Name: Research Lead Sidecar
Author: gabrielmoreira

Overview

Use this skill for research-led work where implementation and evidence gathering are coupled, but the main agent should remain the lead. It keeps the critical path local while bounded sidecars handle non-blocking scout, worker, verifier, or writer tasks.

Rules

Keep the lead responsible for framing, synthesis, and final decisions.
Delegate only tasks that are non-blocking, bounded, inspectable, and recoverable.
Prefer 1-2 sidecars with clear roles instead of spawning a crowd by default.
The lead should keep moving on the critical path instead of waiting idly for sidecars.
Use milestone verification and durable workspace state only when the task span justifies them.

When to Use

Use when:

the user explicitly wants 多智能体分工, research-led multi-agent work, or long-task governance with a lead agent
there is one critical path plus a small number of low-coupling side tasks
sidecars can return artifacts the lead can inspect quickly

Do not use when:

Overview

Rules

Keep the lead responsible for framing, synthesis, and final decisions.
Delegate only tasks that are non-blocking, bounded, inspectable, and recoverable.
Prefer 1-2 sidecars with clear roles instead of spawning a crowd by default.
The lead should keep moving on the critical path instead of waiting idly for sidecars.
Use milestone verification and durable workspace state only when the task span justifies them.

When to Use

Use when:

the user explicitly wants 多智能体分工, research-led multi-agent work, or long-task governance with a lead agent
there is one critical path plus a small number of low-coupling side tasks
sidecars can return artifacts the lead can inspect quickly

Do not use when:

Research Lead Sidecar

Overview

Rules

When to Use

Research Lead Sidecar

Overview

Rules

When to Use

Sessions

Docker Patterns

Autonomous Loops

Kotlin Patterns

Eval Harness

Golang Patterns