WAVE: Skill for Claude Code

.agents/skills/domain-to-spec/SKILL.md

domain-to-spec is a skill for Claude Code, Codex from emilyLi2020/WAVE. It costs 88 tokens per session (2,416 once invoked), scanned A, original, Apache-2.0.

A project-starting skill turns a professional’s domain knowledge into a technical plan and writes AGENTS.md and PRD.md files at the repository root.

In plain words
What is it for?
It is for defining a project’s technology, structure, user flow, and requirements so later scaffolding skills have a shared starting point.
Why use it?
It captures requirements, constraints, likely mistakes, and success criteria before implementation begins.

Skill for Claude CodeCodex

Written for no agent in particular: nothing here depends on one. Also seen: mentions Claude Code; installed under .agents/ (shared by several agents); mentions AGENTS.md.

This is emilyLi2020/WAVE's own configuration. It tells Claude Code and Codex how to work on WAVE itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything WAVE configures →

Reuse

Borrowing it

Nothing to install: this file belongs to emilyLi2020/WAVE. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file
curl -O https://raw.githubusercontent.com/emilyLi2020/WAVE/main/.agents/skills/domain-to-spec/SKILL.md
Clone the repo
git clone --depth 1 https://github.com/emilyLi2020/WAVE

Made for: Claude Code, Codex.

Wrote this? Show the measurements

A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.

agentmods badge for domain-to-spec

README.md
[![agentmods](https://agentmods.dev/badge/skills/emilyli2020/wave/domain-to-spec/github.svg)](https://agentmods.dev/skills/emilyli2020/wave/domain-to-spec)
Your own site
<a href="https://agentmods.dev/skills/emilyli2020/wave/domain-to-spec"><img src="https://agentmods.dev/badge/skills/emilyli2020/wave/domain-to-spec/github.svg" alt="Measured on agentmods" height="20"></a>

Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.

agentmods 80×15 button for domain-to-spec

Your own site · 80×15
<a href="https://agentmods.dev/skills/emilyli2020/wave/domain-to-spec"><img src="https://agentmods.dev/badge/skills/emilyli2020/wave/domain-to-spec.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 88 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 2,416 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
Origin original No closer match found in the catalogue.
Token cost

What it costs to keep this loaded

Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.

ModelPer sessionOnce invoked
Fable 5.1 $0.00088 $0.02416
Opus 5 $0.00044 $0.01208
Sonnet 5 $0.00018 $0.00483
Haiku 4.5 $0.00009 $0.00242

Measured 9d ago against content hash 42ee131e89b8, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-09, from the pricing page.

Security

Grade A, and why

domain-to-spec scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 9d ago.

A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.

Nothing flagged

None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.

.agents/skills/domain-to-spec/SKILL.md · 234 lines

How it starts

The opening of the file, as written. The whole thing — 234 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Domain to Spec

This is the first skill you should run when starting a new project. It captures the user's domain expertise, translates it into a buildable specification, and writes two files to the repo root that every other skill depends on:

  • AGENTS.md: the "README for agents" with setup commands, tech stack, file structure, and guardrails.
  • PRD.md: the Product Requirements Document with the user flow, pages, and success criteria.

Every other scaffold skill (scaffold-frontend, scaffold-backend) reads these two files and refuses to run if they are missing. So this skill is a prerequisite for the rest of the stack.

Step 1: Extract Domain Knowledge

Ask the user:

"I'm a {profession} building a tool to {outcome}."

Then ask follow-up questions:

  • What are the regulations or constraints in your field that this tool must respect?
  • What are the 3 most error-prone or time-consuming steps in the current process?
  • Who will use this tool? (you, your patients/clients, your staff, the public)
  • What does success look like? (one sentence)
  • Does the tool need to store data, authenticate users, or call external APIs? (helps decide if a backend is needed)

Step 2: Map the Domain to Software

For each domain concept the user describes, translate it:

Domain Concept Software Equivalent
Form or checklist Input form with validation
Decision tree Conditional logic / wizard flow
Reference document Searchable knowledge base
Approval process Status workflow with roles
Report or summary Generated output / PDF export
Compliance check Rule engine with pass/fail

Step 3: Propose the Simplest Flow

Design the minimum viable product:

  • One input (what the user provides)
  • One process (what the app does with it)
  • One output (what the user gets back)

Present it as:

INPUT: [what the user enters or uploads]
  |
PROCESS: [what happens behind the scenes]
  |
OUTPUT: [what the user sees or downloads]

Step 4: Decide if a Backend is Needed

Read the full file on GitHub · 234 lines

Changes

What this file has done since we first saw it

Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.

  1. 9d ago First seen · 234 lines · 88 tokens per session scan A 42ee131e89b8

Subscribe to this mod's changes

domain-to-spec is a skill published in the GitHub repository emilyLi2020/WAVE (2 stars, last pushed 2mo ago), licensed Apache-2.0. It adds 88 tokens to every session and 2,416 once invoked, about $0.0004 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.

Related

Other skills, from other repositories

systematic-debugging

Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.

obra/superpowers · 21 tokens

local-ai-agents

Build local-first AI agents that run entirely on a developer workstation with Microsoft Foundry Local and Qwen function-calling models. Covers Small Language Models (SLMs), the OpenAI-compatible local endpoint, sandboxed local tools, local RAG with Chroma, local MCP servers, hybrid cloud/local routing, and the…

microsoft/ai-agents-for-beginners · 200 tokens

next-cache-components-adoption

Turn on Cache Components in a Next.js app and resolve the blocking routes it surfaces. Use when the user wants to enable, adopt, or migrate to Cache Components, flip the cacheComponents flag, work through a flood of blocking-prerender / instant validation errors, run the cache-components-instant-false codemod, or…

vercel/next.js · 95 tokens

insight-error-page

Write or audit an insight-kind error page for the Next.js dev overlay. Use when creating a new errors/ .mdx page, auditing an existing one, or checking that a page matches the framework fix cards. Covers page structure, title alignment, FixCard cards with Copy prompt button, code snippets, terminology verification…

vercel/next.js · 83 tokens

next-cache-components-optimizer

Drive a Next.js route to instant navigation by setting up an agentic loop, under Cache Components / PPR, on initial load (hard navigation) and client-side navigation (soft navigation). Encode the goal as a failing @next/playwright instant() e2e and work it to green, one verified route at a time; the shipped test then…

vercel/next.js · 170 tokens

next-partial-prefetching-adoption

Turn on Partial Prefetching in a Next.js app and work through the insights it surfaces. Use when the user wants to enable or adopt Partial Prefetching, flip the partialPrefetching flag, opt routes in with export const prefetch = 'partial', audit Link prefetch={true} behavior, preserve existing prefetched UI with…

vercel/next.js · 103 tokens