Menu
Skills in this repository
SkillsMP has collected 109 skills from nWave-ai/nWave-experimental. Open a skill to review its source and details.
nWave-ai/nWave-experimentalShowing 29 of 109 collected skills.
Layered test-mechanics mandates for acceptance tests — Universe-bound assertion at layers 1-3 (assert_state_delta), Mandate-9-v2 three-way treatment by mock-status, layer-dependent PBT input mode, two-tier acceptance (Tier A Gojko + optional Tier B…
Port the state-delta + property-based testing paradigm to languages other than Python. DIY recipes per language; canonical Python ref shipped in nwave_ai.state_delta.
Python property-based testing with Hypothesis framework, strategies, and pytest integration
What is reducible in a bloated command - the duplication triangle, the anti-pattern catalog, and the compress/never-compress rules
OO code-design SSOT — the WHAT-to-design anti-smell catalog (Object Calisthenics, RPP smell taxonomy, effect isolation) shared by the solution architect (design-time) and the crafter (execution-time).
Lightweight eval method for testing nWave AGENTS and SKILLS (LLM behavior) as a lean alternative to heavy BDD/ATD. An eval = one prompt -> one captured run (trace + artifacts) -> a small set of checks -> a comparable score over time. Load when validating…
[EXPERIMENTAL] Complex refactoring roadmaps with visual tracking
Applies the Refactoring Priority Premise (RPP) levels L1-L6 for systematic code refactoring. Use when improving code quality through structured refactoring passes.
Scenario-design mandates for acceptance tests — Hexagonal Boundary Enforcement (drive through driving ports, never internals), Business Language Abstraction (three abstraction layers), User Journey Completeness, Pure Function Extraction Before Fixtures,…
Coverage-preserving consolidation patterns applied in order - parametrize-collapse, dict-iteration, fixture-scope, xdist-group, migration-collapse lifecycle, cross-tier dedup, single-lifecycle consolidation, state-delta cross-ref
Git change frequency hotspot analysis — find the most-changed files in your codebase
Speculative parallel implementation methodology — dispatch N candidate implementations, audit all, score, pick best. Auditability mandate: ALL candidates logged (not just winner).
Methodology for minimizing test count while maximizing behavioral coverage - lean core composing behavior-counting, anti-patterns, consolidation, budget-gate, paradigm-match, coverage-validation, scope-selection modules
BDD patterns for acceptance test design - Given-When-Then structure, scenario writing rules, pytest-bdd implementation, anti-patterns, and living documentation
Teaches agents how to run a timeboxed spike - throwaway code that validates one assumption before DESIGN
The default test-writing paradigm for unit + acceptance tests - property-based + state-delta mandate, the applicability matrix, the debt-payoff efficacy curve, and the delta-first trigger/bypass rules for state-mutating code
KNOWLEDGE — the canonical agent-spec template (frontmatter + body skeleton). Reference loaded by the create/migrate procedures; no sequence.
PROCEDURE — create a NEW agent via the 5-phase workflow (ANALYZE→DESIGN→CREATE→VALIDATE→REFINE). Trigger: build a new AI agent. Composes nw-ab-validate-spec.
KNOWLEDGE — canonical worked examples for agent creation, migration, and command optimization. Reference for the relevant procedures; no sequence.
KNOWLEDGE — caveman-native authoring house style + by-construction guarantees (Reasoning Mandate injection, A05/A06 anchors, measured-gain compression). Reference for create/migrate; no sequence.
PROCEDURE — merge agent B into agent A, relocating skills and cleaning up all references. Trigger: two agents must become one. Composes nw-ab-validate-spec.
PROCEDURE — optimize a bloated command file to a lean declarative definition (forge.md pattern). Trigger: a command file over its size target with reducible content.
PROCEDURE — convert an agent/skill/command file's prose workflow + prose success-criteria to numbered task lists. Trigger: a file with prose workflow or prose success-criteria sections.
The v2.8+ new-command installation contract - which three files to produce and their frontmatter when creating a brand-new command
How to size and categorize a command, the declarative command template, and the WHAT-vs-HOW logic-placement rule
Best practices for command definition files - size targets, declarative template, anti-patterns, and canonical examples based on research evidence
Infrastructure as Code patterns (Terraform, Kubernetes), observability design (SLOs, metrics, alerting, dashboards), and pipeline security stages. Load when designing infrastructure, observability, or security scanning.
Deep knowledge for Outside-In TDD - double-loop architecture, ATDD integration, port-to-port testing, walking skeletons, and test doubles policy
Decision rule matching test SHAPE to the right paradigm before authoring/migrating - closed-world vs multi-step-setup vs state-mutation vs unbounded-invariant vs few-examples, plus the falsifier-gate that blocks PBT on finite domains