Not in the top 1,000 by GitHub stars
qiaomiaojoe/ai-academic-workflow
AI学术工作流 · 乔淼PhD「AI学术训练营」skills 库,按工作流分类:期刊初稿 / 综述文章 / 投稿与审稿。涵盖选题、文献、研究设计、数据分析、写作、改稿、投稿与返修,支持 Claude Code / Codex;后续按工作流扩展。
History
Review weekly changes to SKILL.md before updating. Dates mark the weeks in which we observed each version; checks apply to the recorded commits.
View weekly changes
skills/academic-project-init/SKILL.md
Week of Nov 2, 2026 · Line counts unavailable
Before Not checked yet → After Instructions only
First observation → a9ed8b43e3e5
No earlier version was observed for comparison.
skills/analyze-qualitative-data/SKILL.md
Week of Nov 2, 2026 · Line counts unavailable
Before Not checked yet → After Instructions only
First observation → a9ed8b43e3e5
No earlier version was observed for comparison.
skills/analyze-quantitative-data/SKILL.md
Week of Nov 2, 2026 · Line counts unavailable
Before Not checked yet → After Instructions only
First observation → a9ed8b43e3e5
No earlier version was observed for comparison.
skills/article-framework/SKILL.md
Week of Nov 2, 2026 · Line counts unavailable
Before Not checked yet → After Instructions only
First observation → a9ed8b43e3e5
No earlier version was observed for comparison.
skills/cnki/SKILL.md
Week of Nov 2, 2026 · Line counts unavailable
Before Not checked yet → After Network or broad shell
First observation → a9ed8b43e3e5
No earlier version was observed for comparison.
skills/critical-paper-reading/SKILL.md
Week of Nov 2, 2026 · Line counts unavailable
Before Not checked yet → After Instructions only
First observation → a9ed8b43e3e5
No earlier version was observed for comparison.
skills/data-analysis-round/SKILL.md
Week of Nov 2, 2026 · Line counts unavailable
Before Not checked yet → After Instructions only
First observation → a9ed8b43e3e5
No earlier version was observed for comparison.
skills/findings-synthesis/SKILL.md
Week of Nov 2, 2026 · Line counts unavailable
Before Not checked yet → After Instructions only
First observation → a9ed8b43e3e5
No earlier version was observed for comparison.
skills/fulltext-draft/SKILL.md
Week of Nov 2, 2026 · Line counts unavailable
Before Not checked yet → After Instructions only
First observation → a9ed8b43e3e5
No earlier version was observed for comparison.
skills/journal-requirements-check/SKILL.md
Week of Nov 2, 2026 · Line counts unavailable
Before Not checked yet → After Instructions only
First observation → a9ed8b43e3e5
No earlier version was observed for comparison.
skills/knowledge-module-gen/SKILL.md
Week of Nov 2, 2026 · Line counts unavailable
Before Not checked yet → After Instructions only
First observation → a9ed8b43e3e5
No earlier version was observed for comparison.
skills/knowledge-module-list/SKILL.md
Week of Nov 2, 2026 · Line counts unavailable
Before Not checked yet → After Instructions only
First observation → a9ed8b43e3e5
No earlier version was observed for comparison.
skills/lit-pdf-zotero/SKILL.md
Week of Nov 2, 2026 · Line counts unavailable
Before Not checked yet → After Instructions only
First observation → a9ed8b43e3e5
No earlier version was observed for comparison.
skills/lit-pyramid/SKILL.md
Week of Nov 2, 2026 · Line counts unavailable
Before Not checked yet → After Instructions only
First observation → a9ed8b43e3e5
No earlier version was observed for comparison.
skills/lit-verify/SKILL.md
Week of Nov 2, 2026 · Line counts unavailable
Before Not checked yet → After Instructions only
First observation → a9ed8b43e3e5
No earlier version was observed for comparison.
skills/literature-analysis/SKILL.md
Week of Nov 2, 2026 · Line counts unavailable
Before Not checked yet → After Instructions only
First observation → a9ed8b43e3e5
No earlier version was observed for comparison.
skills/literature-search/SKILL.md
Week of Nov 2, 2026 · Line counts unavailable
Before Not checked yet → After Instructions only
First observation → a9ed8b43e3e5
No earlier version was observed for comparison.
skills/manuscript-diagnosis/SKILL.md
Week of Nov 2, 2026 · Line counts unavailable
Before Not checked yet → After Instructions only
First observation → a9ed8b43e3e5
No earlier version was observed for comparison.
skills/manuscript-revision/SKILL.md
Week of Nov 2, 2026 · Line counts unavailable
Before Not checked yet → After Instructions only
First observation → a9ed8b43e3e5
No earlier version was observed for comparison.
skills/methodology-draft/SKILL.md
Week of Nov 2, 2026 · Line counts unavailable
Before Not checked yet → After Instructions only
First observation → a9ed8b43e3e5
No earlier version was observed for comparison.
skills/methods-map/SKILL.md
Week of Nov 2, 2026 · Line counts unavailable
Before Not checked yet → After Instructions only
First observation → a9ed8b43e3e5
No earlier version was observed for comparison.
skills/model-paper-deconstruct/SKILL.md
Week of Nov 2, 2026 · Line counts unavailable
Before Not checked yet → After Instructions only
First observation → a9ed8b43e3e5
No earlier version was observed for comparison.
skills/pxyv-search/SKILL.md
Week of Nov 2, 2026 · Line counts unavailable
Before Not checked yet → After Instructions only
First observation → a9ed8b43e3e5
No earlier version was observed for comparison.
skills/research-design/SKILL.md
Week of Nov 2, 2026 · Line counts unavailable
Before Not checked yet → After Instructions only
First observation → a9ed8b43e3e5
No earlier version was observed for comparison.
skills/research-gap-scan/SKILL.md
Week of Nov 2, 2026 · Line counts unavailable
Before Not checked yet → After Instructions only
First observation → a9ed8b43e3e5
No earlier version was observed for comparison.
skills/review-blueprint/SKILL.md
Week of Nov 2, 2026 · Line counts unavailable
Before Not checked yet → After Instructions only
First observation → a9ed8b43e3e5
No earlier version was observed for comparison.
skills/review-draft/SKILL.md
Week of Nov 2, 2026 · Line counts unavailable
Before Not checked yet → After Instructions only
First observation → a9ed8b43e3e5
No earlier version was observed for comparison.
skills/review-draft-assembly/SKILL.md
Week of Nov 2, 2026 · Line counts unavailable
Before Not checked yet → After Instructions only
First observation → a9ed8b43e3e5
No earlier version was observed for comparison.
skills/review-response-planning/SKILL.md
Week of Nov 2, 2026 · Line counts unavailable
Before Not checked yet → After Instructions only
First observation → a9ed8b43e3e5
No earlier version was observed for comparison.
skills/review-revision-response/SKILL.md
Week of Nov 2, 2026 · Line counts unavailable
Before Not checked yet → After Instructions only
First observation → a9ed8b43e3e5
No earlier version was observed for comparison.
skills/review-synthesis/SKILL.md
Week of Nov 2, 2026 · Line counts unavailable
Before Not checked yet → After Instructions only
First observation → a9ed8b43e3e5
No earlier version was observed for comparison.
skills/skill-forge/SKILL.md
Week of Nov 2, 2026 · Line counts unavailable
Before Not checked yet → After Instructions only
First observation → a9ed8b43e3e5
No earlier version was observed for comparison.
skills/skill-workshop-plan/SKILL.md
Week of Nov 2, 2026 · Line counts unavailable
Before Not checked yet → After Instructions only
First observation → a9ed8b43e3e5
No earlier version was observed for comparison.
skills/sr-search-record/SKILL.md
Week of Nov 2, 2026 · Line counts unavailable
Before Not checked yet → After Network or broad shell
First observation → a9ed8b43e3e5
No earlier version was observed for comparison.
skills/submission-package-preparation/SKILL.md
Week of Nov 2, 2026 · Line counts unavailable
Before Not checked yet → After Instructions only
First observation → a9ed8b43e3e5
No earlier version was observed for comparison.
skills/submission-task-intake/SKILL.md
Week of Nov 2, 2026 · Line counts unavailable
Before Not checked yet → After Instructions only
First observation → a9ed8b43e3e5
No earlier version was observed for comparison.
skills/topic-concept-construction/SKILL.md
Week of Nov 2, 2026 · Line counts unavailable
Before Not checked yet → After Instructions only
First observation → a9ed8b43e3e5
No earlier version was observed for comparison.
skills/topic-hypothesis-testing/SKILL.md
Week of Nov 2, 2026 · Line counts unavailable
Before Not checked yet → After Instructions only
First observation → a9ed8b43e3e5
No earlier version was observed for comparison.
skills/topic-method-driven/SKILL.md
Week of Nov 2, 2026 · Line counts unavailable
Before Not checked yet → After Instructions only
First observation → a9ed8b43e3e5
No earlier version was observed for comparison.
skills/topic-pxyv-parse/SKILL.md
Week of Nov 2, 2026 · Line counts unavailable
Before Not checked yet → After Instructions only
First observation → a9ed8b43e3e5
No earlier version was observed for comparison.
skills/topic-review-integrative/SKILL.md
Week of Nov 2, 2026 · Line counts unavailable
Before Not checked yet → After Instructions only
First observation → a9ed8b43e3e5
No earlier version was observed for comparison.
skills/topic-review-semisystematic/SKILL.md
Week of Nov 2, 2026 · Line counts unavailable
Before Not checked yet → After Instructions only
First observation → a9ed8b43e3e5
No earlier version was observed for comparison.
skills/topic-review-systematic/SKILL.md
Week of Nov 2, 2026 · Line counts unavailable
Before Not checked yet → After Instructions only
First observation → a9ed8b43e3e5
No earlier version was observed for comparison.
skills/topic-theory-interpretation/SKILL.md
Week of Nov 2, 2026 · Line counts unavailable
Before Not checked yet → After Instructions only
First observation → a9ed8b43e3e5
No earlier version was observed for comparison.
skills/topic-workbench/SKILL.md
Week of Nov 2, 2026 · Line counts unavailable
Before Not checked yet → After Instructions only
First observation → a9ed8b43e3e5
No earlier version was observed for comparison.
Heat
Insufficient historyNot enough history yet to measure heat. It appears after a few days of data.
Heat never changes the order by stars, and sponsorship never touches it. How heat works
Stars over time
30-day change not yet available: not enough history.
