OpenClaw

opencode-omo

Turn coding requests into completed work. Plan with Prometheus, execute with Atlas, and iterate with Sisyphus in OpenCode.

iisweetheartii0 来源安装数☆ 0 仓库 Starsv0.3.0

查看来源 ↗安装与使用 SKILL.md ↗

安装与使用

请根据来源仓库和你的 AI 工具说明安装此技能。先阅读技能文件和依赖要求，再添加到工作流。

SkillHub CLI

skillhub install iisweetheartii/opencode-omo

打开来源仓库，查看说明和兼容环境后，按来源提供的命令或步骤安装。

将来源链接提供给你的 Agent，让它先读取说明、核对依赖，并向你说明将执行的安装步骤。

查看来源 ↗使用指南

技能说明

OpenCode + Oh-My-OpenCode Operator

This skill is an operating guide for using OpenCode as your coding runtime, with Oh-My-OpenCode orchestration through Sisyphus, Prometheus, and Atlas.

What this skill gives you

One-shot delivery with ulw for focused coding requests.
Plan-to-execution workflow via @plan and /start-work.
Repeatable defaults so code quality stays consistent across runs.

Core rules

Do not edit code directly outside OpenCode unless explicitly asked.
Prefer Sisyphus-first execution for coding tasks.
For complex work: plan with Prometheus (@plan) then execute with Atlas (/start-work).

Quick start

Verify Oh-My-OpenCode plugin

cat ~/.config/opencode/opencode.json | grep "oh-my-opencode"

If the command returns output, the plugin is installed.

You can also run the bundled checker:

./scripts/check-omo.sh

Run one-shot coding (Sisyphus + ultrawork)

opencode run --agent sisyphus "ulw implement JWT auth in this service and add tests"

Or use the bundled helper:

./scripts/run-ulw.sh "implement JWT auth in this service and add tests"

Start interactive OpenCode (Sisyphus)

opencode --agent sisyphus

Inside OpenCode:

Use @plan "..." to invoke Prometheus planning.
Use /start-work to let Atlas execute the plan.

Failure handling

If the agent asks clarifying questions mid-implementation, answer them in plan mode (Prometheus) and re-run execution.
If you need more determinism, re-run with ulw and a smaller, explicit request.

Integration with other skills

agent-selfie: pair structured coding workflows with generated visual assets.
gemini-image-gen: use the same workflow discipline for image generation automations.
agentgram: publish progress updates, findings, and demos produced...

来源信息

Source: github
Repository: openclaw/skills
Path: skills/iisweetheartii/opencode-omo
Version: 0.3.0
Commit: e0b86455dbb4318aaa5ec4df7c4e6d99e3525c8f
分类来源: rules
状态: active
可见性: public

这些信息来自收录时的来源分析，可能滞后；使用前请核对最新来源文件。

来源内容

SKILL.md

# OpenCode + Oh-My-OpenCode Operator

This skill is an operating guide for using **OpenCode** as your coding runtime, with **Oh-My-OpenCode** orchestration through Sisyphus, Prometheus, and Atlas.

## What this skill gives you

- One-shot delivery with `ulw` for focused coding requests.
- Plan-to-execution workflow via `@plan` and `/start-work`.
- Repeatable defaults so code quality stays consistent across runs.

## Core rules

- Do not edit code directly outside OpenCode unless explicitly asked.
- Prefer Sisyphus-first execution for coding tasks.
- For complex work: plan with Prometheus (`@plan`) then execute with Atlas (`/start-work`).

## Quick start

### Verify Oh-My-OpenCode plugin

```bash
cat ~/.config/opencode/opencode.json | grep "oh-my-opencode"
```

If the command returns output, the plugin is installed.

You can also run the bundled checker:

```bash
./scripts/check-omo.sh
```

### Run one-shot coding (Sisyphus + ultrawork)

```bash
opencode run --agent sisyphus "ulw implement JWT auth in this service and add tests"
```

Or use the bundled helper:

```bash
./scripts/run-ulw.sh "implement JWT auth in this service and add tests"
```

### Start interactive OpenCode (Sisyphus)

```bash
opencode --agent sisyphus
```

Inside OpenCode:

- Use `@plan "..."` to invoke Prometheus planning.
- Use `/start-work` to let Atlas execute the plan.

## Failure handling

- If the agent asks clarifying questions mid-implementation, answer them in plan mode (Prometheus) and re-run execution.
- If you need more determinism, re-run with `ulw` and a smaller, explicit request.

## Integration with other skills

- **[agent-selfie](https://clawhub.org/skills/agent-selfie)**: pair structured coding workflows with generated visual assets.
- **[gemini-image-gen](https://clawhub.org/skills/gemini-image-gen)**: use the same workflow discipline for image generation automations.
- **[agentgram](https://clawhub.org/skills/agentgram)**: publish progress updates, findings, and demos produced...

搜索