Skill dreaming builds evolving code skills from pull request history
Skill Dreaming: Evolving Repository Skills through Pull Request Streams
Artificial IntelligenceSoftware Engineering
Summary
Software projects change often, and tools that help write code need to keep up with those changes. The authors created Skill Dreaming, a system that learns from past code updates called pull requests to build and improve specific skills for a project. These skills help new code fit well with existing code, tests, and documentation. Over time, the system updates its skills as the project evolves, helping developers write better and more consistent code.
What this means in practice
- •For software engineering teams: Automate maintaining coding standards and tests by learning from a project's pull requests to guide new code contributions.
- •For devops teams: Reduce integration errors by continuously updating automation tools with skills extracted from repository changes over time.
Authors
Xinyuan Song, Hasibul Haque, Jay Somasundaram, Ryan Turner, Bowen Zhu, Liang Zhao
Abstract
Large language model (LLM) agents increasingly rely on reusable skills for complex software engineering tasks, making skill libraries essential for repository development and maintenance. However, repository-specific skills must evolve with changing code structures, implementation conventions, and maintenance requirements. Pull requests (PRs) provide a natural source of such knowledge by recording how repositories evolve through implementation and review. Meanwhile, new PRs must follow repository-specific implementation patterns, modify related components consistently, and ensure that existing tests continue to pass while adding coverage for new functionality. This creates a mutually reinforcing cycle: PRs provide knowledge for updating skills, while these skills improve future PRs, maintain repositories, and support further skill evolution. To enable this co-evolution of PRs, repositories, and skills, we propose Skill Dreaming, a framework that learns from PR streams to guide continuous repository development and maintenance. Given a repository and its PR history, Skill Dreaming builds a repository-specific skill library by extracting executable knowledge from validated PRs and continuously refines the skills as new PR information becomes available. These skills guide coding agents not only in implementing requested features but also in maintaining associated tests, documentation, compatibility, and repository conventions. By integrating PR analysis, skill management, code execution, and continuous integration, Skill Dreaming provides an end-to-end workflow for applying learned skills to repository changes and incorporating subsequent PR outcomes into future skill updates.