skills.rest
datorresb
datorresbCOMMUNITY
Explore all skills by this author →
WebsiteGitHub

technical-lead-role

Delegate coding task planning and execution to subagents with tracked reviews.

Updated Jan 23, 2026
Search Tags:#memory#CLAUDE.md#code-review#task-delegation#agent-orchestration#backlog-management#technical-lead
One-click install
npx skills add https://github.com/datorresb/vibecoding-starter --skill technical-lead-role
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: technical-lead-role
Source: https://github.com/datorresb/vibecoding-starter/tree/main/.claude/skills/core/technical-lead-role
Command: npx skills add https://github.com/datorresb/vibecoding-starter --skill technical-lead-role

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

The Skill provides a structured framework for AI-driven software development workflows by separating planning from execution, ensuring tasks are properly scoped, delegated to subagents, and rigorously reviewed.

Core Features & Use Cases

  • Planning & orchestration: main thread handles architecture, task decomposition, and risk assessment; subagents execute well-defined tasks using the Task tool.
  • Backlog-driven work: creates tasks, tracks progress, and documents decisions to ensure traceability across sessions.
  • Quality governance: formal review against acceptance criteria, memory updates (CLAUDE.md), and documented handoffs for handover.

Quick Start

Define a backlog task for a new coding task, assign it to a Haiku/Sonnet/Opus subagent via MCP, and monitor the task until completion.

Frequently Asked Questions about technical-lead-role

High-intent search queries and answers about installing and using this skill.

FAQPage Schema
How do I orchestrate subagents for complex coding workflows?▼

To orchestrate subagents for coding workflows, you separate planning from execution by having the main thread handle task decomposition, then delegate well-defined tasks to subagents using the Task tool for execution and review.

What is the best way to manage a coding backlog across multiple AI sessions?▼

Managing a coding backlog across multiple AI sessions requires creating structured tasks, tracking progress, and documenting decisions to ensure traceability and proper handoffs between different working periods.

Can I use the main thread to write code during agent orchestration?▼

No, you cannot use the main thread to write code during agent orchestration. The framework explicitly prevents main-thread code execution, restricting it to architecture planning, risk assessment, and task delegation.

How do I maintain project context when delegating tasks to subagents?▼

You maintain project context when delegating tasks to subagents by enforcing memory updates through CLAUDE.md, documenting decisions, and maintaining formal handoffs that preserve state across sessions.

How does code review work with delegated subagent tasks?▼

Code review with delegated subagent tasks works through formal quality governance, reviewing subagent outputs against defined acceptance criteria before approving the completed work.

Do I need the Task tool to assign work to Haiku or Sonnet subagents?▼

Yes, you need the Task tool to assign work to Haiku, Sonnet, or Opus subagents via MCP, allowing the main thread to monitor delegated tasks until completion.

Related Skills

Explore More Software Engineering Skills→
GainInsightDevGainInsightDev

af-starting-work

Create a current-task.md file and establish work context for a task.

Official
Basic
EmasoftEmasoft
1

amia-session-memory

Store and retrieve PR review state, integration handoffs, and release history across Claude Code sessions.

Community
Advanced
HomericIntelligenceHomericIntelligence
6

myrmidon-swarm

Decompose complex tasks into hierarchical agent swarms with tiered model assignments.

Official
Advanced
marcusgollmarcusgoll

internal-ralph

Execute unfinished PRD tasks from .deep/prd.json using Claude Code Task subagents.

Community
Advanced