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

90%

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 dense, highly actionable reference with complete JSON/SQL examples and an explicit verification feedback loop for the destructive mutation tools. The main weakness is repetition of the top silent-failure rule and length that could be split into a separate reference file.

Suggestions

Consolidate the "groupBy ignored unless addOns.groupBy is true" warning to one canonical location and cross-reference it, instead of restating it in the silent-failures list, the group-by tokens section, and the addOns section.

Consider moving the large lookup tables (panel types, aggregations per source, group-by tokens, display config) into a references/ file generated by the same mcp:docs command, keeping SKILL.md as the overview plus key traps.

Add a short top-of-file table of contents so readers can jump to the relevant section in the ~480-line body.

Dimension	Reasoning	Score
Conciseness	The body is information-dense and assumes Claude's competence (no preamble on what dashboards/ClickHouse/percentiles are) and leads with Maple-specific traps. It sits below 5 because the "groupBy ignored unless addOns.groupBy is true" rule is restated four times across sections and the file runs ~480 lines with some reinforcement that could be trimmed, matching the score-4 anchor of efficient content with minor over-explanation.	4 / 5
Actionability	Multiple complete copy-paste-ready JSON examples (query, raw_sql, static, breakdown, reduceToValue, full assembled widget) plus a complete macro-based SQL example, alongside tables of valid aggregations, group-by tokens, panel types, and units, and concrete commands (bun run --cwd apps/api mcp:docs, describe_warehouse_tables). This matches the score-5 anchor of fully executable, copy-paste-ready guidance covering common cases.	5 / 5
Workflow Clarity	The mutation workflow has an explicit validate-fix-resubmit loop ("MCP success is not chart correctness… Read the verdict: suspicious or broken means fix and resubmit") and a prerequisite checkpoint ("Call describe_warehouse_tables first"), plus a clear simplified-vs-raw entry decision. The destructive/batch cap-at-3 rule does not apply because validation checkpoints are present, matching the score-5 anchor.	5 / 5
Progressive Disclosure	No bundle files exist; the skill is a single well-sectioned file (When to use, Panel types, Data sources, Units, Queries, Display config, Raw SQL) with no nested references. It is below 5 because at ~480 lines of dense reference tables (panel types, aggregations, group-by tokens, display config) some material could plausibly live in a separate file, matching the score-4 anchor of good structure with minor organization gaps; cohesion from a single generated schema module keeps it from dropping to 3.	4 / 5
	Total	18 / 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 explicitly covers both what the skill does and when to trigger it, with concrete MCP tool/parameter names as triggers. The only minor weakness is that trigger terms skew toward API identifiers rather than the full spread of natural-language synonyms.

Dimension	Reasoning	Score
Specificity	"Build, repair, or review Maple dashboard widgets via the MCP" names three concrete verbs, then enumerates comprehensive coverage (panel-type table, kind-discriminated data source, percent vs percent_100 rule, aggregations, group-by tokens, whereClause grammar, reduceToValue transform, verification step). This matches the score-5 anchor of multiple specific concrete actions with comprehensive coverage, not 4 which has minor gaps.	5 / 5
Completeness	It explicitly answers "what" (build, repair, or review Maple dashboard widgets via the MCP, covering the enumerated sub-topics) and "when" (Triggers on phrases like… or any session that submits widget JSON). Explicit trigger guidance is present, so the missing-'Use when' cap does not apply, matching the score-5 anchor.	5 / 5
Trigger Term Quality	"Triggers on phrases like 'create_dashboard', 'add_dashboard_widget', 'update_dashboard_widget', 'dashboard widget JSON', 'panel_type', 'QueryDraft'" gives strong keyword coverage including the natural phrase "submits widget JSON to the maple MCP". It sits below 5 because the triggers lean toward API/tool identifiers rather than the full range of natural-language synonyms a user might say, and above 3 because the natural phrases and exact invocation tokens are present.	4 / 5
Distinctiveness Conflict Risk	The niche is highly specific — "Maple dashboard widgets via the maple MCP" with distinctive tokens (QueryDraft, panel_type table, percent_100 unit rule), giving a clear niche with distinct triggers and minimal conflict risk, matching the score-5 anchor.	5 / 5
	Total	19 / 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: 3cb9193

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.