SkillForge Manufactures Synthetic Issues From a Repo's Own Tests to Pre-Load Project-Specific Agent Skills

arXiv 2608.18933·medium signalXBlueskyLinkedInCopy link

SkillForge (arXiv 2608.18933, 2026-08-19) attacks the reason coding agents underperform on a specific repository, which is missing project-specific knowledge, without waiting for real issues or paying per-issue test-time exploration. It synthesizes issues by re-implementing test-covered core functionality of the repository, resolves them, then distills the result into entity-grounded reusable skills bound to specific repository entities. Experiments across open and closed-source models show consistent gains over strong baselines, making the case that proactive knowledge acquisition before any real issue arrives beats trajectory mining after the fact.