requirement-structuring

FoundationJIT only

analysis-agent: use when raw requests need behavior, actors, scope, non-goals, constraints, deliverables, acceptance, or test traceability; skip when structure already exists.

Group: Intake & requirements
Supported roles: MainAnalysisTaskReview
Source: SKILL.md

Use when

Trigger signals that make this skill the right owner

structure raw request into scope constraints dependencies and deliverables

Do not use when

Anti-triggers — as binding as the triggers above

no task-local requirement structuring decision is required

Required inputs

What must be supplied before this skill can decide anything

current task contract
selected primary Professional Skill
task-local trigger evidence

Output contract

What this skill owes the next role

structured requirement with sourced current behavior, desired outcomes, actors, scope and exclusions, constraints and assumptions, dependencies, risks, deliverables, acceptance trace, unresolved decisions, and owners

Escalation signals

When this skill must hand the decision back

Unstructured requests hide conflicts and unstated acceptance gaps

Loaded by

This skill never owns a task. These professionals may pull it in as Layer 3.

change-intake-compiler

Targeted references

Each reference carries its own load condition. None of them enter context by default.

Reference	Load when	Do not load when	Required by
benchmarks-and-patterns.mdbenchmark-pattern	current desired scope constraint or dependency framing remains ambiguous	accepted behavior-first structured requirement already fixes every requirement boundary	Analysis
checklist.mddecision-checklist	structured requirement lacks observable behavior actors non-goals constraints or acceptance	accepted structured requirement contains every required task-local field	Analysis
evidence-patterns.mdevidence-pattern	current-behavior constraint dependency or non-goal claims need proof	fresh source and owner evidence substantiate every structured requirement fact	Analysis