ask-user
Conventions for asking the user questions during a workflow via the AskUserQuestion tool. Other skills reference this to keep prompts consistent and structured.
- Installs
- 284
- Last 24h
- —
- Trending rank
- —
- Security
- Not audited
Install
Works with every agent the skills CLI supports.
npx skills add https://github.com/desplega-ai/ai-toolbox --skill ask-user- 01
Install
Run the command in your project. The CLI asks which agents to install for.
- 02
Describe the task
Ask your agent for something this skill covers. It loads ask-user automatically when relevant.
- 03
Review the result
The agent follows the SKILL.md steps, scripts and references bundled with the skill.
SKILL.md
The instructions your agent reads when the skill is triggered.
Ask User
Thin helper that codifies how to ask the user questions during a workflow. Other skills (planning, research, brainstorming, implementing) reference this skill instead of duplicating AskUserQuestion conventions.
Core Rule
Use the AskUserQuestion tool — never as plain-text bullets in chat.
Asking in chat looks like a request for free-form prose; AskUserQuestion gives the user one click per decision and the answer is structured. Always prefer the tool.
When to Use
- Clarifying ambiguous user input
- Choosing between viable design options
- Confirming a non-trivial assumption before acting on it
- Approving a phase boundary, plan structure, or destructive action
- Capturing a workflow preference (e.g., commit-per-phase)
When NOT to Use
- Rhetorical questions or thinking-out-loud
- Asking permission for trivial, reversible actions (just do them)
- "Is the plan ready?" / "Should I proceed?" — those are not decisions, they're checkpoints; just present the artifact and stop
Conventions
Question shape
- One sentence, ends with
? - Include enough context that the user doesn't need to scroll back
- Don't reference invisible artifacts ("does the plan look good?" — they may not see it yet)
Options
- 2–4 mutually exclusive choices
- Each option: 1–5 word label, plus a one-sentence description explaining the trade-off or implication
- If you have a recommendation, put it first and append
(Recommended)to the label - Never include "Other" — the tool adds it automatically
Header chip
- Max 12 characters, names the axis of the choice (e.g.
Auth method,Approach,Scope)
Multi-select
Use multiSelect: true only when choices are non-exclusive (e.g., "which features to enable?"). Default is single-select.
Batching
If you have multiple independent questions to ask at the same checkpoint, send them in one AskUserQuestion call (up to 4 questions) — don't ping-pong.
Good Example
question: "Which storage backend should the worker use?"
header: "Storage"
options:
- label: "Postgres (Recommended)"
description: "Existing infra, transactional, easy to query. Adds one new schema."
- label: "Redis"
description: "Faster but requires new ops. Lossy on eviction — bad fit for audit data."
- label: "S3 + manifest"
description: "Cheapest at scale but adds latency and a sync layer."
Bad Examples
"What do you think?" → too vague, no options
"Should I continue? (yes/no)" → checkpoint, not a decision; just stop
"Pick one: A, B, C, D, E, F, G" → too many options; collapse or split
"Want me to also fix the typo?" → trivial reversible action; just do it
FAQ
What does the ask-user skill do?
Conventions for asking the user questions during a workflow via the AskUserQuestion tool. Other skills reference this to keep prompts consistent and structured.
How do I install ask-user?
Run npx skills add https://github.com/desplega-ai/ai-toolbox --skill ask-user in your project. The skills CLI detects the agents you use and copies the skill into the right folder. For Claude Code you can also place the skill folder at ~/.claude/skills/ask-user/ (personal) or .claude/skills/ask-user/ (project).
Which AI agents can use ask-user?
Any agent that supports the open Agent Skills format (a folder with a SKILL.md file), including Claude Code, Codex, Cursor, GitHub Copilot, Gemini CLI, Windsurf, Cline, OpenCode and more.
Is ask-user safe to install?
No partner security audit is available yet. Skills can run commands and scripts, so read the SKILL.md and any bundled files before installing.
