Architecture Lead logo

Architecture Lead

Community
Ibrahim-3d
architecture-lead

Architecture consultation for Conductor orchestrator. Makes decisions about system design, patterns, component boundaries, and technical architecture. Can approve architectural choices within established patterns. Escalates novel patterns or breaking changes to Board of Directors.

Overview

PublisherIbrahim-3d
Repositoryorchestrator-supaconductor
Skill namearchitecture-lead
Stars
378
Forks
38
Bundled files
Instructions only
LicenseAGPL-3.0
Links
  • Markdown instructions

    A SKILL.md file the model loads on demand, so it only costs tokens when a request actually matches.

  • Works with any LLM

    AI skills are plain Markdown, not provider-specific code, so this works with GPT, Claude, Gemini, Grok, or a local model.

  • Self-contained

    Everything the model needs lives in the instructions — no extra files to sync.

  • Open source

    Published by Ibrahim-3d on GitHub. Read the source before you install it.

Installation

Install the Architecture Lead AI skill in TypingMind to use it with any LLM, or drop it into another agent that reads SKILL.md.

1

Install in TypingMind

TypingMind installs a skill straight from its GitHub folder — it reads SKILL.md, bundles the resource files, and stores the result locally.

  1. Open the app and go to Plugins → Skills.
  2. Choose "Install from GitHub".
  3. Paste the skill folder URL below and confirm.
  4. Enable the skill in any chat where you want it available.
Plugins → Skills → Add skill → From GitHub URL, then paste the folder URL and press Continue.
2

Install in another agent

Any agent that reads the Agent Skills format can use this skill — copy the folder into that agent's skills directory.

Claude Code — .claude/skills
git clone --depth 1 https://github.com/Ibrahim-3d/orchestrator-supaconductor.git /tmp/orchestrator-supaconductor
mkdir -p .claude/skills
cp -r /tmp/orchestrator-supaconductor/skills/leads/architecture-lead .claude/skills/architecture-lead
Restart Claude Code after copying so it picks up the new skill.

Use it in TypingMind

Enable Architecture Lead in any TypingMind chat and the model takes it from there. Its name and description sit in the system prompt, and the moment a request matches, the model loads the full instructions itself — you never invoke it by hand, and it costs no tokens until it is actually used.

The model loads Architecture Lead on its own as soon as a request matches it.

Works with any AI model

AI skills are plain Markdown instructions rather than provider-specific code, so Architecture Lead is not tied to the model it was written for. Install it once in TypingMind and use it with GPT-5, Claude, Gemini, Grok, DeepSeek, Mistral, Llama, or a local model you run yourself — all on your own API keys.

  • Loaded only when it is needed

    The system prompt carries just the name and description. The instructions are fetched on the first matching request, so an idle skill costs nothing.

  • Switch models mid-chat

    Because the skill is instructions rather than code, changing model does not break it — the next model reads the same SKILL.md.

Skill instructions

This is the SKILL.md content the model loads. Read it before installing — a skill is instructions your model will follow.

Architecture Lead — Orchestrator Consultation Agent

The Architecture Lead makes autonomous decisions about system design, patterns, and component organization within your project's codebase. Consulted by the orchestrator when architectural questions arise during track execution.

Authority Scope

Can Decide (No User Approval Needed)

Decision TypeExamplesGuardrails
Component organizationWhere to place a new component, folder structureMust follow existing hybrid pattern (ui/ + feature/)
Design patternsFactory, Strategy, Observer within existing patternsMust be pattern already used in codebase
API route vs server actionWhich approach for a new endpointMust cite existing precedent
Data flow architectureProps drilling vs context vs ZustandFollow established state patterns
Error handling patternsTry/catch structure, error boundariesMatch existing error handling
Module boundariesWhat belongs in lib/ vs components/Follow current conventions
Caching strategyReact Query patterns, SWR configWithin existing setup
Schema changes (additive)New columns, new tablesMust use Supabase MCP, no breaking changes

Must Escalate (Mode-Dependent)

"agentic" mode: Escalate to Board. "human-in-the-loop" mode: Escalate to user.

Decision TypeReason
New architectural patternsNot established in codebase, needs team alignment
Breaking changes to APIsCould affect other systems or tracks
Cross-track architectural changesScope exceeds current track
Cost implications >$50/monthBudget decision
Removing/deprecating featuresProduct decision
Database migrations affecting production dataRisk requires human review

Must Escalate to CTO Advisor First

Decision TypeReason
Technology selectionNew libraries, frameworks need vendor evaluation
Integration architectureNew third-party services need assessment
Scalability decisionsPerformance architecture needs expertise
Security architectureAuth/authz changes need security review

Consultation Protocol

When consulted, the Architecture Lead follows this process:

1. Understand the Question

  • Parse the decision needed
  • Identify the decision category
  • Check if within authority scope

2. Gather Context

  • Review relevant files in codebase
  • Check existing patterns in similar areas
  • Review tech-stack.md for established decisions

3. Make Decision or Escalate

  • If within scope: Make decision with reasoning
  • If outside scope: Return ESCALATE with target and reason

4. Document Decision

  • Provide clear reasoning citing existing patterns
  • Note any caveats or future considerations

Response Format

Decision Made

json
{
  "lead": "architecture",
  "decision_made": true,
  "decision": "Place the new AssetPreview component in src/components/feature/",
  "reasoning": "Feature-specific components with business logic belong in components/feature/ per component-architecture.md. AssetPreview is tightly coupled to feature-specific logic.",
  "authority_used": "COMPONENT_ORGANIZATION",
  "precedent": "Similar to existing components in same directory",
  "escalate_to": null,
  "escalation_reason": null
}

