Trace and document how data transforms through a multi-step pipeline or function chain, showing intermediate state at each step with concrete example values. Use when explaining a data pipeline or complicated codepaths, tracing how a value changes across function calls, answering questions like "how does X get to Y", or producing a step-by-step dataflow walkthrough for a code review or design doc.
99
100%
Does it follow best practices?
Impact
98%
1.15xAverage score across 3 eval scenarios
Passed
No known issues
Multi-stage ETL pipeline dataflow trace
Stage headers present
70%
100%
Intermediate state shown
100%
100%
Concrete values used
100%
100%
Arrow (→) syntax for transformations
100%
100%
Left-arrow (←) annotations
25%
100%
Output type at stage end
62%
100%
Irrelevant fields omitted
37%
50%
Function names as stage labels
100%
100%
Indented continuation lines
37%
100%
No abstract descriptions
90%
100%
normalize_contact merge shown
100%
100%
Authorization filtering flow trace with per-item decisions
✓/✗ per-item decisions
83%
100%
HashMap accumulation shown
100%
100%
Stage headers with function names
100%
100%
Auth request and response shown
100%
100%
Edge case values chosen
100%
100%
Per-item decision trace
100%
100%
Final filtered set shown
100%
100%
Left-arrow annotations
0%
100%
Arrow (→) transformation syntax
100%
100%
Concrete values throughout
100%
100%
Output type at stage end
66%
100%
Single function trace with HashMap accumulation
Single-function format
100%
100%
Input shown at start
100%
100%
HashMap accumulation per entity
100%
100%
Codebase type names used
100%
100%
Left-arrow annotation for owner field
100%
100%
Concrete values throughout
100%
100%
Output type shown
100%
100%
Arrow (→) syntax
0%
100%
entity_list in output
100%
100%
None vs Some distinction
100%
100%
f5efc36
Table of Contents
If you maintain this skill, you can claim it as your own. Once claimed, you can manage eval scenarios, bundle related skills, attach documentation or rules, and ensure cross-agent compatibility.