agentleFS
pauloribeiro16pauloribeiro16/my-skills/academic-writing/SKILL.md

academic-writing

Skill1 starsChanged 6 months agoMITView on GitHub

Draft, structure, and improve each section of a scientific research article (Introduction, Methods, Results, Discussion, Title, Abstract). Use when drafting, writing, or revising manuscript sections. Trigger phrases: draft the introduction, write the methods, how to write results, structure the discussion, improve the title, write the abstract, what tense to use, choose a target journal, prepare a manuscript for submission.

26 other projects use a version of this.

Adopted by

Most recently taken up by

Used with

Projects with it also use scipilot-figure-skill and grill-me.

Other files people use alongside this one.

Files found in the same public projects as a version of this one, more often than they turn up anywhere else. Each project counts once, large collections count for less, and this file's own repository is left out.
  • HaojaeSkill

    scipilot-figure-skill

    SciPilot Skills 家族成员,负责科研数据可视化——但定位不是"画图工具", 而是"可视化顾问"。先做数据剖析(列类型/样本量/分布/异常值/分组结构/相关性), 再结合用户的论证目标推荐图型,主动拦截科研画图的经典错误(小样本画均值柱掩盖 分布、双 Y 轴、饼图、Y 轴不当截断、rainbow 色图、把分类点连成折线等),最后 产出 Nature / Science / IEEE / Elsevier / PNAS / 中文核心期刊级别的成图。 覆盖纯数据图:折线、柱状、散点、箱线 / 小提琴、热力图、误差棒、分布图(直方 图 / KDE)、相关性矩阵 / 散点矩阵、多面板组合。技术栈 matplotlib + seaborn + SciencePlots(静态)+ plotly(交互)。中英文双语,中文模式自动配置 Noto Sans CJK / Source Han Sans / SimHei 并修复负号方框,支持中文期刊"宋体正文 + Times New Roman 数字"混排。默认色盲安全配色 + 冗余编码 + 灰度预览。出图后做 "视觉自检闭环":渲染 PNG 预览→程序自检缺字/文字裁切/刻度重叠→AI 读图复核遮盖 与子图对齐→回改重渲,直到通过。 当用户的任务涉及以下任何情况时主动触发:论文配图、科研画图、数据可视化、 不知道用什么图、怎么展示数据、用什么图好、期刊投稿图、figure、出版级图表、 matplotlib、seaborn、plotly、误差棒、显著性标注、色盲安全配色、矢量图导出、 中文论文图表、多面板。**即使用户只是给一批数据问"这个怎么画"或"用什么图 好",也应使用本技能——本技能首要能力是"判断该用什么图",其次才是绘制。** 不做示意图、流程图、架构图。

    Also in 3 projects that use this

  • GoogleSkill

    grill-me

    A relentless interview to sharpen a plan or design.

    Also in 3 projects that use this

The file

We split this skill into the rules it gives an agent

2 rules. 0 are common, 2 are distinctive, and 0 are very specific to this project.

  • 0

    Common

    Most of the 18 edited versions we read keep these.

  • 2

    Distinctive

    This author's own choices. Worth a look.

  • 0

    Very specific

    Tied to their project's names, files or tools. Probably skip.

  • Common
  • Distinctive
  • Very specific
  1. Distinctive:

    Stop and ask the user if:

    line 113
  2. Distinctive:

    Use this skill whenever the task is to produce or improve the text of a research article — drafting a section, choosing a structure, …

    line 135

“Common” is measured: kept by at least 6 in 10 of the 18 edited versions of this file we could read. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.

Keep what fits and drop the rest. Your version, ready for your agents.
Files
SKILL.md

Academic Writing

Guidance for drafting, structuring, and revising each section of a scientific research article that follows the AIMRaD convention (Abstract, Introduction, Materials and methods, Results, and Discussion). Distilled from Cargill & O'Connor, Writing Scientific Research Articles: Strategy and Steps (2009), generalised for computer-science, cybersecurity, and regulatory papers.

Progressive disclosure: SKILL.md (this file) gives the triggers, the non-negotiable principles, and the topic index. Detailed guidance for each section lives in references/. Annotated example fragments live in examples/. Load only what the current task needs.

When to Activate

Activate this skill when any of the following is true:

  • The user says "draft", "write", "structure", "how to write", "improve", or "revise" in connection with a manuscript section (introduction, methods, results, discussion, title, abstract, summary).
  • The user asks what verb tense to use, how to design a figure/table, how to cite, how to choose a target journal, or how to prepare a manuscript.
  • The user is turning a set of results into a paper, ordering figures/tables, or writing a take-home message.
  • The user asks about sentence templates, noun phrases, article use (a/an/the), or which vs that.

Do NOT activate for reviewing or critiquing an existing draft — that is the academic-evaluation skill. This skill is for producing text.

Core Principles (Non-Negotiable)

These apply to every section being drafted.

