How do I install the Amdsmi Test Runner skill?

Run npx skillmds@latest add rocm/amdsmi-test-runner in your terminal (requires Node.js), paste this page's agent-chat prompt into Claude, Cursor, or any MCP-connected agent, or download the SKILL.md file and copy it into your agent's skills directory.

Is Amdsmi Test Runner safe to use?

This skill has not completed SkillMD's automated safety review yet. SkillMD never runs a skill's scripts for you; review the SKILL.md before installing.

Which AI agents work with Amdsmi Test Runner?

This skill is tagged as working with Claude Code, Claude.ai, OpenAI Codex. SKILL.md is an open format, so most agents that read a skills directory can load it too.

Is Amdsmi Test Runner free to use?

Yes. Installing skills from SkillMD is free, and the skill stays under its author's original license.

Who published Amdsmi Test Runner?

rocm (@rocm) published this skill. Their other Agent Skills are listed on their SkillMD profile.

Amdsmi Test Runner by rocm — Agent Skill

Name: Amdsmi Test Runner
Author: rocm

File contents

Test Runner — amd-smi

How to build and run all test suites for amd-smi. Assumes the amdsmi-build-install skill has already been executed (build exists and is installed).

Prerequisites

amd-smi built and installed (run amdsmi-build-install skill first)
AMD GPU hardware available for integration tests
build/ directory exists with compiled test binaries

C++ Tests (GTest)

Build Test Binary

If not already built (the build skill builds with -DBUILD_TESTS=ON):

cd build && make -j$(nproc) amdsmitst

Run Tests

cd build/tests
source ../../tests/amd_smi_test/amdsmitst.exclude
source ../../tests/amd_smi_test/detect_asic_filter.sh
./amdsmitst --gtest_filter="-${GTEST_EXCLUDE}"

Interpret Results

Output	Meaning	Severity
`[ PASSED ]`	Test passed	—
`[ FAILED ]`	Test failed	❌ BLOCKING
`[ SKIPPED ]`	Test skipped (blacklisted)	—
Binary not found	Build didn't produce test binary	⚠️ IMPORTANT

Python Tests

Unit / Integration / CLI

Run the suite files directly (each sys.exit(0/1)):

cd tests/python
python3 unit_tests.py -v
python3 integration_test.py -v
python3 cli_unit_test.py -v

Import Verification

# System install
python3 -c "import amdsmi; print(amdsmi.__version__)"

# Verify CLI works
amd-smi version
amd-smi static

Test Contexts

Tests must work in both install contexts:

Context	How to Verify
System install (RPM/DEB)	Default after `amdsmi-build-install`

Running All Tests to Logs (One-Shot)

run-all-tests.sh (this skill's directory) runs the C++ GTest, Python unit, integration, and CLI suites, tees each to a timestamped log dir, and prints a pass/fail summary. It derives the project root, so run it from anywhere in the tree:

.claude/skills/amdsmi-test-runner/run-all-tests.sh          # logs under $TMPDIR/amdsmi-tests-<stamp>/
.claude/skills/amdsmi-test-runner/run-all-tests.sh -o ./ci-logs

Each suite's full output is in <logdir>/<suite>.log; the exit code is non-zero if any suite failed.

Output

On success, report:

C++ tests: X passed, Y failed, Z skipped
Python tests: X passed, Y failed
Any new test failures compared to baseline

On failure:

Which suite failed (C++ GTest, Python unit, CLI)
Specific test names that failed
Test output for failed tests
Test failures are ❌ BLOCKING for the review

---name: amdsmi-test-runnerdescription: Run C++ and Python tests for amd-smi. Use when: running tests, verifying test results, checking test coverage, pre-review test validation.---# Test Runner — amd-smiHow to build and run all test suites for amd-smi. Assumes the `amdsmi-build-install` skill has already been executed (build exists and is installed).## Prerequisites- amd-smi built and installed (run `amdsmi-build-install` skill first)- AMD GPU hardware available for integration tests- `build/` directory exists with compiled test binaries## C++ Tests (GTest)### Build Test BinaryIf not already built (the build skill builds with `-DBUILD_TESTS=ON`):```bashcd build && make -j$(nproc) amdsmitst```### Run Tests```bashcd build/testssource ../../tests/amd_smi_test/amdsmitst.excludesource ../../tests/amd_smi_test/detect_asic_filter.sh./amdsmitst --gtest_filter="-${GTEST_EXCLUDE}"```### Interpret Results| Output | Meaning | Severity ||--------|---------|----------|| `[ PASSED ]` | Test passed | — || `[ FAILED ]` | Test failed | ❌ BLOCKING || `[ SKIPPED ]` | Test skipped (blacklisted) | — || Binary not found | Build didn't produce test binary | ⚠️ IMPORTANT |## Python Tests### Unit / Integration / CLIRun the suite files directly (each `sys.exit(0/1)`):```bashcd tests/pythonpython3 unit_tests.py -vpython3 integration_test.py -vpython3 cli_unit_test.py -v```### Import Verification```bash# System installpython3 -c "import amdsmi; print(amdsmi.__version__)"# Verify CLI worksamd-smi versionamd-smi static```## Test ContextsTests must work in **both** install contexts:| Context | How to Verify ||---------|--------------|| System install (RPM/DEB) | Default after `amdsmi-build-install` |## Running All Tests to Logs (One-Shot)`run-all-tests.sh` (this skill's directory) runs the C++ GTest, Python unit,integration, and CLI suites, tees each to a timestamped log dir, and prints apass/fail summary. It derives the project root, so run it from anywhere in the tree:```bash.claude/skills/amdsmi-test-runner/run-all-tests.sh # logs under $TMPDIR/amdsmi-tests-<stamp>/.claude/skills/amdsmi-test-runner/run-all-tests.sh -o ./ci-logs```Each suite's full output is in `<logdir>/<suite>.log`; the exit code is non-zeroif any suite failed.## OutputOn success, report:- **C++ tests:** X passed, Y failed, Z skipped- **Python tests:** X passed, Y failed- **Any new test failures** compared to baselineOn failure:- **Which suite failed** (C++ GTest, Python unit, CLI)- **Specific test names** that failed- **Test output** for failed tests- Test failures are **❌ BLOCKING** for the review

Frequently asked questions

Amdsmi Test Runner