agentleFS
karim-bhalwanikarim-bhalwani/agent-skills-collection/skills/architect/SKILL.md

architect

Skill0 starsChanged 10 months agoMITView on GitHub

Specialized in system architecture, API contracts, and modular black-box design. Use when creating technical specifications, designing system primitives, defining module boundaries and contracts, reviewing architecture for replaceability, or mapping system dependencies.

174 other projects use a version of this, 1 of them edited.

Adopted by

Most recently taken up by

Used with

Projects with it also use ecosystem-reference, fractal-delegation 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.
  • naman10parikhSkill

    ecosystem-reference

    Quick-access directory of Claude Code ecosystem repos, skills, plugins, MCPs, and patterns. Use when improving the harness.

    Also in 5 projects that use this

  • naman10parikhSkill

    fractal-delegation

    Also in 5 projects that use this

  • tristanphvnSkill

    ketchup-video

    Catch the user up like /keel:ketchup, with a short silent video of slides for what happened and the waiting calls as text under it. Use for /keel:ketchup-video.

    Also in 14 projects that use this

  • jaydubya818Skill

    figure-it-out

    Use when novel or multi-phase work needs an auditable workflow and no narrower playbook fits.

    Also in 55 projects that use this

  • ianclearySkill

    principle-explain-the-number

    Apply before you trust, report, or act on a number you measured: a speedup, a regression, a throughput, a latency, or an eval result. Find what limits it, and rule out that it measured something other than the work you think.

    Also in 29 projects that use this

  • eryzerzSkill

    make-bot-ui

    Use when building a custom UI (page, dashboard, buttons) that should wake a Grok Bot over a webhook, when the user must provide a webhook sender key, or when exposing that UI on Tailscale.

    Also in 20 projects that use this

  • +6 more from naman10parikh

The file

We split this skill into the rules it gives an agent

7 rules. 0 are common, 7 are distinctive, and 0 are very specific to this project.

  • 0

    Common

    Most of the 162 edited versions we read keep these.

  • 7

    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:

    Map Dependencies: Ensure no circular dependencies exist (Dry-run Dependency Map).

    line 33
  2. Distinctive:

    Every architectural design must produce or update a specification following this structure:

    line 38
  3. Distinctive:

    Success Criteria: All stakeholders approve the specification before implementation begins

    line 58
  4. Distinctive:

    Ensure each module has a single, clear responsibility

    line 66
  5. Distinctive:

    Ensure no circular dependencies in the dependency graph

    line 73
  6. Distinctive:

    Circular Dependencies: Not catching these during design leads to unmaintainable code.

    line 85
  7. Distinctive:

    Unclear Module Boundaries: When developers can't explain what a module does in one sentence, the boundary is fuzzy.

    line 86

“Common” is measured: kept by at least 6 in 10 of the 162 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

Architect Skill - System Design & Specification

Overview

The Architect skill focuses on the "What" and "Where" of a system, rather than the "How." It is used to design robust, scalable, and maintainable software architectures using black-box principles.

Core Principles

  1. Black Box Interfaces: Modules are defined by what they do, hiding how they do it.
  2. Replaceable Components: Design modules so they can be rewritten from scratch using only their interface.
  3. Single Responsibility: One module = one clear purpose.
  4. Primitive-First Design: Identify core data types (primitives) and design the system around their flow.
  5. Human-Centric: Optimize designs for cognitive load—one developer should be able to understand any single module.

Workflow

  1. Understand: Analyze requirements and identify core business logic primitives.
  2. Define Boundaries: Determine where modules start and end.
  3. Design Contracts: Define API endpoints, data models, and interface protocols.
  4. Map Dependencies: Ensure no circular dependencies exist (Dry-run Dependency Map).
  5. Output Specification: Produce a spec.md that serves as the source of truth for implementation.

Mandatory Output: spec.md Template

Every architectural design must produce or update a specification following this structure:

  • Feature Name & Overview: High-level goal and identified primitives.
  • File Structure: Proposed directory and file layout.
  • Data Models: Table/Object schemas with validation rules.
  • API Contracts: Method, Path, Payload, and Response (RFC 7807 for errors).
  • Architecture Diagrams: Mermaid diagrams showing component flow.
  • Dependency Map: Table identifying module interactions and risks.
  • Replaceability Assessment: Confirmation that modules can be reimplemented from their interfaces.

When to Use

  • Starting a new feature.
  • Major system refactors.
  • Defining database schemas or API contracts.
  • Identifying and isolating system risks.

Outputs & Deliverables

  • Primary Output: spec.md - Complete technical specification document
  • Success Criteria: All stakeholders approve the specification before implementation begins
  • Quality Gate: Specification passes review by implementer and guardian skills

Standards & Best Practices

Black Box Design

  • Define modules by their contracts, not implementations
  • Ensure each module has a single, clear responsibility
  • Design for replaceability - any module should be rewritable from its interface

Data Flow Architecture

  • Identify core business primitives early
  • Map data transformations through the system
  • Ensure no circular dependencies in the dependency graph

Constraints

  • NO implementation code. Snippets for interfaces or data models only.
  • NO testing logic.
  • NO deployment configs.

Common Pitfalls

  • Over-Engineering: Designing for every possible future scenario. Start with the simplest design that solves today's problem; refactor when needs emerge.
  • God Modules: Creating one massive module instead of breaking concerns. Single Responsibility is non-negotiable.
  • Circular Dependencies: Not catching these during design leads to unmaintainable code. Always verify the dependency graph is acyclic.
  • Unclear Module Boundaries: When developers can't explain what a module does in one sentence, the boundary is fuzzy. Refactor immediately.
  • Missing API Contracts: Vague interfaces lead to integration errors downstream. Always document input/output types, validation rules, and error responses.
  • Ignoring Primitive Selection: Choosing the wrong core data types cascades through the entire design. Validate primitives early.

Integration Points

PhaseInput FromOutput ToContext
Discoverybrainstorming, thinkerThis specUnderstand requirements and constraints
SpecificationCore business logicimplementer, data-modelerImplement according to spec
ValidationN/AguardianReview for security and patterns
OperationsDeployment requirementsops-managerInfrastructure needs based on architecture

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.