Individual skills in this repository
- academic-project-init
skills/academic-project-init - analyze-qualitative-data
skills/analyze-qualitative-data - analyze-quantitative-data
skills/analyze-quantitative-data - article-framework
skills/article-framework - cnki
skills/cnki - critical-paper-reading
skills/critical-paper-reading - data-analysis-round
skills/data-analysis-round - findings-synthesis
skills/findings-synthesis - fulltext-draft
skills/fulltext-draft - journal-requirements-check
skills/journal-requirements-check - knowledge-module-gen
skills/knowledge-module-gen - knowledge-module-list
skills/knowledge-module-list - lit-pdf-zotero
skills/lit-pdf-zotero - lit-pyramid
skills/lit-pyramid - lit-verify
skills/lit-verify - literature-analysis
skills/literature-analysis - literature-search
skills/literature-search - manuscript-diagnosis
skills/manuscript-diagnosis - manuscript-revision
skills/manuscript-revision - methodology-draft
skills/methodology-draft - methods-map
skills/methods-map - model-paper-deconstruct
skills/model-paper-deconstruct - pxyv-search
skills/pxyv-search - research-design
skills/research-design - research-gap-scan
skills/research-gap-scan - review-blueprint
skills/review-blueprint - review-draft
skills/review-draft - review-draft-assembly
skills/review-draft-assembly - review-response-planning
skills/review-response-planning - review-revision-response
skills/review-revision-response - review-synthesis
skills/review-synthesis - skill-forge
skills/skill-forge - skill-workshop-plan
skills/skill-workshop-plan - sr-search-record
skills/sr-search-record - submission-package-preparation
skills/submission-package-preparation - submission-task-intake
skills/submission-task-intake - topic-concept-construction
skills/topic-concept-construction - topic-hypothesis-testing
skills/topic-hypothesis-testing - topic-method-driven
skills/topic-method-driven - topic-pxyv-parse
skills/topic-pxyv-parse - topic-review-integrative
skills/topic-review-integrative - topic-review-semisystematic
skills/topic-review-semisystematic - topic-review-systematic
skills/topic-review-systematic - topic-theory-interpretation
skills/topic-theory-interpretation - topic-workbench
skills/topic-workbench
How it works
academic-project-init
When your agent uses it
AI 学术研究项目初始化(乔淼PhD · AI学术训练营 · AI学术工作流)。为一篇论文写项目说明 AGENTS.md(含「文件放哪」表:选题/ 文献/(PDF/、知识模块/)方法/ 数据/ 写作/ skill源材料/)+ CLAUDE.md 指针。文件夹用到才建,不预建空文件夹。初始化后,选题/文献搜索/文献分析/研究设计/数据分析/全文初稿等 skills 都按这张表读写、互相衔接;和「AI学术工作站」新建项目的结构完全一致。Trigger on:"初始化一个学术项目"、"新建论文项目文件夹"、"建一个 AI 学术工作流项目"、"set up an academic paper project"、"initialize research project folder"。
What it loads into context
Frontmatter
200 tokensAlways available to the agent
SKILL.md
2,012 tokensWhen the skill is activated
Reference documents
0 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- 输入
- 任务 1 · 写 AGENTS.md(已存在则保留原有内容,只在末尾补「文件放哪」一节;已有旧的 01_选题 … 命名表就不补,照旧用它)
- 任务 2 · 写 CLAUDE.md(已存在则跳过)
- 任务 3 · 确认
- 各阶段读写约定(skill 在项目里运行时按此找上一步的产出)
Files
SKILL.mdcore6,994 bytes
No excerpt is shown for this license. Read the source on GitHub.
View the complete source on GitHubanalyze-qualitative-data
When your agent uses it
Use when analyzing qualitative social science data following Neuman's Social Research Methods Ch 14 — three-stage coding (open/axial/selective), analytic memo writing, outcropping detection, and seven analytic strategies (ideal types, successive approximation, illustrative method, domain analysis, Mill's analytic comparison, narrative analysis). Trigger on requests like "code these interviews", "analyze field notes", "thematic analysis", "narrative analysis", "compare these cases", "我要做定性分析", "帮我编码这些访谈", "做主题分析".
What it loads into context
Frontmatter
124 tokensAlways available to the agent
SKILL.md
1,404 tokensWhen the skill is activated
Reference documents
15,679 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- When to invoke
- The 11 prompts (Neuman Ch 14)
- How to use
- Cross-cutting principles (apply at every step)
- What this skill does NOT do
- Required outputs at each step
- Companion skill
Files
SKILL.mdcore5,856 bytesprompts/01-open-coding.mddoc4,613 bytesprompts/02-axial-coding.mddoc4,794 bytesprompts/03-selective-coding.mddoc4,091 bytesprompts/04-analytic-memo.mddoc5,502 bytesprompts/05-outcropping.mddoc3,909 bytesprompts/06-ideal-types.mddoc4,596 bytesprompts/07-successive-approximation.mddoc4,341 bytesprompts/08-illustrative-method.mddoc4,778 bytesprompts/09-domain-analysis.mddoc5,192 bytesprompts/10-analytic-comparison-mill.mddoc5,479 bytesprompts/11-narrative-analysis.mddoc5,722 bytes
No excerpt is shown for this license. Read the source on GitHub.
View the complete source on GitHubanalyze-quantitative-data
When your agent uses it
Use when analyzing quantitative social science data following Neuman's Social Research Methods Ch 12 — codebook creation, data cleaning, univariate descriptive statistics, bivariate association, multivariate analysis (elaboration paradigm + multiple regression), and inferential statistics (significance testing, Type I/II errors). Trigger on requests like "analyze this survey data", "run regression on X", "check bivariate relationship between A and B", "what does this codebook need", "interpret these statistics", "我要做定量分析", "帮我跑回归", "分析这份调查数据".
What it loads into context
Frontmatter
131 tokensAlways available to the agent
SKILL.md
1,118 tokensWhen the skill is activated
Reference documents
8,732 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- When to invoke
- The 7-step procedure (Neuman Ch 12)
- How to use
- Cross-cutting principles (apply at every step)
- What this skill does NOT do
- Required outputs at each step
- Companion skill
Files
SKILL.mdcore4,678 bytesprompts/01-codebook.mddoc3,279 bytesprompts/02-clean-data.mddoc3,290 bytesprompts/03-univariate.mddoc3,778 bytesprompts/04-bivariate.mddoc4,258 bytesprompts/05-multivariate-elaboration.mddoc4,447 bytesprompts/06-multivariate-regression.mddoc4,511 bytesprompts/07-inferential.mddoc5,094 bytes
No excerpt is shown for this license. Read the source on GitHub.
View the complete source on GitHubarticle-framework
When your agent uses it
文章框架反推(乔淼PhD · AI学术训练营 · AI学术工作流 · 全文初稿步骤)。基于 Model Paper 拆解报告反推新论文的完整框架(5 Part:四象限定位 / 虚实三过程 / 引用角色配置与承重比例 / 各节段落骨架 / 引用预算 + 综述衔接表 + 结构对照表),并渲染段落骨架可视化 HTML。产出 文章框架.md,是全文扩写的脚手架。Trigger on:"反推文章框架"、"基于 model paper 搭我的论文框架"、"build my paper skeleton from the model paper"、"article framework"。
What it loads into context
Frontmatter
172 tokensAlways available to the agent
SKILL.md
1,965 tokensWhen the skill is activated
Reference documents
0 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- 调用约定(独立运行)
- 关键约束
- Part 1 · 全文层面框架
- Part 2 · 各节段落骨架
- Part 3 · 引用预算表
- Part 4 · 与综述初稿的衔接表(⭐ 关键;综述缺失时跳过)
- Part 5 · 与 Model Paper 的结构对照表
- 可视化(文章框架-part2.html)
Files
SKILL.mdcore6,204 bytes
No excerpt is shown for this license. Read the source on GitHub.
View the complete source on GitHubcnki
When your agent uses it
知网检索与核对(乔淼PhD · AI学术训练营 · AI学术工作流)。用学员自己电脑上的浏览器查中国知网:按主题 / 篇名 / 关键词 / 作者 / 来源检索,可限年份、核心期刊(CSSCI / 北大核心 / CSCD 等)、只要学术期刊;按篇名核对一篇中文文献是否真实存在、作者 / 年份 / 刊名对不对;取题录详情(摘要、关键词、卷期页、DOI、GB/T 引文);导出 RIS 或直接进 Zotero。不用装 MCP,随 skill 附 scripts/cnki.mjs(要 Node.js 18 以上)。Trigger on:"在知网搜一下"、"查知网"、"核对这篇中文文献是不是真的"、"知网检索 CSSCI 期刊"、"把知网结果导出到 Zotero"、"search CNKI"、"verify this Chinese paper on CNKI"。
What it loads into context
Frontmatter
235 tokensAlways available to the agent
SKILL.md
1,513 tokensWhen the skill is activated
Reference documents
0 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- 命令
- 返回
- 规矩
Scripts executed separately
scripts/cnki.mjs
Files
SKILL.mdcore4,876 bytesscripts/cnki.mjsruns30,350 bytes
No excerpt is shown for this license. Read the source on GitHub.
View the complete source on GitHubcritical-paper-reading
When your agent uses it
单篇论文批判性阅读(乔淼PhD · AI学术训练营 · AI学术工作流 · 文献分析步骤)。基于 UOW (University of Wollongong) Critical Analysis 框架 —— 三层升级 (Description → Analysis → Evaluation) + 四维 interrogation (Content / Authorship / Currency & Quality / Critical Writing Language),把一篇论文(PDF / Zotero item)拆成结构化的批判性阅读笔记,每条 claim 锚定页码、绝不编造。可独立运行,输入一个 PDF 路径或 Zotero item 即可。Trigger on:"critically read this paper", "critique this paper", "批判性阅读", "帮我批注这篇 paper", "读一下这篇 paper", "deconstruct this paper", "analyze this article critically", "评一下这篇文章".
What it loads into context
Frontmatter
195 tokensAlways available to the agent
SKILL.md
2,894 tokensWhen the skill is activated
Reference documents
0 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- 调用约定(独立运行)
- 何时使用 / When to invoke
- 核心框架 / The UOW Framework
- 输入处理协议 / Input Protocol
- 执行协议 / Execution Protocol
- 跨切原则 / Cross-cutting Principles
- 输出模板 / Output Template
- 验证 / Verification
Files
SKILL.mdcore10,407 bytes
No excerpt is shown for this license. Read the source on GitHub.
