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.
npx skills add lh17708357536-gif/flutter-cn-overseas-app-skills --skill frontend-backend-alignmentgit clone --depth 1 https://github.com/lh17708357536-gif/flutter-cn-overseas-app-skillsWrote 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.
[](https://agentmods.dev/skills/lh17708357536-gif/flutter-cn-overseas-app-skills/frontend-backend-alignment)<a href="https://agentmods.dev/skills/lh17708357536-gif/flutter-cn-overseas-app-skills/frontend-backend-alignment"><img src="https://agentmods.dev/badge/skills/lh17708357536-gif/flutter-cn-overseas-app-skills/frontend-backend-alignment/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.
<a href="https://agentmods.dev/skills/lh17708357536-gif/flutter-cn-overseas-app-skills/frontend-backend-alignment"><img src="https://agentmods.dev/badge/skills/lh17708357536-gif/flutter-cn-overseas-app-skills/frontend-backend-alignment.svg" alt="Reviewed on agentmods" width="80" height="20"></a>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.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00096 | $0.04020 |
| Opus 5 | $0.00048 | $0.02010 |
| Sonnet 5 | $0.00019 | $0.00804 |
| Haiku 4.5 | $0.00010 | $0.00402 |
Grade A, and why
frontend-backend-alignment 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 12d 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.
How it starts
The opening of the file, as written. The whole thing — 321 lines — stays where its author put it; the contents beside it link to each section on GitHub.
前后端对齐规范 Skill
解决"代码 / 文档 / 版本 / API 字段四处对齐"难题。前端 Flutter + 后端 NestJS + 文档 Markdown 三者必须一致,本 skill 列举强约束 + 自检清单。
1. API 字段对齐:Freezed Model ↔ Prisma Schema
强约束:前端 lib/data/models/<resource>_model.dart 的 Freezed 字段 + 后端 server/prisma/schema.prisma 的 model 字段,一对一对齐。
| 后端 Prisma | 前端 Freezed | 说明 |
|---|---|---|
id String @id @default(uuid()) |
required String id |
主键 |
hotelId String @map("hotel_id") |
required String hotelId |
DB snake_case,TS/Dart camelCase |
title String |
required String title |
|
description String? |
String? description |
nullable 一致 |
tags String[] (Postgres) / String @db.Text(MySQL JSON) |
@Default(<>) List<String> tags |
数组字段两端类型对齐 |
createdAt DateTime |
required DateTime createdAt |
ISO 8601 字符串 ↔ DateTime |
metadata Json? |
Map<String, dynamic>? metadata |
JSON 字段 |
自检脚本:scripts/check_api_alignment.sh(建议每次 schema 改动后跑):
#!/usr/bin/env bash
# 1. 列 Prisma model 字段
echo "=== Prisma <Model> 字段 ==="
sed -n '/^model <Model> /,/^}/p' server/prisma/schema.prisma
# 2. 列 Freezed model 字段
echo "=== Freezed <Resource>Model 字段 ==="
grep -E "required|@Default|String\?|int\?|bool\?" lib/data/models/<resource>_model.dart
肉眼比对 → 字段名 / nullable / 类型 三者必须一致。
2. API 契约改动 → 文档同步铁律
每个 API 改动 → 同时更新三个地方:
1. 后端代码:
server/src/modules/<feature>/dto/<feature>.dto.ts # DTO 类
server/src/modules/<feature>/<feature>.controller.ts # @Post / @Get 端点
server/src/modules/<feature>/<feature>.service.ts # 业务逻辑
2. 前端代码:
lib/data/services/<feature>_api_service.dart # API 调用
lib/data/models/<feature>_model.dart # Freezed 数据类
3. 文档(强约束):
docs/api_contracts/<feature>.md # API 契约(请求/响应 JSON 示例)
docs/backend_spec.md # 后端架构总览(如新增端点段落)
docs/cards/<tool>.md # 前端工具卡片(5 章节)
强约束:
- ★ 改了代码 → 打开文档 → 检查是否一致 → 不一致立即更新
- ★ 文档过时比没文档更危险
- ★ 当前状态 / 实现 / 口径必须与源码一致,禁止历史结论冒充现状
- ★ 旧审计 / 旧验收文档失效后立即删除或标注"历史归档、不可作为当前依据"
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.
- 12d ago First seen · 321 lines · 96 tokens per session scan A 3d2e1781547c
frontend-backend-alignment is a skill published in the GitHub repository lh17708357536-gif/flutter-cn-overseas-app-skills (20 stars, last pushed 2mo ago), licensed MIT. It adds 96 tokens to every session and 4,020 once invoked, about $0.0005 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 2026-08-30.
Other skills, from other repositories
aso-listing
Research and improve app-store keywords, metadata, localization, and seasonal listing changes for Apple App Store and Google Play.
automobileapp
Automates the full mobile app release pipeline — version management, localized metadata, multi-device screenshot generation, i18n translations, and store submission for iOS and Android. Use when the user asks to "release my app", "bump the version", "generate store screenshots", "update metadata in all languages"…
managing-app-localizations
Manages i18n translation files and store metadata localization across iOS, Android, and Google Play. Use when the user says "add a language", "fix missing translations", "translate strings", "audit i18n", "missing locale keys", or any task involving language support. Source of truth for translation keys is…
selecting-app-locales
Enforces locale selection before any localisation, metadata, screenshot, or i18n task begins. Use when starting a new app, adding languages, preparing for store submission, or any time the locale set is unknown or unconfirmed. Presents both the Android BCP 47 locale list (localeconfig.xml) and the Apple App Store…
china-translate
A Chinese-English translation and localisation guide for technical text and product interfaces. Localisation means adapting wording and cultural references so they sound natural to users in the target language.
app-store-preflight-compliance
Pre-submission compliance scanner workflow for Apple App Store apps. Use when reviewing iOS, macOS, tvOS, watchOS, or visionOS projects (Swift, Objective-C, React Native, Expo) for App Store rejection risks, submission readiness, privacy compliance, or guideline violations.