返回目录
学习研究 插件

dsh-plugin-academic-writing

863683348/dsh-plugin-academic-writing

Academic writing toolkit for DeepSeek Harness agents: paper outlines, title/abstract skeletons, GB/T 7714 / APA / MLA citations, phrasing QA, and a pre-submission checklist

Stars
0
Forks
0
Issues
0
更新
今天

PROJECT TOPICS

项目标签

INSTALL REFERENCE

安装参考

未验证
dsh plugin --profile web add github:863683348/dsh-plugin-academic-writing

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

README

dsh-plugin-academic-writing

An academic writing toolkit for DeepSeek Harness agents. The model composes the prose; the plugin supplies structure, formats, and deterministic checks.

Install

dsh plugin --profile <profile> add dsh-plugin-academic-writing

Restart DSH. The academic_writing tool is registered host-wide.

Tool

action purpose
outline Paper outline skeleton (research / review / proposal / essay), optional section cap
title Title variants from style templates (descriptive, question, declarative, colon)
abstract Structured abstract skeleton — background / methods / results / conclusion
citation Reference entry formatted as GB/T 7714, APA 7, or MLA 9
check Phrasing QA on a passage (passive voice, first person, hedging, sentence length)
checklist Pre-submission checklist (ethics, conflict of interest, data, funding, formatting)
references Reference list from citation entries — deduplicated and sorted (GB/T 7714 / APA / MLA)
latex LaTeX snippets: booktabs table, equation (inline/display/align), code listing, thebibliography

Config

All optional, on the composition row's config:

key default meaning
personaSection true register the academic prompt-guidance section
sectionOrder 6 prompt section order (persona is 0, ascending)

Design

Pure logic (lib/academic.js) has zero DSH/Cordis imports and is unit-tested in isolation; lib/index.js is the thin Cordis plugin wiring the tool and the prompt section. No filesystem access — everything is deterministic and side-effect free.

License

MIT

Roadmap

See ROADMAP.md — next five versions (v0.2.0 – v0.6.0): reference management, structure QA, expression risk, journal adaptation, review workflow.

CLASSIFICATION EVIDENCE

分类依据

项目类型插件
功能分类学习研究
规则置信度

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、paper。