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

80%

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

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.

A concise, well-organized single-file skill with concrete tool-invocation examples and a clear workflow. The main weakness is workflow clarity: validation/verification checkpoints are implicit, particularly for multi-document comparison and answer-grounding cases.

Suggestions

Add an explicit validation checkpoint in the workflow for multi-document comparisons, e.g. 'Verify each answer is grounded in returned document evidence before presenting it.'

Add a feedback loop step: if evidence is missing or contradictory across documents, re-query with narrower questions before answering.

Consider trimming one or two of the repetitive example JSON blocks (e.g. consolidate the single-document Q&A and code-file Q&A examples) to tighten conciseness.

Dimension	Reasoning	Score
Conciseness	The body is lean — bullet lists for When To Use, a compact Inputs section, a short numbered workflow, and tool-call JSON examples — with no padding or re-explanation of known concepts; only minor repetition across the five example blocks keeps it from the top anchor.	4 / 5
Actionability	Concrete tool-call JSON examples cover the main cases (extract, Q&A, compare, fallback OCR, code files) and the Inputs section specifies required/optional args and path rules, but the examples are invocation snippets rather than copy-paste executable code, leaving small gaps.	4 / 5
Workflow Clarity	A clear 6-step sequence is present with a 'not found' fallback, but validation checkpoints are implicit and multi-document/comparison cases lack a verify-against-evidence loop, matching the 'steps listed but validation gaps' anchor.	3 / 5
Progressive Disclosure	No bundle files exist; the skill is a single well-organized file with clear sections (When To Use, Inputs, Workflow, Examples), which per the simple-skill note qualifies for the top anchor.	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.

A strong, well-structured description that names concrete actions, file types, and an explicit trigger clause, with a clear vision-first boundary for OCR fallback. Minor extension/synonym coverage gaps keep trigger quality and distinctiveness just below the top anchor.

Dimension	Reasoning	Score
Specificity	Lists multiple concrete actions ('reading, extracting, summarizing, comparing, or answering questions') and a comprehensive set of file types (documents, code files, PDFs, Office files, HTML/text files, scans), matching the 'comprehensive coverage' anchor.	5 / 5
Completeness	Explicit 'Use when...' clause supplies the trigger, and the what (reading/extracting/summarizing/comparing/Q&A plus fallback OCR over named file types) is concrete and clearly stated — both what and when are explicitly answered.	5 / 5
Trigger Term Quality	Good coverage of natural phrases users say ('summarize', 'compare', 'answer questions over', 'PDFs', 'Office files', 'OCR'), but file extensions like .pdf/.docx and a few common synonyms are absent.	4 / 5
Distinctiveness Conflict Risk	The vision-first fallback-OCR framing carves a clear niche, but the broad 'documents, code files, large text-heavy files' scope still overlaps with general file-reading skills, so minor overlap risk remains.	4 / 5
	Total	18 / 20 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: b22a144

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.