Loading skill
Install any skill in seconds. Free to start, no credit card required.
Get Started Free →nwave-ai/nw-test-design-mandates
Design mandates for acceptance tests - hexagonal boundary, business language abstraction, user journey completeness, pure function extraction, 3 Pillars (domain language / chained narrative / production composition), and the layered ATD discipline (Universe-bound assertion, layer-dependent PBT mode, two-tier acceptance, example-based sad paths)
Passed 22 of 22 test cases with the skill, and 4 of 22 without it.
and 27 more in the full report
18 fixed4 passed either way0 still failing0 broke
Tokens, turns and time describe resource use, not a dollar price.
One of 18 test cases the skill fixed. Same model, same prompt, with and without the skill.
List the standard assertion predicate options supported across language implementations for state delta tracking expectations.
| Checked | Without skill | With skill |
|---|---|---|
| Includes set_to, unchanged, appended_with, and containing in the predicate set | Missed | Passed |
The instructions your model reads when the skill loads.
Four mandates enforced during peer review. All must pass before handoff to software-crafter.
Code examples in this skill use Python syntax for illustration only. They are NOT prescriptive about target language. nWave is language-agnostic per the "genericity and agnosticism" mandate (2026-05-24).
Before applying mandates, detect the target project's language from manifest files: package.json → TypeScript/JS; Cargo.toml → Rust; go.mod → Go; pyproject.toml/setup.py/Pipfile → Python; pom.xml/build.gradle → Java/Kotlin; *.csproj/*.fsproj → C#/F#; Gemfile → Ruby; Package.swift → Swift.
When the target language is NOT Python: adapt EVERY code example — replace Python imports (from pytest_bdd import ..., from hypothesis import ...), type hints, class/function syntax, test-framework idioms, directory conventions (tests/ vs test/ vs __tests__/) with target equivalents. Project conventions ALWAYS WIN over skill examples — if the user's repo has 50 TS files and zero Python files, mandates apply via TypeScript test framework, never Python pytest.
Empirical anchor: 5 of 5 Python code blocks in this skill, zero TS/Go/Rust — root-cause for language-leak per F-SKILL-EXAMPLES-LANGUAGE-LEAK. Connects [[feedback_language_adapter_plugin_architecture_2026_05_24]] (genericity mandate).
Tests invoke through driving ports (entry points), never internal components.
Application services/orchestrators | API controllers/CLI handlers | Message consumers/event handlers | Public API facade classes
Internal validators, parsers, formatters | Domain entities/value objects | Repository implementations | Internal service components
# Invoke through system entry point (driving port)
from myapp.orchestrator import AppOrchestrator
def when_user_performs_action(self):
orchestrator = AppOrchestrator()
self.result = orchestrator.perform_action(
context=self.context
)
test cases passed, vs 4 / 22 without
More skills from the same source and nearby in the registry, with their headline benchmark lift.