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'.

68

Quality

83%

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

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.

The body is a well-structured, actionable overview that leans correctly on a canonical facts doc and sibling skills, with concrete MCP tool invocations and real error signatures. Its main weakness is conciseness: a time-sensitive, verbose root-cause narrative is inlined where a pointer would do.

Suggestions

Move the detailed Jun 2026 inflight/current root-cause analysis (PR numbers, commit hash, full IsPackable mechanism) into '.github/docs/maui-ci-facts.md' and keep only the triage signal ('Pack Windows / Build Workloads, Sign & Publish fails with MSB4019 on vs-workload.props') plus a link in SKILL.md.

Tighten the nightly section's prose: the table and the three-step AzDO flow are strong, but the surrounding explanatory paragraphs repeat pipeline-name facts already covered in the canonical doc.

Consider adding a one-line explicit checkpoint in the 'Using this skill' flow (e.g. 'Confirm failure is red on base branch before declaring Not ready') to make the existing base-branch comparison an unmistakable validation step.

DimensionReasoningScore

Conciseness

The body is mostly efficient and avoids explaining concepts Claude already knows, but the inline Jun 2026 inflight/current root-cause narrative (PR numbers #36089/#32203, commit hash 543b1ebeb7, full IsPackable mechanism) is time-sensitive detail that could be tightened and moved to the canonical doc.

3 / 5

Actionability

Provides concrete, real guidance — MCP calls ('azdo_builds' with 'definitionId: 1095', 'azdo_search_timeline', 'azdo_search_log'), a verbatim error signature ('error MSB4019 ... vs-workload.props was not found'), and real pipeline paths — with minor gaps from delegating the core workflow to the ci-analysis skill and canonical doc.

4 / 5

Workflow Clarity

A clear 4-step 'Using this skill' sequence plus a 3-step nightly investigation flow (azdo_builds -> azdo_search_timeline -> azdo_search_log), with the merge-readiness criteria acting as an explicit decision checkpoint; minor validation gaps remain but no destructive operations are involved.

4 / 5

Progressive Disclosure

Good structure with well-signaled, one-level-deep references ('.github/docs/maui-ci-facts.md', the 'ci-analysis' skill, 'helix-investigation' escalation) and no nested reference chains; the minor gap is the inlined nightly root-cause detail that could be split into the canonical doc.

4 / 5

Total

15

/

20

Passed

Description

100%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.

The description is exemplary: third-person voice, concrete actions, comprehensive natural trigger phrases, and an explicit 'Use when' clause covering both the PR and nightly-build surfaces. It clearly communicates both capability and invocation conditions with minimal conflict risk.

DimensionReasoningScore

Specificity

Lists multiple concrete actions — 'build errors, Helix test logs, and binlog analysis' — across both the PR and nightly/official-build investigation surfaces, giving comprehensive coverage of the CI failure surface.

5 / 5

Completeness

Explicitly answers 'what' ('Investigate CI failures for dotnet/maui PRs and the nightly/official signed build') and 'when' via a clear 'Use when...' clause packed with concrete trigger phrases.

5 / 5

Trigger Term Quality

Comprehensive natural phrasing including exact user quotes ('why is CI red', 'build failed', 'is this PR ready to merge', 'nightly is broken', 'inflight feed stale', 'dogfood feed stopped updating') plus synonyms, which is what a maintainer would actually say.

5 / 5

Distinctiveness Conflict Risk

Tightly scoped to dotnet/maui CI investigation with distinct, niche-specific triggers, so overlap with other skills is minimal.

5 / 5

Total

20

/

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.

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.