reasoning

SkillAI & models

Controls oma's reasoning effort level to balance depth, rigor, latency, and token cost.

Available today. Use it from your connected AI after setup.

Connect ahel once, and every AI you use reads what you have installed.

Then ask your AI: use the reasoning skill

What this skill tells your AI

The instructions your AI receives, as published by sswym/oh-my-agent in skills/reasoning/SKILL.md and read by ahel’s review.

目的

使用此技能在规划、执行或重度验证轮次之前设置显式推理姿态。

触发条件

  • 用户要求更快或更深的推理
  • 会话需要更严格的质量门控或更低的延迟
  • 团队希望在各个阶段有可预测的规划/验证努力

支持的努力水平

  • low
  • medium
  • high
  • xhigh

工作流程

  1. 识别请求的努力或推断 medium 作为默认值。
  2. 解释对规划深度、验证严格性和成本/延迟的影响。
  3. 当文件系统工具可用时,持久化/更新 .oma/state/reasoning.json
  4. 根据姿态推荐下一个命令(/oma:mode/oma:team/oma:loop)。

输出模板

## 推理
- 请求:
- 已应用:

## 配置文件
| 维度 | 值 |
| --- | --- |

## 下一个命令
- ...

Signals

GitHub stars
76
Forks
13
Last commit
Apr 2026
Advanced
Catalog kind
skill
Gateway key
reasoning-sswym
Source
github.com/sswym/oh-my-agent