review-test-failures

Classifies PR CI/test failures as likely PR-caused or unrelated, compares against base-branch baseline, and emits an overall merge-readiness verdict. Uses gathered GitHub/AzDO/Helix context and the shared MAUI CI facts.

Quality

72%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

Critical

Do not install without reviewing

Fix and improve this skill with Tessl

tessl review fix ./.github/skills/review-test-failures/SKILL.md

Quality

Content

77%

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

This is a highly actionable, well-sequenced skill with strong validation gates and a precise output contract, but it is verbose and repeats its ceiling-cap rules across sections while keeping most reference material inline rather than split into bundle files.

Suggestions

Deduplicate the verdict-ceiling cap rules: state the full gate.* semantics once in Inputs and reference it from the Overall-verdict and Output-format sections instead of restating the 'any value > 0 caps the ceiling' list multiple times.

Move the long per-field reference documentation for failures.unique.* into a referenced reference file, keeping the body as a lean overview that points to it, to improve progressive disclosure and token efficiency.

Dimension	Reasoning	Score
Conciseness	The body is dense domain-specific guidance Claude would not already know (MAUI CI quirks, gate semantics), but at ~400 lines it repeats the same ceiling-cap rules verbatim across multiple sections (Inputs, Overall verdict, Output format), which keeps it at the mostly-efficient-but-could-be-tightened anchor rather than the lean anchor.	2 / 3
Actionability	It provides a complete, copy-paste-ready output template with stable marker, badges, a per-failure table schema, and a precise field-by-field data contract (gate., failures.unique.), giving fully executable, specific guidance.	3 / 3
Workflow Clarity	The process is explicitly sequenced (classify each failure -> baseline comparison -> synthesize one verdict) with hard validation checkpoints, notably the deterministic verdict-ceiling rule ('MUST NOT be more favorable than gate.verdictCeiling') and a favorability ordering, matching the clear-sequence-with-explicit-validation anchor.	3 / 3
Progressive Disclosure	It correctly pushes detail one level deep to referenced files ('.github/docs/maui-ci-facts.md', the gatherer script in scripts/) that exist in the bundle, but the body itself is a near-400-line monolithic wall of inline reference material that could be split, so it sits at the some-structure-but-could-be-better-organized anchor.	2 / 3
	Total	10 / 12 Passed

Description

67%

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 and distinctive, naming concrete classification, baseline-comparison, and verdict actions within a narrow MAUI CI niche. Its main weakness is the absence of an explicit 'Use when...' trigger clause, which caps completeness and trigger-term quality at 2.

Suggestions

Add an explicit 'Use when...' trigger clause naming the natural phrases users would say, e.g. 'Use when reviewing whether a PR's failing CI checks or tests are caused by the PR or are pre-existing/flaky.'

Include common trigger-term variations such as 'test failures', 'CI failures', 'flaky tests', and 'merge readiness' so the description matches how users actually phrase the request.

Dimension	Reasoning	Score
Specificity	Lists multiple concrete actions — 'Classifies PR CI/test failures as likely PR-caused or unrelated', 'compares against base-branch baseline', and 'emits an overall merge-readiness verdict' — matching the multiple-specific-actions anchor.	3 / 3
Completeness	It clearly answers 'what does this do' but never states 'when should Claude use it' with an explicit trigger clause; per the judging guidelines a missing 'Use when...' clause caps completeness at 2.	2 / 3
Trigger Term Quality	Contains some relevant keywords ('PR CI/test failures', 'merge-readiness') a user might say, but lacks natural common variations and has no explicit 'Use when...' trigger phrasing, so it stops at the some-relevant-keywords anchor rather than the good-coverage anchor.	2 / 3
Distinctiveness Conflict Risk	The niche is sharply scoped to dotnet-maui PR CI test-failure triage and explicitly contrasts itself with the sibling 'azdo-build-investigator' skill, making it clearly distinguishable and unlikely to trigger for the wrong skill.	3 / 3
	Total	10 / 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: dotnet/maui
Path: .github/skills/review-test-failures/SKILL.md
Commit: 6a24ec5

Reviewed: 4 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.