3-identifying-architecture
Third step in building instruction context for codebase
Best use case
3-identifying-architecture is best used when you need a repeatable AI agent workflow instead of a one-off prompt.
Third step in building instruction context for codebase
Teams using 3-identifying-architecture 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/3-identifying-architecture/SKILL.mdinside your project - Restart your AI agent — it will auto-discover the skill
How 3-identifying-architecture Compares
| Feature / Agent | 3-identifying-architecture | 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?
Third step in building instruction context for codebase
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
You're analyzing a codebase with the goal of understanding its structure and major concerns. The tech stack is summarized in ./{output-folder}/1-techstack.md. Categorized files are listed in ./{output-folder}/2-file-categorization.json.
> This task may take some time — that is expected and acceptable.
> Do **not** skip files or produce partial results due to time or complexity. Accuracy and completeness are **mission-critical**.
> You are permitted to take as long as necessary to:
>
> - Review every relevant file
> - Extract actual patterns and conventions
> - Produce complete, high-fidelity output
> If a file is listed in ./{output-folder}/2-file-categorization.json or is part of a relevant domain, it **must** be included in your analysis.
> Do not optimize for speed or brevity. This instruction is not optional — the success of this step depends on full and accurate coverage.
Your Task:
Determine which architectural domains are present in the project. Consider:
- File structure and naming patterns
- Framework conventions
- Imports and usage patterns
- Configuration files
- Common architectural markers (e.g., components/, routes/, handlers/, services/, cli/, etc.)
**Critical Analysis - Mandatory vs Optional Patterns:**
For each domain you identify, determine:
- **REQUIRED**: Which services/hooks/patterns are consistently used across the codebase and appear to be architectural requirements?
- **CONSTRAINTS**: What types of implementations are clearly expected? (e.g., "all canvas work uses useCanvas hook", "all fractals use chaos game algorithms")
Example Domains to Detect:
You do not need to detect all of these — only include what's truly present.
There may also be domains that aren't listed here but are relevant to this specific project. Include any meaningful domains you identify.
Examples:
- ui: UI components, templates, or rendering logic
- routing: App or API routing (e.g., Next.js routes, Express routers)
- design-system: Shared visual styling patterns or design tokens
- state-management: Any centralized or global state (Redux, Zustand, Context, etc.)
- data-layer: Persistence and data-fetching (ORMs, REST clients, GraphQL)
- auth: Authentication / access control logic
Output:
Write a JSON object to ./{output-folder}/3-architectural-domains.json like so:
```json
{
"ui": {
"required_patterns": {
"canvas-rendering": "use useCanvas",
"mathematical-computing": "..."
},
"architectural_constraints": {
"canvas-rendering": "...",
"mathematical-computing": "..."
}
}
}
```
Only include domains you find concrete evidence for based on the actual codebase.
This analysis will help ensure future additions follow the established architectural patterns rather than introducing inconsistent approaches.
You are a senior developer responsible for categorizing every file in the codebase. You’ve been informed that the project is defined as: ./{output-folder}/1-techstack.md (read this file first)
After writing ./{output-folder}/3-file-categorization.json, continue to skill 4-domain-deep-dive and proceed accordingly with {output-folder} as the `output-folder`.Related Skills
Advanced Clean Hexagonal Architecture
Apply Clean Architecture and Hexagonal (Ports & Adapters) patterns for domain isolation and testability. Use when designing system boundaries, creating ports/adapters, or structuring domain-driven applications.
Architecture Decision Records (ADR)
Documenting significant architectural decisions with context, consequences, and rationale for future reference.
adr-architecture
Use when documenting significant technical or architectural decisions that need context, rationale, and consequences recorded. Invoke when choosing between technology options, making infrastructure decisions, establishing standards, migrating systems, or when team needs to understand why a decision was made. Use when user mentions ADR, architecture decision, technical decision record, or decision documentation.
acc-architecture-doc-template
Generates ARCHITECTURE.md files for PHP projects. Creates layer documentation, component descriptions, and architectural diagrams.
1k-architecture
OneKey monorepo architecture and code organization. Use when understanding project structure, package relationships, import rules, or component organization. Triggers on architecture, structure, packages, imports, hierarchy, dependencies, monorepo, organization.
astro
This skill provides essential Astro framework patterns, focusing on server-side rendering (SSR), static site generation (SSG), middleware, and TypeScript best practices. It helps AI agents implement secure authentication, manage API routes, and debug rendering behaviors within Astro projects.
vly-money
Generate crypto payment links for supported tokens and networks, manage access to X402 payment-protected content, and provide direct access to the vly.money wallet interface.
modal-deployment
Run Python code in the cloud with serverless containers, GPUs, and autoscaling using Modal. This skill enables agents to generate code for deploying ML models, running batch jobs, serving APIs, and scaling compute-intensive workloads.
ux
This AI agent skill provides comprehensive guidance for creating professional and insightful User Experience (UX) designs, covering user research, information architecture, interaction design, visual guidance, and usability evaluation. It aims to produce actionable, user-centered solutions that avoid generic AI aesthetics.
tech-blog
Generates comprehensive technical blog posts, offering detailed explanations of system internals, architecture, and implementation, either through source code analysis or document-driven research.
thor-skills
An entry point and router for AI agents to manage various THOR-related cybersecurity tasks, including running scans, analyzing logs, troubleshooting, and maintenance.
whisper-transcribe
Transcribes audio and video files to text using OpenAI's Whisper CLI, enhanced with contextual grounding from local markdown files for improved accuracy.