Enforces a 4-phase architecture design workflow by reading `.arch/state.json` on every request to gate responses by phase. Phase 1 extracts and validates requirements from PRDs; Phase 2 selects architecture patterns and establishes high-level structure; Phase 3 designs and accepts components sequentially; Phase 4 finalises and documents the solution. Use when discussing system design, solution architecture, PRD analysis, component design, technology selection, or architecture patterns — distinct from general coding help by its strict phase-gating, anti-pattern detection, and state-tracked component acceptance.
93
97%
Does it follow best practices?
Impact
89%
1.07xAverage score across 5 eval scenarios
Passed
No known issues
{
"context": "Tests whether the agent correctly executes Phase 1 by extracting functional requirements, all four NFR categories, constraints, and risks from a PRD — and correctly updates state.json to mark requirements as accepted while avoiding premature technology or design decisions.",
"type": "weighted_checklist",
"checklist": [
{
"name": "Functional requirements",
"description": "phase1-evaluation.md contains a section documenting functional requirements extracted from the PRD",
"max_score": 10
},
{
"name": "Availability NFR",
"description": "phase1-evaluation.md explicitly captures an availability or uptime non-functional requirement",
"max_score": 10
},
{
"name": "Security NFR",
"description": "phase1-evaluation.md explicitly captures a security non-functional requirement",
"max_score": 8
},
{
"name": "Cost NFR",
"description": "phase1-evaluation.md explicitly captures a cost or budget non-functional requirement",
"max_score": 8
},
{
"name": "Monitoring NFR",
"description": "phase1-evaluation.md explicitly captures a monitoring or observability non-functional requirement",
"max_score": 8
},
{
"name": "Constraints identified",
"description": "phase1-evaluation.md contains a section or list of project or technical constraints",
"max_score": 8
},
{
"name": "Risks identified",
"description": "phase1-evaluation.md contains a section or list of identified risks",
"max_score": 8
},
{
"name": "Phase 1 marked accepted in state",
"description": "The output .arch/state.json has `phases.evaluation.status` set to `\"accepted\"` and `current_phase` advanced to `\"methodology\"`",
"max_score": 15
},
{
"name": "No technology recommendations",
"description": "phase1-evaluation.md does NOT recommend or name specific technologies, frameworks, or databases",
"max_score": 13
},
{
"name": "No component design details",
"description": "phase1-evaluation.md does NOT describe component structures, API shapes, or architecture patterns",
"max_score": 12
}
]
}