develop-data-analysis-dashboard

Data analysis dashboard (instrument panel) development skill. Use when users need to develop data dashboards, create/edit Dashboard projects, build large-screen data boards, or perform dashboard data cleaning. Includes dashboard project creation, card plan, data cleaning (data_cleaning.py), card management tools (create_dashboard_cards, update_dashboard_cards, delete_dashboard_cards, query_dashboard_cards), map download tool (download_dashboard_maps), dashboard development, and validation.

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

77%

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

A highly actionable, well-sequenced skill body with strong validation feedback loops and complete code examples. Its weaknesses are token efficiency (heavy repetition of the card-count mandates) and the absence of progressive disclosure via separate reference files.

Suggestions

State the mandatory card-count table once in Quick Start and reference it from later sections instead of restating 'metric >=6, echarts 26-30, table 2-3, total 34-39' in Enforcement Rules, Workflow Summary, Decision Tree, Core Tools, and Preferences.

Move the large ECharts v6.0.0 configuration and Card Data DSL sections into reference files (e.g. ECHARTS.md, CARD_DSL.md) and link to them from SKILL.md so the main file stays a concise overview.

Consolidate the duplicated Card Management Tools quick-reference block with the earlier Core Tools parameter tables to remove the repeated batch-limit and auto_layout guidance.

Dimension	Reasoning	Score
Conciseness	The body is mostly operational and avoids explaining concepts Claude already knows, but it repeats the mandatory card-count table/figures across Quick Start, Enforcement Rules, Workflow Summary, Decision Tree, Core Tools, and Preferences; tightening those repetitions would move it from score 2 to the lean score-3 anchor.	2 / 3
Actionability	Provides copy-paste-ready executable examples for every tool (tool.call snippets), full getCardData implementations for all four card types, a runnable data_cleaning.py template, parameter tables, and the project tree, matching the fully-executable anchor.	3 / 3
Workflow Clarity	Sequences the new/edit flows with a Workflow Summary and Decision Tree, and includes explicit validation checkpoints (validate_dashboard -> fix -> re-run, query_dashboard_cards self-check before delivery, data-source exception flow) with feedback loops appropriate to batch/destructive operations.	3 / 3
Progressive Disclosure	There are no bundle files (references/scripts/assets absent) and Quick Start itself states 'Detailed rules are inlined later in this document'; the ECharts config, Card Data DSL, and Data Cleaning Guide are content that could be split into separate reference files but is kept inline, fitting the score-2 'content that should be separate is inline' anchor rather than a one-level-deep reference structure.	2 / 3
	Total	10 / 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.

A strong, third-person description that pairs an explicit 'Use when' trigger with a concrete enumeration of capabilities and named tools. It cleanly answers what, when, and how it differs from other skills.

Dimension	Reasoning	Score
Specificity	Lists multiple concrete actions with named tools (project creation, card plan, data cleaning via data_cleaning.py, create/update/delete/query_dashboard_cards, download_dashboard_maps, validation), matching the 'lists multiple specific concrete actions' anchor rather than the partial score-2 anchor.	3 / 3
Completeness	Explicitly answers what ('Includes...') and when via a clear 'Use when...' trigger clause, satisfying both halves; not score 2 because the 'when' is explicit rather than implied.	3 / 3
Trigger Term Quality	Covers natural user phrasings ('develop data dashboards', 'create/edit Dashboard projects', 'build large-screen data boards', 'dashboard data cleaning') that a user would actually say, rather than technical jargon, so it matches the good-coverage anchor.	3 / 3
Distinctiveness Conflict Risk	Targets a clear niche (dashboard/instrument-panel development) with distinctive tool names and triggers, making it unlikely to fire for unrelated skills.	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
skill_md_line_count	SKILL.md is long (591 lines); consider splitting into references/ and linking	Warning

	Total	15 / 16 Passed

Repository: dtyq/magic
Path: backend/super-magic/agents/skills/develop-data-analysis-dashboard/SKILL.md
Commit: 41d7ef4

Reviewed: about 13 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.