smoke-test

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

Quality

67%

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

70%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 delivers an exceptionally executable and well-validated workflow — per-PM commands, complete code, checklists, and troubleshooting — earning top marks for workflow clarity. Weaknesses are duplication of parameter/route information and a monolithic structure with no reference files for the long test checklist.

Suggestions

Deduplicate: drop the parameter re-enforcement in Step 0 (or the Usage/Parameters tables) and merge the Studio Routes table into the checklist section so routes appear once.

Split the ~130-line Studio smoke-test checklist into a references/ file (e.g. studio-checklist.md) with a concise in-body summary, enabling progressive disclosure.

Resolve the browser-agent placeholder by providing a concrete provider-to-model example or a small mapping table next to the code sample.

Dimension	Reasoning	Score
Conciseness	Mostly efficient tables and commands, but parameters are documented twice (Usage table plus Step 0), Studio routes appear in both the test checklist and a dedicated Routes table, and the Quick Reference repeats prior steps. Matches anchor 3 (could be tightened); not 4 because the duplication is more than minor.	3 / 5
Actionability	Concrete executable guidance throughout: per-package-manager creation commands with explicit flags, complete browser-agent TypeScript, exact Studio routes, test cities, and named env vars. Anchor 4 fits due to minor gaps — the `model: '<provider>/<model>'` placeholder is unresolved and no provider-to-model mapping is given — so not 5.	4 / 5
Workflow Clarity	Steps 0-5 are clearly sequenced with explicit validation (Step 0 parameter validation with fail-and-show-usage behavior, Step 2 structure verification, ordered env-key resolution) plus per-section checklists and a troubleshooting feedback section. Matches anchor 5: explicit validation steps, feedback loops, and checklists for a complex process.	5 / 5
Progressive Disclosure	No bundle files exist and all ~350 lines are inline in one file. Sections are well organized, but the ~130-line Studio smoke-test checklist and route tables are natural candidates for a one-level-deep reference file. Matches anchor 3 (content that should be separate is inline); not 4 because nothing is split out.	3 / 5
	Total	15 / 20 Passed

Description

65%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 states two specific, tool-anchored actions in a distinct niche, but it completely lacks a "when to use" trigger clause, capping completeness, and its action coverage is narrow relative to what the skill body actually does. Adding an explicit trigger clause would lift the two weakest dimensions.

Suggestions

Append a trigger clause, e.g. "Use when asked to create, scaffold, or smoke test a Mastra project or to verify the Mastra Studio in a browser."

Broaden the action list slightly (e.g. mention verifying agents, tools, and workflows in the Studio) to move specificity from 1-2 actions toward several.

Add one or two natural synonyms such as "browser testing" or "QA" to strengthen trigger-term coverage.

Dimension	Reasoning	Score
Specificity	Two concrete, tool-named actions ("Create a Mastra project using create-mastra", "smoke test the studio in Chrome using Chrome MCP server") but coverage is not comprehensive — no mention of what is actually exercised (agents, tools, workflows, observability). Anchor 3 fits: 1-2 concrete actions without breadth; anchor 4 requires several listed actions.	3 / 5
Completeness	"What" is clear and concrete, but there is no "Use when..." or equivalent trigger clause, which caps completeness at 3 per the judging guidelines. Not 2 because the "what" is specific rather than vague.	3 / 5
Trigger Term Quality	Natural phrases a user would say are present: "Mastra", "create-mastra", "smoke test", "studio", "Chrome MCP server". Missing common synonyms such as "browser testing" or "QA", so not anchor 5; core natural terms are all covered, so above anchor 3.	4 / 5
Distinctiveness Conflict Risk	Highly niche combination (Mastra, create-mastra, Chrome MCP server) with distinct triggers and minimal conflict risk; the "Chrome MCP server" qualifier even separates it from the sibling mastracode-smoke-test variant mentioned in the body.	5 / 5
	Total	15 / 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: mastra-ai/mastra
Path: .claude/skills/smoke-test/SKILL.md
Commit: 3b0d190

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.