View the complete source on GitHubdata-analysis-round
When your agent uses it
数据分析 · 跑一轮(乔淼PhD · AI学术训练营 · AI学术工作流)。三种分支:定量(调 analyze-quantitative-data,Neuman Ch12)/ 定性(调 analyze-qualitative-data,Neuman Ch14)/ 自定义 skill(完全按该 skill 自身规则执行,不稀释硬约束)。支持多轮多 skill 分析:每轮产出带前缀不覆盖(-R2/-R3)+ 分析日志.md 逐轮记账。RQ/变量/颗粒度可由用户直接给,不依赖研究设计文件。Trigger on:"跑一轮定量/定性分析"、"用 XX skill 分析这份数据"、"数据分析工作流"、"分析这份问卷/访谈"、"run a quantitative/qualitative analysis round"、"analyze my data with skill X"。
What it loads into context
Frontmatter
211 tokensAlways available to the agent
SKILL.md
1,707 tokensWhen the skill is activated
Reference documents
0 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- 调用约定(独立运行)
- 分支 · 定量(quant)
- 分支 · 定性(qual)
- 分支 · 自定义 skill(custom)
- 【本轮产出 + 多轮记账】(三分支共用 · 务必不要覆盖既有产出)
Files
SKILL.mdcore5,893 bytes
No excerpt is shown for this license. Read the source on GitHub.
View the complete source on GitHubfindings-synthesis
When your agent uses it
综合研究发现(乔淼PhD · AI学术训练营 · AI学术工作流 · 数据分析终点)。把多轮/多 skill 的数据分析产出整合成对应研究问题的研究发现:逐子问题/假设给结论判定 + 证据整合(定量 effect size 与定性主题并列)+ 方法间 convergence/divergence + 置信度局限 + 来源对照表,合法呈现零结果,绝不编造。产出 研究发现.md(全文初稿 Results/Findings 节的权威输入)。Trigger on:"综合发现"、"把各轮分析汇总成研究发现"、"整合数据分析结果"、"synthesize my analysis results"、"combine quant and qual findings"、"write up findings from all analysis rounds"。
What it loads into context
Frontmatter
190 tokensAlways available to the agent
SKILL.md
1,173 tokensWhen the skill is activated
Reference documents
0 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- 调用约定(独立运行)
- 第一步 · 读全部输入
- 硬约束
- 输出 · 写入 研究发现.md
Files
SKILL.mdcore4,246 bytes
No excerpt is shown for this license. Read the source on GitHub.
View the complete source on GitHubfulltext-draft
When your agent uses it
全文初稿扩写(乔淼PhD · AI学术训练营 · AI学术工作流 · 全文初稿步骤 · 管线终点)。把 文章框架.md 的段落骨架扩写成可打磨的全文段落初稿:正文语言最高优先级规则、方法论节直接采用研究设计初稿、结果节据 研究发现.md 撰写(缺则占位,绝不编造数据/引语)、每段紧扣骨架功能与引用角色、文末撰写说明。Trigger on:"扩写全文初稿"、"把框架写成全文"、"写全文初稿"、"expand my framework into a full draft"、"draft my full paper"。
What it loads into context
Frontmatter
173 tokensAlways available to the agent
SKILL.md
967 tokensWhen the skill is activated
Reference documents
0 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- 调用约定(独立运行)
- 强制要求
Files
SKILL.mdcore3,365 bytes
No excerpt is shown for this license. Read the source on GitHub.
View the complete source on GitHubjournal-requirements-check
When your agent uses it
期刊要求核对(乔淼PhD · AI学术训练营 · AI学术工作流 · 投稿与审稿)。从作者指定期刊实际读到的要求(作者指南、模板、投稿系统说明、编辑信)逐条提取,记录来源位置、适用范围、强制还是建议,与确认稿逐项比对差距,形成可追溯的期刊要求矩阵;首次投稿和返修提交都适用。不替作者选刊,读不到的要求标未知、不编造。Trigger on:"核对目标期刊的投稿要求"、"看看我的稿子符不符合这个期刊的要求"、"整理这个期刊的作者指南"、"check the journal's submission requirements"、"compare my manuscript with the author guidelines"。
What it loads into context
Frontmatter
227 tokensAlways available to the agent
SKILL.md
2,187 tokensWhen the skill is activated
Reference documents
1,201 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- 适用范围与来源
- 输入要求
- 执行方法
- 判定分类与默认动作
- 输出结构
- 作者决定点
- 完成标准
- 共用约束与交接
- 典型失败模式
Files
SKILL.mdcore8,276 bytesreferences/source-basis.mddoc4,636 bytes
No excerpt is shown for this license. Read the source on GitHub.
View the complete source on GitHubknowledge-module-gen
When your agent uses it
知识模块生成(乔淼PhD · AI学术训练营 · AI学术工作流 · 文献分析步骤)。按知识模块清单逐模块读全文生成 M_n.md:机械抽取模块 prompt(不改写不补全)、flag 而非 ask、map-reduce 逐篇防爆上下文、页码诚实、每模块一行执行日志自检;全文默认读本地 PDF,也可走 Zotero。Trigger on:"生成知识模块"、"按模块清单跑模块"、"逐模块读全文写 M1-Mn"、"generate knowledge modules from my module list"。
What it loads into context
Frontmatter
146 tokensAlways available to the agent
SKILL.md
1,758 tokensWhen the skill is activated
Reference documents
0 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- 调用约定(独立运行)
- 【准确拾取并执行模块 prompt】(防 AI 自由发挥 · 全程不打断)
- 主数据通道分支
- 【上下文管理 · map-reduce 逐篇】
- 【页码诚实】
- 【字数与结构】
- 【双层产物】
- 输出
Files
SKILL.mdcore6,209 bytes
No excerpt is shown for this license. Read the source on GitHub.
View the complete source on GitHubknowledge-module-list
When your agent uses it
知识模块清单(乔淼PhD · AI学术训练营 · AI学术工作流 · 文献分析步骤)。跨文档分析一批文献(Zotero 集合 / 本地 PDF / 文献清单),用元数据+摘要提出覆盖 Section 1(XY 经验)与 Section 2(PV 理论)的知识模块:每个模块 = 一个概念/argument + 区分性问题 + 涉及文献与角色 + 证据假设 + 独立可运行的生成 prompt。产出 知识模块清单.md,是知识模块生成与综述蓝图的输入。Trigger on:"帮我做知识模块清单"、"把这批文献分成知识模块"、"跨文档分析出模块"、"propose knowledge modules from my collection"。
What it loads into context
Frontmatter
192 tokensAlways available to the agent
SKILL.md
1,116 tokensWhen the skill is activated
Reference documents
0 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- 调用约定(独立运行)
- 硬约束
- 每个模块的标准结构
- 下一步建议
Files
SKILL.mdcore3,915 bytes
No excerpt is shown for this license. Read the source on GitHub.
View the complete source on GitHublit-pdf-zotero
When your agent uses it
文献 PDF 获取 + Zotero 入库 + 可视化(乔淼PhD · AI学术训练营 · AI学术工作流)。对一份文献清单批量:确认 DOI/CNKI ID → 补全引用数 → 多渠道找 PDF 落盘(OA/preprint/sd-download/wos-download/cnki-download)→ 入一个 Zotero Collection(层级和 PXYV 节点记在标签里,不建子集合;含 extra 元数据)→ 生成金字塔分布图 + PXYV 罗盘投影双图 HTML。Trigger on:"把这批文献下载 PDF 入库 Zotero"、"文献入库+可视化"、"batch download PDFs and import to Zotero"、"入 Zotero 并画文献金字塔"。
What it loads into context
Frontmatter
191 tokensAlways available to the agent
SKILL.md
2,180 tokensWhen the skill is activated
Reference documents
0 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- 调用约定(独立运行)
- Step 1 · 确认 DOI / URL / CNKI ID
- Step 2 · 补全引用数
- Step 3 · 查找 PDF 并落盘
- Step 4 · 入库 Zotero + 可视化
Files
SKILL.mdcore7,098 bytes
No excerpt is shown for this license. Read the source on GitHub.
View the complete source on GitHublit-pyramid
When your agent uses it
文献金字塔分层(乔淼PhD · AI学术训练营 · AI学术工作流)。把一份已验真的文献清单按硬指标分到 Classic / Key Texts / Supporting 三层:Classic 四条硬指标(概念奠基 + 被引门槛 + 持续被引)、Key 三条(顶刊 + 对话关系 + 年均引用)、Supporting 按 PXYV 节点配额;含对话关系判定与覆盖配额检查。Trigger on:"把这些文献做金字塔分层"、"文献金字塔"、"帮我把文献库分 Classic/Key/Supporting"、"tier my literature into a pyramid"。
What it loads into context
Frontmatter
169 tokensAlways available to the agent
SKILL.md
1,170 tokensWhen the skill is activated
Reference documents
0 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- 调用约定(独立运行)
- 金字塔三层硬指标
- 三机制检查
- 输出
Files
SKILL.mdcore3,876 bytes
No excerpt is shown for this license. Read the source on GitHub.
View the complete source on GitHublit-verify
When your agent uses it
文献验真(乔淼PhD · AI学术训练营 · AI学术工作流)。对任意来源的文献清单(检索结果 / AI 生成的参考文献 / 论文引文列表 / BibTeX)逐条实查:DOI 解析核对题录、CNKI 详情页核对、采集被引数;无法实查或字段对不上的一律标可疑剔除,零容忍防捏造。独立可用——特别适合"检查这些参考文献是不是真的"。Trigger on:"验真这些文献"、"检查这些参考文献是不是编的"、"核实这份文献清单"、"verify these citations"、"check if these references are real / hallucinated"。
What it loads into context
Frontmatter
184 tokensAlways available to the agent
SKILL.md
1,290 tokensWhen the skill is activated
Reference documents
0 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- 调用约定(独立运行)
- 验真协议(每条三步)
- 输出
Files
SKILL.mdcore4,312 bytes
No excerpt is shown for this license. Read the source on GitHub.
View the complete source on GitHubliterature-analysis
When your agent uses it
文献分析/综述完整任务入口(乔淼PhD · AI学术训练营 · AI学术工作流)。编排步骤 skill 跑完一次完整的文献综述:knowledge-module-list 模块清单 → review-blueprint 综述蓝图 → research-gap-scan gap 识别 → knowledge-module-gen 模块生成 →(可选 critical-paper-reading 深读)→ review-draft-assembly 综述初稿。只要单独某一步(只列模块/只找 gap/只组装)时直接用对应步骤 skill。Trigger on:"帮我做文献综述"、"文献分析工作流"、"从我的 Zotero 集合跑出综述初稿"、"literature review from my collection"。
What it loads into context
Frontmatter
174 tokensAlways available to the agent
SKILL.md
948 tokensWhen the skill is activated
Reference documents
0 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- 编排规则
- 快速模式
Files
SKILL.mdcore3,289 bytes
No excerpt is shown for this license. Read the source on GitHub.
