prototype-alignment-review

prototype-alignment-review is a skill for Claude Code, Codex from hxy91819/mason-skills. It costs 108 tokens per session (2,318 once invoked), scanned A, original, MIT.

A review process for checking whether a working interface behaves like an approved prototype. It compares inputs, choices, defaults, validation, and other functional details, not just visual appearance.

In plain words
What is it for?
Use it to compare prototype and implementation pages, record evidence-based differences, and produce a list that developers can fix.
Why use it?
It finds cases where a feature exists but works differently from the agreed design, before or after a frontend change is merged.

Skill for Claude CodeCodex

Written for no agent in particular: nothing here depends on one.

Good fit Use it to compare prototype and implementation pages, record evidence-based differences, and produce a list that developers can fix.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/hxy91819/mason-skills/prototype-alignment-review
Install

Getting it into your agent

One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.

Any agent
npx skills add hxy91819/mason-skills --skill prototype-alignment-review
Clone the repo
git clone --depth 1 https://github.com/hxy91819/mason-skills

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 prototype-alignment-review

README.md
[![agentmods](https://agentmods.dev/badge/skills/hxy91819/mason-skills/prototype-alignment-review/github.svg)](https://agentmods.dev/skills/hxy91819/mason-skills/prototype-alignment-review)
Your own site
<a href="https://agentmods.dev/skills/hxy91819/mason-skills/prototype-alignment-review"><img src="https://agentmods.dev/badge/skills/hxy91819/mason-skills/prototype-alignment-review/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 prototype-alignment-review

Your own site · 80×15
<a href="https://agentmods.dev/skills/hxy91819/mason-skills/prototype-alignment-review"><img src="https://agentmods.dev/badge/skills/hxy91819/mason-skills/prototype-alignment-review.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 108 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 2,318 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 $0.00108 $0.02318
Opus 5.5 $0.00043 $0.00927
Sonnet 5.5 $0.00022 $0.00464
Haiku 4.5 $0.00011 $0.00232

Measured 7d ago against content hash 2e1aee8c36e4, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

prototype-alignment-review 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 7d 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.

common-skills/prototype-alignment-review/SKILL.md · 107 lines

How it starts

The opening of the file, as written. The whole thing — 107 lines — stays where its author put it; the contents beside it link to each section on GitHub.

原型对齐审查

原型是规格的三层之一:视觉由像素与结构门禁守,领域规则由领域审查守,这个技能守中间那层——功能设计。功能存在不等于功能设计一致:验收结果被预选、默认值从 3 变成空、下拉选变成填 ID、只知店名就找不到案场,都是功能存在而设计走样。

只产清单,不改代码;修补由派发方另行安排。

第 0 步:环境探针

读任何业务代码之前(启动说明、账号表、依赖安装除外),先用派发方给的入口与账号各做一次实际登录并截一张图:原型一张、正式一张,图上必须是登录后的页面(看得到用户名或导航;移动端内页没有用户名时,用同一浏览器 context 从登录后的首页导航过去,探针图取首页),登录表单截图不算探针通过。两边都通过才继续;任何一边打不开,立刻停下,把失败的入口、账号与错误原文报回派发方,不要转成「只读代码的推导报告」——没有实测的对齐审查不是这个技能的产出。派发方明确要求「程序推导模式」时才例外,且报告每一条都标「程序推导」。

基准代码用只读 worktree(git worktree add /tmp/<name> <base>),审完移除;不在主工作区读。

探针常见的三种卡法与处理:登录被限流(429)就等限流窗口过了再试一次,仍不行报回;原型端口被占就换一个端口偏移,占用端口的进程不是你起的就不动它;账号或密码派发方没给或给错,直接报回要,不猜。登录 POST 是探针的一部分,不算业务写入;拦截业务写入从登录后开始。

先读

  1. 项目的移转约定(原型哪些是示范手段不搬、哪些差异已裁决、授权在哪判)。找不到就向派发方要,不自行判断什么算示范手段。
  2. 项目术语表与本次范围内页面对应的领域文档节。
  3. 派发方给的覆盖矩阵:页面 × 角色 × 阶段里哪些组合要测、哪些组合在种子数据里不存在、候选全量性与日期边界要用哪组数据验证。没给就先按两边种子里实际存在的组合做,把做不到的组合列进「未覆盖」,不虚构账号或数据。
  4. 范围内每个页面的原型文件与正式文件。派发方给的路径找不到时,按页面标题或功能文案 rg 两边源码定位(组件常被改名或搬目录),定位结果写进报告的「范围」节。

比对维度

对范围内每个页面 × 角色 × 阶段,逐维度过,每个维度都写结论(一致也写):

