Skills for Real Engineers. Straight from my .agents directory.
science-journal-intel
Agent skill fromyzlin286-wq/Deepscient
Use when you need to know how a journal actually behaves rather than what its aims-and-scope page claims — its real subfield mix over the last two years, first-round review duration and comment difficulty from authors, Chinese-author review speed and accept-rate wording; also use when a manuscript was rejected for "scope" and you need evidence about which journals genuinely publish that kind of work.
How to install science-journal-intel
npx skills add yzlin286-wq/Deepscient# or add only this skill to Claude Code: copy the folder
dsh-science/skills/science/science-journal-intel/
# into
~/.claude/skills/science-journal-intel/ (all projects)
.claude/skills/science-journal-intel/ (one project)
1# 期刊情报:看它发过什么,不看它说自己喜欢什么23## 为什么需要这一层45`aims & scope` 是营销文案。真正决定送审的是**编辑桌上那堆稿子的分布**。6一本刊过去两年在你这个子领域发了 0 篇,你的 cover letter 写得再好也过不了初筛;7发了 9%,那就是它的主场之一。这个差别 scope 关键词永远告诉不了你。89`science_journal_intel` 把三个独立来源拼成一张卡:1011| 源 | 回答的问题 | 记的是什么 |12|---|---|---|13| OpenAlex | 它**实际**在发什么 | 近两年每篇论文的 primary topic,按 subfield 汇总占比 |14| SciRev | 作者**实际**经历了什么 | 首轮月数、总量月数、即时拒天数、审稿轮数、意见难度、样本数 |15| LetPub | 中国作者**实际**怎么说 | 审稿速度档、录用比例措辞、中科院分区、IF |1617三个源互相独立:谁挂了就在 `degraded[]` 里点名,其余照常给结论。1819## 一、用 topicFootprint 判断「这是不是我的主场」2021```22science_journal_intel({ journalId: "nature", title: "<你的标题>", keywords: ["protein folding"] })23```2425输出里的 `topicFootprint` 有两层:26271. `topSubfields`:该刊近两年产出按子领域的分布。**看最大值**——28 最大子领域只有 9%,说明它是综合刊(Nature 就是这样,Molecular Biology 9.1%);29 最大子领域 45%,说明它是专刊,投不进去的领域基本没戏。302. `hitShare`:你的子领域占该刊产出的比例。这是**加权后的命中**,31 稿件标题+关键词先被映射到 1–4 个子领域,再逐一对分布取占比求和。3233读法:3435| hitShare | 含义 | 动作 |36|---|---|---|37| ≥ 5% | 主场,编辑天然认这类稿 | 直接投,cover letter 提一句连续性即可 |38| 1–5% | 边缘,需要读者相关性论证 | 投,但第 4 段必须写「为什么本刊读者会关心」 |39| < 1% | 几乎不发这类 | 换刊;除非你有跨领域意义(那就按综合刊投,别按专刊投) |40| 0(未命中) | 近两年零篇 | 强烈考虑换刊,风险等同于赌博 |4142**铁律**:`hitShare` 是**统计事实**——该刊近两年产出中落在你子领域的比例。43它**不是**录用概率,也不做任何概率推算。没有任何工具能预测录用,只能告诉你「这类工作在这本刊出现过几次」。4445## 二、用 reviewReality 排时间表,不用它做取舍4647SciRev 的数据是作者自报的实际经历,回答的是「投进去要等多久、会被怎么打」:4849- `firstReviewMonths` / `handlingMonths`:**首轮**和**从投到终审决定**的月数。50 毕业/结题倒排时间时用总量,不要用首轮自我安慰。51- `immediateRejectDays`:desk reject 平均几天。这个数字小说明初筛快,等你等到第 20 天还没动静,52 大概率已经进外审了——可以据此决定要不要催稿。53…
Excerpt shown under the repository's MIT license.
More skills in Deepscient
- ▸science-agent-scheduling
- ▸science-campaign-design
- ▸science-consensus-report
- ▸science-discipline-methods
- ▸science-experiment-runbook
- ▸science-figure-for-journal
- ▸science-frontier-to-paper
- ▸science-fulltext-hunting
- ▸science-journal-selection
- ▸science-literature-search
- ▸science-manuscript-formatting
- ▸science-org-roles
Similar skill repositories
An agentic skills framework & software development methodology that works.
A single CLAUDE.md file to improve Claude Code behavior, derived from Andrej Karpathy's observations on LLM coding pitfalls.
Public repository for Agent Skills
Makes your AI agent think like the laziest senior dev in the room. The best code is the code you never wrote.
Persistent Context Across Sessions for Every Agent – Captures everything your agent does during sessions, compresses it with AI, and injects relevant context back into future sessions. Works with Claude Code, OpenClaw, Codex, Gemini, Hermes, Copilot, OpenCode + More
