使用方法
- 复制安装命令，在自己的智能体环境安装前先检查源码包。
- 从原始文档核对所需工具、凭据和支持的宿主。
- 说明输入材料与期望交付物，并对照来源检查输出。
npx skills add https://github.com/aicodeking/deepseek-stack --skill ds-best-of-n开始前需了解
- 安装不包含模型订阅、API 额度或访问文件的权限。
- 仓库星数和安装量反映活跃情况，不等于独立质量或安全测试。
仓库原始内容
按源仓库内容呈现，保留标题、案例、代码、表格、链接以及原文引用的演示图片。
ds-best-of-n
One attempt is a sample, not an answer. DeepSeek is cheap enough that three to five attempts usually cost less than one round of fixing a bad first try.
Steps
- Frame the task. Write one prompt that every attempt gets unchanged. Write a private rubric of 3 to 6 concrete, checkable criteria. Attempts never see the rubric.
- Pick N. Use 3 by default and 5 when the design space is wide. Give each attempt its own output location, such as a git worktree or a separate temp folder.
- Spawn N subagents at once with the prompt, the shared context and their output path. Ask each for the artifact plus a short note on alternatives it rejected. If a harness cannot run subagents, run the attempts one after another in fresh contexts.
- Check each attempt. Run its build, tests or a quick probe. Record pass or fail with output. Discard attempts that do not run.
- Score the survivors against the rubric. Pick the one with the best overall structure as the base. Structure beats polish.
- List the specific strong parts of the other attempts: a test, an edge case, a cleaner function. Graft only those into the base. Do not merge whole files.
- Re-run the full checks on the grafted result and show the output.
Stop when
- The grafted result passes every check and you have reported base, grafts and scores.
- Or no attempt passes after one re-run with a clarified prompt. Report what failed.
Rules
- Never pick by reading the attempt's own summary. Pick by running it.
- Do not let one attempt see another before scoring.
- Keep the losing attempts until the final checks pass.
