agentleFS
maxwell2732maxwell2732/claudecode-research-harness-workflow/skills/crud/SKILL.md

crud

Skill42 starsChanged 6 days agoMITView on GitHub

Explicit helper for CRUD scaffolding and API endpoint generation. Do NOT load for: UI components, form design, database schema discussion, or general implementation.

2 other projects use a version of this.

Adopted by

Most recently taken up by

The file

We split this skill into the rules it gives an agent

3 rules. About 0 are common, 3 are distinctive, and 0 are very specific to this project.

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈3

    Distinctive · estimate

    This author's own choices. Worth a look.

  • 0

    Very specific

    Tied to their project's names, files or tools. Probably skip.

  • Common
  • Distinctive
  • Very specific
  1. Distinctive:

    Create API endpoints (REST or tRPC)

    line 59
  2. Distinctive:

    Add validation schemas (Zod)

    line 60
  3. Distinctive:

    Create unit tests for each endpoint

    line 65

≈ “Common” is an estimate: at least 1 in 5 of the 350,495 skill files we read have a rule of the same kind, not the same words. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.

Keep what fits and drop the rest. Your version, ready for your agents.
Files
SKILL.md

CRUD Skill

Auto-generates CRUD functionality for specified entities (tables) at production-ready level.

Quick Reference

  • "Create CRUD for task management" → /crud tasks
  • "Want search and pagination too" → Includes all together
  • "Include permissions (who can view/edit)" → Sets up authorization/rules together

Deliverables

  • CRUD + validation + authorization + tests, complete production-safe set
  • Minimize diff to match existing DB/code

Features:

  • Validation (Zod) auto-add
  • Auth/authorization (Row Level Security) auto-config
  • Relations (one-to-many, many-to-many) support
  • Pagination, search, filters
  • Auto-generated test cases

Auto-invoke Skills

This skill must explicitly invoke the following skills with the Skill tool:

SkillPurposeWhen to Call
implImplementation (parent skill)CRUD feature implementation
verifyVerification (parent skill)Post-implementation verification

Execution Flow

Detailed steps are described in the phases below.

Phase 1: Entity Analysis

  1. Parse entity name from $ARGUMENTS
  2. Detect existing schema (Prisma, Drizzle, raw SQL)
  3. Infer field types and relations

Phase 2: CRUD Generation

  1. Generate model/schema if needed
  2. Create API endpoints (REST or tRPC)
  3. Add validation schemas (Zod)
  4. Configure authorization rules

Phase 3: Test Generation

  1. Create unit tests for each endpoint
  2. Add integration tests
  3. Generate test fixtures

Phase 4: Verification

  1. Run type check
  2. Run tests
  3. Verify build

Supported Frameworks

FrameworkDetectionGenerated Files
Next.js + Prismaprisma/schema.prismaAPI routes, Prisma client
Next.js + Drizzledrizzle.config.tsAPI routes, Drizzle queries
Expressexpress in package.jsonControllers, routes
Honohono in package.jsonRoute handlers

Output Structure

src/
├── lib/
│   └── validations/
│       └── {entity}.ts        # Zod schemas
├── app/api/{entity}/
│   ├── route.ts              # GET (list), POST (create)
│   └── [id]/
│       └── route.ts          # GET, PUT, DELETE
└── tests/
    └── {entity}.test.ts      # Test cases

Related Skills

  • impl - Feature implementation
  • verify - Build verification
  • auth - Authentication/authorization

Download now (ZIP)

Does it work?

Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.

No reviews yet

People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.

  • It worked
  • Partly
  • It didn't
What did you use it for? e.g. Reviewing pull requests in a Rails app

Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.

Your trail

Files you open will collect here, so you can find them again.

Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.

Now do this for your own.

Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.