CtrlK
BlogDocsLog inGet started
Tessl Logo

file-test-bug

File a GitHub issue for local integration test failures. TRIGGERS: file test bug, report test failure, create bug for test, integration test failed, test failure issue, junit failure

93

2.02x
Quality

95%

Does it follow best practices?

Impact

81%

2.02x

Average score across 3 eval scenarios

SecuritybySnyk

Risky

Do not use without reviewing

SKILL.md
Quality
Evals
Security

Evaluation results

66%

29%

CI Failure Analysis: Azure RBAC Skill

Pre-diagnosis and root cause workflow

Criteria
Without context
With context

Reads junit.xml

50%

100%

Finds most recent test run

62%

100%

Reads agent-metadata.md path

100%

100%

Reads agent-metadata.md for test 2

100%

100%

Extracts test 1 assertion line

0%

0%

Extracts test 2 assertion line

0%

0%

Root cause categorized

0%

50%

2-3 sentences per failure

0%

50%

Covers both failures

100%

100%

Suggested fix category

0%

100%

88%

49%

File GitHub Issue: AppInsights Instrumentation Test Failure

GitHub issue structure and labeling

Criteria
Without context
With context

Correct tool name

0%

0%

Owner: microsoft

100%

100%

Repo: github-copilot-for-azure

100%

100%

Title format

0%

100%

Label: bug

100%

100%

Label: integration-test

0%

100%

Failed Tests section

0%

100%

Diagnosis section

0%

100%

Suggested Fix section

70%

100%

Details section with location

0%

100%

TypeScript code block

100%

100%

90%

45%

Bug Report: Azure Storage Skill Integration Failures

Agent metadata verbatim inclusion

Criteria
Without context
With context

Test 1 metadata present

100%

100%

Test 2 metadata present

100%

100%

Test 1 metadata verbatim

0%

100%

Test 2 metadata verbatim

0%

100%

Details blocks used

0%

100%

Details summary is test name

0%

0%

No truncation

100%

100%

Repository
microsoft/github-copilot-for-azure
Evaluated
Agent
Claude Code
Model
Claude Sonnet 4.6

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.