Create or enhance backend tasks with detailed implementation steps. Supports TWO modes:
MODE A: Enhance existing task (add detailed steps to task in file)
MODE B: Create new standalone task file (can contain single or multiple tasks)
IMPORTANT: This skill creates MICRO-LEVEL atomic steps, NOT macro architecture plans.
For architecture planning or feature scoping, use EnterPlanMode instead.
Use this skill when:
- Running /backend.plan command
- User asks for "atomic steps", "step-by-step plan with verification"
- Have a specific task and need implementation steps
- User wants to create a standalone task file (not from story)
- Need granular steps: Types → DB → Repository → Service → API → Tests
DO NOT use for:
- Architecture planning (use EnterPlanMode)
- General development planning
- Feature scoping or estimation
Output:
- MODE A: Update specific task section in file with Implementation Steps
- MODE B: Create new standalone-{name}.md file with one or multiple tasks
Create or enhance backend tasks with detailed implementation steps. Supports TWO modes:
MODE A: Enhance existing task (add detailed steps to task in file)
MODE B: Create new standalone task file (can contain single or multiple tasks)
IMPORTANT: This skill creates MICRO-LEVEL atomic steps, NOT macro architecture plans.
For architecture planning or feature scoping, use EnterPlanMode instead.
Use this skill when:
- Running /backend.plan command
- User asks for "atomic steps", "step-by-step plan with verification"
- Have a specific task and need implementation steps
- User wants to create a standalone task file (not from story)
- Need granular steps: Types → DB → Repository → Service → API → Tests
DO NOT use for:
- Architecture planning (use EnterPlanMode)
- General development planning
- Feature scoping or estimation
Output:
- MODE A: Update specific task section in file with Implementation Steps
- MODE B: Create new standalone-{name}.md file with one or multiple tasks
Plan
⚠️ CRITICAL RULES - READ FIRST
DETECT MODE: Determine if input is an existing task reference or a new requirement description
If input looks like story-user-api Task 1 or standalone-fix-auth Task 2: MODE A
If input is a new requirement (e.g., "Add user authentication"): MODE B
MODE A - Enhance Existing Task:
Read the task file from docs/reference/backend/tasks/
User must specify task number (e.g., "Task 1", "Task 2")
Add or update the "Implementation Steps" section for that specific task
Keep all other sections intact
Save back to the same file
MODE B - Create Standalone Task File:
Analyze the requirement - is it simple (1 task) or complex (multiple tasks)?
If complex, break into multiple tasks (like task-breakdown does)
Use filename: standalone-{requirement-name}.md (kebab-case)
Save to docs/reference/backend/tasks/
File format: same as story-based (multiple task sections)
READ CONSTRAINTS FIRST:
Must read docs/reference/backend/constraints.md for tech stack
Language Configuration
Before generating any content, check aico.json in project root for language field to determine the output language. If not set, default to English.
MODE A: Enhance Existing Task
Process
Read task file: Get task details from docs/reference/backend/tasks/{task-file}.md
## Step Granularity
Each step = ONE atomic action:
| Good Steps | Bad Steps |
|------------|-----------|
| Create service file with imports | Create service with all methods |
| Add service skeleton (empty methods) | Implement entire service |
| Implement single endpoint | Implement all endpoints |
| Write one test case | Write all tests |
## Step Types
### Setup Step
```markdown
**Files**: Create: `src/services/user.service.ts`
**Action**: Create file with basic structure
**Verify**: `npx tsc --noEmit` → No errors
Implementation Step
**Files**: Modify: `src/services/user.service.ts:L8-L10`**Action**: Implement user creation method
**Verify**: `npm test` → Service tests pass
Test Step
**Files**: Create: `src/services/__tests__/user.service.test.ts`**Action**: Write unit test for user creation
**Verify**: `npm test user.service` → 1 test passed
