让 AI 帮你安装
复制下面这句话，粘贴给 Claude Code、Codex、Cursor 等 AI 编程工具，它会读取安装说明并在你确认后完成安装。
请阅读 https://ai.atlankj.com/install/asset/gh-academic-research-skills-2f667d035752 ，按照其中的说明把「ars-3w」安装到你（当前 AI 工具）中。执行前先告诉我将运行的命令和写入的位置，等我确认。
查看 AI 将读取的安装说明正在读取 GitHub 原文…
复制下面这句话，粘贴给 Claude Code、Codex、Cursor 等 AI 编程工具，它会读取安装说明并在你确认后完成安装。
请阅读 https://ai.atlankj.com/install/asset/gh-academic-research-skills-2f667d035752 ，按照其中的说明把「ars-3w」安装到你（当前 AI 工具）中。执行前先告诉我将运行的命令和写入的位置，等我确认。
查看 AI 将读取的安装说明正在读取 GitHub 原文…
内容来自 GitHub 原始文件，由原作者维护。在 GitHub 查看
three-way-scan mode — WHY / HOW / WHAT paper comparison
model: sonnetFirst invoke the Skill tool with skill: "academic-research-skills:deep-research". Pass the mode and the user's request described below as its arguments. Use the loaded skill and its supporting files before producing the result.
Trigger the deep-research skill in three-way-scan mode. Produces a compact paper shortlist compared by WHY / HOW / WHAT plus a cross-paper synthesis (common WHY, divergent HOW, strongest WHAT, unresolved gap). Lighter than lit-review; escalate to lit-review / systematic-review for full coverage. Fidelity spectrum, low oversight.
Mode reference: ${CLAUDE_PLUGIN_ROOT}/MODE_REGISTRY.md § deep-research.
Skill entry: ${CLAUDE_PLUGIN_ROOT}/deep-research/SKILL.md.
Resolve plugin resources from ${CLAUDE_PLUGIN_ROOT}, not from the paper project's working directory. If the skill or a required file cannot be loaded, report the loading failure and stop; do not substitute this command summary for the mode instructions.