smoke-test

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

Quality

69%

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%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 content is highly actionable with a clearly sequenced, validated workflow and concrete commands, but it is a monolithic ~350-line file with redundant sections and no progressive disclosure to reference files. Trimming duplication and splitting the checklist/route/troubleshooting material into referenced files would materially improve it.

Suggestions

Remove redundancy: delete the Studio Routes table (routes are already enumerated in the 5.2 checklist) and collapse the Quick Reference table into the step prose, or vice versa.

Move the detailed 5.2 smoke-test checklist, the route reference, and Troubleshooting into one-level-deep reference files (e.g. references/smoke-checklist.md, references/troubleshooting.md) linked from the body, since no bundle files currently exist.

Tighten the Notes section, which restates Step 1 guidance already covered inline.

Dimension	Reasoning	Score
Conciseness	The body is mostly efficient and free of concept-explanation fluff, but it carries clear redundancy: the Studio Routes table duplicates routes already named in the 5.2 checklist, the Quick Reference table restates the execution steps, and the Notes restate Step 1 guidance; it could be tightened without losing clarity, landing at the "could be tightened" anchor rather than the verbose one below.	3 / 5
Actionability	Guidance is fully executable: package-manager-specific create commands for npm/yarn/pnpm/bun, a complete browser-agent TypeScript snippet, concrete env-var checks, a dev command, and a smoke-test checklist with specific inputs ("Tokyo", "London", "What's the weather in Tokyo?"), covering the common cases copy-paste ready.	5 / 5
Workflow Clarity	Steps 0-5 are explicitly sequenced with a mandatory Step 0 parameter validation, structural verification in Step 2, a server-ready wait in Step 4, a per-page verification checklist in 5.2, and a troubleshooting section providing error-recovery feedback loops; this matches the clear-sequence-with-validation-and-checklists anchor.	5 / 5
Progressive Disclosure	The body is well-sectioned with clear headers, but at ~350 lines everything is inlined in a single SKILL.md with no reference files (references/, scripts/, assets/ are absent); the detailed smoke-test checklist, route table, and troubleshooting are candidates for one-level-deep separate files, so it sits at the "structure present but content that should be separate is inline" anchor rather than the well-split anchor above.	3 / 5
	Total	16 / 20 Passed

Description

61%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 concrete and domain-specific but omits any explicit trigger guidance, which limits its completeness and distinctiveness. Adding a "Use when..." clause and disambiguating from the sibling mastracode skill would lift it into the top band.

Suggestions

Append an explicit trigger clause, e.g. "Use when the user wants to scaffold a Mastra project and verify the Studio UI end-to-end in Chrome."

Disambiguate from the sibling skill in the description itself (e.g. "For MastraCode's built-in browser, use mastracode-smoke-test") rather than only in the body.

Expand the action list slightly (e.g. mention scaffolding agents/tools/workflows via the managed template) to push specificity toward comprehensive coverage.

Dimension	Reasoning	Score
Specificity	Names the domain and two concrete actions ("Create a Mastra project" and "smoke test the studio in Chrome") but does not enumerate the fuller set of actions the skill performs, so it stops at the 1-2-actions anchor rather than the comprehensive-coverage anchor above.	3 / 5
Completeness	It clearly states what the skill does but has no "Use when..." clause or equivalent explicit trigger guidance, which per the guidelines caps completeness at 3; the "when" is only weakly implied by the verb "smoke test".	3 / 5
Trigger Term Quality	Good coverage of the niche terms a Mastra developer would actually say ("create-mastra", "smoke test", "studio", "Chrome MCP server"), just missing a few natural variations; it is above the "some relevant keywords" anchor but not fully comprehensive enough for a 5.	4 / 5
Distinctiveness Conflict Risk	The Mastra + Chrome MCP niche is mostly distinct, but the body references a sibling `mastracode-smoke-test` skill covering the same task for a different runtime, creating minor overlap risk; not the clear-minimal-conflict anchor of 5.	4 / 5
	Total	14 / 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: d6ce34a

Reviewed: about 18 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.