visual-data-dictionary

Build a Visual Data Dictionary — an interactive qsv viz smart dashboard (a Data Schematic) driven by an LLM-inferred JSON Schema data dictionary, with the dictionary browsable beside the charts. Use when the user asks for a visual data dictionary, a documented dashboard, a dictionary-driven dashboard or Data Schematic, 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

Low

Low-risk findings worth noting

Quality

Content

85%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 an information-dense, highly actionable multi-stage workflow with explicit sequencing and validation — a strong code/ops skill. Its main weakness is progressive disclosure: it ships as a single 600-line file with no bundle, and the edit_dictionary.py script it repeatedly references is absent.

Suggestions

Ship edit_dictionary.py in a scripts/ directory so the Stage 2.5 TUI reference resolves to a real file rather than a dead path.

Move the large inline python helpers (GeoJSON feature-id discovery, dictionary coverage check, HTML verification) into scripts/ and reference them by path to slim SKILL.md into an overview.

Add a short 'Quick start' summary at the top pointing to each stage, so the five-stage flow is navigable without scrolling the whole file.

Dimension	Reasoning	Score
Conciseness	Dense with qsv-specific gotchas Claude would not know (flag semantics, --bivariate implicitly enabling --dictionary infer, x-qsv key behavior), avoiding generic explanations of concepts Claude already knows; a few passages like the top scope note and the --dict-info description could be trimmed.	4 / 5
Actionability	Provides copy-paste-ready bash and python for every stage, defines all shell variables in a Naming table, and walks through a concrete worked example (NMBGMRManualWaterLevels.csv) covering the common cases.	5 / 5
Workflow Clarity	Five stages are explicitly ordered ('in this order and no other', 'The order is load-bearing') with validation checkpoints (Stage 0 preconditions, Stage 1 'Report first', Stage 2 coverage check, Stage 5 'Verify, then report'), feedback loops, and a Guardrails section — satisfying the destructive/batch validation requirement.	5 / 5
Progressive Disclosure	Section headers and staging give internal structure, but the skill is monolithic — no references/scripts/assets bundle exists, large inline python blocks (the ~80-line GeoJSON discovery script, verification scripts) are inlined, and the one referenced external file edit_dictionary.py is missing from the bundle, creating a dead reference at Stage 2.5.	3 / 5
	Total	17 / 20 Passed

Description

92%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, provides explicit 'Use when...' trigger guidance with synonyms, and occupies a distinct niche. It uses appropriate third-person/imperative voice throughout. The only minor gap is the absence of file-extension triggers.

Dimension	Reasoning	Score
Specificity	Lists multiple concrete actions — 'Build a Visual Data Dictionary', 'LLM-inferred JSON Schema data dictionary', 'dictionary browsable beside the charts', 'explore and document a CSV', 'bins rows into GeoJSON regions' — giving comprehensive coverage of what the skill does.	5 / 5
Completeness	Explicitly answers both what ('Build a Visual Data Dictionary — an interactive qsv viz smart dashboard...') and when ('Use when the user asks for a visual data dictionary, a documented dashboard...') with concrete trigger phrases.	5 / 5
Trigger Term Quality	Good coverage of natural trigger phrases with synonyms ('visual data dictionary', 'documented dashboard', 'dictionary-driven dashboard', 'Data Schematic', 'explore and document a CSV'), though no file extensions like '.csv' are included and the terms are fairly specialized jargon.	4 / 5
Distinctiveness Conflict Risk	Occupies a clear niche with distinct triggers ('Data Schematic', 'dictionary-driven dashboard', 'visual data dictionary') that are unlikely to fire for unrelated skills, giving minimal conflict risk.	5 / 5
	Total	19 / 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 (617 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: a46782a

Reviewed: about 2 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.