Milbaxter/dsh-critique-loop ↗★ 0
dsh-critique-loop
DeepSeek Harness 插件，在每个对话回合完成后强制执行一轮自我审查与改进（critique-and-improve）。
AI 分析
核心用途是提升 Agent 输出的准确性与质量。适合对生成结果要求极高、希望 Agent 在输出前自动进行纠错和优化的用户。
安装
$
npx -p @deepseek-ai/dsh dsh plugin --profile web add github:Milbaxter/dsh-critique-loop说明文档
阅读完整 README ↗Configuration
In your cordis.yml or bundle configuration:
- id: dsh-critique-loop
name: dsh-critique-loop
config:
enabled: true
maxRounds: 1
prompt: "Critique what you just did. Be specific about mistakes, gaps, and weaker choices. If the critique finds something worth changing, apply the improvement now. If nothing material needs changing, say so briefly and stop."
Options
| Option | Type | Default | Description |
|---|---|---|---|
enabled | boolean | true | Master switch to enable/disable the critique loop. |
maxRounds | number | 1 | Maximum self-critique rounds per turn before stopping. |
prompt | string | (standard prompt) | Custom critique instruction steered into the agent. |