#PrincipleWhy
1Results drive the paper. Decide the results "story" and take-home message before writing any other section. Every figure/table must support that story.The whole article is governed by the Results.
2Write Stages 4 → 3 → 1 → 2 of the Introduction. Draft the aim (Stage 4) first, then the gap (3), then the setting (1), then the literature foundation (2).Stage 4 is easiest and anchors everything.
3Old information before new information. Begin each sentence with what the reader already knows; end with the new point.This is the single biggest driver of flow in English.
4Subject + verb within the first 7–9 words. Never write "top-heavy" sentences with a long subject and a short passive verb at the end.Readers cannot parse a verb they have not yet reached.
5Tables and figures must stand alone. A reader must understand a table/figure from its title/legend alone, without the article text.Referees check "Are all illustrations required?" and "Are legends adequate?"
6Match claim strength to evidence strength. Choose verbs (demonstrate > indicate > appears > suggests) and modal verbs (will > may) to match how firmly the data support the claim.Over-claiming is a top reason for rejection.
7No commentary in Results. Report what was observed; interpret only in the Discussion. No "surprisingly", "interestingly".Separation of observation from interpretation.

Topic Index — Read on Demand

Load the reference that matches the current task.

TaskFile
Understand the AIMRaD hourglass and its variations (AIRDaM, AIM(RaD)C)references/article-structure.md
Draft the Introduction (5 stages, gap signal words, citation styles)references/introduction.md
Draft the Methods (purpose, organisation, passive vs active, top-heavy fix)references/methods.md
Draft the Results (figure/table/text choice, tense, results sentences)references/results.md
Draft the Discussion (structure, information elements, claim strength)references/discussion.md
Write or revise the Title (4 strategies, noun-phrase ambiguity)references/title.md
Write the Abstract/Summary (B/P/M/R/C elements, word limit)references/abstract.md
Select a target journal (scope, audience, impact factor caveats)references/journal-selection.md
Prepare and edit a manuscript (14-step process, 22-point pre-review checklist)references/manuscript-process.md
Re-use language safely (sentence templates, noun-phrase shells)references/sentence-templates.md
Use English articles (a/an/the) and which vs that correctlyreferences/english-articles.md
Study an annotated real article to see the principles in actionexamples/kaiser-2003-annotated.md, examples/britton-simmons-2008-annotated.md

Quick Reference

Verb tense by section

SectionTypical tenseExample
Introduction — general truthPresent"Cybersecurity is a growing field."
Introduction — prior workPast or present perfect"Smith et al. showed…" / "Several studies have investigated…"
Introduction — gapPresent perfect"It has not yet been established whether…"
Introduction — aimPast"We aimed to evaluate…"
MethodsPast (passive or active)"Models were run via Ollama."
ResultsPast for the study; present for the document/always-true"The model achieved 86.96%." / "Table 1 shows…"
Discussion — claimsPresent (strong) or modal (weak)"demonstrate that… regulate…" / "suggests that… may be…"

Citation styles (Introduction Stages 2–3)

StyleUse whenExample
Information-prominentDefault — the fact matters, not who said it"…since the development of synthetic fibres (Smith 2000)."
Author-prominentYou agree, or you want to flag upcoming contrast"As Smith (2000) pointed out, …" / "Smith (2000) argued that …. However, Jones et al. (2004) found that …."
Weak author-prominentTopic sentence opening a new sub-argument"Several authors have reported that … (Smith 2000, Wilson 2003, Nguyen 2005)."

Introduction Stage 4 sentence templates

The objectives of this study were to: (1) determine [NP];
(2) analyse [NP]; (3) evaluate [NP]; and (4) discuss [NP].

As part of a long-term research effort aimed at [NP1],
this paper presents [NP2].

Claim-strength ladder (Discussion)

Strong   demonstrate / show / establish  … + present tense
         indicate … + present / future
         appear to … + present
Weak     suggest … + modal (may / could)

Stop Conditions

Stop and ask the user if:

  • The target journal is unknown — formatting, length, and structure all depend on it.
  • The results "story" or take-home message is not agreed with co-authors — do not draft other sections until it is.
  • The claim strength the user wants conflicts with what the data support — flag the over- or under-claim rather than silently complying.
  • A section the user asks to write depends on results that are not finalised.
  • The discipline's convention is unclear (e.g., combined vs separate Results and Discussion) — check a sample article from the target journal first.

Coordination with Other Skills

  • academic-evaluation — invoke when the task shifts from drafting to reviewing or critiquing a draft against referee criteria.
  • doc-coauthoring — invoke for the broader co-authoring workflow (track changes, comments, revision rounds).
  • internal-comms — not relevant; this skill is for manuscript content.

Use When

Use this skill whenever the task is to produce or improve the text of a research article — drafting a section, choosing a structure, refining a title, writing an abstract, selecting a journal, or preparing a manuscript for submission. For reviewing or critiquing a finished draft, use academic-evaluation instead.

Download now (ZIP)

Does it work?

Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.

No reviews yet

People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.

  • It worked
  • Partly
  • It didn't
What did you use it for? e.g. Reviewing pull requests in a Rails app

Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.

Your trail

Files you open will collect here, so you can find them again.

Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.

Now do this for your own.

Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.