Closing the intent-to-code chasm - specification-driven development with BDD verification chain
86
92%
Does it follow best practices?
Impact
86%
1.82xAverage score across 14 eval scenarios
Advisory
Suggest reviewing before use
{
"context": "Tests the testify→tasks pipeline segment with a TDD-mandatory constitution. Validates that .feature files are generated with proper traceability tags before tasks are created, that every implementation task in user story phases references TS-XXX IDs, that test setup tasks precede production code tasks within each phase, and that assertion integrity is maintained (test scenarios match spec acceptance criteria, not invented).",
"type": "weighted_checklist",
"checklist": [
{
"name": ".feature files cover all FRs",
"description": "Generated .feature files collectively have @FR-XXX tags covering all 10 functional requirements (FR-001 through FR-010). No functional requirement is left without a test scenario",
"max_score": 12
},
{
"name": "DO NOT MODIFY headers present",
"description": "Every .feature file starts with the DO NOT MODIFY header comment block",
"max_score": 6
},
{
"name": "All required tags on every Scenario",
"description": "Every Scenario has @TS-XXX (unique ID), @FR-XXX (requirement), @US-XXX (user story), priority (@P1 or @P2), and test type (@acceptance, @contract, or @validation)",
"max_score": 8
},
{
"name": "TS-XXX IDs unique across all files",
"description": "No duplicate @TS-XXX tags exist across all .feature files",
"max_score": 6
},
{
"name": "Scenarios match spec acceptance criteria",
"description": "Generated Gherkin scenarios correspond to the acceptance scenarios in spec.md — not invented test cases that go beyond what the spec describes. The concurrent booking scenario (US-1 scenario 3) must be present",
"max_score": 10
},
{
"name": "Privacy/auth scenario present",
"description": "At least one .feature scenario tests the cross-provider access restriction (FR-010: Dr. Jones cannot view Dr. Smith's schedule → 403 error)",
"max_score": 6
},
{
"name": "Every story task references TS-XXX",
"description": "In tasks.md, every task within user story phases (not Setup or Foundational) includes at least one TS-XXX reference, since the constitution mandates TDD and every implementation task MUST reference the test scenario(s) it satisfies",
"max_score": 15
},
{
"name": "TS references are comma-separated",
"description": "Multiple TS references in tasks use comma-separated format [TS-001, TS-002] — not prose ranges like 'TS-001 through TS-003'",
"max_score": 8
},
{
"name": "Test tasks before production tasks per story",
"description": "Within each user story phase, tasks for test infrastructure (step definitions, test fixtures, integration test setup) appear before or interleaved with production code tasks — not all production code first with tests at the end",
"max_score": 10
},
{
"name": "Task file paths match plan structure",
"description": "Task descriptions reference file paths from the plan's Project Structure (e.g., internal/service/booking_service.go, internal/handler/booking_handler.go). No invented paths",
"max_score": 8
},
{
"name": "Phase structure and sequential IDs",
"description": "tasks.md has Setup → Foundational → User Story (P1 before P2) → Polish phases, with sequential T001, T002, T003... IDs",
"max_score": 5
},
{
"name": "Concurrency test scenario present",
"description": "A .feature scenario exists that tests concurrent slot booking (the spec's third acceptance scenario for US-1), and a corresponding task references it",
"max_score": 6
}
]
}evals
scenario-1
scenario-2
scenario-3
scenario-4
scenario-5
scenario-6
scenario-7
scenario-8
scenario-9
scenario-10
scenario-11
scenario-12
scenario-13
scenario-14
rules
skills
iikit-00-constitution
scripts
dashboard
iikit-01-specify
iikit-02-plan
iikit-03-checklist
scripts
bash
dashboard
iikit-04-testify
iikit-05-tasks
iikit-06-analyze
iikit-07-implement
iikit-08-taskstoissues
iikit-bugfix
scripts
dashboard
iikit-clarify
iikit-core
references
scripts
bash
dashboard
powershell
templates