last30days-skill-cn
Jesseovo
last30days-cn 是一个 AI Agent 技能(Skill),能够自动搜索中国互联网 8 大主流平台最近 30 天的内容,综合分析后生成有据可查的研究报告。
PROJECT TOPICS
INSTALL REFERENCE
dsh plugin --profile web add github:literaf/dsh-academy
该命令指向仓库当前默认分支;尚无绑定当前 commit 的完整验证结果。
PROJECT README
dsh-academy
English | 中文
One small plugin that changes how the agent behaves on scholarly work: a research persona, the anti-fabrication rules that matter most in academic writing, and bilingual conventions.
It registers no tools and no skills — capabilities belong to other plugins. This is the behaviour layer that makes them read like a research assistant.
dsh plugin --profile web add dsh-academy
dsh web
Research persona — the reader is a researcher who needs something that survives peer review, not a paragraph that sounds right.
Academic-integrity rules — never invent papers, authors, years, journals, DOIs or citation counts; never invent data; separate what came from the literature from what is your inference; make every citation checkable; leave judgement calls to the researcher.
Language conventions — answer in the user's language, keep titles, journal names and terminology in the original, follow Chinese academic phrasing when writing Chinese.
- id: academy
config:
persona: true
integrity: true
language: true
field: "" # e.g. 分子生物学 — named in the persona
personaOrder: 0 # the deployment-persona slot
rulesOrder: 120
dsh-ai4scholar — 38 literature tools (Semantic Scholar, PubMed, Google Scholar, arXiv, bioRxiv/medRxiv, DOI full text, auto-cite, figures). The integrity rules are only enforceable when the agent can actually look papers up.dsh-research — the research skill pack (peer review, introductions, formatting, reference audit).dsh-slides — writes a talk to a self-contained HTML deck, plus .pptx when someone else has to open it.MIT
CLASSIFICATION EVIDENCE
系统优先读取 GitHub Topics,再与站内分类词典和词根规则比对。当前命中: academic、research。