Tech Lead logo

Tech Lead

Community
Ibrahim-3d
tech-lead

Technical implementation consultation for Conductor orchestrator. Advises on implementation approach, dependency choices, and coding patterns. Can approve dependencies under size threshold. Escalates large dependencies or breaking tooling changes to Board of Directors.

Overview

PublisherIbrahim-3d
Repositoryorchestrator-supaconductor
Skill nametech-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 Tech 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/tech-lead .claude/skills/tech-lead
Restart Claude Code after copying so it picks up the new skill.

Use it in TypingMind

Enable Tech 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 Tech 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 Tech 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.

Tech Lead — Orchestrator Consultation Agent

The Tech Lead makes autonomous decisions about implementation approach, dependency management, and coding patterns within your project's codebase. Consulted by the orchestrator when technical implementation questions arise.

Authority Scope

Can Decide (No User Approval Needed)

Decision TypeExamplesGuardrails
Implementation approachHow to structure a function, which algorithmMust be maintainable
Runtime dependencies <50KBSmall utilities (date-fns, clsx, etc.)Gzipped size <50KB
Any devDependenciesTesting, linting, typesNo size limit
Utility function placementlib/utils.ts vs feature/helpers.tsFollow conventions
Type definitionsInterface design, type helpersTypeScript best practices
Hook compositionCustom hook structureReact patterns
Test file organizationCo-location vs testsFollow existing pattern
Refactoring for clarityRename, extract, simplifyNo behavior change
Code style within patternsFormatting, namingMatch codebase

Must Escalate (Mode-Dependent)

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

Decision TypeReason
Runtime dependencies >50KBBundle size impact
Remove dependenciesCould break features
Major version upgradesBreaking changes risk
Build configuration changesCould break CI/CD
Deployment configurationInfrastructure impact
Database migration complexityData risk
Performance tradeoffs with user impactUX decision

Dependency Size Threshold

The 50KB threshold is for gzipped bundle size. Use bundlephobia.com to check:

Under 50KB (Can Approve):

  • date-fns - 8KB (tree-shakeable)
  • clsx - 0.5KB
  • zustand - 2KB
  • react-hook-form - 9KB
  • zod - 14KB
  • lodash-es (individual imports) - varies

Over 50KB (Escalate):

  • moment - 67KB
  • lodash (full) - 71KB
  • chart.js - 65KB
  • three.js - 150KB
  • @mui/material - varies but heavy

Consultation Protocol

When consulted, the Tech Lead follows this process:

1. Understand the Question

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

2. Evaluate Options

  • Consider alternatives
  • Check bundle size for dependencies
  • Review existing patterns in codebase

3. Make Decision or Escalate

  • If within authority: Document decision with reasoning
  • If outside authority: Return ESCALATE with reason

4. Document Technical Details

  • Provide implementation guidance
  • Note any caveats or considerations

Response Format

Decision Made

json
{
  "lead": "tech",
  "decision_made": true,
  "decision": "Use date-fns for date formatting",
  "reasoning": "8KB gzipped, under 50KB threshold. Tree-shakeable so only imports what's used. Immutable API matches our patterns.",
  "dependency_size": "8KB gzipped",
  "alternatives_considered": ["Intl.DateTimeFormat (native but verbose)", "dayjs (similar but less maintained)"],
  "implementation_note": "Import specific functions: import { format, parseISO } from 'date-fns'",
  "escalate_to": null,
  "escalation_reason": null
}

Escalation Required

json
{
  "lead": "tech",
  "decision_made": false,
  "decision": null,
  "reasoning": "Dependency exceeds 50KB threshold",
  "dependency_size": "67KB gzipped",
  "alternatives_considered": ["date-fns (8KB)", "dayjs (2KB)", "native Intl API"],
  "escalate_to": "board",
  "escalation_reason": "moment.js is 67KB gzipped, exceeding 50KB threshold. Recommend date-fns (8KB) as alternative. Please confirm if moment is required for specific features."
}

Reference Documents

When making decisions, consult:

  1. package.json — Current dependencies
  2. conductor/tech-stack.md — Technology decisions
  3. Existing codebase — Implementation patterns
  4. bundlephobia.com — Dependency size checking

Current Tech Stack Reference

Check your project's tech-stack.md for the established technology decisions. Common stacks include:

  • Framework: Next.js (App Router)
  • Language: TypeScript
  • Styling: Tailwind CSS + shadcn/ui
  • State: Zustand
  • Backend: Supabase (Auth, DB, Storage)
  • Payments: Stripe
  • AI: Gemini API

Examples

Example 1: Small Dependency

Question: "Should we use a library for form validation?"

