plugins/software-project/skills/categorize-task/SKILL.md
Reference guide for classifying development tasks into the 8-phase clean architecture structure (Foundational → Models → Services → Data → Rules → State Management → UI → Tests). Use when you need to determine which architectural phase a task belongs to.
npx skillsauth add hirogakatageri/hirokata categorize-taskInstall this skill globally with one command. Works with Claude Code, Cursor, and Windsurf.
3 of 9 scanners reported clean
Some scanners were skipped, did not run, or reported a non-clean status. Review each row below.
Classify development tasks into the 8-phase clean architecture structure. This helps organize work into the correct architectural layer.
Provide a reference guide for determining which architectural phase (Foundational → Models → Services → Data → Rules → State Management → UI → Tests) a development task belongs to.
Tasks must be classified into one of these sequential phases:
Purpose: Abstract classes, base setup, toolings, utilities, infrastructure
Belongs here if the task involves:
Examples:
Purpose: Entities, models, JSON classes, data structures
Belongs here if the task involves:
Examples:
Purpose: APIs, external services, network layer
Belongs here if the task involves:
Examples:
Purpose: Repositories, DAOs, data access layer, local storage
Belongs here if the task involves:
Examples:
Purpose: Use cases, business rules, domain logic
Belongs here if the task involves:
Examples:
Purpose: View models, presenters, state handlers, controllers
Belongs here if the task involves:
Examples:
Purpose: Widgets, components, screens, views, user interface
Belongs here if the task involves:
Examples:
Purpose: Unit tests, integration tests, e2e tests, test utilities, test fixtures
Belongs here if the task involves:
Examples:
To classify a task, ask these questions in order:
Remember: Dependencies flow inward
Tests → UI → State Management → Rules → Data → Services → Models → Foundational
| If the task creates... | Phase | |------------------------|-------| | Abstract base classes, utilities | 1 - Foundational | | Data models, entities, DTOs | 2 - Models | | API clients, external integrations | 3 - Services | | Repositories, DAOs, local storage | 4 - Data | | Use cases, business rules | 5 - Rules | | ViewModels, Blocs, state handlers | 6 - State Management | | Screens, widgets, components | 7 - UI | | Unit tests, integration tests, e2e tests | 8 - Tests |
Some tasks may span multiple phases. In these cases:
Example: "Implement user authentication"
Configuration files: Phase 1 (Foundational) if infrastructure, Phase 7 (UI) if theme/styling
Validation: Phase 5 (Rules) if business validation, Phase 6 (State Management) if form state validation
Error handling: Goes with the phase where the error occurs
Testing: Always Phase 8 (Tests), regardless of which phase the tested code belongs to
Documentation: Same phase as the feature being documented
If you're unsure between two phases:
Task: "Add user profile picture upload"
Classification:
Result: Phase 7 (UI) - but may require supporting tasks in earlier phases:
development
This skill should be used when the user reports an error, bug, or unexpected behavior and wants it diagnosed and fixed. Trigger on phrases like "check this error", "check this bug", "here's an error", "here's a bug", "I have an error", "I have a bug", "found a bug", "got an error", "debug this", "this is broken", "fix this error", "verify and fix", or any message that includes a stack trace or error output. Runs a structured workflow: gather context, investigate configured log/code sources, report root cause with ranked solutions, then apply a test-driven fix.
testing
This skill should be used when the user says "check svelte env vars", "check environment variables", "validate env vars", "check env var patterns", "audit environment variables", "audit env vars", "check SvelteKit env", "svelte env check", or any phrase asking to audit or validate SvelteKit environment variable usage patterns.
data-ai
Internal skill used by the session-tracker logger agent to append a session entry to .logs/YYYY-MM-DD-log.md, creating the file and directory if needed. Not user-invocable.
data-ai
Internal skill used by the session-tracker logger agent to query git for committed and uncommitted changes in the past 28 hours. Not user-invocable.