Install any skill in seconds. Free to start, no credit card required.
Get Started Free →Ask the user questions or present choices via an interactive form. Use when you need to gather preferences, clarify ambiguous instructions, get decisions on implementation choices, or present a list of options for the user to select from. Never write options or questions as plain text — always use this tool.
.claude/skills/wecode-ai-interactive/SKILL.md| Test case | Without → With | Effect | Δ tokens | Δ turns |
|---|---|---|---|---|
| case-20 | ✗→✓ | ▲ Improved | 310% | 0% |
| case-12 | ✓→✗ | ▼ Worse | 86% | 0% |
| case-13 | ✓→✗ | ▼ Worse | 214% | 0% |
| case-19 | ✓→✓ | = Same ✓ | 374% | 0% |
| case-21 | ✓→✓ | = Same ✓ | 233% | 0% |
You now have access to the interactive_form_question tool. Use it to ask the user questions during execution.
interactive_form_question insteadNever write options, choices, or questions as plain text or markdown lists — always call the tool.
multi_select: true to allow multiple answers to be selected"recommended": true on that option — the frontend will display the recommended badge automatically. NEVER add "(Recommended)", "(推荐)" or any similar text to the label field — the badge is rendered by the frontend, not by text in the labelquestions=[...]. A single-question form is just a one-item questions array.interactive_form_question again if follow-up questions arise — never ask in plain textinteractive_form_question displays an interactive form and returns immediately . The current task ends silently and resumes when the user submits their answer as a new message.
questions (list, required): The full list of questions to renderquestions has:id: Unique identifierquestion: Question text shown to the userinput_type: "choice" or "text"options (optional): [{label, value, recommended?}] for choice questionsmulti_select (optional): Allow multiple selections; default falserequired (optional): Whether the question must be answered; default truedefault (optional): Pre-selected valuesplaceholder (optional): Placeholder for text inputinteractive_form_question(
questions=[
{
"id": "environment",
"question": "Which environment should I deploy to?",
"input_type": "choice",
"options": [
{"label": "Development", "value": "dev", "recommended": true},
{"label": "Staging", "value": "staging"},
{"label": "Production", "value": "prod"}
]
}
]
)interactive_form_question(
questions=[
{
"id": "cache_strategy",
"question": "I found two approaches for the caching layer. Which do you prefer?",
"input_type": "choice",
"options": [
{"label": "Option A — simple in-memory cache", "value": "simple", "recommended": true},
{"label": "Option B — Redis with TTL control", "value": "redis"}
]
}
]
)interactive_form_question(
questions=[
{
"id": "language",
"question": "Which language should I use?",
"input_type": "choice",
"options": [
{"label": "Python", "value": "python", "recommended": true},
{"label": "TypeScript", "value": "typescript"},
{"label": "Go", "value": "go"}
]
},
{
"id": "features",
"question": "Which features to include?",
"input_type": "choice",
"multi_select": true,
"options": [
{"label": "Authentication", "value": "auth", "recommended": true},
{"label": "Rate Limiting", "value": "rate_limit"},
{"label": "Caching", "value": "caching"}
]
},
{
"id": "notes",
"question": "Anything else I should know?",
"input_type": "text",
"required": false,
"placeholder": "Optional notes..."
}
]
)interactive_form_question(
questions=[
{
"id": "overwrite_confirmation",
"question": "This will overwrite the existing file. Proceed?",
"input_type": "choice",
"options": [
{"label": "Yes, overwrite", "value": "yes"},
{"label": "No, keep existing", "value": "no", "recommended": true}
]
}
]
)Single-question: {"answer": ["value"]} (choice) or {"answer": "text"} (text)
Multi-question: {"answers": {"language": ["python"], "features": ["auth", "caching"], "notes": ""}}
Other measured skills in the registry, with their headline benchmark lift.