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
Generate executable Gherkin .feature files from requirement artifacts before implementation. Enables TDD by creating hash-locked BDD scenarios that serve as acceptance criteria.
OS convention: All commands are shown in bash. PowerShell equivalents exist at the same path with a
.ps1extension (e.g.,scripts/powershell/check-prerequisites.ps1) and accept the same flags in PascalCase (e.g.,-Phase 04 -Json).
Load constitution per constitution-loading.md (basic mode), then perform TDD assessment:
Scan for TDD indicators:
Report per formatting-guide.md (TDD Assessment section).
Run:
bash .tessl/tiles/tessl-labs/intent-integrity-kit/skills/iikit-04-testify/scripts/bash/check-prerequisites.sh --phase 04 --jsonWindows: pwsh .tessl/tiles/tessl-labs/intent-integrity-kit/skills/iikit-04-testify/scripts/powershell/check-prerequisites.ps1 -Phase 04 -Json
Parse for FEATURE_DIR and AVAILABLE_DOCS. Require plan.md and spec.md (ERROR if missing).
If JSON contains needs_selection: true: present the features array as a numbered table (name and stage columns). Follow the options presentation pattern in conversation-guide.md. After user selects, run:
bash .tessl/tiles/tessl-labs/intent-integrity-kit/skills/iikit-04-testify/scripts/bash/set-active-feature.sh --json <selection>Windows: pwsh .tessl/tiles/tessl-labs/intent-integrity-kit/skills/iikit-04-testify/scripts/powershell/set-active-feature.ps1 -Json <selection>
Then re-run the prerequisites check from step 1.
Checklist gate per checklist-gate.md.
Search spec.md for Given/When/Then patterns. If none found: ERROR with Run: /iikit-clarify.
spec.md (acceptance scenarios), plan.md (API contracts, tech stack)data-model.md (validation rules)Create .feature files in FEATURE_DIR/tests/features/:
Output directory: FEATURE_DIR/tests/features/ (create if it does not exist)
File organization: Generate one .feature file per user story or logical grouping. Use descriptive filenames (e.g., login.feature, user-management.feature).
Every scenario MUST include traceability tags:
@TS-XXX — test spec ID (sequential, unique across all .feature files)@FR-XXX — functional requirement from spec.md@SC-XXX — success criteria from spec.md@US-XXX — user story reference@P1 / @P2 / @P3 — priority level@acceptance / @contract / @validation — test typeSC-XXX coverage rule: For each SC-XXX in spec.md, ensure at least one scenario carries the corresponding @SC-XXX tag. If an existing FR scenario already covers the criterion, add the tag there rather than creating a duplicate.
Feature-level tags for shared metadata:
@US-XXX on the Feature line for the parent user storyFrom spec.md — Acceptance Tests: For each Given/When/Then scenario, generate a Gherkin scenario.
Use testspec-template.md as the Gherkin file template. For transformation examples, advanced constructs (Background, Scenario Outline, Rule), and syntax validation rules, see gherkin-reference.md.
Add an HTML comment at the top of each .feature file:
# DO NOT MODIFY SCENARIOS
# Derived from requirements. Fix code to pass tests; re-run /iikit-04-testify if requirements change.If tests/features/ already contains .feature files:
# DEPRECATED:)CRITICAL: Store SHA256 hash in both context.json and git note in a single call:
bash .tessl/tiles/tessl-labs/intent-integrity-kit/skills/iikit-04-testify/scripts/bash/testify-tdd.sh store-all "FEATURE_DIR/tests/features"Returns JSON with hash and git_note status. The implement skill verifies this hash before proceeding.
Output: TDD determination, scenario counts by source (acceptance/contract/validation), output directory path, number of .feature files generated, hash status (LOCKED).
| Condition | Response |
|---|---|
| No constitution | ERROR: Run /iikit-00-constitution |
| TDD forbidden | ERROR with evidence |
| No plan.md | ERROR: Run /iikit-02-plan |
| No spec.md | ERROR: Run /iikit-01-specify |
| No acceptance scenarios | ERROR: Run /iikit-clarify |
| .feature syntax error | FIX: Auto-correct and report |
Run post-phase to commit, refresh dashboard, and compute next step in a single call:
bash .tessl/tiles/tessl-labs/intent-integrity-kit/skills/iikit-04-testify/scripts/bash/post-phase.sh --phase 04 --commit-files "specs/*/tests/features/,specs/*/context.json,.specify/context.json" --commit-msg "testify: <feature-short-name> BDD scenarios"Parse next_step from JSON. Present per model-recommendations.md:
Feature files generated!
Next: [/clear → ] <next_step> (model: <tier>)
[- <alt_step> — <reason> (model: <tier>)]
- Dashboard: file://$(pwd)/.specify/dashboard.htmlevals
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