document-query

Use when reading, extracting, summarizing, comparing, or answering questions over local or remote documents, code files, PDFs, Office files, HTML/text files, large text-heavy files, and fallback OCR for document images or scans when vision tools are unavailable or insufficient.

Quality

92%

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

85%

Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.

The content is well-organized and highly actionable, with concrete tool-call examples, a precise input spec, and a clear sequenced workflow including an answer-grounding checkpoint. Its only weakness is mild verbosity from the repeated 'thoughts' fields in examples and slight overlap between the usage-guidance sections.

Suggestions

Trim or remove the 'thoughts' arrays in the JSON examples to reduce token overhead while keeping the tool_name/tool_args pairs.

Merge the overlapping 'When To Use', 'Use vision tools first', and 'Do not use' guidance into a single section to eliminate redundancy.

Consider condensing the five examples to three representative cases (single query, multi-document comparison, fallback OCR) since the pattern repeats.

Dimension	Reasoning	Score
Conciseness	The body avoids explaining concepts Claude already knows and uses compact file-type lists, but the five JSON examples carry verbose 'thoughts' narration and the When-To-Use, Do-not-use, and Use-vision-first sections overlap, so it could be tightened.	2 / 3
Actionability	Provides five complete, copy-paste-ready tool-call JSON examples with real tool_name and tool_args, plus a precise input spec (document/queries, full paths, no directory passthrough), giving concrete executable guidance.	3 / 3
Workflow Clarity	The numbered workflow is clearly sequenced and ends with an explicit evidence-grounding checkpoint ('If the document does not contain the answer, say that it is not found'); as a read-only tool, the destructive-ops validation cap does not apply and the single action is unambiguous.	3 / 3
Progressive Disclosure	The skill is self-contained with no bundle files and is organized into clear sections (When To Use, Inputs, Workflow, Examples) with easy navigation and no nested or deep references, which warrants a 3 for a well-structured single-file skill.	3 / 3
	Total	11 / 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: it states concrete capabilities, includes natural trigger terms and explicit 'Use when' guidance, and adds a distinctive fallback-OCR boundary that separates it from vision skills. It is written in third-person/imperative voice with no padding.

Dimension	Reasoning	Score
Specificity	Lists multiple concrete actions ('reading, extracting, summarizing, comparing, or answering questions') plus fallback OCR across many named file types, matching the 'lists multiple specific concrete actions' anchor.	3 / 3
Completeness	Opens with an explicit 'Use when...' trigger and enumerates the actions it performs, clearly answering both what it does and when to use it; the missing-clause cap at 2 does not apply.	3 / 3
Trigger Term Quality	Uses natural user terms ('documents, code files, PDFs, Office files, OCR') and the trigger_patterns cover common phrasings like 'read document', 'summarize document', and 'ask questions about a document'.	3 / 3
Distinctiveness Conflict Risk	The 'fallback OCR ... when vision tools are unavailable or insufficient' qualifier carves a clear niche and explicitly disambiguates from vision skills, lowering conflict risk.	3 / 3
	Total	12 / 12 Passed

Validation

93%

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 — 15 / 16 Passed

Validation for skill structure

Criteria	Description	Result
frontmatter_unknown_keys	Unknown frontmatter key(s) found; consider removing or moving to metadata	Warning

	Total	15 / 16 Passed

Repository: agent0ai/agent-zero
Path: plugins/_document_query/skills/document-query/SKILL.md
Commit: 391fab9

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.