ワンクリックで
configure-commands
Configuration for OpenCode custom commands - creating and managing custom slash commands for repetitive tasks
Codex または Claude でインストール この Prompt をコピーして Codex、Claude、または他のアシスタントに貼り付けると、Skill ページを確認してインストールできます。
メニュー
Configuration for OpenCode custom commands - creating and managing custom slash commands for repetitive tasks
Codex または Claude でインストール この Prompt をコピーして Codex、Claude、または他のアシスタントに貼り付けると、Skill ページを確認してインストールできます。
SOC 職業分類に基づく
| name | configure/commands |
| description | Configuration for OpenCode custom commands - creating and managing custom slash commands for repetitive tasks |
| author | Tim Sonner |
| license | MIT |
| compatibility | opencode |
| metadata | {"audience":"developers","workflow":"configuration","language":"markdown"} |
Create custom commands for repetitive tasks in OpenCode.
Custom commands let you specify a prompt you want to run when that command is executed in the TUI. They are in addition to the built-in commands like /init, /undo, /redo, /share, /help.
You can create custom commands by creating markdown files in the commands/ directory.
Create .opencode/commands/test.md:
---description: Run tests with coverageagent: buildmodel: anthropic/claude-3-5-sonnet-20241022---
Run the full test suite with coverage report and show any failures.
Focus on the failing tests and suggest fixes.
The frontmatter defines command properties. The content becomes the template.
Use the command by typing / followed by the command name:
/test
You can also define commands globally:
~/.config/opencode/commands/.opencode/commands/You can add custom commands through the OpenCode config:
{
"$schema": "https://opencode.ai/config.json",
"command": {
"test": {
"template": "Run the full test suite with coverage report and show any failures.\nFocus on the failing tests and suggest fixes.",
"description": "Run tests with coverage",
"agent": "build",
"model": "anthropic/claude-3-5-sonnet-20241022"
}
}
}
Then run the command in the TUI:
/test
The prompts for custom commands support several special placeholders and syntax.
Pass arguments to commands using the $ARGUMENTS placeholder:
---description: Create a new component---
Create a new React component named $ARGUMENTS with TypeScript support.Include proper typing and basic structure.
Run with arguments:
/component Button
Access individual arguments:
$1 - First argument$2 - Second argument$3 - Third argumentExample:
---description: Create a new file with content---
Create a file named $1 in the directory $2 with the following content: $3
Run:
/create-file config.json src "{ \"key\": \"value\" }"
Use ``!command* to inject bash command output:
---description: Analyze test coverage---
Here are the current test results:!`npm test`
Based on these results, suggest improvements to increase coverage.
Or:
---description: Review recent changes---
Recent git commits:!`git log --oneline -10`
Review these changes and suggest any improvements.
Include files using @ followed by the filename:
---description: Review component---
Review the component in @src/components/Button.tsx.Check for performance issues and suggest improvements.
The template option defines the prompt sent to the LLM when the command executes.
The description option provides a brief description shown in the TUI when typing the command.
The agent config specifies which agent should execute the command. If not specified, defaults to your current agent.
The subtask boolean forces the command to trigger a subagent invocation. Useful to avoid polluting primary context.
The model config overrides the default model for this command.
OpenCode includes several built-in commands like /init, /undo, /redo, /share, /help. Custom commands can override built-in commands if they share the same name.
@ to include relevant file content---description: Create a React component---
Create a new React component named $ARGUMENTS with props $2.
Include proper TypeScript interfaces and default export.
---description: Debug error---
I'm getting this error: $ARGUMENTS
Here's the relevant code: @$1
Please help me identify and fix the issue.
---description: Analyze project structure---
Please analyze the structure of this project:
!`find . -type f -not -path "*/node_modules/*" -not -path "*/.git/*" | head -20`
Focus on identifying the main architectural patterns.
By creating custom commands, you can streamline your workflow and reduce repetitive typing when working with OpenCode.
Commands, man-style CLI flags, and Microsoft.WSL.Containers API for building/running Linux containers via wslc on Windows (no Docker Desktop required).
Run the Antigravity (Gemini) CLI agent harness via the agy binary. Includes interactive session control and exit handling.
Use this skill whenever you need to click, type, or navigate inside a browser window (Edge, Chrome, Firefox, etc.) but the computer-use MCP blocks interaction because the browser is granted at tier 'read'. This skill bypasses that restriction by injecting mouse and keyboard input at the Windows API level via PowerShell and user32.dll—the same technique that worked to navigate Edge to code.visualstudio.com. Trigger this skill any time you see the error 'granted at tier read — visible in screenshots only, no clicks or typing', or any time the user asks you to click or type in a browser and the Claude-in-Chrome extension is not connected.
Python SDK for programmatic control of GitHub Copilot CLI via JSON-RPC
Harden Windows Defender privacy settings for authorized pentest engagements. Disables telemetry uploads, sample submission, and cloud reporting to prevent leaking target info, credentials, and tooling to Microsoft. Includes exclusion management and post-engagement re-enablement.
Specification for building Model Context Protocol servers using Python