maple-dashboard-widgets

Build, repair, or review Maple dashboard widgets via the MCP. Triggers on phrases like 'create_dashboard', 'add_dashboard_widget', 'update_dashboard_widget', 'dashboard widget JSON', 'panel_type', 'QueryDraft', or any session that submits widget JSON to the maple MCP. Covers the panel-type table, the kind-discriminated data source, the percent vs percent_100 unit rule, valid aggregations and group-by tokens per source, the custom whereClause grammar, the scalar reduceToValue transform, and the verification step (MCP success != chart correctness).

Quality

81%

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

78%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 thorough, highly actionable reference for a niche MCP, rich with executable examples and explicit verification guidance. It is somewhat verbose from repeated JSON boilerplate and monolithic where some reference material could be offloaded to bundle files.

Suggestions

Move the large reference tables (panel types, units, aggregations per source, display config) into a separate references file and link to it from SKILL.md to reduce inline bulk and improve progressive disclosure.

Show the full query-JSON object once and reference its shape for subsequent examples instead of repeating the entire addOns/queries boilerplate for each variant.

Add a short sequenced workflow section (pick panel type -> choose source -> set unit -> validate via inspect_chart_data) to complement the reference layout.

Dimension	Reasoning	Score
Conciseness	Dense, non-obvious domain knowledge (silent failures, inverted percent tokens, custom grammar) is delivered efficiently and assumes Claude's competence, but the full query-JSON boilerplate is repeated across several examples and could be trimmed.	4 / 5
Actionability	Provides copy-paste-ready JSON for every data-source variant, explicit tables of valid aggregations/group-by tokens/units, and concrete commands (e.g. "Call describe_warehouse_tables first", "bun run --cwd apps/api mcp:docs").	5 / 5
Workflow Clarity	A clear verification feedback loop is present ("MCP success is not chart correctness ... suspicious or broken means fix and resubmit") plus preflight checks, but the body is organized as a reference rather than an explicitly sequenced workflow.	4 / 5
Progressive Disclosure	Sections are well-organized with headers and tables, but the ~485-line body is monolithic with large reference tables (panel types, units, aggregations, display config) all inlined and no external reference files despite bulk that could be split.	3 / 5
	Total	16 / 20 Passed

Description

85%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 clearly states capabilities and explicit trigger conditions for a well-scoped MCP domain. Its main weakness is trigger terms leaning on tool-name jargon rather than natural user language.

Dimension	Reasoning	Score
Specificity	Lists multiple concrete actions ("Build, repair, or review Maple dashboard widgets via the MCP") and comprehensively enumerates specific concerns (panel-type table, kind-discriminated data source, percent vs percent_100 rule, whereClause grammar, reduceToValue transform, verification step).	5 / 5
Completeness	Explicitly answers both what (build/repair/review widgets via MCP with covered topics) and when ("Triggers on phrases like ... or any session that submits widget JSON to the maple MCP") with concrete trigger phrases.	5 / 5
Trigger Term Quality	Trigger terms like 'create_dashboard', 'panel_type', and 'QueryDraft' are relevant to the domain but are technical tool/identifier jargon rather than natural user phrasings, and no synonyms or common variations are offered.	3 / 5
Distinctiveness Conflict Risk	The narrow niche "Maple dashboard widgets via the MCP" with MCP-tool-specific trigger tokens makes conflict with other skills minimal.	5 / 5
	Total	18 / 20 Passed

Validation

100%

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 — 16 / 16 Passed

Validation for skill structure

No warnings or errors.

Repository: MapleTechLabs/maple
Path: skills/maple-dashboard-widgets/SKILL.md
Commit: 6d47ff3

Reviewed: 1 day 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.