自然学术搜索

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。它声明了 workflow 轴、允许的值以及每个值映射到的文件路径。另请阅读 always_load 下列出的每个文件: static/core/tools.md — MCP 工具清单(核心搜索、扩展搜索、PubMed 实用程序)和共享模块图。 static/core/routing-and-ops.md — T1→T2→T3 源路由快速指南、环境设置、错误处理和限制。

2. 检测工作流程

将用户的需求映射到一个或多个 workflow 值: multi-source-search — 跨来源查找文献。 citation-verification — 验证从文档中提取的引文。 mesh-strategy — 构建 MeSH/PubMed 搜索策略。 citation-file-mgmt — 转换/管理 .nbib/.ris/.bib 文件。

3. 加载匹配的工作流程片段

读取为每个检测到的工作流程映射的文件(在references/workflows/下)。不要阅读每个工作流程。每个工作流程文件都链接到它所需的共享模块。

4. 使用加载的材料运行工作流程

按以下顺序应用加载的材料:核心工具和路由(core/tools.md、core/routing-and-ops.md)- 哪个 MCP 工具需要哪个,以及 T1→T2→T3 后备链(这是所有工作流程的标准执行顺序)。工作流程片段——它的具体步骤。按需共享模块和脚本(重复数据删除、引文解析器、搜索策略、RIS/BibTeX 格式、格式转换器)。报告特定工具故障并继续使用其余工具;当没有结果时扩大条款;如果脚本失败两次,则退回到从 MCP 获取的元数据手动生成。

5. 仅在需要时才获取参考资料

references/(和scripts/)下的文件是深度引用,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/source-tiers.md用于完整的可靠性分类,references/dedup-engine.md / references/citation-parser.md / references/search-strategy.md / references/ris-bibtex-format.md用于共享模块,以及scripts/format-converter.py / scripts/preflight.py用于工具。

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
需简单配置
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
  • 命令执行
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

# Academic Search — Router

This skill is split into two layers:

- A **static layer** under `static/` that holds versioned, reusable content fragments (the MCP tool inventory and shared modules, and source routing plus operational rules).
- A **dynamic layer** (this file plus `manifest.yaml`) that detects which workflow the user needs and loads that workflow, reaching for shared modules and scripts only when a step needs them.

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

## Routing protocol

Follow these five steps every time the skill is invoked.

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

Read [manifest.yaml](manifest.yaml). It declares the `workflow` axis, the allowed values, and the file paths each value maps to.

Also read every file listed under `always_load`:

- `static/core/tools.md` — the MCP tool inventory (core search, extended search, PubMed utilities) and the shared-module map.
- `static/core/routing-and-ops.md` — the T1→T2→T3 source routing quick guide, environment setup, error handling, and limitations.

### 2. Detect the workflow

Map the user's need to one or more `workflow` values:

- `multi-source-search` — find literature across sources.
- `citation-verification` — verify citations extracted from a document.
- `mesh-strategy` — build a MeSH/PubMed search strategy.
- `citation-file-mgmt` — convert/manage `.nbib`/`.ris`/`.bib` files.
- `reference-mgmt` — BibTeX, related-article discovery, ID conversion.

A combined request (for example search then export) may need more than one. State the detected workflow(s) in one short line before proceeding.

### 3. Load the matching workflow fragment(s)

Read the file mapped for each detected workflow (under `references/workflows/`). Do **not** read every workflow. Each workflow file links to the shared modules it needs.

### 4. Run the workflow using the loaded material

Apply the loaded material in this order:

1. Core tools and routing (`core/tools.md`, `core/routing-and-ops.md`) — which MCP tool for which need, and the T1→T2→T3 fallback chain that is the standard execution order across all workflows.
2. The workflow fragment — its specific steps.
3. Shared modules and scripts on demand (dedup, citation parser, search strategy, RIS/BibTeX format, format converter).

Report specific tool failures and continue with remaining tools; broaden terms when there are no results; fall back to manual generation from MCP-fetched metadata if a script fails twice.

### 5. Reach for references only when needed

The files under `references/` (and `scripts/`) are deep references, not defaults. Open them on demand per the `references.on_demand` table in the manifest — for example `references/source-tiers.md` for the full reliability classification, `references/dedup-engine.md` / `references/citation-parser.md` / `references/search-strategy.md` / `references/ris-bibtex-format.md` for the shared modules, and `scripts/format-converter.py` / `scripts/preflight.py` for the tooling.

## Why this split

- The static layer is versioned and reviewable; the workflow files and shared modules were already factored this way.
- The dynamic layer keeps each invocation cheap: only the workflow the user needs enters context, instead of all five plus every module.
- The router itself is short on purpose. Update fragments and references, not this file, when adding scope.
- This structure mirrors the other nature-* skills (`nature-writing`, `nature-polishing`, `nature-reader`, `nature-paper2ppt`, `nature-figure`, `nature-citation`, `nature-response`, `nature-data`).

讨论

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