菜单
Create and configure custom commands for Opencode to automate repetitive tasks with custom prompts.
用 Codex 或 Claude 帮你安装 复制这段 Prompt，粘贴到 Codex、Claude 或其他助手里，让它检查 Skill 页面并帮你完成安装。
基于 SOC 职业分类
Best practices for writing clean, maintainable, and robust tests with TUnit.
Use `helium-browser --dump-dom` to inspect the fully rendered DOM after JavaScript execution. For debugging layout/scrolling issues and scraping dynamic pages.
Senior UI/UX Engineer. Architect digital interfaces overriding default LLM biases. Enforces metric-based rules, strict component architecture, CSS hardware acceleration, and balanced design engineering.
CLI tool for AI agents to browse the web, interact with UI elements, and analyze frontend applications. Supports navigation, clicking, typing, and capturing snapshots for accessibility analysis.
Expert guide for creating, configuring, and managing Opencode Agents. Use this skill when the user wants to create a new agent or modify an existing one.
Expert guide and best practices for building production-ready web APIs with Axum 0.8+ in Rust. Use this skill when developing, refactoring, or structuring Axum applications.
| name | command-creator |
| description | Create and configure custom commands for Opencode to automate repetitive tasks with custom prompts. |
The command-creator skill helps you define custom commands in Opencode. Custom commands let you specify prompts that run when you execute the command in the TUI with /command-name.
Commands are defined using markdown files in the command/ directory:
~/.config/opencode/command/<name>.md.opencode/command/<name>.mdThe filename becomes the command name. Example: test.md creates /test.
Example: .opencode/command/test.md
---
description: Run tests with coverage
agent: build
model: 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.
| Option | Required | Description |
|---|---|---|
description | No | Brief description shown in TUI |
agent | No | Agent to execute (defaults to current) |
subtask | No | Force subagent invocation (true/false) |
model | No | Override default model |
The prompt template follows the frontmatter section.
$ARGUMENTS - All arguments passed to the command$1, $2, $3... - Individual positional argumentsExample:
---
description: Create a new component
---
Create a React component named $ARGUMENTS with TypeScript support.
Usage: /component Button → $ARGUMENTS = Button
Use !`command` to inject bash output into prompts:
---
description: Analyze test coverage
---
Here are the current test results:
!`npm test`
Based on these results, suggest improvements to increase coverage.
Use @filename to include file content in prompts:
---
description: Review component
---
Review @src/components/Button.tsx for performance issues.
Opencode includes built-in commands: /init, /undo, /redo, /share, /help. Custom commands can override these if they share the same name.
When the skill is triggered: