Loading skill
Install any skill in seconds. Free to start, no credit card required.
Get Started Free →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
.claude/skills/file-test-bug/SKILL.md| Test case | Without → With | Effect | Δ tokens | Δ turns |
|---|---|---|---|---|
| case-04 | ✗→✓ | ▲ Improved | 34% | 0% |
| case-09 | ✗→✓ | ▲ Improved | 140% | 0% |
| case-11 | ✓→✓ | ＝ Same ✓ | 5% | 0% |
| case-12 | ✓→✓ | ＝ Same ✓ | 149% | 0% |
| case-13 | ✓→✓ | ＝ Same ✓ | 212% | 0% |
Creates a GitHub issue in microsoft/github-copilot-for-azure for integration test failures.
azure-ai, appinsights-instrumentationtests/reports/junit.xml for failures matching the skillagent-metadata.md from tests/reports/test-run-<timestamp>/<skillname>-<testname>/github-mcp-server-create_issue:owner: microsoft
repo: github-copilot-for-azure
title: Integration test failure in <skill-name>
labels: ["bug", "integration-test"]
body: |
## Failed Tests
- <test-name>: <error message>
## Diagnosis
### Root Cause
<1-2 sentences explaining WHY the test failed based on agent-metadata.md analysis>
### Analysis per Test
- **<test-name>**: <what agent did vs what test expected>
### Suggested Fix
<one of: update skill, update test assertions, provide test fixtures>
## Details
### <test-name>
**Error:** <failure from junit.xml>
**Location:** <file:line>
```typescript
<actual line of code from the test file at the specified line number>
```
<details>
<summary>agent-metadata.md</summary>
<full contents of agent-metadata.md file, verbatim>
</details>Include the complete, unmodified contents of each agent-metadata.md file in the issue body. Do NOT summarize or truncate the logs. Wrap each log in a <details> block with the test name as the summary.
| Case | Status | Duration (ms) | Turns | Tokens | Tool calls | ||||||||
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| Without | With | Δ | Without | With | Δ | Without | With | Δ | Without | With | Δ | ||
case-08 | fail→fail | 6,434 | 6,232 | -3% | 1 | 1 | 0% | 1,001 | 1,029 | +3% | 0 | 0 | — |
case-01 | fail→fail | 8,366 | 4,700 | -44% | 1 | 1 | 0% | 1,476 | 884 | -40% | 0 | 0 | — |
case-02 | fail→fail | 15,608 | 9,011 | -42% | 1 | 1 | 0% | 2,756 | 1,239 | -55% | 0 | 0 | — |
case-03 | fail→fail | 13,101 | 7,044 | -46% | 1 | 1 | 0% | 2,310 | 1,052 | -54% | 0 | 0 | — |
case-04 | fail→pass | 4,612 | 2,680 | -42% | 1 | 1 | 0% | 775 | 1,040 | +34% | 0 | 0 | — |
case-05 | fail→fail | 11,600 | 34,052 | +194% | 1 | 1 | 0% | 1,743 | 1,019 | -42% | 0 | 0 | — |
case-06 | fail→fail | 8,280 | 6,753 | -18% | 1 | 1 | 0% | 1,352 | 1,185 | -12% | 0 | 0 | — |
case-07 | fail→fail | 4,423 | 7,913 | +79% | 1 | 1 | 0% | 700 | 1,176 | +68% | 0 | 0 | — |
case-09 | fail→pass | 8,965 | 14,864 | +66% | 1 | 1 | 0% | 1,454 | 3,490 | +140% | 0 | 0 | — |
case-10 | fail→fail | 6,633 | 4,213 | -36% | 1 | 1 | 0% | 1,085 | 821 | -24% | 0 | 0 | — |
case-11 | pass→pass | 8,063 | 8,716 | +8% | 1 | 1 | 0% | 1,382 | 1,448 | +5% | 0 | 0 | — |
case-12 | pass→pass | 7,007 | 11,663 | +66% | 1 | 1 | 0% | 1,123 | 2,801 | +149% | 0 | 0 | — |
case-22 | fail→fail | 13,310 | 4,643 | -65% | 1 | 1 | 0% | 2,122 | 908 | -57% | 0 | 0 | — |
case-13 | pass→pass | 2,634 | 3,864 | +47% | 1 | 1 | 0% | 409 | 1,278 | +212% | 0 | 0 | — |
case-14 | fail→fail | 6,662 | 15,798 | +137% | 1 | 1 | 0% | 1,054 | 3,995 | +279% | 0 | 0 | — |
case-15 | fail→fail | 4,472 | 9,879 | +121% | 1 | 1 | 0% | 727 | 1,591 | +119% | 0 | 0 | — |
case-16 | fail→fail | 6,556 | 6,082 | -7% | 1 | 1 | 0% | 1,128 | 1,034 | -8% | 0 | 0 | — |
case-17 | fail→fail | 7,575 | 6,199 | -18% | 1 | 1 | 0% | 1,155 | 1,045 | -10% | 0 | 0 | — |
case-18 | fail→fail | 1,785 | 12,677 | +610% | 1 | 1 | 0% | 237 | 2,742 | +1057% | 0 | 0 | — |
case-19 | fail→fail | 17,105 | 5,624 | -67% | 1 | 1 | 0% | 2,856 | 1,106 | -61% | 0 | 0 | — |
case-20 | fail→fail | 6,719 | 9,127 | +36% | 1 | 1 | 0% | 1,123 | 956 | -15% | 0 | 0 | — |
case-21 | fail→fail | 11,103 | 5,711 | -49% | 1 | 1 | 0% | 1,666 | 963 | -42% | 0 | 0 | — |
DecimalAI ran this skill against gemini-3.6-flash twice over the same eval suite — once with the skill loaded and once without — and compared the two runs case by case. 22 cases were attempted, and 9 counted toward the lift figure. The other 13 produced results that are not comparable between the two arms, so they are excluded from the headline rather than averaged into it. The headline lift of +9 percentage points is the difference between those two pass rates over the 9 comparable cases.
Without the skill loaded, the model failed this case. With it loaded, the same prompt on the same model passed. This is one improved case from the latest verified run; every case, including any that regressed, is in the table above.
| Model | Method | Date | Lift |
|---|---|---|---|
| gemini-3.6-flash | verified | 7/23/2026 | — |
Other measured skills in the registry, with their headline benchmark lift.