View the complete source on GitHubliterature-search
When your agent uses it
文献搜索完整任务入口(乔淼PhD · AI学术训练营 · AI学术工作流)。编排四个步骤 skill 跑完一次完整的文献搜索:pxyv-search 四维检索 → lit-verify 验真 → lit-pyramid 金字塔分层 → lit-pdf-zotero 获取 PDF + 入库 Zotero + 可视化,每阶段停下等确认。用户只要单独某一步(只检索/只验真/只分层/只入库)时直接用对应步骤 skill,不走本入口。Trigger on:"帮我搜文献"、"完整跑一遍文献搜索"、"搜 30 篇文献入 Zotero"、"文献搜索工作流"、"search literature and import to Zotero"。
What it loads into context
Frontmatter
182 tokensAlways available to the agent
SKILL.md
1,202 tokensWhen the skill is activated
Reference documents
0 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- 编排规则
- 快速模式
Files
SKILL.mdcore4,198 bytes
No excerpt is shown for this license. Read the source on GitHub.
View the complete source on GitHubmanuscript-diagnosis
When your agent uses it
初稿诊断(乔淼PhD · AI学术训练营 · AI学术工作流 · 投稿与审稿)。对人文社科初稿做论证与证据诊断:论证角色逐段查主张、推理和适用边界(质性原创研究另按 Q1–Q3 三标准),证据角色回原文核查文献声明;产出带原文定位、稳定问题 ID、修改建议和作者决定栏的诊断表,作者批准的问题交 manuscript-revision 改稿。保留核心观点,没问题不凑条数。Trigger on:"诊断这份初稿"、"看看这篇稿子论证和证据有什么问题"、"改稿前先诊断"、"保留我的核心观点给修改建议"、"diagnose my manuscript draft"、"check the argument and evidence of my draft"。
What it loads into context
Frontmatter
269 tokensAlways available to the agent
SKILL.md
3,239 tokensWhen the skill is activated
Reference documents
2,501 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- 适用范围与来源
- 输入要求
- 执行方法
- 判定分类与默认动作
- 质性研究的三项诊断(文献依据;作者指定纳入)
- 输出结构
- 作者决定点
- 完成标准
- 共用约束与交接
- 典型失败模式
Files
SKILL.mdcore12,109 bytesreferences/qualitative-criteria.mddoc3,643 bytesreferences/source-basis.mddoc5,535 bytes
No excerpt is shown for this license. Read the source on GitHub.
View the complete source on GitHubmanuscript-revision
When your agent uses it
批准范围内改稿(乔淼PhD · AI学术训练营 · AI学术工作流 · 投稿与审稿)。依据作者明确批准的问题清单(manuscript-diagnosis 诊断表或等效清单)修改人文社科稿件:问题 ID 逐项对到原文位置,只改批准项,保留核心观点,不补造文献或结果;产出修订稿(定稿候选)、逐项修改对照表和未完成项,作者确认后交 journal-requirements-check。Trigger on:"按我批准的问题清单改稿"、"按诊断结果修改稿件"、"只改我同意的这几条"、"revise my manuscript per the approved issue list"。
What it loads into context
Frontmatter
220 tokensAlways available to the agent
SKILL.md
2,171 tokensWhen the skill is activated
Reference documents
1,399 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- 适用范围与来源
- 输入要求
- 执行方法
- 判定分类与默认动作
- 输出结构
- 作者决定点
- 完成标准
- 共用约束与交接
- 典型失败模式
Files
SKILL.mdcore8,054 bytesreferences/source-basis.mddoc5,317 bytes
No excerpt is shown for this license. Read the source on GitHub.
View the complete source on GitHubmethodology-draft
When your agent uses it
研究设计初稿(乔淼PhD · AI学术训练营 · AI学术工作流 · 研究设计步骤)。把选定的研究设计方案展开为完整研究设计:B1 全局方法决策 → B2 方法论段骨架(6 维度表)→ B3 可执行设计清单(抽样矩阵/访谈提纲或问卷/编码书或统计链/信效度伦理/时间线)→ B4 合成干净版 Sec 4 方法论 draft,落两份分离文件(初稿 + 设计说明)。Trigger on:"展开研究设计初稿"、"写方法论初稿"、"把选定方案变成研究设计"、"draft my methodology section"。
What it loads into context
Frontmatter
173 tokensAlways available to the agent
SKILL.md
1,394 tokensWhen the skill is activated
Reference documents
0 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- 调用约定(独立运行)
- B1 · 全局方法决策
- B2 · 方法论段骨架(5-7 段),每段输出 6 维度表
- B3 · 研究设计清单(把决策变可执行)
- B4 · Sec 4 方法论 draft(合成)
- 硬约束与落盘
Files
SKILL.mdcore4,766 bytes
No excerpt is shown for this license. Read the source on GitHub.
View the complete source on GitHubmethods-map
When your agent uses it
方法地图(乔淼PhD · AI学术训练营 · AI学术工作流 · 研究设计步骤)。map-reduce 逐篇扫描一批文献的方法论(9 字段:研究类型/设计/收集/样本/抽样/分析/度量层级/RQ链接)→ 汇总成方法地图(分布/组合频率/RQ-方法映射/趋势与方法 gap)+ 内嵌 methodology_plugin YAML + 基于地图给 2-3 个研究设计方案对照表供选 + 可视化 HTML。Trigger on:"帮我做方法地图"、"扫一下这批文献都用什么方法"、"methods map"、"给我 2-3 个研究设计方案"、"survey the methodology of my literature"。
What it loads into context
Frontmatter
182 tokensAlways available to the agent
SKILL.md
1,470 tokensWhen the skill is activated
Reference documents
0 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- 调用约定(独立运行)
- A1 · 文献扫描(逐篇提取 · map-reduce,不一次性拼全文)
- A2 · 方法地图(汇总判断)
- A3 · methodology_plugin(内嵌报告,不单独落盘)
- A4 · 研究设计方案(给用户选)
- 可视化(方法地图.html)
- 硬约束
Files
SKILL.mdcore5,176 bytes
No excerpt is shown for this license. Read the source on GitHub.
View the complete source on GitHubmodel-paper-deconstruct
When your agent uses it
拆 Model Paper(乔淼PhD · AI学术训练营 · AI学术工作流 · 全文初稿步骤)。用动静虚实 2×2 框架对一篇范文做高密度拆解(≥6000 中文字),四产出:四象限填充表(动虚机制链 ≥5 条)+ 虚实转换三过程轨迹(落到具体小节)+ 三种引用角色清单(锚定/定位/框架 + 承重比例)+ Section→象限功能映射(实测引用数),末尾附反直觉发现与 ≥6 条可借鉴结构技巧。输入一个 PDF 路径或 Zotero 论文标题即可,完全独立可跑。Trigger on:"拆这篇 model paper"、"动静虚实拆解"、"拆解这篇范文的结构"、"分析这篇论文的写作结构"、"deconstruct this model paper"、"analyze the structure of this paper for imitation"。
What it loads into context
Frontmatter
237 tokensAlways available to the agent
SKILL.md
2,568 tokensWhen the skill is activated
Reference documents
0 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- 调用约定(独立运行)
- 【动静虚实框架定义】(拆解基础,必须理解后再拆)
- 【信息量与密度要求:必须执行】
- 【产出格式】
Files
SKILL.mdcore9,330 bytes
No excerpt is shown for this license. Read the source on GitHub.
View the complete source on GitHubpxyv-search
When your agent uses it
PXYV 四维度文献检索(乔淼PhD · AI学术训练营 · AI学术工作流)。按 P 理论 / X 现象 / Y 语境 / V 近邻四个维度设计检索式并在可用检索工具(Web Search / Google Scholar / ScienceDirect / WoS / CNKI)里执行,中英双语策略,输出候选文献清单表。只做检索,不验真不分层——验真用 lit-verify,分层用 lit-pyramid。Trigger on:"按 PXYV 四维帮我检索文献"、"四维度文献检索"、"给这个选题设计检索式并搜一轮"、"run a PXYV four-dimension literature search"。
What it loads into context
Frontmatter
185 tokensAlways available to the agent
SKILL.md
1,481 tokensWhen the skill is activated
Reference documents
0 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- 调用约定(独立运行)
- 可用检索工具注册表
- 检索策略
- 输出
Files
SKILL.mdcore4,878 bytes
No excerpt is shown for this license. Read the source on GitHub.
View the complete source on GitHubresearch-design
When your agent uses it
研究设计完整任务入口(乔淼PhD · AI学术训练营 · AI学术工作流)。编排两个步骤 skill 跑完一次完整研究设计:methods-map 方法地图 + 2-3 方案(末尾 CHECKPOINT 用户选)→ methodology-draft 展开为研究设计初稿 + 设计说明。只要单独某一步(只扫方法地图 / 已有方案只写初稿)时直接用对应步骤 skill。Trigger on:"帮我做研究设计"、"研究设计工作流"、"design my study"、"from methods survey to methodology draft"。
What it loads into context
Frontmatter
139 tokensAlways available to the agent
SKILL.md
706 tokensWhen the skill is activated
Reference documents
0 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- 编排规则
- 快速模式
Files
SKILL.mdcore2,632 bytes
No excerpt is shown for this license. Read the source on GitHub.
View the complete source on GitHubresearch-gap-scan
When your agent uses it
Research Gap 识别(乔淼PhD · AI学术训练营 · AI学术工作流)。用组合扫描法找真 gap:展开 P 近邻概念与 X/Y 操作化变体 → 枚举文献已覆盖的 (P,X)/(X,Y)/(P,Y) 组合表 → 标出空白/弱覆盖格子 → 每个候选 gap 过"三问反驳"防伪 gap → 按 empirical/contextual/theoretical/methodological 归类 + 本研究定位陈述。独立可用:"帮我找这个方向的 research gap"。Trigger on:"帮我找 research gap"、"识别研究空白"、"gap 扫描"、"这个领域还有什么空白"、"find research gaps in my literature"。
What it loads into context
Frontmatter
186 tokensAlways available to the agent
SKILL.md
897 tokensWhen the skill is activated
Reference documents
0 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- 调用约定(独立运行)
- 协议
- 硬约束
Files
SKILL.mdcore3,030 bytes
No excerpt is shown for this license. Read the source on GitHub.
