test-triage

Triage macOS tests across Xcode and SwiftPM. Use when narrowing failures, explaining assertions or crashes, or separating setup from regressions.

Quality

86%

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 tight, well-organized triage skill that respects token budget and structures content cleanly. Its main weakness is actionability and workflow rigor: rerun guidance and validation/feedback steps stay abstract rather than giving executable specifics.

Suggestions

Add concrete rerun syntax, e.g. `xcodebuild test -only-testing:TestSuite/ClassName/testMethod` and `swift test --filter ClassName.testMethod`, so the "Rerun intelligently" step is copy-paste ready.

Insert an explicit validation checkpoint after classification, e.g. "Re-run the single failing case in isolation; only treat it as a real failure if it reproduces twice," to add a validate→retry feedback loop.

Tighten the Guardrails into the classify/rerun steps (e.g. flag flakes during classification) so the workflow itself enforces them rather than listing them separately.

Dimension	Reasoning	Score
Conciseness	The body is lean and sectioned with no concept-explanation padding; it assumes Claude already knows xcodebuild/swift test and earns its tokens, matching the lean-and-efficient anchor rather than the score-2 anchor that retains unnecessary explanation.	3 / 3
Actionability	Provides concrete commands (`xcodebuild test`, `swift test`) and a six-category classification taxonomy, but the "Use focused reruns" guidance is abstract with no specific filter syntax such as `-only-testing:`, falling into the some-concrete-but-incomplete anchor rather than copy-paste-ready.	2 / 3
Workflow Clarity	The five steps are clearly sequenced (detect → narrow → classify → rerun → summarize), but there are no explicit validation checkpoints or a validate→fix→retry feedback loop, matching the steps-listed-but-checkpoints-missing anchor instead of the score-3 anchor.	2 / 3
Progressive Disclosure	A short single-purpose skill with no bundle files and clear sections (Quick Start, Workflow, Guardrails, Output Expectations); per the under-50-line guideline, well-organized sections alone warrant the top score here.	3 / 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.

A strong, concise description: it names a clear niche, lists concrete actions, and pairs a what statement with an explicit Use-when trigger in third person. No vague fluff or over-claims.

Dimension	Reasoning	Score
Specificity	Lists multiple concrete actions — "narrowing failures, explaining assertions or crashes, or separating setup from regressions" — beyond the headline "Triage" verb, matching the multiple-specific-actions anchor rather than the partial score-2 anchor.	3 / 3
Completeness	Explicitly states what it does ("Triage macOS tests across Xcode and SwiftPM") and when to use it via a "Use when..." clause, satisfying both halves rather than the score-2 "what only" anchor.	3 / 3
Trigger Term Quality	Uses natural terms a user would say when needing this skill (failures, assertions, crashes, setup, regressions, Xcode, SwiftPM); it is above score 2 because it covers several common variations rather than a single keyword.	3 / 3
Distinctiveness Conflict Risk	The macOS-test / Xcode / SwiftPM niche with distinct triage triggers is clearly separable from other skills and unlikely to fire for the wrong one.	3 / 3
	Total	12 / 12 Passed

Validation

100%

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 — 16 / 16 Passed

Validation for skill structure

No warnings or errors.

Repository: openai/plugins
Path: plugins/build-macos-apps/skills/test-triage/SKILL.md
Commit: 11c74d6

Reviewed: about 14 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.