miro-automation

Automate Miro tasks via Rube MCP (Composio): boards, items, sticky notes, frames, sharing, connectors. Always search tools first for current schemas.

2.41x

Quality

70%

Does it follow best practices?

Impact

94%

2.41x

Average score across 3 eval scenarios

Securityby

Low

Low-risk findings worth noting

Fix and improve this skill with Tessl

tessl review fix ./plugins/all-skills/skills/miro-automation/SKILL.md

Quality

Content

57%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.

The body is a well-organized, domain-specific tool reference with genuinely useful pitfalls, but it suffers from redundant repetition, no validation loop for batch operations, a missing connector-creation tool in the connections workflow, and no progressive disclosure of the detailed parameter reference into separate files.

Suggestions

Add a validation step after batch/destructive operations (e.g., verify created items via MIRO_GET_BOARD_ITEMS and retry failures), which is currently capping workflow clarity.

Deduplicate: state the 'search tools first' rule and ID-resolution pattern once, and either drop the Known Pitfalls section or the per-workflow Pitfalls that repeat it.

Move per-tool parameter detail and the Quick Reference table into a references/ file (e.g., references/tools.md) linked from SKILL.md, and list the actual connector-creation tool in workflow 5.

Dimension	Reasoning	Score
Conciseness	Most content is Miro/Composio-specific detail Claude would not know, but 'Always call RUBE_SEARCH_TOOLS first' appears three times (description, Prerequisites, Setup), the per-workflow Pitfalls duplicate the 'Known Pitfalls' section (ID resolution guidance is stated twice), and the Quick Reference table restates the tool sequences.	3 / 5
Actionability	Concrete tool slugs, parameter names, enum values ('viewer', 'commenter', 'editor'), hex color format, and an ID-resolution recipe make this mostly executable guidance; gaps remain, e.g., workflow 5 'Create Visual Connections' lists no tool that actually creates a connector, and there are no example tool-call payloads.	4 / 5
Workflow Clarity	Each workflow has a clear 'When to use', ordered tool sequence, and the Setup section includes validation checkpoints (confirm ACTIVE before workflows), but batch operations like MIRO_CREATE_ITEMS_IN_BULK have no post-creation verification or fix-and-retry loop, which caps workflow clarity at 3 per the rubric.	3 / 5
Progressive Disclosure	No bundle files exist (no references/, scripts/, or assets/), and roughly 200 lines of per-tool parameter documentation plus a full quick-reference table are inlined in SKILL.md; this detail would be better split into a one-level-deep reference file, matching anchor 3.	3 / 5
	Total	13 / 20 Passed

Description

70%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.

The description is specific and distinct, clearly identifying the Miro automation domain and its capability areas, but it never tells Claude when to use the skill. Adding an explicit 'Use when...' clause with natural trigger phrases would lift it substantially.

Suggestions

Add an explicit trigger clause, e.g., 'Use when the user mentions Miro, whiteboards, sticky notes, or wants to create/share/inspect Miro boards.'

Phrase capabilities as actions rather than a noun list (e.g., 'create boards, add sticky notes and frames, connect items, share boards') to sharpen specificity.

Include common user synonyms like 'whiteboard' or 'collaboration board' to improve trigger term coverage.

Dimension	Reasoning	Score
Specificity	Names the domain and several concrete capability areas ("boards, items, sticky notes, frames, sharing, connectors"), but these are noun lists rather than explicit actions (e.g., "create sticky notes") and coverage has gaps (no read/update/delete verbs), matching anchor 4 rather than 5.	4 / 5
Completeness	The 'what' is clear (automate Miro tasks across boards, items, sticky notes, frames, sharing, connectors) but there is no 'Use when...' clause or equivalent explicit trigger guidance, which per the judging guidelines caps completeness at 3.	3 / 5
Trigger Term Quality	Includes natural user terms like "Miro", "boards", "sticky notes", "frames", "sharing", "connectors", but misses common synonyms such as "whiteboard" or "collaborate", and roughly half the description is integration jargon ("Rube MCP (Composio)").	4 / 5
Distinctiveness Conflict Risk	"Miro" is a clear niche trigger with distinct capability keywords; the description is unlikely to fire for unrelated skills, matching the anchor for minimal conflict risk.	5 / 5
	Total	16 / 20 Passed

Validation

93%

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 — 15 / 16 Passed

Validation for skill structure

Criteria	Description	Result
frontmatter_unknown_keys	Unknown frontmatter key(s) found; consider removing or moving to metadata	Warning

	Total	15 / 16 Passed

Repository: davepoon/buildwithclaude
Path: plugins/all-skills/skills/miro-automation/SKILL.md
Commit: 10bfc43

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.