Use this skill when reasoning about the distributed system design, service orchestration, or request lifecycle of the X recommendation engine. It is essential for tasks involving the "For You" timeline construction, HomeMixer logic, or ProductMixer component definitions.
Use this skill to decode the "DNA" of the recommendation engine. These signals are the foundational data structures used to retrieve candidates (before ranking) and as features for the Heavy Ranker (during ranking).
Use this skill when implementing new features or debugging the core "For You" pipeline. The system has shifted from legacy heuristics toward a unified Rust-based pipeline powered by the Phoenix transformer (Grok).
Use this skill when reasoning about how the algorithm is tuned, why different users see different behaviors, or how "Success" is defined by X's engineering team.
Use this skill when advising on post structure, timing, media selection, and account health to align with the HeavyRanker's scoring weights and anti-spam heuristics.
Use this skill when you need to reason about the machine learning models that determine the final order of the "For You" timeline. It is essential for tasks involving model feature engineering, tuning engagement weights, or understanding the internal mechanics of the Heavy Ranker (Navi).
Use this skill when analyzing how the system narrows down 500 million daily tweets to a candidate pool of 1,500. This is the "top-of-funnel" engineering that determines what is even eligible to be ranked.
Use this skill when analyzing why content is not appearing, checking for "shadowban" conditions, or understanding the safety compliance layer. This skill covers the VisibilityLib logic that runs after candidate sourcing but before final ranking to ensure platform health.
★not rated 2 1mo agoA59 tokens
originalApache-2.0
At most 3 mods per repository are shown here, and a mod shipped inside a plugin is left to that plugin's page — the rest are on their repository pages: