testing

Use this skill when running or writing tests in the FAST monorepo — local test execution, CI workflows, Playwright fixtures, and WebUI integration testing.

Quality

82%

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

72%

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

A highly actionable, well-organized testing guide with copy-paste commands and a clear fixture reference. It loses points on conciseness (mild explanatory padding) and workflow clarity (no explicit validation feedback loops in its multi-step workflows).

Suggestions

Trim explanations of concepts Claude already knows (e.g. the Playwright UI mode sentence) and drop filler like 'This ensures cross-platform and cross-browser compatibility.'.

Add an explicit validation checkpoint to the multi-step workflows, e.g. after running tests locally: 'Confirm all specs pass before pushing; if a spec fails, debug via Playwright UI mode before re-running.'

For the webui-integration trigger sequence, add a verification step such as 'Check the Actions run status and review the trace on failure' to close the feedback loop.

Dimension	Reasoning	Score
Conciseness	Mostly efficient command tables and CI facts, but includes explanatory padding Claude already knows (e.g. what Playwright UI mode does) and a redundant 'This ensures cross-platform and cross-browser compatibility' sentence.	2 / 3
Actionability	Provides fully executable, copy-paste-ready commands (npm run test, npx playwright install, lage --since) and a complete runnable TypeScript spec example.	3 / 3
Workflow Clarity	Sequences like first-time setup and triggering webui CI are clearly numbered, but there are no explicit validation checkpoints or error-recovery feedback loops, so it does not reach a 3.	2 / 3
Progressive Disclosure	Well-organized into Running/Writing sections and offloads the deep fixture guide to one clearly-signaled, one-level reference (WRITING_FIXTURES.md) rather than nesting references.	3 / 3
	Total	10 / 12 Passed

Description

92%

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, well-structured description that clearly pairs a 'Use when' trigger with concrete capabilities and natural keywords. Its only weakness is the somewhat generic testing trigger, which creates mild overlap risk with other testing skills.

Suggestions

Tighten the trigger to reference the FAST-specific stack more strongly (e.g. 'Use when running or writing Playwright integration tests or CI workflows in the FAST monorepo') to reduce overlap with generic testing skills.

Consider naming the monorepo's test runner up front so the trigger reads as FAST-internal rather than a general testing skill.

Dimension	Reasoning	Score
Specificity	Names multiple concrete actions — 'running or writing tests', 'local test execution', 'CI workflows', 'Playwright fixtures', and 'WebUI integration testing' — matching the anchor for listing several specific capabilities.	3 / 3
Completeness	Explicitly states both what the skill does and when to use it via the 'Use this skill when running or writing tests in the FAST monorepo' trigger clause.	3 / 3
Trigger Term Quality	Includes natural terms users would say ('running or writing tests', 'Playwright', 'CI workflows') with good coverage rather than technical jargon.	3 / 3
Distinctiveness Conflict Risk	Scoped to the FAST monorepo with a distinct tech stack, but the trigger 'running or writing tests' is generic and could overlap with other testing skills, so it is not a 3.	2 / 3
	Total	11 / 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
relative_links	Relative link issues: 1 suspicious	Warning

	Total	15 / 16 Passed

Repository: microsoft/fast
Path: .github/skills/testing/SKILL.md
Commit: 27a4304

Reviewed: 1 day 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.