Use this skill when the user wants SQL questions that are hard because of layered logic, rankings, counts, HAVING clauses, nested conditions, or “top / most / per group” style analytics. Trigger it for requests like “make it analytically tricky”, “it should need grouping and filtering together”, “use ranking or nested logic”, or “I want SQL that breaks if the order of reasoning is wrong.” Example trigger: “Make the SQL analytically tricky, not just join-heavy.” Example trigger: “I want tasks with group-by plus conditions plus ranking.” Example trigger: “Use nested logic so the wrong order gives the wrong answer.”
[Case 1]
[Case 2]
To synthesize data for this capability, you must strictly follow a 3-phase pipeline. Do not hallucinate steps. Read the corresponding reference file for each phase sequentially:
Phase 1: Environment Exploration
Read the exploration guidelines to discover raw knowledge seeds:
references/EXPLORATION.md
Phase 2: Trajectory Selection
Once Phase 1 is complete, read the selection criteria to evaluate the trajectory:
references/SELECTION.md
Phase 3: Data Synthesis
Once a trajectory passes Phase 2, read the synthesis instructions to generate the final data:
references/SYNTHESIS.md