View the complete source on GitHubreview-blueprint
When your agent uses it
综述蓝图(乔淼PhD · AI学术训练营 · AI学术工作流 · 文献分析步骤)。把知识模块清单编排成综述的逻辑结构:每个 Section 的标题 + 核心 argument + 模块出场序列 + 模块间逻辑(前置依赖/并列对照/对话张力)+ 段落写作提示,并渲染成自包含 HTML 可视化。Section 3 的 gap 内容由 research-gap-scan 填入。Trigger on:"帮我编综述蓝图"、"把知识模块编排成综述结构"、"review blueprint"、"organize my modules into a review outline"。
What it loads into context
Frontmatter
166 tokensAlways available to the agent
SKILL.md
812 tokensWhen the skill is activated
Reference documents
0 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- 调用约定(独立运行)
- 蓝图结构
- 可视化(综述蓝图.html)
- 下一步建议
Files
SKILL.mdcore2,746 bytes
No excerpt is shown for this license. Read the source on GitHub.
View the complete source on GitHubreview-draft
When your agent uses it
综述文章初稿扩写(乔淼PhD · AI学术训练营 · AI学术工作流 · 综述文章工作台 · 管线终点)。把一篇**综述文章**(review 本身即整篇论文,贡献是综合/框架/议程)按其报告规范(系统→PRISMA / 半系统→RAMESES / 整合→Torraco 2005)扩写成综述初稿:读 综述选题.md 机器锚块定型定规范 + 证据综合.md 写综合/结果节(缺则占位,绝不编造数据/引语)+ 语料库 PRISMA 筛选记录写方法节 + 逐条引用核验出独立报告 + 参考文献表 + 反 AI 味 + 初稿纯净 + 转 docx。区别于 `review-draft-assembly`(那是给**实证论文**写文献综述**节**)。方法锚 Snyder (2019)。Trigger on:"写综述文章初稿"、"把综述扩写成初稿"、"按 PRISMA/RAMESES/Torraco 成文"、"draft my review article"、"write up my literature review paper"。
What it loads into context
Frontmatter
289 tokensAlways available to the agent
SKILL.md
4,363 tokensWhen the skill is activated
Reference documents
0 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- 调用约定(独立运行)
- 【报告规范决定结构】——先读综述选题.md 锚块 `report_standard`,按对应骨架成文
- 强制要求
- 【引用核验(对照 Zotero 库 / 语料库清单)】
- 【参考文献表】
- 【写作要求 · 反 AI 味(内联,不调用外部 skill)】
- 【交付要求 · 初稿纯净】
- 【另存 Word】
- 流程
Files
SKILL.mdcore14,576 bytes
No excerpt is shown for this license. Read the source on GitHub.
View the complete source on GitHubreview-draft-assembly
When your agent uses it
综述初稿组装(乔淼PhD · AI学术训练营 · AI学术工作流 · 文献分析步骤)。按综述蓝图把知识模块组装成综述初稿:三 Section 组装规则 + 深读张力句并入 + 逐条引用核验(对照 Zotero/清单出独立报告)+ 参考文献表 + 反 AI 味写作要求 + 初稿纯净交付(零模块编号零 Zotero key)+ 转 docx。Trigger on:"组装综述初稿"、"把模块拼成综述"、"综述成稿"、"assemble my literature review draft"。
What it loads into context
Frontmatter
162 tokensAlways available to the agent
SKILL.md
1,739 tokensWhen the skill is activated
Reference documents
0 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- 调用约定(独立运行)
- 【字数分配】
- 【Section 1 · XY 经验段】
- 【Section 2 · PV 理论段】
- 【Section 3 · Gap & 定位段】
- 【引用核实(对照 Zotero 库 / 文献清单)】
- 【参考文献表】
- 【写作要求 · 反 AI 味(内联,不调用外部 skill)】
- 【交付要求 · 初稿纯净】
- 【另存 Word】
Files
SKILL.mdcore5,806 bytes
No excerpt is shown for this license. Read the source on GitHub.
View the complete source on GitHubreview-response-planning
When your agent uses it
审稿意见与回应决策(乔淼PhD · AI学术训练营 · AI学术工作流 · 投稿与审稿)。收到编辑信和审稿意见后,完整保留每条意见原文,拆成稳定意见 ID 和子项,逐条解释要求、提出接受 / 部分接受 / 不接受 / 补分析的回应建议和所需证据,形成作者逐条决定的审稿意见台账;作者批准的项交 review-revision-response。AI 建议和作者决定分开写,不漏意见。Trigger on:"拆解审稿意见"、"先给我回应审稿意见的方案"、"整理编辑和审稿人的意见"、"plan my response to reviewers"、"parse these reviewer comments"。
What it loads into context
Frontmatter
220 tokensAlways available to the agent
SKILL.md
2,179 tokensWhen the skill is activated
Reference documents
1,434 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- 适用范围与来源
- 输入要求
- 执行方法
- 判定分类与默认动作
- 输出结构
- 作者决定点
- 完成标准
- 共用约束与交接
- 典型失败模式
Files
SKILL.mdcore8,271 bytesreferences/source-basis.mddoc5,535 bytes
No excerpt is shown for this license. Read the source on GitHub.
View the complete source on GitHubreview-revision-response
When your agent uses it
返修改稿与逐条回复(乔淼PhD · AI学术训练营 · AI学术工作流 · 投稿与审稿)。依据审稿意见台账中作者已批准的意见修改稿件,再据实际改动写逐条回复(response to reviewers):每条回复对应意见 ID 和修改位置,未实施项照实说明,不编造页码、数据或文献;产出返修稿、审稿回复和意见修改对应表,作者确认后交期刊要求复核和返修包整理。Trigger on:"按已确认的意见返修"、"写逐条回复审稿意见"、"写 response letter"、"返修改稿并写回复"、"revise and write the response to reviewers"。
What it loads into context
Frontmatter
218 tokensAlways available to the agent
SKILL.md
2,316 tokensWhen the skill is activated
Reference documents
1,686 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- 适用范围与来源
- 输入要求
- 执行方法
- 判定分类与默认动作
- 输出结构
- 作者决定点
- 完成标准
- 共用约束与交接
- 典型失败模式
Files
SKILL.mdcore8,822 bytesreferences/source-basis.mddoc6,535 bytes
No excerpt is shown for this license. Read the source on GitHub.
View the complete source on GitHubreview-synthesis
When your agent uses it
综述文章的证据综合(乔淼PhD · AI学术训练营 · AI学术工作流 · 综述文章工作台 阶段③)。把最终纳入的文献全文综合成 证据综合.md:按 综述选题.md 锚块的 review_type 三路分流——systematic 走 meta-analysis(效应量/异质性/敏感性/发表偏倚/偏倚风险/GRADE)或降级为 SWiM 定性系统综述;semi-systematic 走主题综合与 meta-narrative(RAMESES);integrative 走概念整合出新框架(Torraco)。方法锚 Snyder (2019) + Cochrane Handbook + RAMESES + Torraco (2005)。**这是综述文章专用,不要用实证论文的 data-analysis-round / analyze-quantitative-data 代替**(那两个锚的是单研究数据分析,没有效应量合成)。Trigger on:"综合我的综述语料库"、"做 meta-analysis"、"把纳入文献综合成研究发现"、"主题综合 / meta-narrative / 整合式综述的综合"、"synthesize my review corpus"、"run the synthesis for my systematic review"。
What it loads into context
Frontmatter
293 tokensAlways available to the agent
SKILL.md
5,330 tokensWhen the skill is activated
Reference documents
0 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- 调用约定(独立运行)
- 全局硬约束
- Step 0 · 定型与对账
- Step 0.5 · 取全文(best-effort,**不阻塞**)
- Step 1 · 数据抽取(三型共用,map-reduce 逐篇)
- Step 2A · systematic:meta-analysis 或 SWiM
- Step 2B · semi-systematic:主题综合 / meta-narrative
- Step 2C · integrative:批判性概念整合(Torraco)
- Step 3 · 交叉检验与置信度(三型共用)
- Step 4 · 产出 `数据/证据综合.md`
- 与其他 skill 的边界
Files
SKILL.mdcore17,686 bytes
No excerpt is shown for this license. Read the source on GitHub.
View the complete source on GitHubskill-forge
When your agent uses it
数据 Skill 工坊 · 源材料 → 成品 skill(乔淼PhD · AI学术训练营 · AI学术工作流)。单次会话从方法学源材料造出可用 skill 的 5 阶段 2 停点链路:①提议筛选准则【停】→ ②筛选 + 7 字段结构化提取 + 自查 3 类 AI 偏差 → ③按平台规范造 skill 草稿(Claude Code 用 skill-creator + prompts/;Codex 用 init_skill.py + references/)→ ④4 控制点诊断(description 防乱触发/步骤颗粒度/硬约束/输出格式)→ ⑤落盘前总审【停】+ 落盘全局 skills 目录。Trigger on:"把这本教科书 PDF 做成 skill"、"源材料造 skill"、"造一个 XX 分析 skill"、"turn this textbook chapter into a skill"、"forge a skill from these materials"。
What it loads into context
Frontmatter
231 tokensAlways available to the agent
SKILL.md
2,608 tokensWhen the skill is activated
Reference documents
0 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- 调用约定(独立运行)
- 全局硬约束
- 阶段 1 · 提议筛选准则
- 阶段 2 · 筛选 + 结构化提取 + 自查偏差(确认准则后自动跑)
- 阶段 3 · 造 skill 草稿(自动跑,按目标平台)
- 阶段 4 · 4 控制点一次性诊断(自动跑,只改内存草稿,不写磁盘)
- 阶段 5 · 落盘前总审 + 落盘
- 快速模式
Files
SKILL.mdcore8,858 bytes
No excerpt is shown for this license. Read the source on GitHub.
View the complete source on GitHubskill-workshop-plan
When your agent uses it
数据 Skill 工坊 · 规划 + 找料(乔淼PhD · AI学术训练营 · AI学术工作流)。诊断现成分析 skills(analyze-quantitative-data / analyze-qualitative-data)够不够、要不要造新 skill、造哪几个(带停点等确认);确认后检索权威方法学源材料(教科书章节 / 方法学经典 / 官方手册)下载到源材料文件夹并写 源材料清单.md。造 skill 本身用 skill-forge。Trigger on:"规划要造哪些数据分析 skill"、"我这个方法现成 skill 够不够"、"帮我找造 skill 的方法学材料"、"plan and source materials for a new analysis skill"。
What it loads into context
Frontmatter
175 tokensAlways available to the agent
SKILL.md
1,219 tokensWhen the skill is activated
Reference documents
0 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- 调用约定(独立运行)
- 阶段 1 · 诊断要不要造、造哪几个
- 阶段 2 · 找料 + 下载(确认要造之后才做)
- 产出
- 快速模式
Files
SKILL.mdcore4,316 bytesSKILL.mdcore4,316 bytes
No excerpt is shown for this license. Read the source on GitHub.
