Name: miro-diagram
Rating: 79.89 (1 reviews)
Author: miroapp

miro-diagram

Use when the user wants to create or update a diagram as a widget on a Miro board they're already working on. For a brand-new, standalone diagram not tied to an existing board, use the miro-format skill instead.

1.33x

Quality

80%

Does it follow best practices?

Impact

100%

1.33x

Average score across 2 eval scenarios

Securityby

Passed

No findings from the security scan

The canonical home for this skill is miro-diagram in miroapp/miro-ai

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 deliberately minimal, well-structured MCP-delegating skill that is token-efficient and clearly scoped. Its main gap is actionability: it tells Claude to pick and call a tool without naming any specific MCP tool or providing an example invocation.

Suggestions

Name one or two concrete Miro MCP diagramming tools and show a minimal example call (with a board URL and a couple of parameters) so Claude has a copy-paste-ready starting point.

Add a brief output-validation step to the workflow (e.g., confirm the returned widget ID/URL exists on the board) to close the workflow_clarity validation gap.

Optionally list the most common diagram types supported so Claude can map a user request to the right tool without first inspecting every MCP tool description.

Dimension	Reasoning	Score
Conciseness	Extremely lean body that assumes Claude's competence and delegates detail to the MCP server ("The MCP server is the source of truth..."), with every token earning its place per anchor 5.	5 / 5
Actionability	Gives a clear procedure (identify board URL, identify what to diagram, pick and call a tool) but defers all concrete execution to MCP schemas without naming specific tools or showing an example call, fitting anchor 3's incomplete-concrete-guidance criteria.	3 / 5
Workflow Clarity	A clear three-step sequence with input-gathering checkpoints ("If missing, ask"; "Ask if unclear"), but no post-execution validation, matching anchor 4's clear-sequence-with-minor-validation-gaps description.	4 / 5
Progressive Disclosure	Under 50 lines with well-organized sections (Workflow, When not to use) and no need for external references since detail lives in the MCP server, satisfying the under-50-lines simple-skill criterion for anchor 5.	5 / 5
	Total	17 / 20 Passed

Description

82%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 concise, well-targeted description that clearly states both capability and trigger, with strong boundary guidance distinguishing it from the sibling miro-format skill. Its only weakness is modest action coverage (create/update only).

Dimension	Reasoning	Score
Specificity	Names the Miro-board domain with two concrete actions ("create or update a diagram as a widget"), but lists only two actions and is not comprehensive, matching anchor 3 rather than anchor 4 which requires several actions.	3 / 5
Completeness	Explicitly answers both what (create/update a diagram widget on an existing Miro board) and when ("Use when the user wants to create or update a diagram...") with concrete trigger phrases, matching anchor 5.	5 / 5
Trigger Term Quality	Includes natural user-facing terms ("diagram", "Miro board", "widget") with a clear "Use when" trigger, but misses common synonyms such as flowchart or chart, fitting anchor 4.	4 / 5
Distinctiveness Conflict Risk	Carves a clear niche (widget on an existing board) and explicitly routes the standalone case to the miro-format skill, giving minimal conflict risk per anchor 5.	5 / 5
	Total	17 / 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: miroapp/miro-ai
Path: codex-plugins/miro/skills/miro-diagram/SKILL.md
Commit: c2494b2

Reviewed: 17 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.