miro-browse

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

0.98x

Quality

46%

Does it follow best practices?

Impact

93%

0.98x

Average score across 3 eval scenarios

Securityby

Advisory

Suggest reviewing before use

Fix and improve this skill with Tessl

tessl review fix ./claude-plugins/miro/skills/miro-browse/SKILL.md

Quality

Content

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 a lightweight routing instruction that tells Claude to defer to the Miro MCP server for tool discovery and usage. While concise and well-structured, it lacks actionability — it provides no concrete tool names, example calls, or specific parameters, making it essentially a vague pointer rather than an instructive skill. The workflow steps are logical but too abstract to be truly useful.

Suggestions

Add specific Miro MCP tool names (e.g., the actual tool identifiers for board overview, item retrieval, etc.) so Claude knows exactly which tools to call rather than having to 'explore'.

Include at least one concrete example showing a user request mapped to a specific tool call with parameters, e.g., 'User asks for board summary → call `miro_get_board_overview` with board URL'.

Add a brief troubleshooting note for common failure cases, such as invalid board URLs or permission errors.

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 commands, code, tool names, or executable examples. It defers entirely to the MCP server's tool descriptions, telling Claude to 'explore' and 'pick the appropriate tool' without specifying any actual tool names, parameters, or example calls. This is vague direction rather than concrete guidance.	1 / 3
Workflow Clarity	There is a clear 3-step sequence (identify board URL, identify user intent, pick tool), but it lacks validation checkpoints and concrete details about what to do when things go wrong. The steps are more conceptual than operational.	2 / 3
Progressive Disclosure	For a simple, short skill under 50 lines with no need for external references, the content is well-organized with a clear header and workflow section. No bundle files are needed or referenced, which is appropriate for this scope.	3 / 3
	Total	8 / 12 Passed

Description

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 establishes a clear domain (Miro boards) and provides a 'Use when' trigger clause, which is good. However, it lacks specificity in what concrete actions the skill performs and misses common user trigger terms beyond 'Miro board'. The generic action verbs make it harder to distinguish from other potential Miro-related skills.

Suggestions

Add specific concrete capabilities like 'Retrieves and lists sticky notes, frames, shapes, and connectors from a Miro board' instead of generic verbs like 'explore' and 'inspect'.

Expand trigger terms to include variations users might say: 'Miro', 'board contents', 'sticky notes', 'frames', 'widgets', 'what's on the board'.

Clarify the read-only nature of this skill (if applicable) to distinguish it from skills that create or modify Miro board items.

Dimension	Reasoning	Score
Specificity	Names the domain (Miro board) and some actions (explore, list, summarize, inspect), but these actions are somewhat generic and don't describe concrete capabilities like 'extract sticky notes', 'count frames', or 'read card contents'.	2 / 3
Completeness	Has a 'Use when' clause that covers the 'when' aspect, but the 'what does this do' part is weak — it only lists generic verbs without explaining the actual capabilities or outputs of the skill.	2 / 3
Trigger Term Quality	Includes 'Miro board' as a key trigger term and some action verbs (explore, list, summarize, inspect), but misses common user phrasings like 'Miro', 'board items', 'widgets', 'sticky notes', 'frames', or 'what's on my board'.	2 / 3
Distinctiveness Conflict Risk	The mention of 'Miro board' provides some distinctiveness, but the generic verbs like 'explore', 'summarize', and 'inspect' could overlap with other Miro-related skills (e.g., a skill for editing or creating Miro board items).	2 / 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: 85c2c73

Reviewed: 26 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.