test-strategy

FoundationJIT only

analysis-agent/task-agent/review-agent: use to recommend a risk-to-test evidence portfolio and omissions; skip test implementation, fixed-command, and release-verdict work.

Group: Quality & testing
Supported roles: MainAnalysisTaskReview
Source: SKILL.md

Use when

Trigger signals that make this skill the right owner

choose risk based proof portfolio test levels failure mechanisms oracles omissions and admissibility evidence

Do not use when

Anti-triggers — as binding as the triggers above

one test level and command are already fixed or the task only implements tests or decides release readiness

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

risk based test strategy decision with failure mechanisms oracles proof levels coverage obligations omissions command-signal requirements and admissibility limits

Escalation signals

When this skill must hand the decision back

Failure mechanism oracle omission admissibility or evidence ownership remains unresolved

Loaded by

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

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	Test levels layered proof assertion challenge or omission tradeoffs remain contested	One accepted portfolio covers each material failure mechanism	AnalysisTaskReview
checklist.mddecision-checklist	Negative paths nondeterminism flaky containment omissions and risk tracing need multi-part closure	The accepted portfolio already closes those decisions	AnalysisTaskReview
evidence-patterns.mdevidence-pattern	Admissibility depends on fresh changed-path consumer command fixture or report evidence	No strategy-confidence claim awaits proof	AnalysisTaskReview