miro-browse

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

0.98x

Quality

51%

Does it follow best practices?

Impact

93%

0.98x

Average score across 3 eval scenarios

Securityby

Low

Low-risk findings worth noting

Fix and improve this skill with Tessl

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

Quality

Content

53%

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

This skill is concise and well-structured for a short browsing guide, but it critically lacks actionability: it names no specific MCP tools, provides no example calls, and essentially tells Claude to figure it out from the MCP server at runtime. The workflow is logically sequenced but too abstract to be reliably executable without prior knowledge of the available tools.

Suggestions

List the specific Miro MCP tool names (e.g., `miro_get_board_overview`, `miro_get_item`) so Claude knows exactly which tools to call rather than having to 'explore' them.

Add 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` parameter'.

Include brief guidance on handling common failure modes, such as invalid board URLs or empty results from filtered listings.

Dimension	Reasoning	Score
Conciseness	Mostly efficient. The opening sentence is slightly redundant with the title, and the paragraph explaining what the MCP server is the source of truth for could be tightened, but overall it avoids explaining concepts Claude already knows and stays lean.	4 / 5
Actionability	The skill provides high-level direction (identify the board URL, identify what the user wants, pick a tool) but never names specific MCP tools, provides no concrete commands or code, and delegates all specifics to the MCP server's own descriptions. Claude is told to 'explore' tools rather than given executable guidance.	2 / 5
Workflow Clarity	A three-step sequence is present and logically ordered, but steps are vague ('pick the appropriate tool'), there are no validation checkpoints, and no guidance on what to do if a tool call fails or returns unexpected results. Since this is a read-only browsing skill (non-destructive), the missing feedback loop doesn't trigger the cap, but the steps remain underspecified.	3 / 5
Progressive Disclosure	For a short, single-purpose skill with no bundle files, the structure is reasonable — a brief overview followed by a clear workflow section. It could benefit from a quick-reference list of the actual MCP tool names or a link to documentation, but the organization is clean and navigable for its size.	4 / 5
	Total	13 / 20 Passed

Description

48%

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' clause, but it lacks specificity about what concrete actions the skill performs and what outputs it produces. The action verbs used (explore, list, summarize, inspect) are generic and don't convey the skill's actual capabilities. It would benefit from explicitly stating what the skill does and including more natural trigger terms related to Miro-specific elements.

Suggestions

Add a concrete 'what' statement before the 'Use when' clause, e.g., 'Retrieves and displays sticky notes, shapes, frames, and other widgets from a Miro board. Summarizes board content and lists items by type.'

Include Miro-specific trigger terms such as 'sticky notes', 'frames', 'widgets', 'cards', 'connectors', or 'Miro elements' to improve matching when users reference specific board components.

Clarify the scope boundary—whether this skill is read-only (inspection/listing) vs. editing—to reduce potential conflict with other Miro-related skills.

Dimension	Reasoning	Score
Specificity	Names the domain (Miro board) and lists some actions (explore, list, summarize, inspect), but these are generic verbs that don't describe concrete, specific capabilities. It doesn't explain what kinds of items or what the outputs look like.	2 / 5
Completeness	Has a 'when' clause ('Use when the user wants to...') but the 'what' is only weakly implied through the action verbs. There is no explicit statement of what the skill does—only when to use it. Per the rubric, the 'what' is missing or only weakly implied, capping this at 3.	3 / 5
Trigger Term Quality	Includes 'Miro board' as a key trigger term and some action words like 'list', 'summarize', 'inspect', but misses natural user phrases like 'Miro items', 'sticky notes', 'frames', 'widgets', or specific Miro element types users might reference.	3 / 5
Distinctiveness Conflict Risk	The mention of 'Miro board' provides a clear domain niche that distinguishes it from most other skills. However, there could be overlap with other Miro-related skills (e.g., editing or creating Miro content vs. reading/inspecting), and the description doesn't clearly delineate its read-only or inspection scope.	4 / 5
	Total	12 / 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 — 11 / 11 Passed

Validation for skill structure

No warnings or errors.

Repository: miroapp/miro-ai
Path: claude-plugins/miro/skills/miro-browse/SKILL.md
Commit: 85c2c73

Reviewed: 4 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.