smoke-test

Create a Mastra project using create-mastra and smoke test the studio in Chrome using Chrome MCP server

Quality

72%

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 ./.claude/skills/smoke-test/SKILL.md

Quality

Content

77%

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

The body is highly actionable and well-sequenced with strong validation checkpoints, but it is monolithic and padded with redundant tables that restate earlier content. Splitting the detailed smoke-test checklist into a reference file and trimming duplicated tables would improve conciseness and progressive disclosure.

Suggestions

Move the per-route smoke-test checklist (5.2) and the Studio Routes table into a reference file (e.g. references/studio-checklist.md) and link to it one level deep.

Remove the Quick Reference and "Flags explained" sections that duplicate Step 1 content and self-evident flag meanings.

Collapse the duplicate route listings (test checklist vs. Studio Routes table) into a single canonical source to tighten the token budget.

Dimension	Reasoning	Score
Conciseness	Mostly efficient operational detail, but it repeats the create command across Step 1 and the Quick Reference table, restates routes in a separate Studio Routes table already covered by the test checklist, and over-explains self-evident flags in "Flags explained".	2 / 3
Actionability	It provides fully executable, copy-paste-ready commands for each package manager, a complete browser-agent TypeScript snippet, exact Studio routes, and a concrete test checklist with expected results.	3 / 3
Workflow Clarity	Steps are clearly sequenced (Step 0 through 5) with an explicit parameter-validation gate, verification checkpoints ("Wait for the server to be ready", "Verify project has package.json"), and a troubleshooting section for error recovery.	3 / 3
Progressive Disclosure	The skill is a single ~360-line monolithic file with no reference bundle and no offloaded reference files; sections are well-organized but the detailed per-route test checklist and route tables are content that could be split into a separate reference.	2 / 3
	Total	10 / 12 Passed

Description

67%

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 names two concrete, well-scoped actions and is clearly distinct from other skills, but it omits any explicit "Use when..." trigger guidance and relies on product jargon rather than natural user phrasings. Adding a trigger clause and broader natural keywords would lift the weakest dimensions.

Suggestions

Add a "Use when..." clause stating when to invoke this skill (e.g., when the user asks to smoke test or verify a Mastra Studio app in Chrome).

Broaden trigger terms with natural phrasings users would say, such as "test Mastra app", "verify Mastra Studio", or "browser smoke test".

Soften the jargon ("Chrome MCP server") or pair it with a user-facing term so the description reads naturally.

Dimension	Reasoning	Score
Specificity	Lists multiple concrete actions with named tools — "Create a Mastra project using create-mastra" and "smoke test the studio in Chrome using Chrome MCP server" — matching the anchor that lists several specific concrete actions.	3 / 3
Completeness	It clearly states what the skill does but lacks any "Use when..." clause or explicit trigger guidance, so per the judging guideline completeness is capped at 2.	2 / 3
Trigger Term Quality	It includes some relevant terms ("Mastra", "smoke test", "studio", "Chrome") but leans on product/tool names and jargon like "Chrome MCP server", missing common user phrasings; not the broad coverage of the level-3 anchor.	2 / 3
Distinctiveness Conflict Risk	The combination of "Mastra project", "smoke test the studio", and "Chrome MCP server" carves a clear niche unlikely to trigger for unrelated skills.	3 / 3
	Total	10 / 12 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: mastra-ai/mastra
Path: .claude/skills/smoke-test/SKILL.md
Commit: 3b78ed9

Reviewed: about 23 hours 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.