agentleFS
Sign inStart free
shiranjitshiranjit/agentic-primer/skills/architecture/SKILL.md

architecture

Skill1 starsChanged 4 months agoMITView on GitHub

Architecture standards and decision rules for this project. Use this skill whenever designing a new feature, service, component, data model, or API; whenever choosing a library, framework, or technology; whenever creating a plan that touches system structure; and whenever reviewing a plan or PR for architectural fitness. Consult it even for "small" features — small features that ignore architecture become large problems.

136 other projects use a version of this.

Adopted by

Most recently taken up by

Used with

Projects with it also use intelligent-routing, bash-linux and 10 more.

Other files people use alongside this one.

Files found in the same public projects as a version of this one, more often than they turn up anywhere else. Each project counts once, large collections count for less, and this file's own repository is left out.
  • SKB3002Skill

    intelligent-routing

    Automatic agent selection and intelligent task routing. Analyzes user requests and automatically selects the best specialist agent(s) without requiring explicit user mentions.

    Also in 6 projects that use this

  • xenitV1Skill

    bash-linux

    Bash/Linux terminal patterns. Critical commands, piping, error handling, scripting. Use when working on macOS or Linux systems.

    Also in 8 projects that use this

  • xenitV1Skill

    red-team-tactics

    Red team tactics principles based on MITRE ATT&CK. Attack phases, detection evasion, reporting.

    Also in 8 projects that use this

  • SKB3002Skill

    nextjs-react-expert

    React and Next.js performance optimization from Vercel Engineering. Use when building React components, optimizing performance, eliminating waterfalls, reducing bundle size, reviewing code for performance issues, or implementing server/client-side optimizations.

    Also in 3 projects that use this

  • +8 more from xenitV1

The file

We split this skill into the rules it gives an agent

4 rules. 0 are common, 4 are distinctive, and 0 are very specific to this project.

  • 0

    Common

    Most of the 118 edited versions we read keep these.

  • 4

    Distinctive

    This author's own choices. Worth a look.

  • 0

    Very specific

    Tied to their project's names, files or tools. Probably skip.

  • Common
  • Distinctive
  • Very specific
  1. Distinctive:

    Keep every design decision consistent with the system's established architecture, so that code written by any agent, in any session, fits …

    line 9
  2. Distinctive:

    Boring technology wins: Prefer widely used, well-documented libraries.

    line 22
  3. Distinctive:

    Keep the feature small enough that its tests can genuinely cover it.

    line 29
  4. Distinctive:

    Check, in order: Does it respect the client/server split?

    line 32

“Common” is measured: kept by at least 6 in 10 of the 118 edited versions of this file we could read. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.

Keep what fits and drop the rest. Your version, ready for your agents.
Files
SKILL.md

Architecture Skill

Purpose

Keep every design decision consistent with the system's established architecture, so that code written by any agent, in any session, fits the same product without translation.

System shape (edit for your project)

  • Client: iOS app (SwiftUI). Owns UI/UX, user flows, input capture, and client-side validation. No business logic that the server must also enforce.
  • Server: Python services. Owns all business logic, document lifecycle rules, and integrations. The client asks; the server decides.
  • Database: Postgres. All schema changes travel through versioned migrations (Alembic). Never hand-edit a schema.
  • Repos: one per side (client repo, server repo). Cross-side requirements travel as handoff documents committed to the consuming repo — never as chat context alone.

Non-negotiable rules

  1. Server is the source of truth. Any rule the business depends on (state machines, permissions, totals) is enforced server-side, even if the client also checks it.
  2. State machines are explicit. Documents with lifecycles (e.g., estimate → approved → invoice) are modeled as explicit states with allowed transitions. No implicit status via booleans.
  3. APIs are contracts. New or changed endpoints require: request/response schema, error cases, and a handoff document. Breaking changes require a version bump and a migration note.
  4. Migrations only. Database changes are Alembic migrations, reviewed like code. Production is initialized and evolved by replaying migrations — never by DDL snapshots.
  5. Boring technology wins. Prefer widely used, well-documented libraries. A new dependency requires a one-paragraph justification in the plan.
  6. Integration points are proven first. For any new technology or integration, build a hello-world vertical slice end-to-end before building features on it.

When planning a feature

  • State which components change (client / server / schema / infra).
  • Identify the riskiest element (new tech, new integration) and schedule it first.
  • Define the API contract before implementation begins.
  • Keep the feature small enough that its tests can genuinely cover it.

When reviewing (plans or PRs)

Check, in order: Does it respect the client/server split? Are lifecycle rules server-enforced? Is the API contract documented? Are schema changes migrations? Any new dependency justified? If any answer is no — the review verdict is NO-GO with the specific rule cited.

Download now (ZIP)

Does it work?

Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.

No reviews yet

People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.

  • It worked
  • Partly
  • It didn't
What did you use it for? e.g. Reviewing pull requests in a Rails app

Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.

Your trail

Files you open will collect here, so you can find them again.

Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.

Now do this for your own.

Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.

Check your setup, free