catch-admin: Skill for Claude Code

.claude/skills/curd/SKILL.md

curd is a skill for Claude Code from JaguarJack/catch-admin. It costs 42 tokens per session (3,737 once invoked), scanned A, original, Apache-2.0.

A complete CRUD module generator for CatchAdmin that turns a database table definition into matching backend PHP files and Vue pages. Vue is a JavaScript framework used to build the user interface.

In plain words
What is it for?
Use it when you provide a table structure and want a full module with database setup, record management, Excel import and export, API routes, and list and create pages.
Why use it?
It coordinates the separate steps required for migrations, models, controllers, validation, routes, imports, exports, and CRUD screens, so the module structure stays consistent.

Skill for Claude Code

Written for Claude Code: installed under .claude/.

This is JaguarJack/catch-admin's own configuration. It tells Claude Code how to work on catch-admin 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 catch-admin configures →

Reuse

Borrowing it

Nothing to install: this file belongs to JaguarJack/catch-admin. 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/JaguarJack/catch-admin/v5/.claude/skills/curd/SKILL.md
Clone the repo
git clone --depth 1 https://github.com/JaguarJack/catch-admin

Made for: Claude Code.

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 curd

README.md
[![agentmods](https://agentmods.dev/badge/skills/jaguarjack/catch-admin/curd/github.svg)](https://agentmods.dev/skills/jaguarjack/catch-admin/curd)
Your own site
<a href="https://agentmods.dev/skills/jaguarjack/catch-admin/curd"><img src="https://agentmods.dev/badge/skills/jaguarjack/catch-admin/curd/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 curd

Your own site · 80×15
<a href="https://agentmods.dev/skills/jaguarjack/catch-admin/curd"><img src="https://agentmods.dev/badge/skills/jaguarjack/catch-admin/curd.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 42 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 3,737 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. Third-party audits
  • NVIDIA SkillSpector pass 7 Sept 2026
How audits are shown
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 $0.00042 $0.03737
Opus 5.5 $0.00017 $0.01495
Sonnet 5.5 $0.00008 $0.00747
Haiku 4.5 $0.00004 $0.00374

Measured 2mo ago against content hash ba879d7a42f5, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

curd 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 2mo 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.

.claude/skills/curd/SKILL.md · 491 lines

How it starts

The opening of the file, as written. The whole thing — 491 lines — stays where its author put it; the contents beside it link to each section on GitHub.

CatchAdmin CRUD Generator

一键生成完整 CRUD 模块 - 从数据表定义到前后端完整实现。

Sub-Skills (9 个子 Skills)

Step Skill 生成文件
1 01-parse-table - (解析输入)
2 02-migration database/migrations/*.php
3 03-model Models/{Model}.php
4 04-controller Http/Controllers/{Model}Controller.php
5 05-request Http/Requests/{Model}Request.php
6 06-routes routes/route.php
7 07-export Export/{Model}.php
8 08-import Import/{Model}.php
9 09-vue-pages index.vue + create.vue

Input: Table Definition

Table: products
Fields:
- id (primary key)
- name (string, 100, required)
- category_id (foreign key -> categories)
- description (text, nullable)
- price (decimal 10,2, required)
- stock (integer, default 0)
- status (tinyint, default 1)

Output: Complete Module Structure

modules/{Module}/
├── Http/
│   ├── Controllers/{Model}Controller.php
│   └── Requests/{Model}Request.php
├── Models/{Model}.php
├── Export/{Model}.php
├── Import/{Model}.php
├── database/migrations/*.php
└── routes/route.php

web/src/views/{module}/
├── index.vue
└── create.vue

Pre-checks (执行前)

  • 模块存在性:若 modules/{Module} 不存在,先询问是否创建新模块。
  • 文件冲突:目标文件已存在时,先询问覆盖或增量修改。
  • 路由/权限前缀:检查 modules/{Module}/routes/route.php 是否已有相同资源前缀。
  • 依赖/配置:新增依赖或改动 config/ 前必须先询问。

Output Contract (输出契约)

  • 必须生成 9 步完整产物(迁移/模型/控制器/请求/路由/导入导出/前端页)。
  • 所有路径、类名、命名空间与 {Module}/{Model}/{table} 一致。
  • 前端 catch-table 的 api 与后端路由前缀保持一致。

Consistency Validation (生成后校验)

  • 迁移包含 CatchAdmin 标准字段:creator_id/created_at/updated_at/deleted_at + 索引。
  • Model/Request 与迁移字段一致(类型/必填/默认值)。
  • Route API 前缀与前端 api/permission 前缀一致。

Fallback Rules (失败兜底)

  • 输入缺失关键字段(如 table/fields)时必须先澄清,停止生成。
  • 复杂关系或非标准业务逻辑需用户确认后再生成。

Workflow

Step 1: Parse Table Definition → 01-parse-table

Extract from user input:

  • Table name (snake_case plural)
  • Model name (PascalCase singular)
  • Module name (PascalCase)
  • Fields with types, constraints, and relationships

Read the full file on GitHub · 491 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. 2mo ago First seen · 491 lines · 42 tokens per session scan A ba879d7a42f5

Subscribe to this mod's changes

curd is a skill published in the GitHub repository JaguarJack/catch-admin (940 stars, last pushed 10d ago), licensed Apache-2.0. It adds 42 tokens to every session and 3,737 once invoked, about $0.0002 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 2026-08-30.

Related

curd compared with skills from other repositories

curd next to 6 skills from other repositories
ModTypeStarsLast pushLicenceScanTokensWorks with
curdJaguarJack/catch-adminSkill94010d agoApache-2.0A42Claude Code
owl-admin-app-devslowlyo/owl-adminSkill6203d agoMITA114Claude Code, Codex
owl-admin-devtools-generatorslowlyo/owl-adminSkill6203d agoMITA82Claude Code, Codex
owl-admin-ops-commandsslowlyo/owl-adminSkill6203d agoMITA71Claude Code, Codex
owl-admin-extension-moduleslowlyo/owl-adminSkill6203d agoMITA75Claude Code, Codex
owl-admin-frontend-assetsslowlyo/owl-adminSkill6203d agoMITA80Claude Code, Codex
owl-admin-amis-pageslowlyo/owl-adminSkill6203d agoMITA84Claude Code, Codex