Most widely cited AI coding benchmarks, including the original SWE-bench, were built primarily around Python repositories, meaning headline performance results may not accurately predict how coding ag ...
A knowledge base that turns an AI coding agent into a senior Java/Spring Boot engineer. Instead of relying on the model's general Java knowledge, this skill injects curated, opinionated best practices ...
Skills encode deep Qdrant knowledge so coding agents can make the engineering decisions that determine whether vector search works well: quantization, sharding, tenant isolation, hybrid search, model ...
Some results have been hidden because they may be inaccessible to you
Show inaccessible results