View the complete source on GitHubsr-search-record
When your agent uses it
综述文章的检索与筛选记录(乔淼PhD · AI学术训练营 · AI学术工作流 · 综述文章工作台 阶段②)。**Snyder 三型通用**——系统 / 半系统·叙事 / 整合式共用一套内核。AI 全自动跑完:概念块拆解 → 检索式多轮自动校准(种子召回 + 精度守卫)→ 全量抓取去重 → **按相关性排序截断出候选集** → 摘要筛选(**摘要层定稿,不做全文筛选**)→ include 收敛到目标带 → 引文追踪补漏 → Zotero 入库 → 产出论文可直接贴的三张表(检索记录表 S1–Sn / 纳入排除标准表 / 选择流程数字)+ 待人工复核清单。**全程只有一个硬停点**,其余一律降级继续。检索引擎用 OpenAlex 开放 API(免登录;翻页要免费 API key,随 skill 附 scripts/oa_search.py),医学题目补 Europe PMC(MeSH)。AI 只出筛选建议不当第二评审。Trigger on:"跑综述的文献检索"、"自动检索并筛选文献"、"建综述语料库"、"生成检索记录表和 PRISMA 数字"、"systematic review search"、"build the corpus for my review"、"run the search and screening for my review"。
What it loads into context
Frontmatter
359 tokensAlways available to the agent
SKILL.md
8,102 tokensWhen the skill is activated
Reference documents
0 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- 摘要层定稿模式(本 skill 的核心设定)
- 规模链(三个数必须一致,流程才闭得上)
- 调用约定(独立运行)
- 全局硬约束
- 降级阶梯("不卡住"的实现)
- 步骤
- 与其他 skill 的边界
Scripts executed separately
scripts/oa_search.py
Files
SKILL.mdcore26,361 bytesSKILL.mdcore26,361 bytesSKILL.mdcore26,361 bytesSKILL.mdcore26,361 bytesSKILL.mdcore26,361 bytesSKILL.mdcore26,361 bytesSKILL.mdcore26,361 bytesscripts/oa_search.pyruns46,549 bytes
No excerpt is shown for this license. Read the source on GitHub.
View the complete source on GitHubsubmission-package-preparation
When your agent uses it
投稿包整理(乔淼PhD · AI学术训练营 · AI学术工作流 · 投稿与审稿)。期刊要求矩阵已确认、确认稿就位后,按要求 ID 整理投稿或返修提交材料:投稿稿、投稿信(cover letter)、返修提交稿与附信、附件和声明,逐项标满足依据、格式核验状态和待补事实(实名信息用匿名占位,由作者在 AI 之外补齐);产出投稿包核对表与包状态。不代为提交或对外发送。Trigger on:"整理投稿包"、"准备投稿材料"、"准备返修提交包"、"写投稿信并核对附件"、"prepare my submission package"。
What it loads into context
Frontmatter
215 tokensAlways available to the agent
SKILL.md
2,267 tokensWhen the skill is activated
Reference documents
1,200 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- 适用范围与来源
- 输入要求
- 执行方法
- 判定分类与默认动作
- 输出结构
- 作者决定点
- 完成标准
- 共用约束与交接
- 典型失败模式
Files
SKILL.mdcore8,596 bytesreferences/source-basis.mddoc4,692 bytes
No excerpt is shown for this license. Read the source on GitHub.
View the complete source on GitHubsubmission-task-intake
When your agent uses it
投稿与审稿 · 共用前置核实(乔淼PhD · AI学术训练营 · AI学术工作流 · 投稿与审稿)。投稿、改稿或返修开工前,核实论文项目、匿名任务标识、稿件与材料版本、作者核心观点与批准范围,写 `写作/投稿/任务登记-R<n>.md` 交给本轮要做的 skill。其余 6 个投稿与审稿 skill 开工时会先执行它,一般不用单独运行。Trigger on:"登记这次投稿任务"、"核实投稿材料和版本"、"投稿前先核对一下材料"、"set up a submission task"、"check my submission materials"。
What it loads into context
Frontmatter
213 tokensAlways available to the agent
SKILL.md
2,215 tokensWhen the skill is activated
Reference documents
681 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- 适用范围与来源
- 输入要求
- 执行方法
- 判定分类与默认动作
- 输出结构
- 作者决定点
- 完成标准
- 共用约束与交接
- 典型失败模式
Files
SKILL.mdcore8,450 bytesreferences/source-basis.mddoc2,581 bytes
No excerpt is shown for this license. Read the source on GitHub.
View the complete source on GitHubtopic-concept-construction
When your agent uses it
「AI学术训练营」选题工作流 · 模式③概念建构(乔淼PhD · AI学术工作流)。PXYV 公式 + 三阶段选题教练(A 挖掘 → B 校准 → C 输出:诠释路径 + 案例切口 + 原创概念命名),支持断点续跑(直接从阶段 B / C 进入)。适用:现有理论命名不了的新现象,需要造新概念。范例锚:Manovich (2009) 等。可独立运行,口头给研究方向即可。Trigger on:"用概念建构模式帮我选题"、"这个现象没有现成概念,帮我造一个"、"原创概念选题"、"concept-building topic"。
What it loads into context
Frontmatter
189 tokensAlways available to the agent
SKILL.md
2,287 tokensWhen the skill is activated
Reference documents
3,399 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- 调用约定(独立运行)
- 最小输入(Step 0 收集,①-④ 必填)
- 断点续跑
- 产出规则(最高优先级)
- 流程
- 教练核心法则(贯穿全程)
- 快速模式
Files
SKILL.mdcore7,363 bytesreferences/stages.mddoc10,982 bytes
No excerpt is shown for this license. Read the source on GitHub.
View the complete source on GitHubtopic-hypothesis-testing
When your agent uses it
「AI学术训练营」选题工作流 · 模式②假设检验(乔淼PhD · AI学术工作流)。PXYV 公式 + 三阶段选题教练(A 挖掘 → B 校准 → C 输出:H 假设链 + 完整操作化(量表来源)+ 数据与方法),支持断点续跑(直接从阶段 B / C 进入)。适用:变量间因果 / 中介 / 调节关系的定量检验。范例锚:Khin & Ho (2019) 等。可独立运行,口头给研究方向即可。Trigger on:"用假设检验模式帮我选题"、"我想验证 X 对 Y 的影响"、"帮我设计假设链"、"hypothesis-testing topic with mediation"。
What it loads into context
Frontmatter
194 tokensAlways available to the agent
SKILL.md
2,301 tokensWhen the skill is activated
Reference documents
3,694 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- 调用约定(独立运行)
- 最小输入(Step 0 收集,①-④ 必填)
- 断点续跑
- 产出规则(最高优先级)
- 流程
- 教练核心法则(贯穿全程)
- 快速模式
Files
SKILL.mdcore7,437 bytesreferences/stages.mddoc12,327 bytes
No excerpt is shown for this license. Read the source on GitHub.
View the complete source on GitHubtopic-method-driven
When your agent uses it
「AI学术训练营」选题工作流 · 模式④方法驱动(乔淼PhD · AI学术工作流)。PXYV 公式 + 三阶段选题教练(A 挖掘 → B 校准 → C 输出:Specific Aims(或直接陈述体例)+ 完整方法计划 + 双 V 实现路径),支持断点续跑(直接从阶段 B / C 进入)。适用:用新方法 / 新数据解决领域已知局限(计算 / 实验取向)。范例锚:Esteva et al 等。可独立运行,口头给研究方向即可。Trigger on:"用方法驱动模式帮我选题"、"我有方法和数据,帮我找研究定位"、"双V选题"、"method-driven research aims"。
What it loads into context
Frontmatter
191 tokensAlways available to the agent
SKILL.md
2,291 tokensWhen the skill is activated
Reference documents
3,391 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- 调用约定(独立运行)
- 最小输入(Step 0 收集,①-④ 必填)
- 断点续跑
- 产出规则(最高优先级)
- 流程
- 教练核心法则(贯穿全程)
- 快速模式
Files
SKILL.mdcore7,434 bytesreferences/stages.mddoc11,221 bytes
No excerpt is shown for this license. Read the source on GitHub.
View the complete source on GitHubtopic-pxyv-parse
When your agent uses it
已有选题的 PXYV 四维拆分(乔淼PhD · AI学术训练营 · AI学术工作流)。用户已有现成的选题 / 研究计划 / 摘要 / RP,不需要重跑选题三阶段,只需要把它结构化成 PXYV(P 理论视角 / X 现象 / Y 语境 / V 贡献)+ RQ + workbench 锚块,好直接接文献搜索、研究设计等下游步骤;同时诊断四维的缺口与弱点。Trigger on:"把我的选题拆成 PXYV"、"我已经有选题了,帮我结构化"、"给我的研究计划做 PXYV 拆分"、"parse my topic into PXYV"、"structure my existing research idea"。
What it loads into context
Frontmatter
193 tokensAlways available to the agent
SKILL.md
1,139 tokensWhen the skill is activated
Reference documents
0 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- 调用约定(独立运行)
- 协议
- 硬约束
Files
SKILL.mdcore3,582 bytes
No excerpt is shown for this license. Read the source on GitHub.
View the complete source on GitHubtopic-review-integrative
When your agent uses it
「AI学术训练营」选题工作流 · 综述③整合式综述(乔淼PhD · AI学术工作流)。为一篇**整合式综述(integrative review)**磨选题的三阶段教练(A 挖掘 → B 校准 → C 输出):理清研究对象/范围/问题 → 要造什么+成熟/新兴判断+批判角度+语料策略 → 综述规格 + PXYV 投影。方法锚 Snyder (2019);范例锚 Rodell et al. (2016)。适用:想用综述批判性整合、造一个新框架/概念/类型学。支持断点续跑,可独立运行。Trigger on:"做整合式综述选题"、"integrative review 选题"、"我想用综述造一个新框架"、"帮我把整合式综述题目磨清楚"、"integrative literature review topic"。
What it loads into context
Frontmatter
235 tokensAlways available to the agent
SKILL.md
2,439 tokensWhen the skill is activated
Reference documents
1,494 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- 这一型 vs 另两型(Snyder 三型)
- 调用约定(独立运行)
- 下游路径(选题之后)
- 最小输入(Step 0 收集,①-④ 必填)
- 断点续跑
- 产出规则(最高优先级)
- 流程
- 教练核心法则(贯穿全程)
Files
SKILL.mdcore7,893 bytesreferences/stages.mddoc4,685 bytes
No excerpt is shown for this license. Read the source on GitHub.
