smoke-check

Run the critical path smoke test gate before QA hand-off. Executes the automated test suite, verifies core functionality, and produces a PASS/FAIL report. Run after a sprint's stories are implemented and before manual QA begins. A failed smoke check means the build is not ready for QA.

Quality

88%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

Passed

No findings from the security scan

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 with a clear, well-validated multi-phase workflow, but it is verbose due to repeated boilerplate and monolithic: all platform batches and the report template are inline with no progressive disclosure to supporting files.

Suggestions

Extract the per-platform AskUserQuestion batches and the full Phase 5 report template into reference files (e.g. references/platform-batches.md, references/report-template.md) and link to them, reducing inline bulk and enabling progressive disclosure.

De-duplicate the repeated 'ask the user to briefly describe what failed' boilerplate by stating the convention once and referencing it, and consolidate the NOT RUN rule to a single authoritative location instead of Phase 2 plus the Collaborative Protocol.

Tighten the Phase 6 gate messaging, which restates the Phase 5 verdict rules; reference the rules once and focus Phase 6 on the hand-off instructions.

Dimension	Reasoning	Score
Conciseness	Mostly efficient and free of concept-explanation fluff, but repeats boilerplate ('For any selected item, ask the user to briefly describe what failed before generating the report' appears 5+ times) and restates the NOT RUN rule and verdict/gate messaging across multiple sections.	2 / 3
Actionability	Provides concrete, executable guidance throughout — per-engine bash commands, exact AskUserQuestion batch definitions with specified options, a fill-in report template, and explicit copy-paste-ready verdict rules.	3 / 3
Workflow Clarity	A clear six-phase sequence with explicit validation checkpoints (report findings before proceeding, verdict rules with 'first matching rule wins', approval gate before writing) and feedback loops, satisfying the validation requirement for batch operations.	3 / 3
Progressive Disclosure	Well-organized into phases, but it is a single monolithic ~414-line document with no bundle files and no references — content that could be split (per-platform batches, the full report template, engine-specific commands) is inline rather than progressively disclosed.	2 / 3
	Total	10 / 12 Passed

Description

100%

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, complete, and distinctive, clearly stating both what the skill does and when to invoke it using natural trigger terms. It uses correct third-person voice throughout with no over-claims.

Dimension	Reasoning	Score
Specificity	Lists multiple concrete actions — 'Executes the automated test suite, verifies core functionality, and produces a PASS/FAIL report' — going beyond a single domain action to enumerate execute, verify, and produce.	3 / 3
Completeness	Explicitly answers both what ('Executes the automated test suite, verifies core functionality, and produces a PASS/FAIL report') and when ('Run after a sprint's stories are implemented and before manual QA begins'), with explicit trigger guidance.	3 / 3
Trigger Term Quality	Uses natural terms a PM or developer would say — 'smoke test', 'QA hand-off', 'automated test suite', 'PASS/FAIL report', 'sprint's stories', 'manual QA' — with good coverage of variations.	3 / 3
Distinctiveness Conflict Risk	Occupies a clear niche — a critical-path smoke-test gate before QA hand-off in a sprint/game-dev context — with distinct triggers unlikely to conflict with general testing skills.	3 / 3
	Total	12 / 12 Passed

Validation

87%

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 — 14 / 16 Passed

Validation for skill structure

Criteria	Description	Result
allowed_tools_field	'allowed-tools' contains unusual tool name(s)	Warning
frontmatter_unknown_keys	Unknown frontmatter key(s) found; consider removing or moving to metadata	Warning

	Total	14 / 16 Passed

Repository: Donchitos/Claude-Code-Game-Studios
Path: .claude/skills/smoke-check/SKILL.md
Commit: 984023d

Reviewed: 3 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.