skills/task-plan-phase-testing/SKILL.md
Load when the task's primary concern is tests — fixing failing tests, adding coverage to existing code, or implementing a feature test-first (TDD).
npx skillsauth add maestria-co/ai-playbook task-plan-phase-testingInstall this skill globally with one command. Works with Claude Code, Cursor, and Windsurf.
3 of 9 scanners reported clean
Some scanners were skipped, did not run, or reported a non-clean status. Review each row below.
Load this skill when the task's dominant focus targets test quality. This encompasses: remediating failing tests, augmenting coverage for under-tested implementations, or implementing features via test-driven development (TDD). For tasks treating testing as trailing test step rather than primary objective — load task-plan-phase-completion instead, which addresses lightweight tests.
Load task-plan-phase-testing when tasks exhibit these characteristics:
Bypass when:
All tester dispatches require these components. The @tester agent internally loads testing-discipline; direct loading unnecessary.
What to test: [feature, module, or failure characterization]
Implicated files:
- [file/path]: [operational purpose]
Test requirements from plan: [plan.md acceptance criteria catalog]
Extant test patterns: [.context/testing/ citations]
Targeted scenarios for tests:
- [scenario 1 — nominal execution]
- [scenario 2 — error/boundary scenario]
- [scenario 3 — edge scenario]
Success thresholds:
- All catalogued scenarios possess passing tests
- Zero test smells (no internal mocking, no implementation detail tests)
- [coverage threshold, when specified]
Insert this matrix into plan.md ## Progress section when dispatching @tester:
| Test Domain | Status | Annotations |
|-------------------|--------|-------------|
| Unit — [component] | ⏸️ Pending | — |
| Integration — [flow] | ⏸️ Pending | — |
| Coverage | ⏸️ Pending | — |
| Defects discovered | — | — |
Status indicators: ⏸️ Pending · 🔄 In Progress · ✅ Complete · ❌ Obstructed
Refresh post-@tester completion. Channel discovered defects to @coder steps before progression.
When tests fail with opaque causation:
systematic-debugging before re-dispatch.systematic-debugging — causation is architectural, not superficial.plan.md ## Decisions as performed.testing-discipline: @tester loads internally. Direct loading unnecessary.systematic-debugging: Load when test failures exhibit unclear causation following initial @tester pass, or following 3+ failed attempts.task-plan-phase-implementation: For test remediation requiring code alterations, dispatch via implementation skill, then resume tests.task-plan-phase-completion: Load post-test completion to finalize task: code audit, context refresh, retrospective.Excluded scope: investigation, architecture, @coder orchestration, retrospectives, context updates, completion summary.
development
Writes and runs a test suite for a piece of code, covering happy path, edge cases, error cases, and security cases. Use when: implementation is complete and needs test coverage, a bug needs a reproduction test and fix validation, or code needs coverage before a refactor. Do not use when: the code under test is not yet implemented, or the spec is still unclear.
testing
Use when creating a new skill, editing an existing skill, or helping a user author a skill for this system. Covers structure, discoverability, quality, and discipline hardening.
development
Evidence-based verification process to run before marking any task complete. Use this skill every time you're about to report that work is done — for features, bug fixes, refactoring, or any code change. This catches the most common failure mode: declaring "done" without proof. If you're finishing up and about to tell the user the task is complete, run this checklist first.
development
Teaches agents how to discover, select, and invoke skills from the skill library. Use this skill whenever you're uncertain which skill applies to a task, when composing multiple skills for complex work, or when you need to understand what skills are available. This is your go-to when facing an ambiguous task and need to figure out the right approach before diving into implementation.