维度 看什么
输入方式 文本框/下拉/可搜索下拉/stepper/日期/单选多选;原型是选,正式变成填,就是差异
候选来源 选项从哪来、是否全量、是否截断(前 N 笔)、是否可搜索、搜索比对哪些字段
默认值 预选/预填/带入本人资料/空;原型空而正式预选,是差异
必填与校验 必填项、格式、何时提示、是否代填(原型要本人填「无」,正式自动补「无」,是差异)
条件显示 哪些区块随选择展开、随数量出现、随角色与阶段出现
动作后导向 提交/取消/返回去哪、停在哪个页签、是否清空
列表 筛选项集合、时间条件的语义(含不含迄日、筛哪个事件)、文本搜索覆盖字段、排序、分页、清除条件、各页签计数
空状态 资料空与搜索空是否区分、是否给出清除或建立入口
可见范围 同一角色在原型能看到、正式看不到的区块;先对照移转约定里的授权投影规则,再判是否差异
错误定位 缺项是否定位到字段、是否聚焦第一个缺项

每个维度的判断依据是原型文件的行与实际操作,不是对原型的印象。先前的对比报告、修补 PR 说明、聊天记录都在审查做完之前不读:它们描述的是过去某个 commit,读了会把旧结论写进新报告。派发方要求对照旧报告时,放在报告最后一节,审完再读。

分级

按使用情境定级,与改动大小无关:

  • P1:用户在该情境下做不下去或容易写入错误结果(不知完整电号就建不了单;验收预选让人一键通过)。
  • P2:要额外操作或少一项能力(要另选单号再复制;筛选少一个字段)。
  • P3:提示、顺序、回复细节。
  • 扩充:正式比原型多出的能力(多一个清除入口、多一个筛选)。是差异,不是缺陷,列出来让派发方决定留不留。
  • 已裁决:移转约定或决策记录已接受的差异(例如同一组输入与结果下的控件替换)。列出并引裁决,不再分级。

证据

  • 每条差异引原型文件行号与正式文件行号,附并排截图(原型在左,正式在右,同角色同阶段)。行里写的「原型行为」「正式行为」必须能在该行引用的截图上看到;写行之前重新打开截图确认元素在场,看不到就不写这一行。行号引的是当次基准 commit 的文件,引用前 sed -n 把那几行读出来核对。截图用 Playwright 以同一视口各截一张,再拼成一张;命名 <页面>-<角色>-<阶段或状态>.png,单边图加后缀 -proto/-formal。
  • 只做只读操作:查询、选取、展开、切页签、未保存的表单。业务提交在浏览器层拦截;截图只证明画面与非提交互动。
  • 动态行为(点哪个控件、清除后停在哪、焦点落在哪)单张终点图证明不了,行里加一句操作步骤(「选待现勘页签→清除条件→停在全部」),配终点图。
  • 程序推导(没有实测)的条目单独标明。
  • 没有证据的差异不列。

Read the full file on GitHub · 107 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. 7d ago First seen · 107 lines · 108 tokens per session scan A 2e1aee8c36e4

Subscribe to this mod's changes

prototype-alignment-review is a skill published in the GitHub repository hxy91819/mason-skills (3 stars, last pushed yesterday), licensed MIT. It adds 108 tokens to every session and 2,318 once invoked, about $0.0004 per session on Opus 5.5. 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 2026-10-18.

Related

Other skills, from other repositories

webgl-holographic-foil

A self-contained WebGL2 hero: thin-film interference over a crushed-foil surface whose palette shifts with the viewing angle; move the cursor to tilt the film.

nexu-io/open-design · 41 tokens

html-ppt-hermes-cyber-terminal

OpenDesign + BYOK: choosing and wiring your own model, hands-on — cost, quality, and the routing decision. Built as a decision-grade AI literacy deck for engineers, IT, applied-AI teams.

nexu-io/open-design · 53 tokens

html-ppt-taste-brutalist

16:9 HTML deck in tactical-telemetry / CRT-terminal taste. Deactivated-CRT charcoal slides, white-phosphor monospace, hazard-red accent, scanline overlay, ASCII syntax, density over decoration. Distilled from Leonxlnx/taste-skill brutalist-skill (Tactical Telemetry mode).

nexu-io/open-design · 78 tokens

visual-ralph

Visual Ralph orchestration for frontend UI from generated references, static references, or live URL targets, using $ultragoal with built-in visual verdict and pixel-diff evidence until the implementation matches and leaves a reproducible design system.

Yeachan-Heo/oh-my-codex · 52 tokens

glance-canonical-layouts

Use this skill to create home screen widgets using Jetpack Glance Canonical Layouts from the Android Platform Samples project, or when asked to implement standard widget layout patterns (including Check List, Image Grid, Snap Scrolling, and Standard Toolbar).

android/skills · 56 tokens

accessibility

Consolidated accessibility skill entrypoint for WCAG 2.2, ARIA Authoring Practices, cognitive accessibility, Section 508, EN 301 549, design intent verification, and the Accessibility Planner workflow.

microsoft/hve-core · 47 tokens