repo-intake-and-plan
Compare original and translation side by side
🇺🇸
Original
English🇨🇳
Translation
Chineserepo-intake-and-plan
repo-intake-and-plan
When to apply
适用场景
- At the beginning of README-first reproduction work.
- When the main skill needs a fast map of repo structure and documented commands.
- When inference, evaluation, and training candidates must be classified conservatively.
- When the user explicitly wants to inspect the repo first and not run anything yet.
- README优先的复现工作启动阶段
- 主技能需要快速获取仓库结构和文档记录命令的映射时
- 需要保守分类推理、评估和训练候选项时
- 用户明确要求先检查仓库、暂不执行任何操作时
When not to apply
不适用场景
- When execution has already started and the task is now about running commands or writing outputs.
- When the target is not a repository-backed reproduction task.
- When the user only wants paper interpretation without repo inspection.
- When the user already has a selected documented command and only needs setup or execution.
- 执行流程已启动，当前任务为运行命令或写入输出时
- 目标不是基于仓库的复现任务时
- 用户仅需要论文解读、不需要检查仓库时
- 用户已选定文档记录的命令，仅需要完成搭建或执行时
Clear boundaries
明确边界
- This skill scans and plans.
- It does not install environments.
- It does not prepare large assets.
- It does not execute substantive reproduction commands.
- It does not decide high-risk patching.
- 本技能仅负责扫描和规划
- 不执行环境安装
- 不准备大型资源
- 不执行实质性复现命令
- 不决策高风险补丁操作
Input expectations
输入要求
- Target repository path.
- Access to README and common project files if present.
- Optional user hints about desired priority, such as inference-first.
- 目标仓库路径
- 有权限访问README及存在的通用项目文件
- 可选的用户优先级提示，例如优先处理推理相关内容
Output expectations
输出要求
- concise repo structure summary
- documented command inventory
- inferred candidate categories: inference, evaluation, training, other
- minimum trustworthy reproduction recommendation
- notable ambiguity or risk list
- 简洁的仓库结构摘要
- 文档记录的命令清单
- 推断出的候选类别：inference、evaluation、training、其他
- 最小可信复现建议
- 值得注意的歧义或风险列表
Notes
注意事项
Use and helper scripts under .
references/repo-scan-rules.mdscripts/使用 及 目录下的辅助脚本。
references/repo-scan-rules.mdscripts/