https://github.com/zavora-ai/skill-test-execution
Test execution skill — unit, integration, E2E tests, coverage, and failure analysis via mcp-test-runner
https://github.com/zavora-ai/skill-test-execution
adk-rust agent-skills claude-skills coverage enterprise mcp quality testing
Last synced: 3 days ago
JSON representation
Test execution skill — unit, integration, E2E tests, coverage, and failure analysis via mcp-test-runner
- Host: GitHub
- URL: https://github.com/zavora-ai/skill-test-execution
- Owner: zavora-ai
- License: other
- Created: 2026-05-25T04:35:28.000Z (25 days ago)
- Default Branch: main
- Last Pushed: 2026-05-25T05:08:09.000Z (25 days ago)
- Last Synced: 2026-05-25T07:11:08.398Z (24 days ago)
- Topics: adk-rust, agent-skills, claude-skills, coverage, enterprise, mcp, quality, testing
- Size: 2.93 KB
- Stars: 0
- Watchers: 0
- Forks: 0
- Open Issues: 0
-
Metadata Files:
- Readme: README.md
- License: LICENSE
Awesome Lists containing this project
README
# Test Execution Skill
> Test operations for AI agents — run unit/integration/E2E tests, track coverage deltas, debug failures, and gate merges on quality via mcp-test-runner.
[](https://agentskills.io)
[](https://github.com/zavora-ai/mcp-test-runner)
[](https://enterprise.adk-rust.com)
[](LICENSE)
## What This Skill Does
| Workflow | Tool Calls | What It Achieves |
|----------|-----------|------------------|
| Pre-Merge Validation | 3 | Unit + coverage + integration |
| Debug Failure | 2 | Identify test + root cause |
| Targeted Tests | 1 | Run specific file/pattern |
### Without this skill:
- Tests skipped "to save time"
- Coverage decreases go unnoticed
- Flaky tests rerun endlessly without investigation
- No coverage delta reporting (just absolute numbers)
### With this skill:
- Tests always run before merge approval
- Coverage delta tracked (regression = blocked)
- Flaky vs genuine failures distinguished
- Clear failure reports with stack traces
## Installation
```bash
git clone https://github.com/zavora-ai/skill-test-execution.git \
~/.skills/skills/test-execution
```
## Requirements
**Required:** `mcp-test-runner` (7 tools)
**Cross-MCP:**
- `mcp-github` — approve PRs only when tests pass
- `mcp-cicd` — post-deploy verification
- `mcp-jira` — create bugs from test failures
## Folder Structure
```
test-execution/
├── SKILL.md # Decision tree + test strategy
├── scripts/
│ └── coverage_delta.py # Coverage regression detector
├── references/
│ ├── tool-sequences.md # 7 tools
│ ├── cross-mcp-workflows.md # Tests + GitHub + CI/CD + Jira
│ └── examples.md # Run, debug, coverage
├── README.md
└── LICENSE
```
## Scripts
### `coverage_delta.py`
```bash
python scripts/coverage_delta.py '{"current": {"line": 82}, "baseline": {"line": 80}}'
# → {"line_delta": 2.0, "regression": false, "message": "✅ Coverage improved by +2.0%"}
```
## Success Criteria
| Metric | Target |
|--------|--------|
| Pre-merge gate | Tests always run before approval |
| Coverage tracking | Delta reported, regressions blocked |
| Flaky detection | Distinguish flaky from genuine failures |
## Contributors
| [
James Karanja Maina](https://github.com/jkmaina) |
|:---:|
## License
Apache-2.0 — Part of [ADK-Rust Enterprise](https://enterprise.adk-rust.com). Built with ❤️ by [Zavora AI](https://zavora.ai)