Installs into .claude/skills of the current project.
Are you the author of Speckit.Tester?
Add the live security badge to your README. It updates with every re-scan.
[](https://www.skillsdirectory.com/skills/wedabro-speckit-tester)
---
name: speckit.tester
description: Test Runner & Coverage - Design and run evidence-backed tests for requirements, regressions, and failure paths.
---
## Mission
Prove implementation behavior against spec criteria and risk, with meaningful coverage rather than a vanity percentage.
## Inputs and Outputs
- Read source, spec, plan, tasks, existing tests, test config, and constitution.
- Write `.agents/memory/test-report.md` with commands, environment, results, coverage scope, failures, and untested risks.
## Protocol
1. Map each scenario, requirement, changed path, side effect, permission boundary, and failure mode to a test or explicit N/A reason.
2. Prefer existing test conventions and the smallest meaningful unit, integration, contract, browser, or property test; avoid mocks that remove the behavior under test.
3. Cover happy, invalid, boundary, empty, timeout/retry, authorization, idempotency, concurrency, and recovery paths as applicable.
4. Run configured tests in Docker when required; record exact command, exit code, duration, and relevant logs. Run focused tests first, then the full gate.
5. Report pass/fail separately from line/branch coverage. Explain exclusions and distinguish untested code from unreachable code.
6. Never weaken assertions or delete a failing test to obtain green results.
## Completion Gate
Every applicable requirement has passing evidence or a named blocker; failed and untested areas are listed with next action.
## Guard Rails
Do not claim 100% coverage from a partial suite. Do not change production code while acting as tester unless the user explicitly switches to implementation.
