nWave Agent Creation Workflow

from nwave544

A practical five-phase workflow for designing, building, validating, and refining agent definitions and skills.

triggers:agent creationdesign workflowvalidate agentskill loadingnw-agent-creationquality gates

What it does

Provides a step-by-step five-phase (Analyze → Design → Create → Validate → Refine) methodology for creating agent definitions and companion skills. It defines clear inputs, outputs, quality gates, and naming conventions so teams can produce maintainable, testable agents and skill sets. The workflow includes frontmatter templates, skill-loading strategies, and a 14-point validation checklist to ensure consistency and safety.

When to use it

Use this workflow when you need to scope and build a new agent or refactor an existing one — especially when multiple skills are involved, when you need reproducible validation, or when teams want a standardized agent production process. It's intended for technical audiences building agent definitions and skills (Claude/Claude-Code style environments).

What's included

Scripts: none detected in the repo path (has_scripts=false)
References: none bundled (has_references=false)
Instructions: detailed phase-by-phase guidance including frontmatter examples, skill-loading strategy, validation checklist, and naming conventions.

Compatible agents

Best suited for Claude Code / Claude-style agent tooling and multi-agent frameworks that deploy SKILL.md style definitions and subagents. It is tooling-agnostic but references Claude Code patterns and subagent loading practices.

Not yet audited

This skill has not been reviewed by our automated audit pipeline yet.

Information

Repository: nwave
Stars: 544
Installs: 0

More from nwave

Diverger Review Criteria

Checks rigor and quality of DIVERGE-wave artifacts: JTBD extraction, research coverage, option diversity, taste scoring, and recommendation traceability.

Related Skills

Retriever (Membrane CLI)

Integrate Retriever search and discovery via the Membrane CLI — manage connections and run queries across Retriever data sources.

Cost Tracker

Monitor agent session costs, set budget alerts, and get actionable token-spend optimizations to keep multi-session workflows within budget.

GraphQL Inspector — Validate

Validate GraphQL operations against a schema with configurable depth, complexity, alias and directive limits to catch errors before runtime.

Alpha Forge Pre-Ship Quality Gates

Pre-merge quality gates for PRs that validate RNG determinism, forked URLs, runtime parameter ranges, and manifest synchronization to reduce review cycles.

Skill Issue — Skill Auditor

Scan and audit installed agent skills to produce a health report covering inventory, usage, dependency checks, version status, and actionable recommendations.

Evolve — Goal-Driven Improvement Loop

Autonomous improvement loop that selects high-value work, runs a full research-plan-implement (/rpi) cycle, validates changes, and repeats to compound repo impr

Node.js Best Practices

Guidelines and decision-making for Node.js architecture, runtime, async patterns, security, validation, and testing to inform framework and system choices.

Bash Pro

Defensive, production-grade Bash scripting patterns and CI/CD best practices: strict mode, safe argument parsing, testing with Bats, and tooling (ShellCheck/shf

Back to Skills