// Use EVERY TIME you need to run tests, verify tests pass, or check for regressions. ALWAYS use this instead of running eldev directly.
| name | test |
| description | Use EVERY TIME you need to run tests, verify tests pass, or check for regressions. ALWAYS use this instead of running eldev directly. |
Run ./run-tests.sh (in this skill's directory) to execute tests. The script handles all noise filtering and outputs only a clean summary.
.claude/skills/test/run-tests.sh [ARGUMENT]
Parse the ARGUMENTS line and pass it through:
| Argument | What it does |
|---|---|
(none) / all | Full suite |
test/unit/foo-test.el | Single file |
unit / integration / acceptance | Category |
If the argument contains / but no .el (looks like a test name, e.g. stuck-sa-filter/cancelled-project-task-skipped):
deftest <name> in test/ to find the filerun-tests.shThe script returns one of:
Success: PASS: 1195 tests in 18.4s
Failure: Summary line + full failure/error details (test name, expected/actual, file:line)
Unexpected: Last 30 lines of raw output
Report the script output verbatim. Do not add commentary unless the user asks.
Use when code quality needs improvement after implementation, without changing behavior
Use when implementation is complete and you want to verify quality through adversarial testing that writes code and provides evidence
Use when a design exists and it's time to break it into tasks and execute with subagent dispatch and review
Use when requirements exist and a technical design is needed before implementation begins
Use when a new feature request, bug report, or work request needs requirements defined before implementation
Use when starting any conversation - establishes how to find and use skills, requiring Skill tool invocation before ANY response including clarifying questions