CtrlK
BlogDocsLog inGet started
Tessl Logo

macios-ci-failure-inspector

Investigate and triage CI failures for dotnet/macios from Azure DevOps build URLs. Use this skill whenever the user shares a DevOps build link, asks about CI failures, wants to understand why a build failed, or asks to investigate test failures on any platform (iOS, tvOS, macOS, Mac Catalyst). Also use when the user says things like "CI is red", "tests are failing", "build broke", or "what happened in CI".

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

Low

Low-risk findings worth noting

SKILL.md
Quality
Evals
Security

Quality

Content

82%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 thorough, highly actionable CI investigation workflow with executable code at every phase and clear sequencing. Could be tightened by offloading the duplicated artifact-name/JSON-parsing detail to the existing reference file.

Suggestions

Move the full artifact-name-to-job mapping table and the json.JSONDecoder().raw_decode() caveat into references/azure-devops-cli.md, keeping only a pointer inline to reduce duplication.

Trim transitional prose like "Download these in parallel for all failing jobs to save time" to bare directives.

Add an explicit verification checkpoint in Phase 6 confirming all failing jobs from the timeline are accounted for before reporting.

DimensionReasoningScore

Conciseness

Mostly lean and executable without explaining concepts Claude already knows, with minor padding (e.g., "to save time", transitional prose) that could be trimmed.

4 / 5

Actionability

Fully copy-paste-ready bash and Python with specific artifact names, logId handling, JSON-parsing caveats, and grep patterns covering the common failure cases.

5 / 5

Workflow Clarity

Clear 6-phase sequence with explicit checkpoints ("If the build succeeded, tell the user and stop"; "Always start with these before digging into raw logs"); non-destructive inspection work, but the report phase lacks an explicit completeness verification step.

4 / 5

Progressive Disclosure

One clearly signaled one-level-deep reference (azure-devops-cli.md) confirmed present, but the artifact-name mapping table and JSON parsing caveats are duplicated inline rather than deferred to the reference.

4 / 5

Total

17

/

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, well-structured description that clearly states both capability and explicit invocation triggers with natural user phrasings. Minor room to sharpen the distinct concrete actions beyond the investigate/triage verbs.

DimensionReasoningScore

Specificity

Names the domain (dotnet/macios CI failures) and several concrete actions (investigate, triage, understand why a build failed), though the verbs overlap rather than enumerating distinct capabilities.

4 / 5

Completeness

Explicitly answers both what ("Investigate and triage CI failures for dotnet/macios from Azure DevOps build URLs") and when ("Use this skill whenever the user shares a DevOps build link…") with concrete triggers.

5 / 5

Trigger Term Quality

Comprehensive natural trigger phrases including user-quoted synonyms ("CI is red", "tests are failing", "build broke", "what happened in CI") alongside platform names.

5 / 5

Distinctiveness Conflict Risk

Scoped tightly to dotnet/macios and Azure DevOps build URLs, creating a clear niche with minimal risk of triggering for unrelated skills.

5 / 5

Total

19

/

20

Passed

Validation

100%

Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.

Validation16 / 16 Passed

Validation for skill structure

No warnings or errors.

Repository
dotnet/macios
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.