Skills Plugins MCP Prompt Model 博客 我的中心
学习教育 #automation #writing

paper-writing-workflow

Modular 8-stage academic paper writing workflow — from planning to submission. Combines nature-skills + ARS + Omniscale best capabilities. Supports single-stage invocation or full pipeline automation. Trigger when user asks about paper writing workflow, 论文写作流程, academic writing pipeline, or wants to start/continue a structured paper project.

DeepseekModel 官方收录技能 质量 良好 · 64 v1.0.0

获取

https://deepseekmodel.com/api/download.php?id=csgf9k6s79-byte-paper-writing-workflow-plugin-skills-paper-workflow-skill-md&format=skill
下载 .skill 标准格式,含 system_prompt 与 model_config,导入任意 Agent 框架即可使用
.skill 文件中 system_prompt 字段的实际内容。
name paper-writing-workflow description Modular 8-stage academic paper writing workflow — from planning to submission. Combines nature-skills + ARS + Omniscale best capabilities. Supports single-stage invocation or full pipeline automation. Trigger when user asks about paper writing workflow, 论文写作流程, academic writing pipeline, or wants to start/continue a structured paper project. version 1.0.0 author xyy license MIT tags ["academic","writing","workflow","paper","research"] Paper Writing Full-Pipeline Workflow Overview This skill provides a modular 8-stage academic paper writing workflow that combines the best capabilities of installed Claude Code skills: nature-skills : polishing, writing, citation, figures, reviewer, response, reader ARS (Academic Research Skills) : deep-research, academic-paper, reviewer, pipeline Omniscale : critique, summarize-paper, research-map When to Use Trigger this skill when the user: Asks about paper writing workflow / 论文写作流程 Wants to start a structured paper project Needs guidance on which skill to use at which stage Wants to run a specific stage (e.g., "润色我的论文", "审稿自查") Asks "如何写论文" / "写论文的流程" 8-Stage Workflow Stage Name Key Skills 1 Planning & Research Map /ars-plan , research-map 2 Literature Survey nature-academic-search, ARS deep-research, summarize-paper 3 Writing First Draft nature-writing, /ars-outline , nature-polishing 4 Citations & Data nature-citation, /ars-citation-check , nature-data 5 Figures & Charts nature-figure (Python/R) 6 Review & Self-Check nature-reviewer, /ars-reviewer , critique 7 Revision & Response /ars-revision , nature-polishing, nature-response 8 Submission Output /ars-format-convert , /ars-disclosure , nature-paper2ppt Usage Quick Start The workflow script is at paper-workflow.js . Invoke via: Workflow({scriptPath: "path/to/paper-workflow.js", args: {stage: 3}}) Set stage to 1-8 for a single stage, or "all" for the full pipeline. Manual Stage Execution Each stage can also be run manually using the slash commands and Skill calls documented in paper-writing-workflow-guide.md . Recommended Order for Existing Drafts If you already have a draft: Stage 3 (polishing) → fix language issues Stage 5 (figures) → optimize charts Stage 4 (citations) → verify and supplement references Stage 6 (review) → pre-submission self-check Stage 7 (revision) → address findings Stage 8 (output) → format and package Design Principles Human-in-the-loop : Every stage has a checkpoint before proceeding Skill complementarity : ARS excels at pipeline automation; nature-skills excel at language/figures/citations Flexible invocation : Run any stage independently or the full pipeline Degradation strategy : If a required skill is missing, manual alternatives are provided Files paper-workflow.js — Executable workflow script paper-writing-workflow-guide.md — Complete user manual with slash commands and checklists paper-writing-skill-workflow.png — Visual flowchart (300 DPI) paper-writing-skill-workflow.svg — Editable vector version paper-writing-skill-workflow.pdf — PDF version for embedding
Agent 识别该技能的关键词,点击任意一个即可复制。

该技能未提供触发词。

下载的 .skill 包内含以下字段。
字段 说明
format格式标识(skill/v1)
skill_id技能唯一 ID
name技能名称
version版本号
description技能描述
category所属分类(数组)
trigger_words触发词列表
tags标签列表
source来源标识
source_url来源链接(本页地址)
exported_at导出时间(每次下载生成)
system_prompt系统提示词正文
model_config模型参数:provider / model / temperature / max_tokens / top_p
examples示例
install_guide各平台导入说明(Coze / Dify / Claude / 自定义框架)
同一份技能可按不同平台格式导出。
.skill 标准格式,含 system_prompt 与 model_config,导入任意 Agent 框架即可使用 下载
.skillpro 增强格式,额外含脚本 / 工具 / 依赖 / 钩子占位 下载
.json 纯 JSON 导出,只含 system_prompt 与模型参数 下载
Coze 带 frontmatter 的 Markdown,Coze 平台导入用 下载
Dify Dify DSL,创建应用后直接导入 下载

每日精选 Skill 推荐,免费送到你邮箱

输入邮箱,每天接收一个精选 AI Agent 技能推荐。完全免费,持续更新。

提交后我们会发送一封确认邮件,点击邮件里的链接才会开始收信。

完全免费,取消任意时间。我们不会发送垃圾邮件。