Skip to content
Back to skills

Ui

ASecurity

Ask the human directly through the optional question plugin.

  • 43 stars
  • 0 votes
  • 0 copies
  • 0 views
  • Added November 13, 2026
ai-agents

Security analysis

A100/100

Scanned November 13, 2026

npx -y skills add acyclic-labs/sdk --skill ui --agent claude-code

Installs into .claude/skills of the current project.

Are you the author of Ui?

Add the live security badge to your README. It updates with every re-scan.

Security grade badge for Ui
[![Security: A — Skills Directory](https://www.skillsdirectory.com/api/skills/acyclic-labs-sdk-sdk/badge)](https://www.skillsdirectory.com/skills/acyclic-labs-sdk-sdk)

More formats (shields.io, HTML) on the badges page. Keep it an A: scan every change in CI with Pro.

Download with Pro
SKILL.md
---
name: question
description: Ask the human directly through the optional question plugin.
---
Use the ordinary file tools at `volume:///private/ui/<path>`. This is an authenticated tool address, not a directory mounted in the cwd; managed private outputs remain read-only.
The default ui/index.md, status.md and paged children/ need no maintenance. Write ui/<path> in your private agent volume (outside the repo) to override that path; delete it to restore the default. An empty fenced `ui:default` block embeds the default at that point. Only orchestrators ask the human, using ask_question to publish a private ui/ file containing a CommonMark fence with header `input <kind> id=<stable-id> [key=value ...]` and literal body; choose/multi use list items, text uses prose, recommended=<value> is optional. End your turn to wait. Replies arrive as one ordinary prompt containing {ui,generation,answers,text}; free-form text is always available, including for unknown kinds. Approval blocks use the existing approval decision path and cannot be authored to grant authority. Do not re-read your own ui/index.md: it repeats your context. Pull source files when needed. No active content or automatically followed links.

Attribution

Is this your skill, or is something wrong with this listing? Request removal or report an issue. Author removals are honored within 72 hours.

View all in ai-agents →

Comments

Loading comments…

Newsletter

Get the weekly list of safe new skills, and the ones we pulled.