leszekgruchala/buddy / skills/test-runner
test-runner
VerifiedRun and report tests, lint, formatting checks, type checks, builds, or independent validation without editing or installing. Keep the current request in this skill; route new requests by their own scope.
Test Runner
Validate the complete assigned scope read-only.
Model selection
Apply model selection; recommend balanced.
Mode lock
Keep the current request in this skill. Do not activate another Buddy skill without user or develop direction. Workers return to their caller. For a new request after completion, apply change size and route by its own scope.
Rules
- Never edit, fix, create tracked artifacts, or install dependencies; report and stop if required.
- Inspect change state (Git status/diff only in Git repos), then applicable
AGENTS.md,CLAUDE.md, READMEs, manifests, project/test/build config, and CI. - Prefer documented commands; run only relevant, environment-safe checks in required lint/static-before-test order. Apply change size to scope and supplied evidence. Map affected tests reliably; investigate and report coverage gaps. Honor explicit repository checks.
- Keep concise diagnostic failure evidence; never repeatedly retry flaky/environment failures. Escalate missing dependencies, credentials, services, or permissions.
Skip conditions
Return SKIPPED when:
- The change is documentation-only and no documentation validation exists.
- Required dependencies, environment variables, credentials, or services are unavailable.
- Running the command would modify shared or external state.
- The caller explicitly excluded validation.
Output
## Test Results: PASS | FAIL | PARTIAL | SKIPPED
### Commands
- `<command>` — PASS | FAIL | SKIPPED; mark reused evidence
### Failures
- `<file/test>`: concise failure and likely category
### Coverage
- Validated: ...
- Not validated: ...
### Blockers
- None | ...
Return the report and stop; never transition into implementation.
Related skills
| Skill | Stars | Updated | Works with | Status | Install |
|---|---|---|---|---|---|
| finishing-a-development-branchobra/superpowersUse when implementation is complete, all tests pass, and you need to decide how to integrate the work | Stars: 321k | Updated | Claude CodeCodex | Verified | Install |
| systematic-debuggingobra/superpowersUse when encountering any bug, test failure, or unexpected behavior, before proposing fixes | Stars: 321k | Updated | Claude CodeCodex | Verified | Install |
| test-driven-developmentobra/superpowersUse when implementing any feature or bugfix, before writing implementation code | Stars: 321k | Updated | Claude CodeCodex | Verified | Install |
| skill-creatoranthropics/skillsCreate new skills, modify and improve existing skills, and measure skill performance. Use when users want to create a skill from scratch, edit, or optimize an existing skill, run evals to test a skill, benchmark skill performance with variance analysis, or optimize a skill's description for better triggering accuracy. | Stars: 197k | Updated | Claude CodeCodex | Verified | Install |