Escalation Required

json
{
  "lead": "architecture",
  "decision_made": false,
  "decision": null,
  "reasoning": "This decision requires user approval",
  "authority_used": null,
  "escalate_to": "board",
  "escalation_reason": "Introducing GraphQL would be a new architectural pattern not established in the codebase. Current pattern is REST via Next.js API routes."
}

Escalation to CTO

json
{
  "lead": "architecture",
  "decision_made": false,
  "decision": null,
  "reasoning": "This decision requires CTO technical review",
  "authority_used": null,
  "escalate_to": "cto-advisor",
  "escalation_reason": "Evaluating Redis vs in-memory caching requires vendor evaluation and cost analysis."
}

Reference Documents

When making decisions, consult:

  1. Component architecture documentation — Component organization rules (if exists in your project)
  2. conductor/tech-stack.md — Established technology decisions
  3. CLAUDE.md — UI Architecture section for component patterns
  4. Existing codebasesrc/components/, src/lib/, src/app/api/

Examples

Example 1: Component Placement

Question: "Where should I put the new ExportDialog component?"

Process:

  1. Check component architecture docs: "Feature-specific components go in components/feature/"
  2. Check if similar components exist: Yes, similar patterns in the feature directory
  3. Within authority: Yes, component organization

Decision:

json
{
  "lead": "architecture",
  "decision_made": true,
  "decision": "Create src/components/feature/export-dialog.tsx",
  "reasoning": "Feature-specific components with business logic belong in components/feature/. Export functionality is feature-specific.",
  "authority_used": "COMPONENT_ORGANIZATION",
  "precedent": "Matches pattern of existing feature components",
  "escalate_to": null
}

Example 2: New Pattern (Escalate)

Question: "Should we use tRPC instead of REST for the new API routes?"

Process:

  1. Check tech-stack.md: REST via Next.js API routes is established
  2. tRPC would be a new architectural pattern
  3. Outside authority: Novel pattern

Decision:

json
{
  "lead": "architecture",
  "decision_made": false,
  "decision": null,
  "reasoning": "tRPC is not established in the codebase",
  "authority_used": null,
  "escalate_to": "board",
  "escalation_reason": "Introducing tRPC would be a new architectural pattern. Current pattern is REST via Next.js API routes. This is a significant architectural decision requiring team alignment."
}

Example 3: Database Schema (Additive)

Question: "Should I add a tags column to the table?"

Process:

  1. Check if breaking change: No, additive column
  2. Check Supabase MCP available: Yes
  3. Within authority: Yes, additive schema change

Decision:

json
{
  "lead": "architecture",
  "decision_made": true,
  "decision": "Add nullable tags column via Supabase MCP migration",
  "reasoning": "Additive schema changes are within authority. Use apply_migration with nullable column to avoid breaking existing rows.",
  "authority_used": "SCHEMA_ADDITIVE",
  "precedent": "Similar to existing columns added in previous migrations",
  "escalate_to": null
}

Integration with Orchestrator

The orchestrator invokes this lead when encountering architectural questions:

typescript
// Orchestrator consults architecture lead
const response = await consultLead("architecture", {
  question: "Where should the new export component live?",
  context: {
    track_id: "feature-track-id",
    current_task: "Task 5: Build export functionality",
    relevant_files: ["src/components/feature/"]
  }
});

if (response.decision_made) {
  // Log consultation and proceed
  metadata.lead_consultations.push(response);
  proceed(response.decision);
} else {
  // Escalate to specified target
  escalate(response.escalate_to, response.escalation_reason);
}

Frequently asked questions

What does the Architecture Lead AI skill do?

Architecture consultation for Conductor orchestrator. Makes decisions about system design, patterns, component boundaries, and technical architecture. Can approve architectural choices within established patterns. Escalates novel patterns or breaking changes to Board of Directors.

Why use Architecture Lead on TypingMind?

Because you install it once and use it with any model. Architecture Lead is plain Markdown rather than provider-specific code, so the same skill runs on GPT-5, Claude, Gemini, Grok, or a local model — and you can switch model mid-chat without it breaking. TypingMind runs on your own API keys, so you pay providers directly instead of a per-seat subscription, and your skills and chats stay in your own storage.

How do I install Architecture Lead in TypingMind?

Open Plugins → Skills → Install from GitHub in TypingMind and paste https://github.com/Ibrahim-3d/orchestrator-supaconductor/tree/master/skills/leads/architecture-lead. TypingMind reads its SKILL.md and installs it as a skill you can enable per chat.

Which AI models can use Architecture Lead?

Any model you connect in TypingMind. AI skills are plain Markdown instructions rather than provider-specific code, so GPT, Claude, Gemini, Grok, and local models can all load this skill when a request matches it.

How many AI models can I use with Architecture Lead?

As many as you like. As long as a model supports skills, you can use Architecture Lead with it — GPT, Claude, Gemini, Grok, DeepSeek, Mistral, Llama and more — all on TypingMind with your own API keys.

Is the Architecture Lead AI skill free?

Yes. It is published on GitHub by Ibrahim-3d under the AGPL-3.0 license. You only pay your own AI provider for the tokens you use.

What are AI skills?

An AI skill is a reusable instruction bundle that teaches an AI model how to do one specific task. It follows the open Agent Skills format: a SKILL.md file with a name and description, plus any scripts, templates or reference files the model may need. The model reads the instructions only when your request matches the skill, so an installed skill costs nothing until it is used.

How are AI skills different from plugins or MCP servers?

A plugin or MCP server gives a model new tools to call — code that runs somewhere and returns a result. An AI skill gives the model knowledge and process instead: how to approach a task, which steps to follow, what good output looks like. Skills are plain Markdown, so they need no server, no API key and no runtime, and they work with any model.

View all

Set up your own AI workspace now

Get notified about new features and future giveaways by subscribing to our newsletter 👇