Who maintains ask-user?
It is published by desplega-ai in desplega-ai/ai-toolbox. It has 284 recorded installs.
More from desplega-ai/ai-toolbox
planning
desplega-ai/ai-toolbox
Open the skill to read its SKILL.md instructions.
tdd-planning
desplega-ai/ai-toolbox
TDD-focused implementation planning. Creates plans with strict Red-Green-Commit/Rollback cycles for each step.
implementing
desplega-ai/ai-toolbox
Plan implementation skill. Executes approved technical plans phase by phase with verification checkpoints.
wts-expert
desplega-ai/ai-toolbox
Git worktree management expert for @desplega.ai/wts. Use when the user asks about git worktrees, wts commands, worktree workflows, or wants help managing multiple branches simultaneously.
Popular ai & agents skills
google-agents-cli-publish
google/agents-cli
This skill should be used when the user wants to "publish an agent", "publish my ADK agent", "register an agent with Gemini", "publish to Gemini" (formerly Gemini Enterprise), or needs guidance on the agents-cli publish gemini command. Also use when the user wants to "manage agents in Agent Registry", "list/update/delete registered agents", or "register an MCP server". Covers ADK vs A2A registration modes, programmatic and interactive usage, flag reference, auto-detection from deployment metadata, Agent Registry fleet management, and troubleshooting. Part of the agents-cli skills suite. Do NOT use for deployment (use google-agents-cli-deploy).
google-agents-cli-eval
google/agents-cli
This skill should be used when the user wants to "run an evaluation", "evaluate my agent", "evaluate my ADK agent", "write an eval dataset", "analyze eval failures", "compare eval results", "optimize agent", or needs guidance on the Gemini platform eval methodology and the Quality Flywheel. Covers eval metrics, dataset schema, LLM-as-judge scoring, and common failure causes. Applies to any agents-cli project, whatever framework the agent is written in. Do NOT use for agent API code patterns (ADK: use google-agents-cli-adk-code), deployment (use google-agents-cli-deploy), or project scaffolding (use google-agents-cli-scaffold).
skill-creator
anthropics/skills
Create new skills, modify and improve existing skills, and measure skill performance. Use when users want to create a skill from scratch, edit, or optimize an existing skill, run evals to test a skill, benchmark skill performance with variance analysis, or optimize a skill's description for better triggering accuracy.
codex-pet
prime-skills/runcomfy-agent-skills
Codex Pet generator on RunComfy. Build a Codex-compatible Codex Pet spritesheet.webp + pet.json from a single reference image, drop it into ${CODEXHOME:-$HOME/.codex}/pets/ / and Codex picks it up as a custom Codex Pet next to the 8 built-ins. This skill produces the exact Codex Pet atlas Codex expects (1536x1872 PNG/WebP, 8 cols x 9 rows, 192x208 cells, 9 animation states — idle, running-right, running-left, waving, jumping, failed, waiting, running, review). Calls OpenAI GPT Image 2 edit ONCE via the local RunComfy CLI as runcomfy run openai/gpt-image-2/edit to produce a canonical Codex Pet pose, then assembles all 9 animation rows programmatically with ImageMagick micro-transforms — no Codex Pro, no $imagegen, no OPENAIAPIKEY required, only RUNCOMFYTOKEN. Triggers on "codex pet", "create codex pet", "make codex pet", "hatch codex pet", "/hatch image", "desktop pet codex", "codex pets", "spritesheet.webp", or any explicit ask to build a custom pet for OpenAI Codex.
full-output-enforcement
leonxlnx/taste-skill
Overrides default LLM truncation behavior. Enforces complete code generation, bans placeholder patterns, and handles token-limit splits cleanly. Apply to any task requiring exhaustive, unabridged output.
executing-plans
obra/superpowers
Use when executing an implementation plan in the current session as the implementer yourself — your human partner chose inline execution, or no subagent tool is available