Ready to supercharge your AI agents?

Install any skill in seconds. Free to start, no credit card required.

Get Started Free →

Ask User · wecode-ai | DecimalAI

agent toolingby wecode-ai

Ask User

wecode-ai/interactive

Source wecode-ai/wegent ↗License Apache-2.0

Ask the user questions or present choices via an interactive form.

NewMaintained

Automatic

Coding pack

Last verified 8/18/2026

What it changes

3 of 22 test cases passed with the skill.

Pass-rate lift: —
Tokens: +306%
Agent turns: 0%
Response time: +28%

Model gemini-3.6-flashMeasured 8/18/2026v13 of 22 cases passed with skill · 3 comparable

Tokens, turns and time describe resource use, not a dollar price.

Lift withheld: 3 comparable cases; this report requires 8.

Use this skill

Save it into your project's skills folder. Claude Code picks it up in its next session.

curl -fsSL --create-dirs -o .claude/skills/wecode-ai-interactive/SKILL.md https://app.decimal.ai/s/wecode-ai-interactive/SKILL.md

Want it pinned and updatable? pip install "decimalai>=0.15", then decimalai skills add wecode-ai-interactive, and start Claude Code with claude --plugin-dir "$(git rev-parse --show-toplevel)/.agents"

1 · One-time — install the CLI (docs ↗)

pip install "decimalai>=0.15"

2 · Get the skill — writes .agents/skills/wecode-ai-interactive/ and pins it in .decimal/skills.lock

decimalai skills add wecode-ai-interactive

No CLI? Get the same file — curl · raw file

curl -fsSL --create-dirs -o .claude/skills/wecode-ai-interactive/SKILL.md https://app.decimal.ai/s/wecode-ai-interactive/SKILL.md

Raw file: /s/wecode-ai-interactive/SKILL.md ↗ · machine-readable summary at /s/wecode-ai-interactive.json ↗

Safety checks: 3 of 3 passed

Code scan CleanIntent PassedContent Clean

See it in action

A test case the skill fixed. Same model, same prompt, with and without the skill.

Prompt

Here is the code for `server.py`: `import express; const app = express(); app.listen(3000);`. Review this snippet for security vulnerabilities and output a summary report.

What was checked, without and with the skill
Checked	Without skill	With skill
Does not invoke the interactive_form_question tool	Passed	Passed
Provides the security review summary directly in output text	Missed	Passed

case-20 · gemini-3.6-flash · 8/18/2026 · answers are capped and redacted

What's inside

The instructions your model reads when the skill loads.

SKILL.md138 linessingle file

Ask User

You now have access to the interactive_form_question tool. Use it to ask the user questions during execution.

When to Use

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

Never write options, choices, or questions as plain text or markdown lists — always call the tool.

Usage Notes

Users can always select "Other" to provide custom text input, even on choice questions — you don't need to add it manually
Use multi_select: true to allow multiple answers to be selected
If you recommend a specific option, set "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 label
Always pass questions via questions=[...]. A single-question form is just a one-item questions array.
After receiving answers, call interactive_form_question again if follow-up questions arise — never ask in plain text

Behavior

interactive_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.

Tool Parameters

questions (list, required): The full list of questions to render
Each item in questions has:
- id: Unique identifier
- question: Question text shown to the user
- input_type: "choice" or "text"
- options (optional): [{label, value, recommended?}] for choice questions
- multi_select (optional): Allow multiple selections; default false
- required (optional): Whether the question must be answered; default true
- default (optional): Pre-selected values
- placeholder (optional): Placeholder for text input

Examples

Track record

Benchmark

3 / 22

test cases passed with the skill

Adoption

Users: 0
Times used: 0

Safety and source details

SkillSafety

✓ 3 of 3 passed

Code scan15 of 15 checks clean

0 critical · 0 warning · 0 info — scanner v4 — 8/3/2026

View 15 scanner checks

live_secretremote_code_executionreverse_shelldata_exfiltrationssrf_metadataagent_snoopinganti_refusaldestructive_commandsobfuscated_unicodeunicode_homoglyphopaque_blobsuspicious_urltool_overreachtrigger_abuseprompt_injection_phrasing

IntentSafe

LLM judge · does the skill do what it claims

ContentClean

LLM judge · policy & harmful-content review

Source

Imported

wecode-ai / wegent

backend/init_data/skills/interactive/SKILL.md

View on GitHub ↗

License Apache-2.0Imported 8/3/2026Version v1

More skills from the same source and nearby in the registry, with their headline benchmark lift.

Ready to supercharge your AI agents?

See it in action

What's inside

Ask User

When to Use

Usage Notes

Behavior

Tool Parameters

Examples

Track record

Benchmark

Adoption

SkillSafety

Source

Related skills