agentleFS
sugarforeversugarforever/01coder-agent-skills/skills/interactive-input/SKILL.md

interactive-input

Skill139 starsChanged 9 months agoMITView on GitHub

Enables rich interactive UI components in chat responses. When presenting questions that require structured input (multiple choice, true/false, forms), embed interactive blocks that compatible clients render as native UI elements. Use when user asks for quizzes, exercises, surveys, or any structured input scenario.

The file

We split this skill into the rules it gives an agent

7 rules. About 0 are common, 2 are distinctive, and 5 are very specific to this project.

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈2

    Distinctive · estimate

    This author's own choices. Worth a look.

  • 5

    Very specific

    Tied to their project's names, files or tools. Probably skip.

  • Common
  • Distinctive
  • Very specific
  1. Distinctive:

    When presenting a multiple-choice question, instead of listing options as text:

    line 27
  2. Very specific:

    Every interactive block MUST have a unique id field

    line 55
  3. Very specific:

    Every interactive block MUST have at least one element in card.body

    line 56
  4. Very specific:

    Use "style": "expanded" for choice sets to show all options visually (recommended for quizzes)

    line 58
  5. Very specific:

    Use "style": "compact" for dropdown selects when there are many options

    line 59
  6. Very specific:

    Always wrap the JSON in a interactive code fence — never use json for interactive blocks

    line 63
  7. Distinctive:

    Keep the JSON compact and valid — no comments, no trailing commas

    line 64

≈ “Common” is an estimate: at least 1 in 5 of the 350,495 skill files we read have a rule of the same kind, not the same words. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.

Keep what fits and drop the rest. Your version, ready for your agents.
Files
SKILL.md

Interactive Input Blocks

Embed interactive UI components (radio buttons, checkboxes, text fields, toggles) directly in chat responses. Compatible clients render these as native UI elements; other clients show a readable JSON code block as fallback.

When to Use

  • Quizzes and exercises (single/multiple choice, fill-in-the-blank)
  • Surveys and polls
  • Structured data collection (forms)
  • Any scenario where the user needs to select from options or provide structured input

How It Works

Wrap a JSON block in a ```interactive code fence within your normal markdown response. You can mix regular text and interactive blocks freely in the same message.

Schema Reference

See references/schema.md for the complete schema specification.

Quick Example

When presenting a multiple-choice question, instead of listing options as text:

Here's your first question:

```interactive
{
  "id": "q1",
  "card": {
    "body": [
      { "type": "TextBlock", "text": "What is the capital of France?", "weight": "bold" },
      { "type": "Input.ChoiceSet", "id": "answer", "style": "expanded",
        "choices": [
          { "title": "A. London", "value": "london" },
          { "title": "B. Paris", "value": "paris" },
          { "title": "C. Berlin", "value": "berlin" },
          { "title": "D. Madrid", "value": "madrid" }
        ]
      }
    ],
    "actions": [{ "type": "Action.Submit", "title": "Submit" }]
  }
}
```

Rules

  1. Every interactive block MUST have a unique id field
  2. Every interactive block MUST have at least one element in card.body
  3. Include an Action.Submit in card.actions so the user can submit their response
  4. Use "style": "expanded" for choice sets to show all options visually (recommended for quizzes)
  5. Use "style": "compact" for dropdown selects when there are many options
  6. Set "isMultiSelect": true on Input.ChoiceSet for multiple-choice questions
  7. The first TextBlock in the body is used as the question label in the submitted response
  8. You can include multiple interactive blocks in one message (e.g., a full quiz)
  9. Always wrap the JSON in a ```interactive code fence — never use ```json for interactive blocks
  10. Keep the JSON compact and valid — no comments, no trailing commas

Download now (ZIP)

Does it work?

Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.

No reviews yet

People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.

  • It worked
  • Partly
  • It didn't
What did you use it for? e.g. Reviewing pull requests in a Rails app

Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.

Your trail

Files you open will collect here, so you can find them again.

Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.

Now do this for your own.

Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.