Introduction

In discussions about Claude Code, many have asked about the differences between skills and agents. Should prompts be placed in skills or made into agents? Skills execute specific tasks, while agents carry underlying thinking models and work modes. Understanding these differences is essential for building an efficient AI collaboration workspace.

Initially, my approach was quite straightforward. What is the most notable feature of agents in Claude Code? They can operate independently without interfering with the current conversation or consuming context resources, and they can be linked to specific models. Therefore, I turned prompts like manuscript review into agents.

However, as I delved deeper into usage and the upgrades of Claude Code, I realized this method was not the best choice for the following reasons:

1. This approach essentially still creates skills, and distributing these specific capabilities between skills and agents makes prompt management scattered and chaotic, complicating future maintenance.
2. If the only goal is to operate independently, it is unnecessary because Claude Code now supports enabling agent operation for skills or having agents actively mount certain skills during operation, perfectly addressing previous scenario needs.

So, when should you create a skill, and when should you write an agent?

Fundamental Differences Between Agents and Skills

I have written extensively about skills, and many experts have shared their insights online, so most are likely familiar with them. In simple terms, a skill is a prompt fragment used to execute specific processes or solve particular problems (which can also include scripts).

What about agents? What are they primarily used for?

When we feel confused, the official documentation is the best guide. We can glean some insights from several built-in agents in Claude Code, including the following types:

Excluding a few in the “Others” category, the Explore, Plan, and General-purpose agents have distinct characteristics. They are designed for broader scenarios and are supported by a mechanism to ensure generation quality.

For a more intuitive example, the Planning mode in Antigravity is similar to these agents in Claude Code. In Planning mode, the AI undergoes in-depth analysis and thought, plans tasks and execution steps, then executes according to the plan, ultimately providing users with feedback on changes, completing Task → Implementation → (user-requested) generated content → Walkthrough. This mechanism ensures high-quality delivery.

Thus, it is evident that agents do not carry specific execution techniques or routines but rather more fundamental thinking models and work modes. This is the fundamental difference between agents and skills.

Designing Agents

Agents are not aimed at a specific problem but rather at a category of problems, providing process management for solving these types of issues.

In our work scenarios, this processing method is quite common. For instance, the PDCA model used in quality management, the pyramid model used in document writing, and the snowflake writing method used in story creation. The generation-review cycle I previously demonstrated and the popular multi-expert review model can also be solidified into a framework for problem-solving.

Why are these frameworks effective? Because they establish a method for “doing things,” making the processing steps clear and forming processes, rules, and standards. This avoids aimless attempts and uncontrolled delivery quality. With these methods in place, even a novice can achieve satisfactory results.

When applied to human-machine collaboration, turning these frameworks into prompts becomes agents. Calling an agent is essentially selecting a thinking model or framework to enhance output quality.

Now, is the design of agents clearer?

The writing techniques remain the same, focusing on defining roles, workflows, and read-write interactions. Agents emphasize ensuring result quality through good process control rather than being bogged down by minor detail techniques.

Conclusion

The above is my understanding of the skill and agent mechanisms in Claude Code after a period of practice.

As Claude Code continues to upgrade and iterate, both skills and agents are becoming more refined. While flexibly building an “AI writing platform,” we can conduct more detailed control and configuration, with the usage scenarios of both becoming increasingly distinct.

Currently, the built-in agents in Claude Code do not fully align with the scenarios of web fiction creation. Issues like improving plot quality, addressing memory problems, and avoiding out-of-character (OOC) moments are challenges that writing agents cannot overlook.

Interested individuals can brainstorm and experiment, and perhaps create something remarkable!

For official documentation on building agents in Claude Code, visit: https://code.claude.com/docs/zh-CN/sub-agents