gemini-document-processing

Guide for implementing Google Gemini API document processing - analyze PDFs with native vision to extract text, images, diagrams, charts, and tables. Use when processing documents, extracting structured data, summarizing PDFs, answering questions about document content, or converting documents to structured formats. (project)

Quality

80%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

Passed

No findings from the security scan

Quality

Content

72%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.

The body is highly actionable and well-structured with proper progressive disclosure to real bundle files. Its weaknesses are notable redundancy across sections and the absence of validation/feedback loops for batch document processing, which cap workflow clarity.

Suggestions

Consolidate redundant sections: merge the 'Common Use Cases' commands with the 'Script Reference' block, fold the decision tree into 'Performance Tips', and show the API-key setup once with a priority list instead of three near-identical code blocks.

Add an explicit validation/feedback step for batch and structured-output workflows, e.g. after extraction validate the JSON against the Pydantic schema and retry or report on failure.

Standardize the script path (it appears as both '.claude/skills/gemini-document-processing/scripts/process-document.py' and 'scripts/process-document.py') to avoid confusion.

Dimension	Reasoning	Score
Conciseness	Mostly efficient and free of concept over-explanation, but several sections repeat each other (use-case examples restate the script reference; the decision tree restates the performance tips; API-key setup is shown in three near-identical forms), which is more than minor padding.	3 / 5
Actionability	Fully executable, copy-paste-ready guidance throughout: pip install, script invocations with flags, complete Python SDK and Pydantic structured-output examples, and a troubleshooting script — covering the common cases.	5 / 5
Workflow Clarity	A useful decision tree gives sequence guidance, but there are no explicit validation checkpoints or feedback loops (e.g. verify extracted JSON), and batch operations are mentioned — the batch/destructive cap holds this at 3.	3 / 5
Progressive Disclosure	SKILL.md is a clear overview with a well-signaled References section pointing one level deep to three real reference files (report, quick-reference, code-examples) plus scripts, with content appropriately split and easy to navigate.	5 / 5
	Total	16 / 20 Passed

Description

88%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.

The description is strong: it states concrete capabilities and gives explicit 'Use when...' triggers covering the main use cases. It is held back only by missing a few natural synonyms and file extensions, and minor overlap risk with generic PDF/document skills.

Dimension	Reasoning	Score
Specificity	Lists multiple concrete actions ('extract text, images, diagrams, charts, and tables') plus processing, structured extraction, summarization, Q&A, and format conversion — comprehensive coverage matching the score-5 anchor.	5 / 5
Completeness	Explicitly answers both what ('analyze PDFs with native vision to extract...') and when ('Use when processing documents, extracting structured data, summarizing PDFs...') with concrete trigger phrases.	5 / 5
Trigger Term Quality	Good natural triggers ('processing documents, extracting structured data, summarizing PDFs, answering questions about document content, converting documents'), but missing common synonyms like 'forms'/'invoices' and the .pdf file extension that the score-5 anchor expects.	4 / 5
Distinctiveness Conflict Risk	The Gemini-API framing carves a clear niche, but the broad document/PDF triggers ('processing documents', 'summarizing PDFs') could overlap with other general document or PDF skills, so minor overlap risk remains.	4 / 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: einverne/dotfiles
Path: claude/skills/gemini-document-processing/SKILL.md
Commit: 837e856

Reviewed: ~6 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.