View the complete source on GitHubtopic-review-semisystematic
When your agent uses it
「AI学术训练营」选题工作流 · 综述②半系统/叙事综述(乔淼PhD · AI学术工作流)。为一篇**半系统 / 叙事综述(semi-systematic / narrative review)**磨选题的三阶段教练(A 挖掘 → B 校准 → C 输出):理清研究对象/范围/问题 → 组织性问题+组织框架+边界+综合方法 → 综述规格 + PXYV 投影。方法锚 Snyder (2019);范例锚 McColl-Kennedy et al. (2017)。适用:宽而跨学科的主题、想理清脉络/主题、给一份研究议程。支持断点续跑,可独立运行。Trigger on:"做叙事综述选题"、"semi-systematic / narrative review 选题"、"我要理清某个领域的脉络"、"帮我把综述题目磨成研究议程"、"map a research field topic"。
What it loads into context
Frontmatter
250 tokensAlways available to the agent
SKILL.md
2,290 tokensWhen the skill is activated
Reference documents
1,426 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- 这一型 vs 另两型(Snyder 三型)
- 调用约定(独立运行)
- 下游路径(选题之后)
- 最小输入(Step 0 收集,①-④ 必填)
- 断点续跑
- 产出规则(最高优先级)
- 流程
- 教练核心法则(贯穿全程)
Files
SKILL.mdcore7,458 bytesreferences/stages.mddoc4,569 bytes
No excerpt is shown for this license. Read the source on GitHub.
View the complete source on GitHubtopic-review-systematic
When your agent uses it
「AI学术训练营」选题工作流 · 综述①系统综述(乔淼PhD · AI学术工作流)。为一篇**系统综述(systematic review)**磨选题的三阶段教练(A 挖掘 → B 校准 → C 输出):理清研究对象/范围/问题 → 收窄问题+纳入排除标准+检索协议+是否 meta-analysis → 综述规格 + PXYV 投影。方法锚 Snyder (2019);范例锚 Snyder et al. (2016)。适用:窄而具体的问题、要"证据说话"、领域有一批可比实证。支持断点续跑,可独立运行。Trigger on:"做系统综述选题"、"systematic review 选题"、"我要综合某效应的证据"、"帮我把系统综述题目磨清楚"、"systematic literature review topic"。
What it loads into context
Frontmatter
225 tokensAlways available to the agent
SKILL.md
2,271 tokensWhen the skill is activated
Reference documents
1,457 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- 这一型 vs 另两型(Snyder 三型)
- 调用约定(独立运行)
- 下游路径(选题之后)
- 最小输入(Step 0 收集,①-④ 必填)
- 断点续跑
- 产出规则(最高优先级)
- 流程
- 教练核心法则(贯穿全程)
Files
SKILL.mdcore7,454 bytesreferences/stages.mddoc4,721 bytes
No excerpt is shown for this license. Read the source on GitHub.
View the complete source on GitHubtopic-theory-interpretation
When your agent uses it
「AI学术训练营」选题工作流 · 模式①理论诠释(乔淼PhD · AI学术工作流)。PXYV 公式 + 三阶段选题教练(A 挖掘 → B 校准 → C 输出:RQ 1-2 个或 Thesis 论点句 + V 三层贡献),支持断点续跑(直接从阶段 B / C 进入)。适用:用理论视角诠释一个现象(定性 / 批判取向)。范例锚:Manolev, Sullivan & Slee (2019) 等。可独立运行,口头给研究方向即可。Trigger on:"用理论诠释模式帮我选题"、"我想用某某理论分析某某现象"、"把这个现象磨成理论诠释类选题"、"theory-driven interpretive topic"。
What it loads into context
Frontmatter
209 tokensAlways available to the agent
SKILL.md
2,325 tokensWhen the skill is activated
Reference documents
3,614 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- 调用约定(独立运行)
- 最小输入(Step 0 收集,①-④ 必填)
- 断点续跑
- 产出规则(最高优先级)
- 流程
- 教练核心法则(贯穿全程)
- 快速模式
Files
SKILL.mdcore7,490 bytesreferences/stages.mddoc11,752 bytes
No excerpt is shown for this license. Read the source on GitHub.
View the complete source on GitHubtopic-workbench
When your agent uses it
「AI学术训练营」选题工作流总入口(乔淼PhD · AI学术工作流)。当用户想选题但没说用哪种模式时,先分诊:先判大类(研究性文章 / 综述性文章),再判最贴近的模式——研究性 ①理论诠释 ②假设检验 ③概念建构 ④方法驱动;综述性 系统 / 半系统 / 整合式(Snyder 三型)——然后转入对应的独立 skill 执行;用户已有现成选题只需结构化时转 topic-pxyv-parse。Trigger on:"帮我选题"、"选题工作流"、"我想做一个关于…的研究,帮我把选题磨出来"、"help me develop a research topic"、"topic coaching"。
What it loads into context
Frontmatter
201 tokensAlways available to the agent
SKILL.md
1,113 tokensWhen the skill is activated
Reference documents
0 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- 第一步 · 判大类
- 研究性 4 模式
- 综述性 3 模式(Snyder 2019 三型)
- 特殊入口
- 判型提示
Files
SKILL.mdcore3,708 bytes
No excerpt is shown for this license. Read the source on GitHub.
View the complete source on GitHubSkills included
- academic-project-init
- analyze-qualitative-data
- analyze-quantitative-data
- article-framework
- cnki
- critical-paper-reading
- data-analysis-round
- findings-synthesis
- fulltext-draft
- journal-requirements-check
- knowledge-module-gen
- knowledge-module-list
- lit-pdf-zotero
- lit-pyramid
- lit-verify
- literature-analysis
- literature-search
- manuscript-diagnosis
- manuscript-revision
- methodology-draft
- methods-map
- model-paper-deconstruct
- pxyv-search
- research-design
- research-gap-scan
- review-blueprint
- review-draft
- review-draft-assembly
- review-response-planning
- review-revision-response
- review-synthesis
- skill-forge
- skill-workshop-plan
- sr-search-record
- submission-package-preparation
- submission-task-intake
- topic-concept-construction
- topic-hypothesis-testing
- topic-method-driven
- topic-pxyv-parse
- topic-review-integrative
- topic-review-semisystematic
- topic-review-systematic
- topic-theory-interpretation
- topic-workbench
Repository facts
- License
- No license detected
- Created
- Apr 28, 2026
- Last pushed
- Nov 3, 2026
- Forks
- 2
- Open issues
- 0
- Project activity
- Active
Before you install
Network or broad shellAutomated signals, not a guarantee
Checked Nov 5, 2026
Not fully analyzed: some files were too long, unreadable or missing. This never lowers the level.
Show 7 notes
skills/skill-workshop-plan/SKILL.md:1Analysis incomplete: Referenced executable target unavailable; not analyzedskills/sr-search-record/SKILL.md:1Analysis incomplete: Referenced executable target unavailable; not analyzedskills/sr-search-record/SKILL.md:1Analysis incomplete: Referenced executable target unavailable; not analyzedskills/sr-search-record/SKILL.md:1Analysis incomplete: Referenced executable target unavailable; not analyzedskills/sr-search-record/SKILL.md:1Analysis incomplete: Referenced executable target unavailable; not analyzedskills/sr-search-record/SKILL.md:1Analysis incomplete: Referenced executable target unavailable; not analyzedskills/sr-search-record/SKILL.md:1Analysis incomplete: Referenced executable target unavailable; not analyzed
- No broad tool permissions
- No dangerous shell commands
- 25 network referencesin 5 files: cnki/scripts/cnki.mjs:29 sr-search-record/scripts/oa_search.py:38 manuscript-diagnosis/references/qualitative-criteria.md:7 and 2 more
- 3 obfuscation signalsin 1 file: cnki/scripts/cnki.mjs:165
- No instruction overrides
- 2 executable scriptsin 2 files: cnki/scripts/cnki.mjs:1 sr-search-record/scripts/oa_search.py:1
- 11 references to secretsin 3 files: sr-search-record/scripts/oa_search.py:40 review-synthesis/SKILL.md:66 sr-search-record/SKILL.md:41
- No requests to vote in Hot
Show all 41 signals by file
skills/cnki/scripts/cnki.mjs
- Executable scriptline 1
#!/usr/bin/env node - Network accessline 29
const HOURLY_LIMIT = 150; // 一小时内最多发给知网的请求数,防止被当成机器人 const HOSTS = [ // 先国内站;证书错 / 打不开就换海外版 { name: '国内站', base: 'https://kns.cnki.net', extra: '' }, - Network accessline 30
const HOSTS = [ // 先国内站;证书错 / 打不开就换海外版 { name: '国内站', base: 'https://kns.cnki.net', extra: '' }, { name: '海外版', base: 'https://oversea.cnki.net', extra: '&language=CHS&uniplatform=OVERSEA' }, - Network accessline 31
{ name: '国内站', base: 'https://kns.cnki.net', extra: '' }, - Network accessline 32
{ name: '海外版', base: 'https://oversea.cnki.net', extra: '&language=CHS&uniplatform=OVERSEA' }, - Possible obfuscationline 165
const clean = s => (s || '').replace(/[<U+00AD><U+200B>-<U+200F><U+202A>-<U+202E><U+2060>-<U+206F><U+FEFF>]/g, '').replace(/\s+/g, ' ').trim(); - Network accessline 183
b.set('boolSearch', turnpage ? 'false' : 'true'); b.set('pageNum', String(pageNum)); b.set('CurPage', String(pageNum)); if (turnpage) b.set('turnpage', turnpage); const r = await fetch(window.__cnkiGrid, { method: 'POST', credential - Network accessline 184
if (turnpage) b.set('turnpage', turnpage); const r = await fetch(window.__cnkiGrid, { method: 'POST', credentials: 'include', body: b, headers: { 'Content-Type': 'application/x-www-form-urlencoded; charset=UTF-8', 'X-Requested-Wit - Network accessline 185
const r = await fetch(window.__cnkiGrid, { method: 'POST', credentials: 'include', body: b, - Network accessline 219
for (const [i, id] of ids.entries()) { if (i) await new Promise(r => setTimeout(r, 800 + Math.random() * 700)); const r = await fetch(new URL('/dm8/API/GetExport', location.href), { method: 'POST', credentials: 'include', - Network accessline 220
if (i) await new Promise(r => setTimeout(r, 800 + Math.random() * 700)); const r = await fetch(new URL('/dm8/API/GetExport', location.href), { method: 'POST', credentials: 'include', headers: { 'Content-Type': 'application/x-www-f - Network accessline 221
const r = await fetch(new URL('/dm8/API/GetExport', location.href), { method: 'POST', credentials: 'include', - Possible obfuscationline 360
const norm = s => (s || '').replace(/[<U+00AD><U+200B>-<U+200F><U+202A>-<U+202E><U+2060>-<U+206F><U+FEFF>]/g, '').normalize('NFKC').toLowerCase().replace(/[\s\p{P}\p{S}]/gu, ''); - Network accessline 436
const good = metas.filter(m => !m.error), ris = good.map(toRis).join('\r\n'); if (opt.to === 'zotero') { const r = await fetch('http://127.0.0.1:23119/connector/import', { method: 'POST', headers: { 'Content-Type': 'applicatio - Network accessline 437
if (opt.to === 'zotero') { const r = await fetch('http://127.0.0.1:23119/connector/import', { method: 'POST', headers: { 'Content-Type': 'application/x-research-info-systems' }, body: ris }) .catch(() => { throw new Stop(' - Network accessline 438
