ask
Async via ask, end turn immediately; use when user explicitly delegates to any AI provider (gemini/codex/opencode/droid); NOT for questions about the providers themselves.
Best use case
ask is best used when you need a repeatable AI agent workflow instead of a one-off prompt.
Async via ask, end turn immediately; use when user explicitly delegates to any AI provider (gemini/codex/opencode/droid); NOT for questions about the providers themselves.
Teams using ask should expect a more consistent output, faster repeated execution, less prompt rewriting.
When to use this skill
- You want a reusable workflow that can be run more than once with consistent structure.
When not to use this skill
- You only need a quick one-off answer and do not need a reusable workflow.
- You cannot install or maintain the underlying files, dependencies, or repository context.
Installation
Claude Code / Cursor / Codex
Manual Installation
- Download SKILL.md from GitHub
- Place it in
.claude/skills/ask/SKILL.mdinside your project - Restart your AI agent — it will auto-discover the skill
How ask Compares
| Feature / Agent | ask | Standard Approach |
|---|---|---|
| Platform Support | Not specified | Limited / Varies |
| Context Awareness | High | Baseline |
| Installation Complexity | Unknown | N/A |
Frequently Asked Questions
What does this skill do?
Async via ask, end turn immediately; use when user explicitly delegates to any AI provider (gemini/codex/opencode/droid); NOT for questions about the providers themselves.
Where can I find the source code?
You can find the source code on GitHub using the link provided at the top of the page.
Related Guides
AI Agents for Coding
Browse AI agent skills for coding, debugging, testing, refactoring, code review, and developer workflows across Claude, Cursor, and Codex.
Best AI Skills for Claude
Explore the best AI skills for Claude and Claude Code across coding, research, workflow automation, documentation, and agent operations.
ChatGPT vs Claude for Agent Skills
Compare ChatGPT and Claude for AI agent skills across coding, writing, research, and reusable workflow execution.
SKILL.md Source
# Ask AI Provider (Async) Send the user's request to specified AI provider asynchronously. ## Usage The first argument must be the provider name, followed by the message: - `gemini` - Send to Gemini - `codex` - Send to Codex - `opencode` - Send to OpenCode - `droid` - Send to Droid ## Execution (MANDATORY) ``` Bash(CCB_CALLER=claude ask $PROVIDER "$MESSAGE") ``` ## Rules - Follow the **Async Guardrail** rule in CLAUDE.md (mandatory). - Local fallback: if output contains `CCB_ASYNC_SUBMITTED`, end your turn immediately. - If submit fails (non-zero exit): - Reply with exactly one line: `[Provider] submit failed: <short error>` - End your turn immediately. ## Examples - `/ask gemini What is 12+12?` - `/ask codex Refactor this code` - `/ask opencode Analyze this bug` - `/ask droid Execute this task`
Related Skills
ping
Test connectivity with AI provider (gemini/codex/opencode/droid/claude).
tr
Execute current step in AutoFlow workflow. Use when running /tr or continuing task execution.
tp
Create a task plan with collaborative design. Use when starting a new task or running /tp.
review
Dual review with Claude and Codex for quality verification. Use for step or task review.
pend
View latest reply from AI provider (gemini/codex/opencode/droid/claude).
mounted
Report which CCB providers are mounted (session exists AND daemon is online). Outputs JSON.
file-op
Delegate file I/O to Codex via FileOpsREQ protocol. Use when Claude needs Codex to modify files.
cping
Test connectivity with AI provider (gemini/codex/opencode/droid/claude).
continue
Attach the newest context-transfer Markdown from the current project's ./.ccb/history/ into Claude using @file. Use when the user types /continue or asks to resume with the latest transfer file in this project.
autonew
Send /new to a provider's pane to start a new session without context injection.
all-plan
Collaborative planning using abstract roles (designer + inspiration + reviewer).
compose-multiplatform-patterns
KMP项目中的Compose Multiplatform和Jetpack Compose模式——状态管理、导航、主题化、性能优化和平台特定UI。