CtrlK
BlogDocsLog inGet started
Tessl Logo

azdo-build-investigator

Investigate CI failures for dotnet/maui PRs and the nightly/official signed build — build errors, Helix test logs, and binlog analysis. Use when asked about failing checks, CI status, test failures, 'why is CI red', 'build failed', 'what's failing on PR', 'is this PR ready to merge', Helix failures, device test failures, or 'nightly is broken', 'nightly build failing', 'inflight feed stale', 'dogfood feed stopped updating', 'official build failed'.

67

Quality

81%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

SecuritybySnyk

Low

Low-risk findings worth noting

SKILL.md
Quality
Evals
Security

Quality

Content

67%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.

A well-structured, operationally rich investigation skill that delegates MAUI facts to a canonical doc and gives concrete parameterized commands for the nightly-build path. Its main weakness is the long inlined historical root-cause narrative, which costs conciseness and would sit better in a separate reference.

Suggestions

Move the Jun 2026 inflight/current outage root-cause narrative (PR #32203, commit 543b1ebeb7, #36089) into a dated reference file or the canonical doc, keeping only the recurring MSB4019 signature and the short triage lesson ('confirm IsPackable evaluates true in pack.binlog and that _GenerateVSWorkloadProps ran') inline.

Add a fallback for the nightly path when internal AzDO access is unavailable (e.g., who to page or what anonymous signal can substitute), since definition 1095 requires dnceng/internal.

Tighten the MAUI CI facts bullet list — it previews the canonical doc's contents at length; a shorter pointer would preserve navigation while cutting tokens.

DimensionReasoningScore

Conciseness

The body is mostly lean — MAUI facts are delegated to the canonical doc ('Do not restate those facts from memory') and the nightly section is dense with operational specifics. However, the ~250-word 'Root cause of the Jun 2026 inflight/current outage' paragraph inlines time-sensitive historical narrative (PR numbers, commit hash 543b1ebeb7, dates) that is not placed in an 'old patterns'/'deprecated' section and could be tightened or split out.

3 / 5

Actionability

Concrete parameterized tool calls ('azdo_builds with definitionId: 1095, branch: refs/heads/inflight/current', 'azdo_search_timeline (filter failed)'), exact pipeline IDs, an exact recurring error signature (MSB4019 vs-workload.props), and file paths make the nightly path near copy-paste ready. Minor gap: the most common case (PR investigation) delegates execution to the ci-analysis skill and the canonical doc rather than showing runnable commands itself.

4 / 5

Workflow Clarity

'Using this skill' gives a numbered 1–4 sequence with escalation, and the nightly section is an explicit three-step chain (azdo_builds → azdo_search_timeline → azdo_search_log) plus 'confirm whether it's a one-off or a multi-day streak'. Validation cross-checks exist (baseline comparison, XHarness exit-0, binlog IsPackable check), but there are minor gaps — e.g., no guidance when internal AzDO access is unavailable for definition 1095.

4 / 5

Progressive Disclosure

No bundle files exist; the single external reference ('.github/docs/maui-ci-facts.md — read it') is clearly signaled, one level deep, with an itemized coverage list, and sections are well organized. The inlined Jun 2026 outage root-cause narrative is content that arguably belongs in a separate reference file, keeping this a 4 rather than a 5.

4 / 5

Total

15

/

20

Passed

Description

95%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.

A strong description: concrete capabilities, explicit and comprehensive 'Use when' trigger phrases, third-person voice, and a well-scoped niche that minimizes conflict risk. Only minor specificity headroom remains.

DimensionReasoningScore

Specificity

'Investigate CI failures for dotnet/maui PRs and the nightly/official signed build — build errors, Helix test logs, and binlog analysis' names the domain and several concrete capabilities. It lists three concrete action areas rather than a comprehensive set (e.g., no mention of the merge-readiness verdict or baseline comparison), so it fits 'several specific actions; minor gaps in coverage' (4) rather than the comprehensive 5 anchor.

4 / 5

Completeness

It explicitly answers what ('Investigate CI failures for dotnet/maui PRs and the nightly/official signed build — build errors, Helix test logs, and binlog analysis') and when ('Use when asked about failing checks, CI status, test failures...'), with concrete trigger phrases — matching the top anchor.

5 / 5

Trigger Term Quality

The 'Use when' clause packs natural user phrasings with synonyms: 'why is CI red', 'build failed', 'what's failing on PR', 'is this PR ready to merge', 'Helix failures', 'nightly is broken', 'inflight feed stale', 'dogfood feed stopped updating', 'official build failed'. Coverage is comprehensive — these are exactly the phrases a maintainer would type.

5 / 5

Distinctiveness Conflict Risk

The niche is tightly scoped by product-specific signals (dotnet/maui, Helix, inflight feed, dogfood feed, devicetests) so it is clearly distinguishable from generic CI skills and unlikely to fire for the wrong one.

5 / 5

Total

19

/

20

Passed

Validation

93%

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

CriteriaDescriptionResult

relative_links

Relative link issues: 2 suspicious

Warning

Total

15

/

16

Passed

Repository
dotnet/maui
Reviewed

Table of Contents

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.