| name | create-feature |
| description | [Implementation] Scaffold a new feature with backend and frontend components Use when this capability is needed. |
[IMPORTANT] Use TaskCreate to break ALL work into small tasks BEFORE starting — including tasks for each file read. This prevents context loss from long files. For simple tasks, AI MUST ATTENTION ask user whether to skip.
Prerequisites: MUST ATTENTION READ before executing:
Understand Code First — HARD-GATE: Do NOT write, plan, or fix until you READ existing code.
- Search 3+ similar patterns (
grep/glob) — cite file:line evidence
- Read existing files in target area — understand structure, base classes, conventions
- Run
python .claude/scripts/code_graph trace <file> --direction both --json when .code-graph/graph.db exists
- Map dependencies via
connections or callers_of — know what depends on your target
- Write investigation to
.ai/workspace/analysis/ for non-trivial tasks (3+ files)
- Re-read analysis file before implementing — never work from memory alone
- NEVER invent new patterns when existing ones work — match exactly or document deviation
BLOCKED until: - [ ] Read target files - [ ] Grep 3+ patterns - [ ] Graph trace (if graph.db exists) - [ ] Assumptions verified with evidence
Quick Summary
Goal: Scaffold a new full-stack feature with backend (entities, CQRS, controllers) and frontend (Angular components, services).
Workflow:
- Analyze — Break down requirements, identify scope (backend/frontend/full-stack)
- Identify — Determine target microservice and Angular app/module
- Plan — Map out entities, commands/queries, endpoints, components, DTOs
- Approve — Present plan, wait for explicit user approval before creating files
- Create — Scaffold files in order: entities → application → DTOs → controllers → frontend
Key Rules:
- DO NOT proceed without explicit user approval
- Follow platform patterns from CLAUDE.md and
.github/prompts/ templates
- Build order: Domain → Application → API → Frontend
- Verify with
dotnet build and nx build after creation
Be skeptical. Apply critical thinking, sequential thinking. Every claim needs traced proof, confidence percentages (Idea should be more than 80%).
Create a new feature: $ARGUMENTS
Steps:
-
Analyze Requirements
- Break down the feature requirements
- Identify the scope (backend only, frontend only, or full-stack)
-
Identify Service Location
- Determine the appropriate microservice for backend
- Identify the Angular app/module for frontend
-
Plan Implementation
- Domain entities needed
- CQRS Commands/Queries
- API endpoints (controllers)
- Angular components and services
- DTOs and validation
-
Use Project Patterns
- Reference patterns from CLAUDE.md
- Use
.github/prompts/ templates for scaffolding:
create-cqrs-command.prompt.md
create-cqrs-query.prompt.md
create-entity-event.prompt.md
create-angular-component.prompt.md
create-api-service.prompt.md
-
Wait for Approval
- Present the implementation plan
- DO NOT proceed without explicit approval
-
Create Files (After Approval)
Execute in this order:
- Domain entities (
.Domain/Entities/)
- Application layer (
.Application/UseCaseCommands/, .Application/UseCaseQueries/)
- Entity DTOs (
.Application/EntityDtos/)
- API controllers (
.Api/Controllers/)
- Frontend components and services
-
Verify
- Build backend:
dotnet build
- Build frontend:
nx build <app-name>
Closing Reminders
- MANDATORY IMPORTANT MUST ATTENTION break work into small todo tasks using
TaskCreate BEFORE starting
- MANDATORY IMPORTANT MUST ATTENTION search codebase for 3+ similar patterns before creating new code
- MANDATORY IMPORTANT MUST ATTENTION cite
file:line evidence for every claim (confidence >80% to act)
- MANDATORY IMPORTANT MUST ATTENTION add a final review todo task to verify work quality
- MANDATORY IMPORTANT MUST ATTENTION validate decisions with user via
AskUserQuestion — never auto-decide
MANDATORY IMPORTANT MUST ATTENTION READ the following files before starting:
- MANDATORY IMPORTANT MUST ATTENTION search 3+ existing patterns and read code BEFORE any modification. Run graph trace when graph.db exists.
Converted and distributed by TomeVault — claim your Tome and manage your conversions.