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'.

72

Quality

88%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

SecuritybySnyk

Passed

No findings from the security scan

SKILL.md
Quality
Evals
Security

Quality

Content

77%

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-sequenced investigation skill with specific tool calls and validation checkpoints. Its main weaknesses are verbosity in the inline root-cause narrative and reference-grade content that would be better split into a bundled reference file.

Suggestions

Tighten the Jun 2026 outage root-cause narrative into a concise signature plus a fix-link; the full IsPackable causal chain is reference material that bloats SKILL.md.

Move detailed reference-grade content (the nightly pipeline table and the MSB4019 root-cause analysis) into a bundled file under references/ and link to it one-level-deep instead of inlining it.

Reduce cross-section redundancy: pipeline names and definition IDs appear in both the 'MAUI CI facts' summary and the nightly section — defer to the canonical doc and reference them once.

DimensionReasoningScore

Conciseness

Mostly efficient and assumes competence (no generic CI/AzDO primer), but the Jun 2026 outage root-cause narrative is a long causal chain and pipeline names/IDs are restated across the facts and nightly sections.

2 / 3

Actionability

Provides concrete, parameterized MCP invocations ('azdo_builds with definitionId: 1095, branch: refs/heads/inflight/current', 'azdo_search_timeline', 'azdo_search_log'), a quoted MSB4019 signature, and exact definition IDs — copy-paste ready.

3 / 3

Workflow Clarity

Clear numbered 'Using this skill' sequence plus a nightly investigation chain, with explicit checkpoints (base-branch comparison, one-off vs streak confirmation, distinguish from release pipelines); read-only so no destructive-feedback-loop gap.

3 / 3

Progressive Disclosure

References to the canonical doc and sibling skills are well-signaled and one-level-deep, but reference-grade detail (the root-cause narrative, the full pipeline table) is inlined in SKILL.md and no bundle reference files ship alongside it.

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.

A strong, third-person description that crisply states capabilities and packs in natural trigger phrases for both PR and nightly-build investigation paths. It clearly distinguishes itself from generic CI skills.

DimensionReasoningScore

Specificity

Lists multiple concrete actions — 'Investigate CI failures', 'build errors, Helix test logs, and binlog analysis' — and names the domain (dotnet/maui PRs and nightly/official signed build).

3 / 3

Completeness

Explicitly answers both what (investigate CI failures, build/Helix/binlog analysis) and when via a clear 'Use when asked about...' clause with enumerated triggers.

3 / 3

Trigger Term Quality

Excellent coverage of natural maintainer phrases — 'why is CI red', 'build failed', 'is this PR ready to merge', 'nightly is broken', 'inflight feed stale', 'dogfood feed stopped updating'.

3 / 3

Distinctiveness Conflict Risk

Highly specific dotnet/maui CI niche with distinct triggers (Helix, inflight feed, dogfood feed) unlikely to fire for unrelated skills.

3 / 3

Total

12

/

12

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.

Validation15 / 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.