Asks Claude CLI for coding assistance. Use for getting a second opinion, code generation, debugging, or delegating coding tasks.
View on GitHubhiroro-work/claude-plugins
security-scanner
January 25, 2026
Select agents to install to:
npx add-skill https://github.com/hiroro-work/claude-plugins/blob/main/skills/ask-claude/SKILL.md -a claude-code --skill ask-claudeInstallation paths:
.claude/skills/ask-claude/# Ask Claude Executes the local `claude` CLI to get coding assistance. **Note:** This skill requires the `claude` CLI to be installed and available in your system's PATH. ## Quick start Run a single query with `-p` (print mode): ```bash claude -p "Your question or task here" ``` ## Common options | Option | Description | |--------|-------------| | `-p` | Non-interactive print mode (required for scripting) | | `--model MODEL` | Specify model (e.g., `sonnet`, `opus`, `haiku`) | | `--output-format FORMAT` | Output format: `text`, `json`, `stream-json` | | `-c, --continue` | Continue the most recent conversation | > For all available options, run `claude --help` ## Examples **Ask a coding question:** ```bash claude -p "How do I implement a binary search in Python?" ``` **Use a specific model:** ```bash claude -p --model opus "Review this code for potential issues" ``` **Get JSON output:** ```bash claude -p --output-format json "List the main functions in this file" ``` **Continue a previous conversation:** ```bash claude -p -c "Now add error handling to that function" ``` ## Notes - The `-p` flag runs Claude non-interactively and outputs result to stdout - If `--model` is not specified, the default model is used - `stream-json` outputs responses incrementally as they are generated - **Warning**: The `-p` flag skips the workspace trust dialog. Only use in directories you trust. - The command inherits the current working directory