Name: miro-code-spec
Rating: 60.8 (1 reviews)
Author: miroapp

miro-code-spec

Use when the user wants to extract a Miro board's specs (documents, diagrams, prototypes, tables, frames, images) to local `.miro/specs/` files for AI-assisted planning and implementation — accepts a board URL or single-item URL.

Quality

70%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

High

Do not use without reviewing

Fix and improve this skill with Tessl

tessl review fix ./cursor-plugins/miro/skills/miro-code-spec/SKILL.md

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

Quality

Content

62%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 workflow itself is excellent — clearly sequenced, mandatory, and validated end-to-end with concrete executable templates. The body is undermined by heavy repetition of the same prototype-screen rules and a large inlined Background section that should live in the existing reference file or a new one.

Suggestions

State the prototype-screen subagent rule once (in Step 7) and trim its restatements in Step 5, Implementation Notes, and Common Mistakes to single-line reminders, cutting substantial duplication.

Move the Background section's Best Practices, Troubleshooting, and Content Types table into references/spec-storage.md or a separate reference file, keeping SKILL.md as a lean overview that links to them.

Either name the specific Miro MCP tools to call or add one explicit sentence justifying why tool names are left flexible (e.g., they vary by MCP server version), removing the repeated vagueness.

Dimension	Reasoning	Score
Conciseness	The ~465-line body repeats the prototype-screen subagent rules across at least four sections (Step 5, Step 7, Implementation Notes, Common Mistakes) and includes padded bullet lists ("✓ All items are tracked / ✓ Nothing gets skipped...") — noticeably verbose even though it avoids explaining concepts Claude already knows.	2 / 5
Actionability	Highly concrete: a copy-paste subagent prompt template, an exact curl download command, precise file paths, index.json schemas, and worked HTML before/after examples; the recurring "call the appropriate Miro MCP item-retrieval tool" leaves tool selection unspecified without explicitly justifying that flexibility, which is a minor gap.	4 / 5
Workflow Clarity	A 9-step sequence with a mandatory per-item task breakdown, progressive index updates, and a final verification checklist with an explicit feedback loop ("If mismatch, identify and save any missing items... Re-extract missing items before finishing") — matching the anchor for batch operations with explicit validation and recovery.	5 / 5
Progressive Disclosure	The single reference (references/spec-storage.md) is real and one level deep but only surfaced in a bottom "See Also" section, while ~110 lines of Background (best practices, troubleshooting, content-type table, image-extraction detail that duplicates the workflow) are inlined in SKILL.md where they belong in reference files.	3 / 5
	Total	14 / 20 Passed

Description

78%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 strong description with an explicit 'Use when' clause, a concrete action, enumerated content types, and precise input/output details. Its main weakness is narrow trigger phrasing that restates the capability instead of covering the varied ways a user would ask for it.

Suggestions

Broaden the trigger clause with concrete variations users actually say, e.g. "Use when the user wants to extract, export, or download specs/documents/prototypes from a Miro board or item, or to prepare Miro content for AI-assisted planning."

Name the output value earlier and more concretely for searchability, e.g. mentioning "spec extraction" and "offline/local copies of Miro content" as keywords.

Dimension	Reasoning	Score
Specificity	"extract a Miro board's specs (documents, diagrams, prototypes, tables, frames, images) to local `.miro/specs/` files" names the domain, a concrete destination, enumerated content types, and accepted inputs ("board URL or single-item URL"), which goes beyond 1-2 concrete actions, though it centers on a single extraction action rather than several distinct ones.	4 / 5
Completeness	Both what ("extract a Miro board's specs ... to local `.miro/specs/` files") and when ("Use when the user wants to...") are explicit, but the trigger clause mostly restates the what rather than offering concrete, varied trigger phrases, so it falls just short of the 5 anchor.	4 / 5
Trigger Term Quality	Natural terms users would say are present — "Miro", "board", "specs", "extract", plus the item-type keywords (documents, diagrams, prototypes, tables, frames, images) and "board URL" — but common variations like "export", "download", or "whiteboard" are missing.	4 / 5
Distinctiveness Conflict Risk	"Miro board's specs" with URL and output-path specificity carves out a clear niche; only another Miro-specific skill could overlap, and the enumerated scope keeps conflict risk minimal.	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: cursor-plugins/miro/skills/miro-code-spec/SKILL.md
Commit: b6408e1

Reviewed: 5 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.