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
No external API in core data path
100%
100%
PM's specific service suggestions not adopted blindly
90%
100%
Expense submission works offline in spec
100%
100%
Currency conversion handled offline
100%
100%
Local storage as primary in plan
100%
100%
Sync designed as optional enhancement
100%
100%
Conflict resolution addressed
100%
100%
Spec uses numbered requirements
50%
100%
Spec has acceptance scenarios
0%
100%
Spec is technology-agnostic
50%
50%
Plan references spec requirements
0%
28%
No governance restated in plan
100%
100%
Spec does not promise network-dependent core features
100%
100%
plan.md exists
0%
100%
Technical Context fields
0%
100%
No bare Option labels
0%
100%
research.md with rationale
0%
100%
data-model.md entities
0%
100%
State transitions in data-model
0%
100%
contracts/ directory
0%
100%
Contracts reference spec requirements
0%
100%
quickstart.md exists with scenarios
0%
100%
No governance content in plan
0%
100%
Spec quality assessment performed
0%
25%
Plan decisions trace to spec FRs
0%
100%
context.json updated
0%
100%
Exactly 3 user stories in spec
100%
100%
No mentioned-but-deferred features in spec
100%
100%
No excluded features in plan
100%
100%
No excluded features in tasks
100%
100%
Spec uses numbered requirements
0%
100%
Spec has acceptance scenarios
37%
100%
FR count proportional to scope
0%
50%
Task count proportional to scope
75%
0%
Data model matches scope
100%
100%
Plan tech stack appropriate for scope
100%
100%
Tasks use structured format
50%
100%
Accessibility addressed
100%
100%
T-BNNN task ID format
0%
100%
At least 1 fix task with TS ref
100%
100%
TDD task references test spec
0%
100%
bugs.md BUG-NNN entry
100%
100%
bugs.md required fields
70%
100%
bugs.md date format
100%
100%
Existing tasks unmodified
100%
100%
Bug ID in task descriptions
100%
100%
New .feature file created
0%
0%
TS-XXX tags present
0%
100%
FR-XXX tags present
0%
100%
SC-XXX tags present
0%
100%
SC-XXX majority coverage
0%
100%
US-XXX tags present
0%
0%
Priority tags present
0%
100%
Test type tags present
0%
100%
DO NOT MODIFY header
0%
100%
Feature-level US tag
0%
100%
All acceptance scenarios covered
100%
100%
TS-XXX uniqueness
0%
100%
Spec is technology-agnostic
100%
87%
Plan has no governance content
100%
33%
FR-XXX to TS-XXX coverage
0%
100%
TS-XXX to task coverage
0%
75%
.feature files have DO NOT MODIFY headers
0%
100%
.feature files have required tags
0%
75%
Tasks ordered: Setup → Foundational → Stories → Polish
83%
100%
TDD task ordering within story phases
40%
100%
No phantom requirements
100%
100%
Privacy constraint in .feature files
100%
100%
No FR orphans in either direction
37%
100%
TS-XXX IDs are unique across files
0%
100%
File paths match plan structure
86%
80%
Every user story has tagged tasks
20%
100%
Setup/Foundational tasks have no story tags
100%
100%
TS references are comma-separated
75%
100%
TS references match provided .feature files
100%
100%
Priority ordering respected
50%
100%
Phase structure complete
62%
100%
[P] markers only on parallelizable tasks
37%
75%
No technologies beyond the plan
100%
100%
Checkbox format used
0%
100%
Sequential T-prefixed IDs
50%
100%
NEEDS CLARIFICATION flagged
100%
100%
FR count assessed
0%
100%
Measurable criteria warning
0%
100%
Quality score reported
0%
100%
Semantic diff present
80%
100%
Semantic diff format
0%
100%
Downstream impact flagged
12%
100%
Updated plan has new dependencies
100%
100%
Updated architecture diagram
100%
100%
No governance in plan
100%
100%
Clarification assumptions documented
60%
100%
No technology in spec.md
100%
100%
No governance in plan.md
16%
41%
FR-XXX requirements in spec
0%
100%
SC-XXX success criteria in spec
0%
100%
User stories in spec
0%
100%
Given/When/Then scenarios in spec
0%
100%
Plan references spec FRs
0%
0%
Every spec FR traceable to plan
50%
100%
No phantom requirements in plan
100%
100%
data-model.md traces to spec entities
100%
100%
Connection-lost requirement survives to plan
100%
100%
No technology stack in spec
0%
100%
FR-XXX numbered requirements
0%
100%
SC-XXX success criteria
0%
100%
Given/When/Then scenarios
0%
100%
User stories present
100%
100%
Measurable success criteria
0%
100%
Max 3 NEEDS CLARIFICATION
100%
100%
No implementation details
0%
100%
2-4 word branch name
100%
100%
Requirements.md checklist created
100%
100%
Sequential T-prefixed IDs
50%
100%
[P] marker usage
20%
80%
[USn] label on story tasks
0%
100%
Comma-separated TS references
53%
100%
Phase 1 Setup section
100%
100%
Phase 2 Foundational section
87%
100%
User Story phases ordered by priority
75%
100%
File paths in descriptions
100%
100%
Checkbox format
0%
100%
Polish/Final phase
80%
100%
.feature files cover all FRs
50%
100%
DO NOT MODIFY headers present
0%
100%
All required tags on every Scenario
0%
75%
TS-XXX IDs unique across all files
100%
100%
Scenarios match spec acceptance criteria
90%
100%
Privacy/auth scenario present
100%
100%
Every story task references TS-XXX
80%
80%
TS references are comma-separated
100%
100%
Test tasks before production tasks per story
100%
100%
Task file paths match plan structure
100%
100%
Phase structure and sequential IDs
80%
100%
Concurrency test scenario present
100%
100%
ASCII architecture diagram
100%
100%
Named components in diagram
100%
100%
context.json exists
0%
0%
planview.nodeClassifications key
0%
0%
Existing data preserved
0%
0%
Client node classified
0%
0%
Server node classified
0%
0%
Storage node classified
0%
0%
External node classified
0%
0%
No technology stack in constitution
25%
100%
No implementation details
62%
100%
At least 3 principles
100%
100%
Principles are declarative
100%
100%
Semver version present
42%
100%
Amendment procedure present
100%
100%
.specify/context.json created
41%
0%
TDD determination value valid
0%
50%
Principles are domain-agnostic
40%
70%
Testing philosophy explicitly stated
50%
100%
Dates in ISO format
100%
100%
No feature-specific content
100%
100%
Table of Contents