Skip to content
Agentmart
Submit a tool

architecture-before-coding

Use before implementing a new feature or non-trivial code change when the agent should design responsibilities, boundaries, interfaces, data flow, and…

Skill by WangYao-GoGoGo

IndexedMIT
Write a review

Chalk Labs

Need help deploying architecture-before-coding?

Chalk Labs sets up agents like this inside real teams: connected to your tools, tested on your data, with a human in the loop where it matters.

Book a call

Install

Works with Claude Code, Claude apps, Codex, Cursor, Gemini CLI, GitHub Copilot, VS Code, OpenCode, Goose, Windsurf. Read the repository before you give any tool access to your data.

npx agentmarket install skill/wangyao-gogogo-architecture-before-coding

Asks which of your tools to add it to (Claude Code, Codex, Cursor, VS Code, Windsurf, Gemini CLI, Claude Desktop) and shows the change first. See https://agentmart.dev/cli.

Get the weekly diff

The weekly diff: one email a week with new agent tools, notable updates and grade changes, plus security alerts for tools you follow. Double opt-in, one-click unsubscribe.

We use your email only for this newsletter. Privacy

About

Use before implementing a new feature or non-trivial code change when the agent should design responsibilities, boundaries, interfaces, data flow, and verification before writing code. Especially useful for object-oriented Java or Python work, backend services, domain logic, and changes likely to grow over time.

Use cases: design, backend, data, writing

No reviews yet. Installed it? Reviews come from verified installers only. How reviews work

Permissions

What this skill can do and what it asks for, from its SKILL.md. Checked Oct 25, 2026.

Tools
No tools found
Secrets
None asked for
Install scripts
None found

Network hosts it talks to 1

  • codeload.github.com · found in install command

Files it touches

  • ~/.claude/skills/architecture-before-coding

What's inside

Skill name
architecture-before-coding
Description
Use before implementing a new feature or non-trivial code change when the agent should design responsibilities, boundaries, interfaces, data flow, and verification before writing code. Especially useful for object-oriented Java or Python work, backend services, domain logic, and changes likely to grow over time.
License
MIT
Instructions
69 lines in SKILL.md · view on GitHub

Files (2)

  • README.md
  • SKILL.md

SKILL.md (first lines)

# Architecture Before Coding

Use this skill before writing new code or making a broad feature change. The goal is to prevent large unstructured code generation by forcing a small architecture pass first.

## When To Use

- The user asks for a new feature with multiple responsibilities.
- The change touches domain logic, persistence, APIs, workflows, or integrations.
- The code may need extension points later.
- The implementation could become a long method, god class, large conditional, or tangled dependency graph.

Do not use this skill for tiny edits, simple bug fixes, formatting, or one-line changes.

## Workflow

1. Inspect the existing codebase and identify local conventions.
2. State the feature goal in one or two sentences.
3. Identify responsibilities and assign an owner for each one.
4. Define boundaries: public interfaces, internal helpers, data models, external services, persistence, and side effects.
5. Decide whether a known pattern is justified. If unsure, prefer the simpler structure.
6. Propose the smallest implementation sequence that keeps behavior verifiable.
7. Implement in small steps and verify with existing tests or focused checks.

## Knowledge To Use

- `knowledge/architecture/application-styles/` for in-process application structure.
- `knowledge/architecture/integration-patterns/` when events, async workflows, gateways, or read/write model separation are involved.
- `knowledge/architecture/distributed-systems/` when service boundaries or deployment units are involved.
- `knowledge/principles/` and `knowledge/patterns/` for responsibility and pattern decisions.

## Design Checklist

- What is the domain concept?
- Which class, module, or service owns the core rule?
- Which dependencies point inward, and which point outward?
- What should be mocked or substituted in tests?
- What future change is likely, and is it worth designing for now?
- Which abstraction would be harmful if the feature never grows?

## Pattern Selection Rules

- Use Strategy when behavior varies by type, mode, policy, or provider.
- Use Factory Method or Abstract Factory when object creation varies and callers should not know concrete classes.
- Use Builder when construction has many optional parts or validation steps.
- Use Adapter when integrating an incompatible external interface.
- Use Facade when callers need a simpler boundary over a complex subsystem.
- Use Observer when many subscribers react to domain events.
- Use Template Method only when the algorithm skeleton is stable and subclasses fill clear steps.

If none of these conditions is present, use plain classes or functions with clear names.

## Output Format Before Coding

When the task is non-trivial, produce this concise plan before editing:

```markdown
Design sketch:
- Goal:
- Responsibilities:
- Boundaries:
- Pattern, if any:
- Files likely to change:
- Verification:
- Overengineering check:
```

After the design sketch, proceed with implementation unless the user asks to pause.

From WangYao-GoGoGo/architecture-agent-skills, MIT.

More from WangYao-GoGoGo/architecture-agent-skills

Signals

Stars
0
Forks
0
Open issues
0
Last commit (this folder)
Apr 27, 2026 (6 months ago)

From GitHub (fetched Oct 24, 2026).

Details

License
MIT
First seen
Oct 24, 2026
Last checked
Oct 24, 2026

More from WangYao-GoGoGo

Done for you

Rather not set it up yourself?

Chalk Labs scopes, builds and runs agents for your team: the task audit, the eval harness, the integrations and the weekly ops report. Fixed scope, priced before we start.

See how we build AI agents →Read the case studies

Chalk Labs is a two-founder AI and growth studio. We build AI agents, CRMs and MVPs for Web3 and AI companies, and have shipped 50+ product and token launches.

launches shipped
50+
launches shipped
media placements
500+
media placements
founders on every account
2
founders on every account

Press we've placed: Forbes · CoinDesk · Decrypt · Cointelegraph · The Block

Rahil Jain, Co-founder, Chalk Labs. Ex-Goldman Sachs engineer. You talk to the person who builds it.

Get architecture-before-coding running in your business

Tell us what you want to automate. A founder replies within one working day with a plan, not a pitch deck.

Goes to the Chalk Labs founders, not the newsletter. Privacy

Need help deploying architecture-before-coding?

CallGet help
Cite this page

architecture-before-coding skill. Agent Mart. https://agentmart.dev/skills/wangyao-gogogo-architecture-before-coding (last updated 2026-10-24)