architecting
Architects new features through the full lifecycle. Use when designing, planning, implementing, or extending features. Triggers on 'new feature', 'design', 'plan', 'implement', 'architect', 'prd', 'spec'.
Best use case
architecting is best used when you need a repeatable AI agent workflow instead of a one-off prompt.
Architects new features through the full lifecycle. Use when designing, planning, implementing, or extending features. Triggers on 'new feature', 'design', 'plan', 'implement', 'architect', 'prd', 'spec'.
Teams using architecting should expect a more consistent output, faster repeated execution, less prompt rewriting.
When to use this skill
- You want a reusable workflow that can be run more than once with consistent structure.
When not to use this skill
- You only need a quick one-off answer and do not need a reusable workflow.
- You cannot install or maintain the underlying files, dependencies, or repository context.
Installation
Claude Code / Cursor / Codex
Manual Installation
- Download SKILL.md from GitHub
- Place it in
.claude/skills/architecting/SKILL.mdinside your project - Restart your AI agent — it will auto-discover the skill
How architecting Compares
| Feature / Agent | architecting | Standard Approach |
|---|---|---|
| Platform Support | Not specified | Limited / Varies |
| Context Awareness | High | Baseline |
| Installation Complexity | Unknown | N/A |
Frequently Asked Questions
What does this skill do?
Architects new features through the full lifecycle. Use when designing, planning, implementing, or extending features. Triggers on 'new feature', 'design', 'plan', 'implement', 'architect', 'prd', 'spec'.
Where can I find the source code?
You can find the source code on GitHub using the link provided at the top of the page.
SKILL.md Source
# Architect Feature
> **Role**: Oversee the entire lifecycle of a Feature—from 0 to 1 to N—ensuring architectural consistency and UX integrity.
## When to use this skill
- Creating a **new feature** from scratch
- Extending an **existing feature** with new capabilities
- Implementing code based on a finalized **design spec**
## How to use it
Choose a mode based on your intent:
| Mode | Trigger keywords | Scenario |
|------|-----------------|----------|
| **DESIGN** | new feature, 设计 | Create a brand-new feature directory from scratch |
| **EXTEND** | 扩展, add capability | Add sub-capabilities to an existing feature |
| **BUILD** | implement, 实现 | Code an already-designed spec |
---
### DESIGN Mode (从 0 到 1)
1. **Context Check**: Read `src/features/` to avoid reinventing the wheel.
2. **KISS Check**: Really need a new directory? If < 3 files, consider `shared`.
3. **Generate Spec**: Use `resources/spec-template.md`.
4. **Tech Decisions**: Define dependencies and Schema.
**Output**: `src/features/{name}/docs/spec.md`
---
### EXTEND Mode (从 1 到 N)
1. **Locate Host**: Identify the target Feature.
2. **Architecture Conformance**: Read the host's `spec.md`, follow its design philosophy.
3. **Incremental Design**: Append an "Extension Section" instead of creating new docs.
**Output**: Updated `src/features/{name}/docs/spec.md` or core code.
---
### BUILD Mode (编码实现)
1. **Read Contract**: Always read `spec.md` first for scope.
2. **Quality Gate**: Establish "Type-First" (Zod Schema -> TypeScript Type).
3. **Layered Implementation**:
* **L1 Core**: Schema & Service (no UI, pure logic)
* **L2 UI**: Components (no business logic)
* **L3 Integration**: Pages & Routing
4. **Self-Verify**: `npm run type-check` and `npm run lint` must pass.
---
## Resources
| Resource | Purpose |
|----------|---------|
| [spec-template.md](resources/spec-template.md) | Standardized design doc template |
| [kiss-checklist.md](resources/kiss-checklist.md) | Anti-over-engineering checklist |
| [anti-patterns.md](resources/anti-patterns.md) | Architecture anti-pattern warnings |
---
## Quality Baseline
As an architect, you MUST reject:
- ❌ **Circular Dependencies**: Features importing each other.
- ❌ **Global State Abuse**: Local state pushed to global store.
- ❌ **Any Type**: Even one `any` is a disgrace.
- ❌ **Implicit Logic**: Critical logic without comments or docs.Related Skills
architecting-data
Strategic guidance for designing modern data platforms, covering storage paradigms (data lake, warehouse, lakehouse), modeling approaches (dimensional, normalized, data vault, wide tables), data mesh principles, and medallion architecture patterns. Use when architecting data platforms, choosing between centralized vs decentralized patterns, selecting table formats (Iceberg, Delta Lake), or designing data governance frameworks.
architecting-database-schema
Defines schema, attributes, indexes, and enums for Tourly collections. Use when setting up the database in Appwrite.
architecting-systems
Best practices and rules for architecting scalable, maintainable systems.
architecting-innovation-agents
Propose multi-agent and workflow architectures for CustomGPT.ai Labs projects, showing how Claude Code, CustomGPT.ai, and supporting tools interact to deliver the desired business outcome.
bgo
Automates the complete Blender build-go workflow, from building and packaging your extension/add-on to removing old versions, installing, enabling, and launching Blender for quick testing and iteration.
activations
Query activation logs to check for errors and view volume
activation-map
Use to link segments and insights to GTM plays, owners, and measurement plans.
activate-lightning-page
Activates a newly deployed Lightning App Page so it appears in the App Launcher. Use when you've deployed a new flexipage and need to make it accessible to users.
actions-pattern
Garante que novas Actions sigam o padrão de classes actions reutilizáveis do Easy Budget.
actionbook
This skill should be used when the user needs to automate multi-step website tasks. Activates for browser automation, web scraping, UI testing, or building AI agents. Provides complete action manuals with step-by-step instructions and verified selectors.
actionable-review-format-standards
Standardized output format for code reviews with severity labels, file:line references, and fix code snippets. Use when generating review reports that need consistent, actionable feedback structure.
action-policy-coder
Use proactively for authorization with ActionPolicy. Creates policies, scopes, and integrates with GraphQL/ActionCable. Preferred over Pundit for composable, cacheable authorization.