verify' callout at the end of Path B and Path C confirming the output PDF opens and has the expected page count.

Dimension	Reasoning	Score
Conciseness	Lean and token-efficient; it assumes Claude's competence and avoids explaining what PDFs or libraries are. Every section (decision table, paths, pitfalls, boundaries) earns its place.	5 / 5
Actionability	Copy-paste ready commands with `{baseDir}/scripts/*.py` paths, complete JSON manifest and data examples, and a complete inline reportlab snippet covering the common generate-from-scratch case.	5 / 5
Workflow Clarity	A decision table cleanly routes to four sequenced paths, and the form-fill path offers `--list-fields` validation plus a Common pitfalls table for error recovery. It falls just short of 5 because the batch/destructive operations lack an explicit validate→fix→retry loop checklist.	4 / 5
Progressive Disclosure	The body is a clear overview with a routing table; scripts are separate invoked-by-path files and references (reportlab.md, pypdf.md) are one level deep and clearly signaled — easy to navigate.	5 / 5
	Total	19 / 20 Passed

Description

100%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 model description: it concretely lists capabilities, gives explicit trigger guidance with natural example phrases, and draws a clear boundary against a sibling skill. No verbosity or over-claims.

Dimension	Reasoning	Score
Specificity	Lists five concrete, distinct operations (extract text/tables, merge pages, split by ranges, fill form fields, generate from JSON) — comprehensive coverage with no vague language.	5 / 5
Completeness	Explicitly states both what it does (five named operations) and when to use it via an explicit 'Trigger when...' clause with concrete example phrases.	5 / 5
Trigger Term Quality	Comprehensive natural terms including the `.pdf` extension, plus user-facing phrases like 'pull tables from a report', 'combine three PDFs', and 'fill a tax form'.	5 / 5
Distinctiveness Conflict Risk	Clearly carves a niche and explicitly distinguishes itself from the sibling `nano-pdf` skill, minimizing the chance of triggering for the wrong skill.	5 / 5
	Total	20 / 20 Passed

Validation

81%

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 — 13 / 16 Passed

Validation for skill structure

Criteria	Description	Result
metadata_version	'metadata.version' is missing	Warning
metadata_field	'metadata' should map string keys to string values	Warning
frontmatter_unknown_keys	Unknown frontmatter key(s) found; consider removing or moving to metadata	Warning

	Total	13 / 16 Passed

Repository: TokenRhythm/opensquilla
Path: src/opensquilla/skills/bundled/pdf-toolkit/SKILL.md
Commit: 94ac35e

Reviewed: 4 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.