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
Patterns for interactive sessions where the skill asks the user questions and integrates answers.
For multiple-choice questions, use this pattern:
Analyze options and determine the most suitable based on best practices, risk reduction, and project alignment
State recommendation prominently:
**Recommended:** Option [X] - <reasoning>Render options table:
| Option | Description | Implications |
|---|---|---|
| A | First option | Trade-offs |
| B | Second option | Trade-offs |
| C | Third option | Trade-offs |
| Short | Provide a different short answer |
Accept flexible responses: letter ("A"), affirmation ("yes", "recommended"), or custom text
When a gap or ambiguity is identified:
---
Gap N of M: [Item ID]
---
**Missing Requirement:**
[Quote the checklist item or ambiguous spec text]
**Why This Matters:**
[Brief risk explanation if left unspecified]
**Suggested Options:**
| Option | Description | Implications |
|--------|-------------|--------------|
| A | [First reasonable default] | [Trade-offs] |
| B | [Alternative approach] | [Trade-offs] |
| C | [Another option] | [Trade-offs] |
| Skip | Leave unspecified for now | Will remain as gap |
**Your choice (A/B/C/Skip/Custom):** _After user responds:
Show confirmation of what was added/changed after each resolution.
When asking multiple questions one at a time:
When recording Q&A in a spec or artifact:
- Q: <question> -> A: <final answer> [REF-001, REF-002]### Session YYYY-MM-DDInstall with Tessl CLI
npx tessl i tessl-labs/intent-integrity-kitrules
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