design-agent-perception-layers

Community

Optimize agent perception with fast and slow thinking separation

AuthorEnigmaWU
Version1.0.0
Installs0

System Documentation

What problem does it solve?

This Skill helps in designing the context-gathering tools for autonomous agents, optimizing perception by separating fast (API queries) from slow (UI vision tools) methods.

Core Features & Use Cases

  • Fast vs. Slow Perception: Separates "Fast Thinking" (API queries) from "Slow Thinking" (UI vision tools) to enhance performance.
  • Use Case: When designing an agent that interacts with UIs, this Skill ensures the agent uses the fastest method for perception, optimizing token usage and execution speed.

Quick Start

To use this skill, trigger it to execute the defined workflow. Refer to SKILL.md for specific triggers and inputs.

Dependency Matrix

Required Modules

None required

Components

scripts

💻 Claude Code Installation

Recommended: Let Claude install automatically. Simply copy and paste the text below to Claude Code.

Please help me install this Skill:
Name: design-agent-perception-layers
Download link: https://github.com/EnigmaWU/MyCodeAgentSkills/archive/main.zip#design-agent-perception-layers

Please download this .zip file, extract it, and install it in the .claude/skills/ directory.
View Source Repository

Agent Skills Search Helper

Install a tiny helper to your Agent, search and equip skill from 620,000+ vetted skills library on demand.