const r = await fetch('http://127.0.0.1:23119/connector/import', { method: 'POST', headers: { 'Content-Type': 'application/x-research-info-systems' }, body: ris }) - Possible obfuscationline 444
fs.writeFileSync(out, '<U+FEFF>' + ris);
skills/critical-paper-reading/SKILL.md
- Network accessline 10
> 来源:https://www.uow.edu.au/student/support-services/academic-skills/online-resources/assessments/critical-analysis/
skills/lit-pdf-zotero/SKILL.md
- Network accessline 23
英文用 OpenAlex API(`https://api.openalex.org/works/doi:{DOI}` 取 `cited_by_count`)或 Google Scholar;中文用 `cnki` skill 的 `verify` 或 `detail`(取 `cited`)。清单里已有的不重采。
skills/manuscript-diagnosis/references/qualitative-criteria.md
- Network accessline 7
Stenius, K., Mäkelä, K., Miovský, M., & Gabrhelík, R. (2017). How to Write Publishable Qualitative Research. In T. F. Babor et al. (Eds.), Publishing Addiction Science: A Guide for the Perplexed (pp. 155–172). Ubiquity Press. https://doi.or - Network accessline 9
出版方页面:https://ubiquitypress.com/chapters/e/10.5334/bbd.h 。标题、作者顺序、书名、年份、DOI 与作者提供的章首页一致。网页将第三作者显示为 Miovsky?;本记录依据PDF首页修正为 Miovský。书章没有期刊字段,不编造期刊名。章首页给出155–172页,实际PDF共18页;本次逐页提取并查看PDF第5–7页,印刷页159–161。来源类型:文献类(方法指导书章),不是期刊或学会强制规范。出版页标注2017-05
skills/review-synthesis/SKILL.md
- Access to secretsline 66
[Credential-related source omitted]
skills/sr-search-record/SKILL.md
- Access to secretsline 41
[Credential-related source omitted]
skills/sr-search-record/scripts/oa_search.py
- Executable scriptline 1
#!/usr/bin/env python3 - Network accessline 38
约定:所有请求带 mailto 进 OpenAlex 礼貌池;失败重试 3 次;不静默吞错。 OpenAlex 翻页(游标第二页起)要 API key(https://help.openalex.org/api/authentication/): - Network accessline 39
OpenAlex 翻页(游标第二页起)要 API key(https://help.openalex.org/api/authentication/): - Access to secretsline 40
[Credential-related source omitted] - Network accessline 57
OA_BASE = "https://api.openalex.org/works" - Network accessline 58
EPMC_BASE = "https://www.ebi.ac.uk/europepmc/webservices/rest/search" - Access to secretsline 63
[Credential-related source omitted] - Access to secretsline 74
[Credential-related source omitted] - Access to secretsline 76
[Credential-related source omitted] - Access to secretsline 89
[Credential-related source omitted] - Network accessline 95
for i in range(tries): try: req = urllib.request.Request(url, headers={"User-Agent": UA, "Accept": "application/json"}) - Network accessline 96
try: req = urllib.request.Request(url, headers={"User-Agent": UA, "Accept": "application/json"}) with urllib.request.urlopen(req, timeout=60) as r: - Network accessline 97
req = urllib.request.Request(url, headers={"User-Agent": UA, "Accept": "application/json"}) - Network accessline 98
with urllib.request.urlopen(req, timeout=60) as r: - Access to secretsline 124
[Credential-related source omitted] - Access to secretsline 125
[Credential-related source omitted] - Access to secretsline 132
[Credential-related source omitted] - Access to secretsline 987
[Credential-related source omitted]
How the signals fit together
Facts from a static read of the files at the pinned commit. They describe what the code does, not why.
Some files could not be read; the facts below still hold.
Declared and executed: 3 facts
- Contacts kns.cnki.net, which SKILL.md, the README and the plugin manifest do not mentioncnki/scripts/cnki.mjs:31High confidence
- Contacts oversea.cnki.net, which SKILL.md, the README and the plugin manifest do not mentioncnki/scripts/cnki.mjs:32High confidence
- Contacts www.ebi.ac.uk, which SKILL.md, the README and the plugin manifest do not mentionsr-search-record/scripts/oa_search.py:58High confidence
Hidden characters: 2 facts
- Text direction control U+202A, in codecnki/scripts/cnki.mjs:165High confidence
- Text direction control U+202A, in codecnki/scripts/cnki.mjs:360High confidence
Signal confidence: 41 facts
- Executable script in code of a file that runscnki/scripts/cnki.mjs:1High confidence
- Network access in code of a file that runscnki/scripts/cnki.mjs:29High confidence
- Network access in code of a file that runscnki/scripts/cnki.mjs:30High confidence
- Network access in code of a file that runscnki/scripts/cnki.mjs:31High confidence
- Network access in code of a file that runscnki/scripts/cnki.mjs:32High confidence
- Possible obfuscation in code of a file that runscnki/scripts/cnki.mjs:165High confidence
- Network access in code of a file that runscnki/scripts/cnki.mjs:183High confidence
- Network access in code of a file that runscnki/scripts/cnki.mjs:184High confidence
- Network access in code of a file that runscnki/scripts/cnki.mjs:185High confidence
- Network access in code of a file that runscnki/scripts/cnki.mjs:219High confidence
- Network access in code of a file that runscnki/scripts/cnki.mjs:220High confidence
- Network access in code of a file that runscnki/scripts/cnki.mjs:221High confidence
- Possible obfuscation in code of a file that runscnki/scripts/cnki.mjs:360High confidence
- Network access in code of a file that runscnki/scripts/cnki.mjs:436High confidence
- Network access in code of a file that runscnki/scripts/cnki.mjs:437High confidence
- Network access in code of a file that runscnki/scripts/cnki.mjs:438High confidence
- Possible obfuscation in code of a file that runscnki/scripts/cnki.mjs:444High confidence
- Network access in prose of the SKILL.mdcritical-paper-reading/SKILL.md:10Low confidence
- Network access in prose of the SKILL.mdlit-pdf-zotero/SKILL.md:23Low confidence
- Network access in prose of documentationmanuscript-diagnosis/references/qualitative-criteria.md:7Low confidence
- Network access in prose of documentationmanuscript-diagnosis/references/qualitative-criteria.md:9Low confidence
- Access to secrets in prose of the SKILL.md: a variable, placeholder or call, not a stored valuereview-synthesis/SKILL.md:66Low confidence
- Access to secrets in prose of the SKILL.mdsr-search-record/SKILL.md:41Low confidence
- Executable script in code of a file that runssr-search-record/scripts/oa_search.py:1High confidence
- Network access in prose of a file that runssr-search-record/scripts/oa_search.py:38Low confidence
- Network access in prose of a file that runssr-search-record/scripts/oa_search.py:39Low confidence
- Access to secrets in prose of a file that runssr-search-record/scripts/oa_search.py:40Low confidence
- Network access in code of a file that runssr-search-record/scripts/oa_search.py:57High confidence
- Network access in code of a file that runssr-search-record/scripts/oa_search.py:58High confidence
- Access to secrets in code of a file that runs: a variable, placeholder or call, not a stored valuesr-search-record/scripts/oa_search.py:63Low confidence
- Access to secrets in code of a file that runs: a variable, placeholder or call, not a stored valuesr-search-record/scripts/oa_search.py:74Low confidence
- Access to secrets in code of a file that runssr-search-record/scripts/oa_search.py:76High confidence
- Access to secrets in code of a file that runssr-search-record/scripts/oa_search.py:89High confidence
- Network access in code of a file that runssr-search-record/scripts/oa_search.py:95High confidence
- Network access in code of a file that runssr-search-record/scripts/oa_search.py:96High confidence
- Network access in code of a file that runssr-search-record/scripts/oa_search.py:97High confidence
- Network access in code of a file that runssr-search-record/scripts/oa_search.py:98High confidence
- Access to secrets in code of a file that runssr-search-record/scripts/oa_search.py:124High confidence
- Access to secrets in code of a file that runssr-search-record/scripts/oa_search.py:125High confidence
- Access to secrets in code of a file that runssr-search-record/scripts/oa_search.py:132High confidence
- Access to secrets in code of a file that runs: a variable, placeholder or call, not a stored valuesr-search-record/scripts/oa_search.py:987Low confidence
Works with
| Agent | Status | Evidence | Install to |
|---|---|---|---|
| Claude Code | Compatible | Standard SKILL.md skills/academic-project-init/SKILL.md | .claude/skills/<skill-name>/ |
| Codex | Compatible | Standard SKILL.md skills/academic-project-init/SKILL.md | .agents/skills/<skill-name>/ |
| Cursor | Compatible | Standard SKILL.md skills/academic-project-init/SKILL.md | .cursor/skills/<skill-name>/ |
| Gemini CLI | Compatible | Standard SKILL.md skills/academic-project-init/SKILL.md | .gemini/skills/<skill-name>/ |
| GitHub Copilot | Compatible | Standard SKILL.md skills/academic-project-init/SKILL.md | .github/skills/<skill-name>/ |
| OpenCode | Compatible | Standard SKILL.md skills/academic-project-init/SKILL.md | .opencode/skills/<skill-name>/ |
- Native The repository ships a manifest, folder or frontmatter field for this agent.
- Compatible A standard SKILL.md that this agent can read.
- Unknown No evidence either way.
Derived automatically from paths, manifests and frontmatter. Not tested on each agent.