miro-browse

Use when the user wants to explore, list, summarize, or inspect items on a Miro board.

Quality

46%

Does it follow best practices?

Impact

—

No eval scenarios have been run

Securityby

Advisory

Suggest reviewing before use

Optimize this skill with Tessl

npx tessl skill review --optimize ./claude-plugins/miro/skills/miro-browse/SKILL.md

Quality

Discovery

50%

Based on the skill's description, can an agent find and select it at the right time? Clear, specific descriptions lead to better discovery.

The description benefits from explicitly mentioning Miro and providing a 'Use when' clause, but it lacks concrete specificity about what actions are performed and what types of board items are handled. The 'what it does' component is essentially absent — the description only has a 'when' clause without a preceding capability statement.

Suggestions

Add an explicit 'what it does' statement before the 'Use when' clause, e.g., 'Reads and retrieves items from Miro boards including sticky notes, frames, shapes, and connectors.'

Include more natural trigger terms and variations users might say, such as 'Miro', 'board contents', 'sticky notes', 'widgets', 'frames', or 'what's on the board'.

Specify concrete actions more precisely — e.g., 'lists all items on a board, summarizes sticky note contents, inspects item properties and metadata' to improve specificity and distinctiveness.

Dimension	Reasoning	Score
Specificity	Names the domain (Miro board) and some actions (explore, list, summarize, inspect), but these actions are somewhat generic and not deeply concrete — e.g., it doesn't specify what kinds of items (sticky notes, frames, connectors) or what 'inspect' entails.	2 / 3
Completeness	It answers 'when' clearly with 'Use when the user wants to...', but the 'what does this do' portion is weak — it only implies capabilities through the trigger clause rather than explicitly stating what the skill does as a separate declaration.	2 / 3
Trigger Term Quality	Includes 'Miro board' as a strong trigger term and some action verbs like 'list', 'summarize', 'inspect', but misses common user phrasings like 'Miro', 'board items', 'widgets', 'sticky notes', 'frames', or 'read from Miro'.	2 / 3
Distinctiveness Conflict Risk	The mention of 'Miro board' provides some distinctiveness, but the generic verbs like 'explore', 'list', 'summarize', and 'inspect' could overlap with other board or project management skills. It doesn't clearly carve out a unique niche beyond the Miro keyword.	2 / 3
	Total	8 / 12 Passed

Implementation

42%

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

This skill is essentially a thin wrapper that delegates almost entirely to the Miro MCP server's own tool descriptions. While it's reasonably concise and well-structured, it provides almost no actionable value — no specific tool names, no example calls, no parameter guidance, and no concrete examples of what a successful interaction looks like. It reads more like a routing hint than a skill.

Suggestions

Add concrete tool names and example invocations (e.g., show a specific MCP tool call with parameters for getting a board overview or listing items by type).

Include at least one end-to-end example showing a user request, the tool(s) called, and the expected output format.

Add guidance on error handling or common failure modes (e.g., invalid board URL, permissions issues, empty results).

Dimension	Reasoning	Score
Conciseness	Reasonably concise but includes some unnecessary phrasing like 'Shortcut to the Miro MCP browsing and context tools' and the parenthetical list '(board-level overview, item-level content, item listing/filtering, image and asset retrieval)' which restates what the MCP server already describes. Could be tighter.	2 / 3
Actionability	The skill provides no concrete tool names, no executable commands, no example calls, and no specific parameters. It entirely defers to the MCP server's tool descriptions, making it vague direction rather than actionable guidance. Claude is told to 'pick the appropriate tool' without knowing which tools exist or how to call them.	1 / 3
Workflow Clarity	There is a clear 3-step sequence (identify board URL, identify user intent, pick tool), but it lacks any validation checkpoints, error handling, or concrete examples of tool chaining. The workflow is more of a decision framework than an executable process.	2 / 3
Progressive Disclosure	For a simple, short skill under 50 lines with no bundle files and no need for external references, the content is appropriately organized in a single file with clear sections. No unnecessary nesting or monolithic walls of text.	3 / 3
	Total	8 / 12 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 — 11 / 11 Passed

Validation for skill structure

No warnings or errors.

Repository: miroapp/miro-ai
Commit: da5405f

Reviewed: 8 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.