Delegate independent tasks to specialized agents working concurrently with isolated context.
Task Breakdown
aico-backend-task-breakdown
Break down PM story into organized tasks in a single file following LAYERED ARCHITECTURE order: Types → Database → Repository → Service → API → Tests. UNIQUE VALUE: Creates single task file (story-{name}.md) containing all tasks for a story. Tasks are ordered by backend architecture layers. Use...
SKILL.md
Full skill instructions
Task Breakdown
⚠️ CRITICAL RULES - READ FIRST
BEFORE doing anything, you MUST:
-
CHECK EXISTING TASK FILE FIRST:
- ALWAYS check if
story-{story-name}.mdalready exists indocs/reference/backend/tasks/ - If exists: READ it and continue from current progress (add new tasks or update existing ones)
- If not exists: Create new task breakdown file
- NEVER re-break down existing tasks
- ALWAYS check if
-
FILE NAMING:
- Pattern:
story-{story-name}.md(single file per story) - Example:
story-user-profile.md - All tasks for this story go into this ONE file
- Tasks are separated by
---dividers
- Pattern:
-
MULTIPLE TASKS IN ONE FILE:
- One file contains ALL tasks for the story
- Each task = independently testable section
- Clear scope and acceptance criteria per task
- Tasks numbered sequentially (Task 1, Task 2, etc.)
-
ALWAYS SAVE TO CORRECT PATH:
- Path:
docs/reference/backend/tasks/story-{story-name}.md - NO exceptions, NO other locations
- Path:
-
READ CONTEXT FIRST:
- Read story from
docs/reference/pm/stories/ - Read design from
docs/reference/backend/designs/if exists - Read design system from
docs/reference/backend/design-system.md - Read constraints from
docs/reference/backend/constraints.md
- Read story from
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.
Process
- Read story/PRD: Load from
docs/reference/pm/stories/ordocs/reference/pm/versions/ - Read design (if exists): Load from
docs/reference/backend/designs/ - Read constraints: Load design system and technical constraints
- Identify components: What backend layers are needed
- Identify interactions: What APIs and data flows are needed
- Break into tasks: Independently testable, single responsibility, by architecture layer
- Order by dependencies: Types → DB → Repository → Service → API → Tests
- Generate single file: Create
story-{story-name}.mdwith all tasks in sections - Update Story file: Add "Related Tasks" section to story file with link to task file
- Summary: Show created file and next steps
Task File Format
See Task File Template for complete structure.
Key points:
- Single file contains all tasks for the story
- Tasks numbered sequentially (Task 1, Task 2, etc.)
- Each task has: Description, Context, Acceptance Criteria, Scope, Implementation Steps
- Progress section at the end tracks completion
- Both story-based and standalone use the same format (only filename differs)
- Backend tasks ordered by architecture layers: Types → DB → Repository → Service → API → Tests
Updating Story File
After generating the task file, ALWAYS update the story file to add the "Related Tasks" section:
## Related Tasks
### Backend Tasks
Task breakdown: [docs/reference/backend/tasks/story-user-profile.md](../backend/tasks/story-user-profile.md)
**Progress**: 0/6 tasks completed
- [ ] Task 1: Define Types
- [ ] Task 2: Database Schema
- [ ] Task 3: Repository Layer
- [ ] Task 4: Service Layer
- [ ] Task 5: API Endpoints
- [ ] Task 6: Add Tests
Key points:
- Add this section at the end of the story file (before any existing notes)
- Include link to the task file
- Use
- [ ]checkboxes for each task (will be checked when task completes) - List tasks in execution order (Types → DB → Repository → Service → API → Tests)
- Keep the section organized by frontend/backend if both exist
- Include progress counter (X/Y tasks completed)
Output Example
After breaking down "user-profile" story:
Created task file for story 'user-profile':
✓ docs/reference/backend/tasks/story-user-profile.md
Task breakdown includes:
- Task 1: Define Types (setup)
- Task 2: Database Schema (feature)
- Task 3: Repository Layer (feature)
- Task 4: Service Layer (feature)
- Task 5: API Endpoints (feature)
- Task 6: Add Tests (testing)
Total: 6 tasks
Next steps:
1. Review task breakdown in story-user-profile.md
2. Use /backend.plan to add detailed steps to specific tasks
3. Use /backend.implement to start executing tasks
Key Rules
- ALWAYS create a single file containing all tasks for the story
- MUST use
story-{story-name}.mdnaming (NOT multiple files) - ALWAYS include test tasks at the end
- MUST note dependencies between tasks (in each task's metadata)
- Keep tasks focused - not too big, not too small
- Each task section is self-contained with clear acceptance criteria
- Separate tasks with
---dividers - Include Story Progress section at the end of file
Common Mistakes
- ❌ Tasks too large (full feature) → ✅ Break into layers
- ❌ Tasks too small (add one field) → ✅ Group related work
- ❌ Skip dependencies → ✅ Note which tasks depend on others
- ❌ Forget testing → ✅ Always include test tasks
- ❌ Create multiple files → ✅ Use single file with multiple task sections
More Other skills
brand-guidelines
Applies Anthropic's official brand colors and typography to any sort of artifact that may benefit from having Anthropic's look-and-feel. Use it when brand colors or style guidelines, visual formatting, or company design standards apply.
theme-factory
Toolkit for styling artifacts with a theme. These artifacts can be slides, docs, reportings, HTML landing pages, etc. There are 10 pre-set themes with colors/fonts that you can apply to any artifact that has been creating, or can generate a new theme on-the-fly.
internal-comms
A set of resources to help me write all kinds of internal communications, using the formats that my company likes to use. Claude should use this skill whenever asked to write some sort of internal communications (status reports, leadership updates, 3P updates, company newsletters, FAQs, incident reports, project updates, etc.).
Fundamental design principles for writing maintainable, testable Python code.
responsive-design
Modern responsive layouts using container queries, fluid typography, CSS Grid, and mobile-first strategies.
Generate Playwright tests from scenarios using interactive browser exploration and validation.
Automated website exploration and test case generation using Playwright.
Modern React state management with Redux Toolkit, Zustand, Jotai, and React Query for every state category.
gdpr-data-handling
GDPR-compliant data handling with consent management, data subject rights, and privacy controls.
Python error handling patterns including input validation, exception hierarchies, and partial failure handling. Use when implementing validation logic, designing exception strategies, handling batch processing failures, or building robust APIs.
refactor-plan
Detailed multi-file refactor planning with safety checks and rollback guidance.
