自然反应

其他 社区

技能解读

当前原文的自动摘译,尚未人工审校。

1.加载manifest和核心层

阅读manifest.yaml。然后阅读always_load下列出的每个文件:static/core/stance.md - 面向编辑的目的、默认立场、红线以及适用于每个响应作业的源层次结构。 static/core/workflow.md — 接受的输入、十步工作流程和输出包格式。

2. 无内容轴——识别模式和语言内联

与自然写作或自然人物不同,自然响应没有片段轴。它的变化是在运行时识别的,而不是通过加载不同的内容体来识别:任务模式 - draft / audit / revise / triage-only / appeal-like。决策类型——小修改、大修改、修改并重新提交、审核后转移或不清楚。用户语言——如果用户写中文,也会产生中文核对块。

3. 运行工作流程

遵循core/workflow.md中的十步工作流程:识别模式和决策类型,提取编辑器说明(IDE.1),然后提取审稿人评论(R1.1,R2.1),对每个项目进行分类,构建策略摘要,从保留的评论中起草逐点响应,将每个声明的更改映射到手稿位置或显式占位符,标记缺少的作者输入,运行质量保证,并使用准备状态。

4. 仅在需要时才获取参考资料

references/下的文件是深层引用,而不是默认文件。根据清单中的references.on_demand表按需打开它们 - 例如references/comment-taxonomy.md对评论进行分类,references/action-mapping.md用于跟踪字段,references/tone-and-stance.md用于分歧措辞,references/difficult-cases.md用于不可能的实验/冲突的审稿人/类似上诉的情况,references/chinese-author-alignment.md用于中文作者注释,以及references/qa-checklist.md 最终确定之前。

为何如此分裂

静态层是版本化且可审查的;核心保持较小以实现正常响应。动态层使每次调用都很便宜:仅在步骤需要时才加载困难情况、分类和 QA 深度。路由器本身故意较短。添加范围时更新片段和引用,而不是此文件。该结构镜像nature-writing、nature-polishing、nature-reader、nature-paper2ppt、nature-figure和nature-citation。

流狐档案 运行与权限由流狐静态检查推断,不代表作者声明或实际测试结果。
领域
通用
作者声明的智能体
未找到明确声明;不据此推断已兼容或已测试
静态检查
88 / 100 · 启发式扫描,不代表运行安全
运行环境证据
未执行;当前没有隔离运行测试证据
作者 / 版本 / 许可证
@Yuan1z0825 · 未声明许可证
上下文用量评级
低消耗
接入复杂程度
即装即用
是否需要外部接口密钥
不需要
兼容的系统
未声明(默认跨平台)
运行环境要求
未检出明确要求
检测到的文件与系统行为
  • 只读
  • 允许写入 / 修改
网络行为
仅限本地
安装命令数
无(仅作为资料)

需要注意: 未声明工具权限范围;实际权限由运行环境决定。

作者说明文件(原文) SKILL.md

# Nature Reviewer Response — Router

This skill is split into two layers:

- A **static layer** under `static/` that holds versioned, reusable content fragments (the default stance and red lines, and the response workflow with output format).
- A **dynamic layer** (this file plus `manifest.yaml`) that loads the core every time and reaches for the deeper response references only when a step needs them.

Do not try to apply the response logic from memory or from this router. Always load fragments from disk as described below.

## Routing protocol

Follow these four steps every time the skill is invoked.

### 1. Load the manifest and the core layer

Read [manifest.yaml](manifest.yaml). Then read every file listed under `always_load`:

- `static/core/stance.md` — the editor-facing purpose, the default stance, the red lines, and the source hierarchy that apply to every response job.
- `static/core/workflow.md` — accepted inputs, the ten-step workflow, and the output package format.

### 2. No content axis — identify mode and language inline

Unlike nature-writing or nature-figure, nature-response has no fragment axis. Its variation is identified at runtime, not by loading different content bodies:

- **task mode** — `draft` / `audit` / `revise` / `triage-only` / `appeal-like`.
- **decision type** — minor revision, major revision, revise-and-resubmit, transfer after review, or unclear.
- **user language** — if the user writes Chinese, also produce the 中文核对 block.

Use `references/intake-and-routing.md` to fix the task mode, minimum inputs, and readiness state before drafting. Route appeal-like cases separately; do not draft an appeal as the default path.

### 3. Run the workflow

Follow the ten-step workflow in `core/workflow.md`: identify mode and decision type, extract editor instructions (IDs `E.1`) then reviewer comments (`R1.1`, `R2.1`), classify each item, build a strategy summary, draft point-by-point responses from the preserved comments, map every claimed change to a manuscript location or an explicit placeholder, flag missing author input, run QA, and return the package with a readiness state.

Never invent experiments, citations, line numbers, figure panels, supplementary items, editor instructions, or manuscript changes. Mark anything the author must supply as `AUTHOR_INPUT_NEEDED`.

### 4. Reach for references only when needed

The files under `references/` are deep references, not defaults. Open them on demand per the `references.on_demand` table in the manifest — for example `references/comment-taxonomy.md` to classify comments, `references/action-mapping.md` for tracker fields, `references/tone-and-stance.md` for disagreement wording, `references/difficult-cases.md` for impossible experiments / conflicting reviewers / appeal-like cases, `references/chinese-author-alignment.md` for Chinese author notes, and `references/qa-checklist.md` before finalizing.

## Why this split

- The static layer is versioned and reviewable; the core stays small for a normal response.
- The dynamic layer keeps each invocation cheap: the difficult-case, taxonomy, and QA depth load only when a step needs them.
- The router itself is short on purpose. Update fragments and references, not this file, when adding scope.
- This structure mirrors `nature-writing`, `nature-polishing`, `nature-reader`, `nature-paper2ppt`, `nature-figure`, and `nature-citation`.

讨论

基于 GitHub Discussions。登录 GitHub 即可参与讨论、点赞、订阅更新。