Continuous Learning v2 FAQs

Question 1

How do I turn learned behaviors into permanent tools?

Accepted Answer

By using the /evolve command, the system identifies clusters of high-confidence instincts and generates the necessary markdown and configuration files to create new Skills, Commands, or Agents.

Question 2

How does Continuous Learning v2 differ from standard Claude skills?

Accepted Answer

Unlike static skills, this system uses deterministic hooks to observe every interaction and builds a local library of behaviors that evolve and strengthen based on your actual usage patterns.

Question 3

Does this impact the performance of Claude Code?

Accepted Answer

The observation hooks are lightweight shell scripts. The actual pattern analysis is performed by a background agent (Haiku), ensuring your main coding session remains fast and responsive.

Question 4

Is my code data shared or uploaded anywhere?

Accepted Answer

No. All observations and instincts are stored locally in your homunculus directory. You have full control over what is processed, and only metadata 'instincts' are exported if you choose to share them.

Question 5

What are 'Instincts' in this architecture?

Accepted Answer

Instincts are small, learned behaviors with metadata like confidence scores and evidence logs. They represent specific patterns, such as a preference for a code style or a specific testing workflow.

Continuous Learning v2

主要功能

使用场景

Continuous Learning v2

主要功能

使用场景