academic-writing
Skill4 starsChanged 2 days agoMITView on GitHub
Route and coordinate Indonesian academic writing tasks across outline, draft, edit, and audit. Identify genre, applicable campus or journal rules, evidence, and the smallest suitable workflow. Use for end-to-end academic writing help or choosing the right specialist skill.
28 other projects use a version of this.
Adopted by
Most recently taken up by
- bimajanuri/academic-writing-skilltheir own version, first seen Nov 15, 2026
- BrightGold70/skillstheir own version, first seen Nov 8, 2026
- Noam-Marom/academic-studentstheir own version, first seen Nov 8, 2026
- cjh-solver/MathModeling-Skills-Arsenaltheir own version, first seen Nov 8, 2026
- leolou0512/claude-skillstheir own version, first seen Oct 25, 2026
- hua695/MathModeling-Skills-Arsenaltheir own version, first seen Oct 25, 2026
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.
HaojaeSkillscipilot-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
GoogleSkillgrill-me
A relentless interview to sharpen a plan or design.
Also in 3 projects that use this
Other versions28 projects use a version of this.
Word for word · 0
None found.
Edited · 0
None found.
Wrote their own version · 28
- wentorai/Research-Claw★ 858same name
- ZimoLiao/scholaraio★ 585same name
- poemswe/co-researcher★ 139same name
- hua695/MathModeling-Skills-Arsenal★ 68same name
- cjh-solver/MathModeling-Skills-Arsenal★ 62same name
- NatureBlueee/Nature-use-skills★ 39same name
- dariia-m/my_claude_skills★ 35same name
- TashanGKD/tashan-research-skills★ 19same name
- XYD-GIS/paper-toolkits★ 12same name
- Noam-Marom/academic-students★ 11same name
18 more not listed
How matches are found. Word for word: the exact same text. Edited: shares passages with this file (“99% same” means 99% of its five-word phrases also appear here; 10% or more counts). Their own version: similar meaning, or, weakest, the same name. We can’t tell which project had it first. Projects are counted among the 200 most-starred candidates, and mentions are links to the repository we found, up to 50 per site, so both counts are a floor.
The file
We split this skill into the rules it gives an agent
3 rules. 0 are common, 3 are distinctive, and 0 are very specific to this project.
0
Common
Most of the 20 edited versions we read keep these.
3
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
- Distinctive: line 36
If genre is ambiguous, state the working assumption and proceed where safe.
- Distinctive: line 40
Use the shared handoff contract.
- Distinctive: line 44
Never invent data, references, respondents, results, DOI metadata, approvals, or institutional rules.
“Common” is measured: kept by at least 6 in 10 of the 20 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.
Files
Academic Writing Workflow
Act as the workflow coordinator. Read ../shared/workflow-contract.md before routing. Treat ../shared/institution-profile.md as a template; reuse a completed task profile from the current project when available.
Classify
Identify intent (outline/draft/edit/audit/combined), genre, purpose, discipline, program/level when applicable, institution or venue when supplied, target reader, available guide and material, document stage, and requested output. Do not infer missing official rules. Continue with uncertainty labels when possible and ask at most one essential question.
Route to the smallest skill set
| Request | Route |
| Build, restructure, or check an outline | outline |
| Draft a section from user material | draft |
| Correct or revise existing text | edit |
| Inspect requirements, evidence, citations, or readiness | audit |
| End-to-end work explicitly requested | outline → draft → edit → audit, skipping completed or irrelevant stages |
Genre routing
- Research thesis/proposal/dissertation: research structure and only the methodology path actually used.
- Journal/conference article: target venue instructions first; IMRaD only when suitable.
- Internship/KP/PKL: placement-specific checks only for an actual placement report and only when required by the current guide.
- Technical/professional report: structure follows purpose and evidence; do not assume an internship.
- Study notes: explanatory structure, not thesis compliance gates.
If genre is ambiguous, state the working assumption and proceed where safe.
Handoff
Use the shared handoff contract. Preserve task profile, guide provenance, inspected artifacts, evidence labels, completed checks, blockers, and next step. Never claim another skill ran unless its output is available. Never ask the user to repeat known information.
Integrity
Never invent data, references, respondents, results, DOI metadata, approvals, or institutional rules. Distinguish existing state from proposals. Preserve facts and author voice during editing. Do not promise grades, detector outcomes, similarity scores, or formal approval.
Specialist entrypoints
../outline/SKILL.md../draft/SKILL.md../edit/SKILL.md../audit/SKILL.md
Load only relevant specialist instructions and their required references.
Updater
The installed dispatcher folder ships its own updater at scripts/update.py (standard library only). From the installed dispatcher folder, python scripts/update.py version shows the installed version, check-update compares it with the latest GitHub Release without changing files, update downloads that release, validates it, backs the current family up outside the skills directory, and replaces it, and rollback restores the latest backup. There is no automatic update. A v1.0.0 installation does not have the updater yet: install v1.1.0 once with the installer first, then use the updater for later versions.
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
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.

