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

85%

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

77%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 content is highly actionable with complete executable examples and an excellently sequenced, validation-gated workflow. Its weaknesses are verbosity from heavy repetition of the mandatory counts and protected-file rules, and a lack of progressive disclosure: large reference sections are inlined rather than split into referenced files.

Suggestions

State the mandatory card-count table and the 'never modify index.html/dashboard.js/index.css' rule once in Quick Start and reference them from other sections instead of repeating the numbers and rule verbatim 5-6 times.

Move the Card Data DSL, ECharts v6.0.0 configuration reference, and the Dashboard Data Cleaning Guide into separate files under references/ (e.g. CARD_DSL.md, ECHARTS_CONFIG.md, DATA_CLEANING.md) and link to them from SKILL.md so the main file stays a lean overview.

Tighten the Tool Usage Example by either completing the abbreviated cards/updates/card_ids payloads or explicitly pointing to the DSL section for the full entry shape, reducing placeholder [...] blocks.

Dimension	Reasoning	Score
Conciseness	Mostly efficient domain-specific reference material, but the mandatory card counts are restated 6+ times (Quick Start, Workflow Summary, Decision Tree, Core Tools, Preferences, Quick Reference) and the 'never modify index.html/dashboard.js/index.css' rule is repeated 5+ times, which is more than minor over-explanation and could be tightened.	3 / 5
Actionability	Provides fully executable, copy-paste-ready guidance: complete tool.call('create_dashboard_project', ...) invocations with real parameters, full getCardData JavaScript for all four card types, a complete data_cleaning.py template, and concrete ECharts outerBounds configs covering the common cases.	5 / 5
Workflow Clarity	Sequences the full new/edit flows with explicit validation checkpoints (validate_dashboard), a fix-and-re-run feedback loop ('fix errors and re-run until passing'), and a pre-delivery self-check (query_dashboard_cards count by type), with the Decision Tree covering failure branches; validation is present for the batch card operations so no cap applies.	5 / 5
Progressive Disclosure	The body is well-sectioned by headers, but at ~590 lines it is a single inlined monolith with no bundle files: large reference blocks (Card Data DSL ~130 lines, ECharts v6.0.0 config ~40 lines, the Data Cleaning Guide) that could live in separate referenced files are all inline, so content that should be separate is inline.	3 / 5
	Total	16 / 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.

A strong, specific description that names concrete capabilities and tools, explicitly answers both 'what' and 'when', and carves out a distinct niche. Its only weakness is trigger-term breadth: it lacks the synonyms and file extensions that would make triggering fully comprehensive.

Dimension	Reasoning	Score
Specificity	Lists multiple specific concrete actions including named proprietary tools (create_dashboard_cards, update_dashboard_cards, delete_dashboard_cards, query_dashboard_cards, download_dashboard_maps, data_cleaning.py) plus project creation, card plan, development, and validation, giving comprehensive coverage.	5 / 5
Completeness	Explicitly states what the skill does ('Data analysis dashboard (instrument panel) development skill... Includes dashboard project creation, card plan, data cleaning...') and when to use it ('Use when users need to develop data dashboards, create/edit Dashboard projects...') with concrete trigger phrases.	5 / 5
Trigger Term Quality	Includes natural phrases users would say ('develop data dashboards', 'create/edit Dashboard projects', 'build large-screen data boards', 'perform dashboard data cleaning') with good coverage, but lacks synonyms and file extensions that would push it to a 5.	4 / 5
Distinctiveness Conflict Risk	Occupies a clear niche (instrument-panel/large-screen dashboard development) anchored by named proprietary tools and specific triggers, making conflict with other skills unlikely.	5 / 5
	Total	19 / 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
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: f9973c5

Reviewed: 2 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.