frontend-testing

FoundationJIT only

analysis-agent/task-agent/review-agent: use for component, route, browser, accessibility, and API-backed UI-state tests; skip backend, portfolio, and release-verdict work.

Group: Frontend engineering
Supported roles: MainAnalysisTaskReview
Source: SKILL.md

Use when

Trigger signals that make this skill the right owner

test component route browser accessibility interaction and API backed UI state behavior

Do not use when

Anti-triggers — as binding as the triggers above

work is limited to backend enforcement overall proof portfolio integration seams or 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

Return a frontend-test decision: state behaviors, interactions, oracles, boundaries, fixtures, cleanup, accessibility, flake controls, evidence, and proof limits

Escalation signals

When this skill must hand the decision back

User-visible state oracle test boundary fixture cleanup accessibility or flake evidence remains unresolved

Loaded by

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

frontend-change-builder

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	Component route browser visual network-fixture or accessibility evidence competes	One frontend boundary clearly carries the risk	TaskAnalysisReview
checklist.mddecision-checklist	Roles async states recovery forms accessibility cleanup or flake controls need multi-part closure	No user-observable frontend behavior changes	TaskAnalysisReview
evidence-patterns.mdevidence-pattern	Confidence depends on fresh stories schemas fixtures browsers accessibility artifacts commands or reports	No frontend-confidence claim awaits proof	TaskAnalysisReview