visual-data-dictionary

Build a Data Schematic with its Data Dictionary beside it — an interactive qsv viz smart dashboard driven by an LLM-inferred JSON Schema data dictionary, browsable in-page next to the charts. Use when the user asks for a Data Schematic, a visual data dictionary, a documented dashboard or a dictionary-driven dashboard, or wants to explore and document a CSV at the same time. Optionally bins rows into GeoJSON regions.

Quality

88%

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

88%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 highly executable, well-sequenced workflow with strong validation checkpoints and feedback loops, scoring at the top on actionability and workflow clarity. Conciseness and progressive disclosure are slightly below the ceiling due to a few long deep-dive sections and an inlined reference table plus a referenced bundle file not present in the review tree.

Suggestions

Move the six-row hand-edited-keys table (x-qsv.gauge_range/target/currency/denominator/relationships/tour) into a references/ file and link to it, keeping only the one-line summary inline to tighten progressive_disclosure.

Trim the denominator/aggregation collapse deep-dive (issues #4528/#4401) to the rule and its two observable consequences; the full mechanism is more than the workflow needs.

Ensure edit_dictionary.py ships alongside SKILL.md (it is referenced but not present in this review bundle), or note its expected location explicitly so the Stage 2.5 reference resolves.

Dimension	Reasoning	Score
Conciseness	Most prose is genuinely non-obvious qsv behavior (flag interactions, edge cases, issue references) rather than concepts Claude already knows, and code is dense, but a few deep-dives (the denominator/aggregation and tour-refinement sections) could be trimmed, fitting 'efficient; minor instances of over-explanation' rather than the lean 5.	4 / 5
Actionability	Every stage ships copy-paste-ready bash and python with concrete flag combinations, plus a worked end-to-end example, matching 'fully executable; copy-paste ready code or commands; specific examples cover the common cases'.	5 / 5
Workflow Clarity	Explicit numbered stages with load-bearing ordering, validation checkpoints (Stage 2 coverage check, Stage 5 verify), and feedback loops (re-validate after edits, re-render); the destructive denull --apply is gated by report-first and guardrails, matching the 'clear sequence with explicit validation steps; feedback loops for error recovery' anchor.	5 / 5
Progressive Disclosure	Well-sectioned overview with one signaled one-level reference (edit_dictionary.py beside this SKILL.md), but no references/scripts/assets directories exist in the review tree so that referenced file is absent here, and the large hand-edited-keys table is inlined rather than split out — good structure with minor organization gaps, below the clean 5.	4 / 5
	Total	18 / 20 Passed

Description

87%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, third-person description that states concrete capabilities and an explicit 'Use when…' trigger clause with good synonym coverage. It is comprehensive on completeness and distinctiveness; only specificity and trigger-term coverage have minor gaps.

Dimension	Reasoning	Score
Specificity	Lists several concrete actions — 'Build a Data Schematic with its Data Dictionary beside it', 'LLM-inferred JSON Schema data dictionary', 'browsable in-page next to the charts', 'Optionally bins rows into GeoJSON regions' — with only minor coverage gaps, fitting the 'several specific actions; minor gaps' anchor rather than the comprehensive 5.	4 / 5
Completeness	Explicitly answers both: what ('Build a Data Schematic with its Data Dictionary beside it…') and when ('Use when the user asks for a Data Schematic, a visual data dictionary, a documented dashboard…'), matching the 'clearly and explicitly answers both what AND when with concrete trigger phrases' anchor.	5 / 5
Trigger Term Quality	Covers natural phrases a user would say — 'Data Schematic', 'visual data dictionary', 'documented dashboard', 'dictionary-driven dashboard', 'explore and document a CSV', 'GeoJSON regions' — with good synonym coverage but missing common variations like the '.csv' extension, so it sits above 3 but below the fully comprehensive 5.	4 / 5
Distinctiveness Conflict Risk	Occupies a clear niche (Data Schematic / visual data dictionary / qsv viz smart) with distinct, specific triggers and minimal overlap with other skills, matching the 'clear niche with distinct triggers; minimal conflict risk' anchor.	5 / 5
	Total	18 / 20 Passed

Validation

87%

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 — 14 / 16 Passed

Validation for skill structure

Criteria	Description	Result
skill_md_line_count	SKILL.md is long (739 lines); consider splitting into references/ and linking	Warning
frontmatter_unknown_keys	Unknown frontmatter key(s) found; consider removing or moving to metadata	Warning

	Total	14 / 16 Passed

Repository: dathere/qsv
Path: .claude/skills/visual-data-dictionary/SKILL.md
Commit: 19d6491

Reviewed: 20 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.