Skills DirectorySkills Directory
SkillsLearnSecurityCategoriesDocsCommunityBlog
Sign InSubmit Skill
Skills Directory

Security-tested agent skills for Claude, coding agents, and AI workflows.

Directory

  • Browse Skills
  • All Skills A–Z
  • Claude Skills
  • Claude Code Skills
  • Agent Skills
  • Categories
  • Submit a Skill

Learn

  • Learn Hub
  • Install Claude Skills
  • Write SKILL.md
  • Skills vs MCP
  • Directories Compared

Security

  • Security
  • Methodology
  • Secure Claude Skills
  • Security Badges

Company

  • About
  • Community
  • Blog
  • API Docs
  • Advertise

2026 Skills Directory. All rights reserved.

Back to skills

Writing Ai Paper

ASecurity

Guide the planning, drafting, and revision of AI/ML conference papers (NeurIPS, ICML, ICLR, CVPR, AAAI, ACL, etc.) using the handbook "Writing AI Conference Papers" by hzwer (Zhewei Huang) and DingXiaoH (Xiaohan Ding). Use when the user is writing a machine-learning / deep-learning / computer-vision / NLP paper and needs help finding the core idea, building the paper framework, writing the introduction or related work, improving readability and defensibility, preparing for the deadline, antic...

2 stars
0 votes
0 copies
0 views
Added 9/19/2026
documentationgo

Security Analysis

A100/100

Scanned 9/19/2026

Install to Claude Code

$npx -y skills add caixinyu2017-star/xixi --skill writing-ai-paper --agent claude-code

Installs into .claude/skills of the current project.

Are you the author of Writing Ai Paper?

Add the live security badge to your README — it updates automatically with every re-scan.

Security grade badge for Writing Ai Paper
[![Security: A — Skills Directory](https://www.skillsdirectory.com/api/skills/caixinyu2017-star-writing-ai-paper/badge)](https://www.skillsdirectory.com/skills/caixinyu2017-star-writing-ai-paper)

More formats (shields.io, HTML) on the badges page.

Download Zip
Files
SKILL.md
---
name: writing-ai-paper
description: Guide the planning, drafting, and revision of AI/ML conference papers (NeurIPS, ICML, ICLR, CVPR, AAAI, ACL, etc.) using the handbook "Writing AI Conference Papers" by hzwer (Zhewei Huang) and DingXiaoH (Xiaohan Ding). Use when the user is writing a machine-learning / deep-learning / computer-vision / NLP paper and needs help finding the core idea, building the paper framework, writing the introduction or related work, improving readability and defensibility, preparing for the deadline, anticipating reviewer criticism, or judging whether a research idea is worth pursuing. Also trigger on Chinese phrasings such as 写AI论文、写顶会论文、深度学习论文写作、投稿NeurIPS/ICML/ICLR/CVPR、改论文、提升论文可读性、审稿意见、rebuttal、idea是否值得做.
version: 1.0.0
author: hzwer (Zhewei Huang) and DingXiaoH (Xiaohan Ding); packaged as a Claude skill
---

# Writing AI Conference Papers — Skill Router

This skill packages the community handbook *"Writing AI Conference Papers: A Handbook for Beginners"* so it can be applied directly to a user's manuscript. The full source text lives under `reference/` and is the authoritative content — **do not rely on memory; load the relevant reference section before advising.**

- `reference/handbook.md` — the complete handbook (idea → framework → introduction → related work → readability → defensibility → checklists → review/appendix).
- `reference/not-good-ideas.md` — patterns of research ideas that tend to fail review (compute-overwhelming, hyperparameter tuning, minor tweaks, incremental designs, weak evaluation, "ultimate" methods).

## Routing protocol

Every time this skill is invoked:

1. **Identify the task axis** from the request and map it to the handbook section(s):
   - *"Is my idea worth doing?" / topic selection / novelty worry* → `reference/handbook.md` §"Build a Paper from Scratch → Find the Core Idea" **and** `reference/not-good-ideas.md`.
   - *Paper structure / outline / framework* → §"Construct the Framework".
   - *Introduction drafting or rewriting* → §"Write an Introduction".
   - *Related work* → §"Describe the Related Work".
   - *Make it clearer / reviewers misunderstand / writing quality* → §"Readability Improvement" (Logical Strength, Defensibility, Shorten Confusion Time, Information Density, Detail Checklist).
   - *Deadline crunch / final pass* → §"Appendix → Checklist for the Last Few Hours".
   - *Anticipating or answering reviews / rebuttal* → §"Appendix → Common Negative Review Comments" and §"If the Paper is Not Accepted".
   - *Venue choice / timeline* → §"Appendix → AI Conference List" and §"AI Paper Production and Publication".

2. **Read the matched section(s)** from `reference/` in full before responding. Quote or paraphrase the handbook's concrete advice; do not invent rules it does not state.

3. **Apply it to the user's material.** When the user provides a draft, claim, idea, or section, diagnose it against the handbook's principles (logical strength, defensibility, confusion time, information density) and produce specific, actionable edits — not generic writing tips.

4. **Stay honest about scope.** This handbook is opinionated guidance aimed at beginners writing AI conference papers. It does not replace the target venue's official formatting/policy requirements; flag when the user should consult the call-for-papers.

## Style of help

- Be concrete and example-driven, mirroring the handbook's tone.
- When critiquing an idea, name the failure pattern from `not-good-ideas.md` if one applies, then suggest how to strengthen it.
- When editing prose, preserve the author's technical meaning and contribution while fixing structure, clarity, and defensibility.

Attribution

caixinyu2017-starcaixinyu2017-star
View sourceMore from caixinyu2017-star →
SSkills DirectorySkills Directory

Ship a skill? Prove it's safe.

Free 120-pattern security scan, letter grade, and an embeddable README badge.

Submit a skill

Is this your skill, or is something wrong with this listing? Request removal or report an issue. Author removals are honored within 72 hours.

Comments (0)

No comments yet. Be the first to comment!

SSkills DirectorySkills Directory

Ship a skill? Prove it's safe.

Free 120-pattern security scan, letter grade, and an embeddable README badge.

Submit a skill

Related Skills

Context Fundamentals

Understand the components, mechanics, and constraints of context in agent systems. Use when designing agent architectures, debugging context-related failures, or optimizing context usage.

179001 votes

release-notes

Draft release notes and changelog entries from git history or merged PRs between two refs (tags/SHAs/branches), including breaking changes, migrations, and upgrade steps. Use when the user asks for release notes, changelog updates, or a GitHub Release draft.

1301 votes

docs-style-guide

Documentation style guide enforcer by @planetabhi. Applies and reviews the writing style guide when authoring or editing product documentation and tutorials. Use to check prose for voice, tense, word choice, inclusive language, formatting, code block, UI, Markdown, and number/date conventions.

11 votes

Caveman Help

Quick-reference card for all caveman modes, skills, and commands. One-shot display, not a persistent mode. Trigger: /caveman-help, "caveman help", "what caveman commands", "how do I use caveman".

1023330 votes

How It Works

Explain how claude-mem captures observations, when memory injection kicks in, and where data lives. Use when the user asks "how does claude-mem work?" or "what is this thing doing?".

929660 votes
View all in documentation →