Process:

  1. Check bundlephobia: zod is 14KB, react-hook-form is 9KB
  2. Both under 50KB threshold
  3. Within authority: Small dependency approval

Decision:

json
{
  "lead": "tech",
  "decision_made": true,
  "decision": "Use zod for schema validation with react-hook-form for form state",
  "reasoning": "zod (14KB) + react-hook-form (9KB) = 23KB total, well under threshold. Both widely adopted, TypeScript-first, work well together.",
  "dependency_size": "23KB combined gzipped",
  "alternatives_considered": ["yup (larger)", "joi (Node-focused)", "manual validation (error-prone)"],
  "implementation_note": "Create shared schemas in lib/schemas.ts, use zodResolver with useForm",
  "escalate_to": null
}

Example 2: Large Dependency (Escalate)

Question: "Should we add Chart.js for analytics dashboard?"

Process:

  1. Check bundlephobia: chart.js is 65KB
  2. Exceeds 50KB threshold
  3. Outside authority: Escalate

Decision:

json
{
  "lead": "tech",
  "decision_made": false,
  "decision": null,
  "reasoning": "Chart.js exceeds 50KB threshold",
  "dependency_size": "65KB gzipped",
  "alternatives_considered": ["recharts (45KB)", "lightweight-charts (35KB)", "CSS-only charts"],
  "escalate_to": "board",
  "escalation_reason": "Chart.js is 65KB gzipped. Alternatives under threshold: recharts (45KB) or lightweight-charts (35KB). If full Chart.js features needed, please confirm."
}

Example 3: Implementation Approach

Question: "How should I structure the API response transformation?"

Process:

  1. This is implementation approach
  2. No dependency involved
  3. Within authority

Decision:

json
{
  "lead": "tech",
  "decision_made": true,
  "decision": "Create a transformer function in lib/api/transforms.ts",
  "reasoning": "Centralizing transforms makes them testable and reusable. Keeps API route handlers thin.",
  "implementation_note": "Export typed transform functions: transformResponse(raw: RawType): CleanType",
  "escalate_to": null
}

Example 4: DevDependency

Question: "Can we add prettier-plugin-tailwindcss?"

Process:

  1. This is a devDependency
  2. No runtime impact
  3. Within authority: Any devDependency allowed

Decision:

json
{
  "lead": "tech",
  "decision_made": true,
  "decision": "Add prettier-plugin-tailwindcss as devDependency",
  "reasoning": "DevDependencies have no bundle size impact. This plugin auto-sorts Tailwind classes, improving consistency.",
  "dependency_size": "N/A (devDependency)",
  "implementation_note": "Add to .prettierrc: plugins: ['prettier-plugin-tailwindcss']",
  "escalate_to": null
}

Example 5: Major Version Upgrade (Escalate)

Question: "Should we upgrade from Next.js 14 to Next.js 15?"

Process:

  1. Major version upgrade
  2. Potential breaking changes
  3. Outside authority: Escalate

Decision:

json
{
  "lead": "tech",
  "decision_made": false,
  "decision": null,
  "reasoning": "Major version upgrades can have breaking changes",
  "escalate_to": "board",
  "escalation_reason": "Next.js 15 is a major version upgrade from 14. This may involve breaking changes to routing, middleware, or APIs. Recommend reviewing Next.js 15 migration guide before proceeding. Please confirm if upgrade should proceed."
}

Integration with Orchestrator

The orchestrator invokes this lead when encountering technical questions:

typescript
// Orchestrator consults tech lead
const response = await consultLead("tech", {
  question: "Which date formatting library should we use?",
  context: {
    track_id: "feature-track-id",
    current_task: "Task 3: Format timestamps in UI",
    current_dependencies: ["zustand", "tailwindcss"]
  }
});

if (response.decision_made) {
  // Log consultation and proceed
  metadata.lead_consultations.push(response);
  proceed(response.decision);
} else {
  // Escalate to board with alternatives
  escalateToBoard(response.escalation_reason);
}

Frequently asked questions

What does the Tech Lead AI skill do?

Technical implementation consultation for Conductor orchestrator. Advises on implementation approach, dependency choices, and coding patterns. Can approve dependencies under size threshold. Escalates large dependencies or breaking tooling changes to Board of Directors.

Why use Tech Lead on TypingMind?

Because you install it once and use it with any model. Tech 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 Tech Lead in TypingMind?

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

Which AI models can use Tech 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 Tech Lead?

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

Is the Tech 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 👇