Interactive

What it does

When your agent uses it

• You need to gather preferences
• Clarify ambiguous instructions
• Get decisions on implementation choices
• Present a list of options for the user to select from

Example prompts

• “/interactive”

Workflow steps

5 steps, taken from the first numbered list in SKILL.md.

1. 1Gather user preferences or requirements — before starting or when more detail is needed
2. 2Clarify ambiguous instructions — when the request could be interpreted multiple ways
3. 3Get decisions on implementation choices as you work — when a fork in the road requires user input
4. 4Offer choices on direction — let the user steer when multiple valid paths exist
5. 5Present any list of options to the user — whenever you would naturally write a numbered/bulleted list of choices for the user to pick…

What it can do on your machine

Read from SKILL.md and the folder at commit 428f207. It shows what the files ask for, not the result of running them.

• Tool permissions

  Pre-approves nothing: there is no allowed-tools line, so your agent's usual permission prompts apply.

  From allowed-tools in the SKILL.md frontmatter.

• Runs code

  No scripts in the folder and no shell commands in SKILL.md.

  From the folder's file list and the shell code blocks in SKILL.md.

• Network

  No URLs in SKILL.md.

  From URLs in SKILL.md, links to its own repository left out.

• Credentials

  Names no API keys, tokens, secrets or passwords.

  From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.

Context cost

Interactive loads about 1.4k tokens when it runs. Until then it costs about 80 tokens; SKILL.md has 360 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it

~80

When it runs · the whole SKILL.md, loaded when a task matches

~1.4k

Estimates: characters ÷ 4, the usual rule of thumb; real counts depend on the model's tokenizer. Scripts and assets cost tokens only if the agent reads them.

Safety

Automated static check — not a guarantee. Review scripts before installing. It scans the text of SKILL.md for risky patterns (piping downloads into a shell, reading credential files, hidden Unicode, destructive commands); files beside SKILL.md are not scanned.

SKILL.md

The full file from wecode-ai/Wegent at commit 428f207, republished under its Apache-2.0 licence (© wecode-ai). 360 words, ~1,370 tokens.

name

interactive

description

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.

displayName

交互式表单提问

version

2.0.0

author

Wegent Team

tags

interaction, user-input, form, clarification

bindShells

Chat, Agno, ClaudeCode

interactive_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}
      ]
    }
  ]
)

© wecode-ai, Apache-2.0. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file

Files

Just SKILL.md in backend/init_data/skills/interactive of wecode-ai/Wegent.

Open the folder on GitHubat commit 428f207