Closing the intent-to-code chasm - specification-driven development with BDD verification chain
Overall
score
96%
Does it follow best practices?
Validation for skill structure
Ask targeted clarification questions to reduce ambiguity in the active feature spec until all critical areas are clear, then encode answers back into the spec.
$ARGUMENTSYou MUST consider the user input before proceeding (if not empty).
Load constitution per constitution-loading.md (soft mode — parse if exists, continue if not).
Run: bash .tessl/tiles/tessl-labs/intent-integrity-kit/skills/iikit-02-clarify/scripts/bash/check-prerequisites.sh --phase 02 --json
Windows: pwsh .tessl/tiles/tessl-labs/intent-integrity-kit/skills/iikit-02-clarify/scripts/powershell/check-prerequisites.ps1 -Phase 02 -Json
Parse JSON for FEATURE_DIR and FEATURE_SPEC. If missing: ERROR with Run: /iikit-01-specify.
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-02-clarify/scripts/bash/set-active-feature.sh --json <selection>Windows: pwsh .tessl/tiles/tessl-labs/intent-integrity-kit/skills/iikit-02-clarify/scripts/powershell/set-active-feature.ps1 -Json <selection>
Then re-run the prerequisites check from step 1.
Load spec and perform structured scan using this taxonomy. Mark each: Clear / Partial / Missing.
Constraints:
Present ONE question at a time.
For multiple-choice: follow the options presentation pattern in conversation-guide.md. Analyze options, state recommendation with reasoning, render options table. User can reply with letter, "yes"/"recommended", or custom text.
After answer: validate against constraints, record, move to next.
Stop when: all critical ambiguities resolved or user signals done.
## Clarifications section exists in spec with ### Session YYYY-MM-DD subheading- Q: <question> -> A: <answer> [FR-001, US-2]
See clarification-format.md for format details.
After each write and final pass:
[refs]Output: questions asked/answered, path to updated spec, sections touched, traceability summary table (clarification -> referenced items), coverage summary (category -> status), suggested next command (/iikit-03-plan).
You MUST read model-recommendations.md, check the expiration date (refresh via web search if expired), detect the agent via env vars, and include a model switch tip in the output below if the next phase needs a different model tier.
Clarification complete! Next: /clear then /iikit-03-plan
(Q&A consumed significant context — /clear before planning is recommended)
Tip: <model switch suggestion if tier mismatch, omit if already on the right model>
- Dashboard: file://$(pwd)/.specify/dashboard.html (resolve the path)Install with Tessl CLI
npx tessl i tessl-labs/intent-integrity-kit@2.3.5rules
skills
iikit-00-constitution
scripts
iikit-01-specify
iikit-02-clarify
iikit-03-plan
iikit-04-checklist
scripts
dashboard
iikit-05-testify
iikit-06-tasks
iikit-07-analyze
iikit-08-implement
iikit-09-taskstoissues
iikit-bugfix
scripts
iikit-core
scripts
bash
dashboard
powershell