Files
claude-code-best-practice/docs/PROMPTS.md
T
2025-11-03 19:20:35 +05:00

46 lines
1.8 KiB
Markdown

# Prompts
# Creating Agents and Commands
create a claude agent and command. the agent will first use tool to call weather api to fetch karachi weather in degree centigrade and then read instructions from @input/input.md to transform the result and update the @output/output.md
# Invocation difference between agents and commands
I have claude agents @.claude/agents folder and claude commands @.claude/commands folder. I want to invoke agents and commands differently. For example, I want to invoke agents with @agent_name and commands with @command_name. How can I achieve this?
## Claude Answer
For Commands (Slash Commands)
Commands in .claude/commands/ are invoked using the slash prefix:
/command-name
For your update-readme command:
/update-readme
For Agents (Sub-agents)
Agents in .claude/agents/ are invoked using the Task tool within commands or directly:
#### Using Task tool in your code/commands
Task(subagent_type="readme-writer", prompt="Generate README content")
Or by mentioning them in your instructions to Claude Code.
| What | How | Example |
|----------------------|------------------------|-------------------------------------|
| Commands | /command-name | /update-readme |
| Agents (in commands) | Task tool | Task(subagent_type="readme-writer") |
# based on @prompts/README.md claude answer, what I understand is commands must be invoked by using / on claude and it cannot be invoked like "claude use
- Commands are invoked using the slash prefix syntax: /command-name
- Example: /update-readme
However:
You can also invoke commands in natural language by asking Claude Code to use them. For example:
- "use the weather command to fetch the weather"
- "Run the weather slash command"