generic-subagent

Delegate read-only research tasks to subagents and return structured digests.

346|50|Updated Jan 17, 2026
One-click install
npx skills add https://github.com/liza-mas/liza --skill generic-subagent-liza-mas
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: generic-subagent
Source: https://github.com/liza-mas/liza/tree/main/skills/generic-subagent
Command: npx skills add https://github.com/liza-mas/liza --skill generic-subagent-liza-mas

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

Subagents offload context-expensive read-only work. The caller receives a digest, not the full trace. Subagents cannot modify state — they research, analyze, and summarize.

Core Features & Use Cases

  • Context-efficient delegation of read-only tasks to subagents to optimize workflows.
  • Produces concise digests instead of full traces for faster decision making.
  • Use Case: when you need in-depth analysis of a document without mutating source data or sharing sensitive context.

Quick Start

Delegate a read-only research task to a subagent for the target document or dataset and request a concise digest.

Frequently Asked Questions about generic-subagent

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

FAQPage Schema
How do I delegate read-only research tasks to AI agents without exposing full context?

Read-only research tasks can be delegated to subagents to generate concise digests instead of full traces. This approach ensures subagents research, analyze, and summarize data without mutating state or sharing sensitive context back to the caller.

What is the structured output format for subagent digests?

Subagent digests enforce a structured output contract containing a summary, concerns, blockers, and detailed findings. This format ensures the caller receives decision-support information without needing to process the entire context trace.

Can I use subagents for scope assessment and document summarization?

Yes, subagents are applicable for tasks requiring scope assessment, content summarization, and decision-support. They analyze documents or datasets and return a concise digest, preventing context bloat in the main workflow.

How do I get in-depth analysis of a document without mutating source data?

You can delegate the document to a subagent for read-only research. The subagent analyzes the content and produces a concise digest, guaranteeing the source data remains unmodified while still providing decision-support.

Why use subagents for read-only work in an AI workflow?

Subagents offload context-expensive read-only work from the main workflow. They produce concise digests for faster decision making, preventing context overload while enforcing a structured summary of concerns and blockers.

Are there limitations when delegating tasks to read-only subagents?

Read-only subagents cannot modify state; they are limited to researching, analyzing, and summarizing. They return structured outputs but cannot execute actions that mutate source data or change the workflow state.