Skip to content
Agentmart
Submit a tool

architecture

Route architecture work to the right lens.

Skill by ryanmazzolini

IndexedMIT
Write a review

Chalk Labs

Need help deploying architecture?

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/ryanmazzolini-architecture

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

Route architecture work to the right lens. Use when shaping or reviewing consequential choices across code, data, interfaces, domain language, and systems.

Use cases: data

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

What's inside

Skill name
architecture
Description
Route architecture work to the right lens. Use when shaping or reviewing consequential choices across code, data, interfaces, domain language, and systems.
License
MIT
Instructions
16 lines in SKILL.md · view on GitHub

Files (12)

  • SKILL.md
  • data-structures.md · references/
  • domain-language.md · references/
  • interface-design.md · references/
  • presentation.md · references/
  • concurrency.md · references/relational-databases/
  • concurrency.md · references/relational-databases/postgresql/
  • seams-tests-and-notes.md · references/
  • shape-a-change.md · references/
  • simplest-sufficient-change.md · references/
  • simplify-codebase.md · references/
  • system-review.md · references/

SKILL.md (first lines)

# Architecture

Inspect the live code, tests, documentation, and recent decisions first. Route the current question to the smallest matching branch and read that reference first. Follow its conditional pointers only when their stated conditions apply. Combine branches only when the current decision genuinely needs both.

- **Shape a change:** read [references/shape-a-change.md](references/shape-a-change.md) when the experience is settled but data, rules, local interfaces, or code structure are not.
- **Choose a data structure:** read [references/data-structures.md](references/data-structures.md) when a consequential representation or access pattern needs comparison.
- **Design an interface:** read [references/interface-design.md](references/interface-design.md) when a module boundary or public API needs meaningfully different options.
- **Simplify existing code:** read [references/simplify-codebase.md](references/simplify-codebase.md) when looking for repeated decisions, needless layers, misplaced seams, or mock-heavy tests.
- **Review a system:** read [references/system-review.md](references/system-review.md) for architecture decisions, migrations, scaling, rollout, or operational risk.
- **Review relational database concurrency:** read [references/relational-databases/concurrency.md](references/relational-databases/concurrency.md) when transactions can overlap on shared state or a change affects isolation, locking, contention, or retries.
- **Choose an implementation:** read [references/simplest-sufficient-change.md](references/simplest-sufficient-change.md) immediately before implementing a settled behavior.
- **Clarify domain language:** read [references/domain-language.md](references/domain-language.md) when domain terms are ambiguous, overloaded, or inconsistent.

Across branches, lead with the recommendation or current decision, then expose evidence and mechanics under named sections so the reader can drill in. If spatial layout or comparison would materially improve judgment, read [references/presentation.md](references/presentation.md). Stop at the branch's checkpoint instead of carrying architecture work into implementation without approval.

From ryanmazzolini/pi-skills, MIT.

More from ryanmazzolini/pi-skills

Signals

Stars
0
Forks
0
Open issues
0
Last commit (this folder)
Sep 9, 2026 (1 month ago)

From GitHub (fetched Oct 24, 2026).

Details

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

More from ryanmazzolini

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 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?

CallGet help
Cite this page

architecture skill. Agent Mart. https://agentmart.dev/skills/ryanmazzolini-architecture (last updated 2026-10-24)