---
title: "imwenyaot-skills"
description: "Agent Skills for academic paper work: training-pipeline diagnosis, drafting and review, publication figures, and getting a manuscript through a journal, source, packet, and response to reviewers."
canonical: https://agentpluginsdirectory.com/plugins/imwenyaot-skills
last-updated: 2026-09-25
---

# imwenyaot-skills
Agent Skills for academic paper work: training-pipeline diagnosis, drafting and review, publication figures, and getting a manuscript through a journal, source, packet, and response to reviewers.
- Slug: imwenyaot-skills
- Publisher: Tian Wenyao
- Repository: https://github.com/ImWenyaoT/skills
- Manifest: plugin.json
- Version: 1.0.0
- License: MIT
- Category (editorial): documentation
- Skills: 5 (comparing-runs, drawing-figures, publishing-papers, training-models, writing-papers)
- MCP servers: 0
- Stars: 0
- Repository created: 2026-06-28
- Repository last pushed: 2026-08-26
- Publisher type: User
- Listing: https://agentpluginsdirectory.com/plugins/imwenyaot-skills
- Schema: https://agent-plugins.org/schemas/1.0.0/plugin.schema.json

## What imwenyaot-skills does, in the publisher's words

由 Tian Wenyao 维护的一组可组合 Agent Skills，适用于 Codex、Claude Code 及其他兼容 Agent Skills 的工具。

这些 skills 来自真实工作流，强调可预测的过程、明确的完成标准和渐进披露。每个 skill 都由模型按任务触发， 边界互不重叠，也可以单独安装、单独分享。

使用官方 skills CLI 浏览并安装：

- 一个含 SKILL.md 的目录就是一个可安装 skill；scripts、references 和 assets 与其共置。
- 每个 skill 自洽：不引用别的 skill，单独发给别人也能用。
- 每个 skill 保留精确的 description、自己的完成标准和单一事实来源。
- 只有具备独立触发或跨流程复用价值的纪律才拆成 skill；局部分支放进 references/。

From the project README, punctuation lightly normalized. Full text: https://raw.githubusercontent.com/ImWenyaoT/skills/HEAD/README.md

## Skills

- comparing-runs: Use when several finished runs have to become one table that survives review: ablation arms that differ in more than the thing under study, 消融臂不可比, 消融表, a baseline reproduced below its published number, an unfair comparison where one arm got a bigger tuning budget, how many seeds to run and what an…
- drawing-figures: Publication figure budgeting and production for academic papers, including 论文绘图/画图/架构图/结果图: reference-derived budgets, Elsevier/CVPR/ICCV/NeurIPS figures, diagrams, plots, result stitches, and publication-ready exports. Covers charts of every form, grouped bars, scatter, Pareto fronts, heatmaps, …
- publishing-papers: Use when a paper has to get through a journal, its source, its upload packet, or its answer to the reviewers. Covers 期刊模板, 双栏 layout, 页数超限, and an elsarticle or IEEEtran source that will not compile; 投稿 and 投稿材料 for Elsevier Editorial Manager or the IEEE Author Portal, cover letter, highlights, re…
- training-models: Staged setup and silent-failure diagnosis for neural network training. Use when you start a new training pipeline, when you review a training loop, or when a run goes wrong, the loss does not decrease, accuracy stalls, gradients explode or vanish, train and eval disagree, inference is wrong, or a…
- writing-papers: Academic-paper drafting, review, and polishing. Use when experiment results or an algorithm need a paper structure; to draft an introduction, abstract, related work, or contribution bullets; to polish manuscript LaTeX or a NeurIPS paragraph while preserving technical claims; to review logical self-…

Descriptions come from the frontmatter of each SKILL.md, punctuation lightly normalized.