nwave
Guides a feature from idea to working code in Claude Code, with agents drafting the artifacts for each stage while you review and approve before the next one begins.

Guides a feature from idea to working code in Claude Code, with agents drafting the artifacts for each stage while you review and approve before the next one begins.
KNOWLEDGE — the canonical agent-spec template (frontmatter + body skeleton). Reference loaded by the create/migrate procedures;…
KNOWLEDGE — agent/skill/command anti-pattern catalog with fixes. Reference scanned by validate-spec; no sequence.
PROCEDURE — create a NEW agent via the 5-phase workflow (ANALYZE→DESIGN→CREATE→VALIDATE→REFINE). Trigger: build a new AI agent.…
Review dimensions for validating agent quality - template compliance, safety, testing, and priority validation
KNOWLEDGE — canonical worked examples for agent creation, migration, and command optimization. Reference for the relevant…
KNOWLEDGE — caveman-native authoring house style + by-construction guarantees (Reasoning Mandate injection, measured-gain…
PROCEDURE — merge agent B into agent A, relocating skills and cleaning up all references. Trigger: two agents must become one.…
PROCEDURE — migrate one legacy monolithic agent to a lean core plus routed skills. Trigger: an existing agent has measured size,…
PROCEDURE — optimize a bloated command file to a lean declarative definition (forge.md pattern). Trigger: a command file over its…
PROCEDURE — optimize one requested existing skill. Measures multi-trigger, duplication, and resident-context debt before editing;…
PROCEDURE — validate an EXISTING agent spec against the nw-ab-validation-checklist. Trigger: checking a spec for compliance (also…
KNOWLEDGE (data) — the agent-spec validation checklist. The item definitions the validate-spec procedure RUNS against. No…
Authors the public executable oracle when required.
Independently approves or finds defects in the consolidated public oracle.
Use when creating new AI agents, validating agent specifications, optimizing requested existing SKILL.md assets, optimizing…
Use for review and critique tasks - Agent design and quality review specialist. Runs on Haiku for cost efficiency.
Use for database technology selection, data architecture design, query optimization, schema design, security implementation, and…
Use for review and critique tasks - Data architecture and pipeline review specialist. Runs on Haiku for cost efficiency.
Use for DESIGN wave domain modeling. Discovers bounded contexts, designs aggregates, facilitates Event Modeling sessions, and…
Use for reviewing DDD domain models. Validates bounded context boundaries, aggregate design, context mapping, ES/CQRS…
Use before DISCUSS — runs JTBD analysis, competitive research, structured brainstorming, and taste-filtered evaluation to produce…
Use as peer reviewer for nw-diverger outputs — validates JTBD rigor, research evidence quality, option structural diversity,…
Use for documentation quality enforcement using DIVIO/Diataxis principles. Classifies documentation type, validates against…
Use for reviewing documentarist assessments. Validates classification accuracy, validation completeness, collapse detection, and…
Is this you? Claim your profilePut a plugin at the top of Plugins, from $9