skills/qe/tdd-coach/SKILL.md
Guide Test-Driven Development workflow — teach red-green-refactor cycle, test-first approach, and TDD best practices. Validate test quality. A teaching / coaching flow rather than a persistent role; dispatched on demand when a developer wants TDD guidance for a specific feature or bug fix. Use when: "guide me through TDD", "red-green-refactor", "test-first approach", "TDD this feature", "teach me TDD", "coach me on TDD".
npx skillsauth add mikeparcewski/wicked-garden tdd-coachInstall 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.
Guides a developer through a Test-Driven Development cycle — writing a failing test first, making it pass with minimal code, and refactoring while keeping tests green. Teaches the discipline, reviews test quality, and catches common TDD anti-patterns.
This is a coaching flow, not a persistent role. Dispatch this skill when someone wants to TDD a specific feature or bug fix. For persistent test strategy and test automation work, use the test-strategist or test-automation-engineer agents.
Invoke this skill when someone says:
Typical output:
1. RED: Write a failing test
2. GREEN: Write minimal code to pass
3. REFACTOR: Improve code quality (tests stay green)
4. REPEAT
Ask: "What should the code do?" Guide: "Let's write a test that describes that behavior first."
Test quality checklist:
Good vs bad examples:
// Good — describes behavior
test('calculateTotal should sum item prices', () => {
const items = [{price: 10}, {price: 20}];
expect(calculateTotal(items)).toBe(30);
});
// Bad — too vague
test('test calculation', () => {
expect(calculate()).toBeTruthy();
});
Verify the test fails:
npm test -- {test_file}
# Expected: FAIL (the RED)
Guidance:
Anti-pattern: writing extra code "just in case"
Example:
// First iteration — hardcoded
function calculateTotal(items) {
return 30; // Passes the one test
}
// Next test forces real implementation
test('works with different prices', () => {
const items = [{price: 5}, {price: 15}];
expect(calculateTotal(items)).toBe(20);
});
Checklist:
Key rule: tests stay green during refactoring.
For the next behavior:
Quick shape for the three most-asked scenarios (new feature, bug fix, refactoring). Full step-by-step playbooks live in refs/patterns.md#common-tdd-scenarios.
See refs/patterns.md for:
Return a structured coaching block per cycle (feature, phase, current test, status, next step, tips, coverage). Optionally append TDD-cycle progress to the active task via TaskUpdate. Full output template + TaskUpdate snippet: refs/patterns.md#coaching-output-template.
Watch for and surface the common TDD missteps: implementation-before-test, oversized test, missing edge cases, duplication, hardcoded-value-as-premature-solution. Full checklist: refs/patterns.md#teaching-moments-checklist.
development
Pattern-conformance agent-half: evaluates a produced artifact or diff against a set of architectural/design pattern rules from the conformance-rule store (wicked_governance schema). Returns structured findings with rule ID, severity, and rationale — the deterministic half (mechanical rule recall) is done by the guard pipeline; this is the semantic evaluation step. Triggered by: the guard_pipeline `outgov_pattern` check (session-close), or explicitly by an engineering review when WICKED_OUTGOV_RULES_DIR is populated. NOT a replacement for the full `engineering` review skill — focuses only on conformance to stored Pattern rules; architecture and code-quality checks live in the `engineering` skill. Semantic evaluation reuses `wicked-garden-qe-semantic-reviewer` as the designated agent-half evaluator (per garden#983 spec). This skill is the orchestrating wrapper that loads applicable Pattern rules and delegates the per-rule semantic judgment to qe-semantic-reviewer.
tools
The FOUNDATIONAL domain-model capability: extract a codebase's domain — testable business rules (with confidence + provenance), entities, requirements — as a schema-conformant model on the estate graph. The workers annotate the store; wicked-core reads it and builds the requirements graph, coverage-gating fail-closed. Steers three fork workers. A shared substrate, not a modernization tool. The `modernize` archetype DERIVES from it; build / migrate / review / specify / explore consume the SAME domain model — none OWN it. Understanding a codebase's domain is upstream of almost everything else garden does. Use when: "extract the business rules / domain model from this codebase", "build a requirements graph from the code", "what does this system actually require", "reverse-engineer the domain before we build/port/migrate". Works on ANY codebase (modern or legacy) — the value is the domain model, not the porting. NOT the code transform itself (that is the archetype consuming this model). This skill produces the DOMAIN MODEL, not new code.
development
Domain-graph fork worker for the modernize archetype. Groups the estate's Louvain communities into business domains, attaches each requirement to its cluster (advisory cluster_id provenance), and invokes wicked-core's domain-graph build (which reads the annotated estate store, recomputes coverage fail-closed, and builds the requirements graph) — then validates core's output against the vendored schema. Use when: dispatched by wicked-garden-domain after rule extraction to turn a flat rule set into cluster-keyed domains; "group these into domains", "build the requirements graph", "translate clusters into a domain model". NOT for mining the rules themselves (that is domain-extractor) or threat-modeling (that is domain-coverage).
tools
Rule-extraction fork worker for the FOUNDATIONAL domain-model capability. Mines testable business rules from a codebase — each with a numeric confidence and a provenance{source, ref, source_kinds} — and annotates them into the estate store so wicked-core can build the domain-model requirements graph (coverage-gated). This is a substrate, not a modernization tool: the `modernize` archetype DERIVES from it, and build / migrate / review / specify / explore can consume the same domain model — none OWN it. Use when: dispatched by wicked-garden-domain to mine the business_rules of a codebase (or a module); "extract the domain rules", "what does this system require", building the requirements half of a domain model. NOT for grouping into domains (that is domain-modeler) or judging coverage (that is domain-coverage — a seat-distinct evaluator).