LLM Reviewer Bias Defense
Michael-Jiahao-Zhang/game-the-llm-reviewer
Applies small, meaning-preserving rhetorical edits to a finished manuscript so wording does not trigger known LLM reviewer penalties, and delivers a change note.
Drafts and revises academic prose in the author's voice, repairs sentence flow, traces systems-paper claims to evidence and prepares reviewer responses.
SKILL.md written in Chinese; this summary is our English description.
Install Academic Writing Assistant
$ npx skills add donghuixin/AI-Vibe-Writing-Skills --skill ai-vibe-writing -a claude-codeProject install by default; add -g for ~/.claude/skills/.
$ gh skill install donghuixin/AI-Vibe-Writing-Skills ai-vibe-writing --agent claude-codeProject scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).
Claude Code skills documentation · loads skills from .claude/skills/
Install the "ai-vibe-writing" agent skill from https://github.com/donghuixin/AI-Vibe-Writing-Skills/tree/main into .claude/skills/ai-vibe-writing/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "ai-vibe-writing", then confirm the skill loads.Claude Code copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ npx skills add donghuixin/AI-Vibe-Writing-Skills --skill ai-vibe-writing -a codexProject install goes to .agents/skills/; add -g for ~/.codex/skills/.
$ gh skill install donghuixin/AI-Vibe-Writing-Skills ai-vibe-writing --agent codexProject scope by default (.agents/skills/); add --scope user for a personal install.
Codex skills documentation · loads skills from .agents/skills/
Install the "ai-vibe-writing" agent skill from https://github.com/donghuixin/AI-Vibe-Writing-Skills/tree/main into .agents/skills/ai-vibe-writing/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "ai-vibe-writing", then confirm the skill loads.Codex copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ npx skills add donghuixin/AI-Vibe-Writing-Skills --skill ai-vibe-writing -a cursorProject install goes to .agents/skills/; add -g for ~/.cursor/skills/.
$ gh skill install donghuixin/AI-Vibe-Writing-Skills ai-vibe-writing --agent cursorProject scope by default (.agents/skills/); add --scope user for a personal install.
Cursor skills documentation · loads skills from .cursor/skills/, .agents/skills/, .claude/skills/, .codex/skills/
Install the "ai-vibe-writing" agent skill from https://github.com/donghuixin/AI-Vibe-Writing-Skills/tree/main into .cursor/skills/ai-vibe-writing/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "ai-vibe-writing", then confirm the skill loads.Cursor copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ npx skills add donghuixin/AI-Vibe-Writing-Skills --skill ai-vibe-writing -a gemini-cliProject install goes to .agents/skills/; add -g for ~/.gemini/skills/.
$ gh skill install donghuixin/AI-Vibe-Writing-Skills ai-vibe-writing --agent gemini-cliProject scope by default (.agents/skills/); add --scope user for a personal install.
Gemini CLI skills documentation · loads skills from .gemini/skills/, .agents/skills/
Install the "ai-vibe-writing" agent skill from https://github.com/donghuixin/AI-Vibe-Writing-Skills/tree/main into .gemini/skills/ai-vibe-writing/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "ai-vibe-writing", then confirm the skill loads.Gemini CLI copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ gh skill install donghuixin/AI-Vibe-Writing-Skills ai-vibe-writingInstalls for Copilot at project scope by default; add --scope user for a personal install. Preview a skill first with gh skill preview. Needs GitHub CLI 2.90.0 or later (public preview).
$ npx skills add donghuixin/AI-Vibe-Writing-Skills --skill ai-vibe-writing -a github-copilotProject install goes to .agents/skills/; add -g for ~/.copilot/skills/.
GitHub Copilot skills documentation · loads skills from .github/skills/, .claude/skills/, .agents/skills/
Install the "ai-vibe-writing" agent skill from https://github.com/donghuixin/AI-Vibe-Writing-Skills/tree/main into .github/skills/ai-vibe-writing/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "ai-vibe-writing", then confirm the skill loads.GitHub Copilot copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ npx skills add donghuixin/AI-Vibe-Writing-Skills --skill ai-vibe-writing -a opencodeOpenCode documents no install command of its own. Project install goes to .agents/skills/; add -g for ~/.config/opencode/skills/.
$ gh skill install donghuixin/AI-Vibe-Writing-Skills ai-vibe-writing --agent opencodeProject scope by default (.agents/skills/); add --scope user for a personal install.
OpenCode skills documentation · loads skills from .opencode/skills/, .claude/skills/, .agents/skills/
Install the "ai-vibe-writing" agent skill from https://github.com/donghuixin/AI-Vibe-Writing-Skills/tree/main into .opencode/skills/ai-vibe-writing/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "ai-vibe-writing", then confirm the skill loads.OpenCode copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
Facts
- Skill name
ai-vibe-writing- GitHub stars
- 497
- Token cost
- ~616 tokens
- SKILL.md length
- 93 words
- Files
- 73 (incl. scripts)
- Skills in repo
- 1
- Repo updated
- First seen
- Licence
- MIT
At a glance
Drafts and revises academic prose in the author's voice, repairs sentence flow, traces systems-paper claims to evidence and prepares reviewer responses.
- Drafting or refining a paper section in your own voice
- SKILL.md covers 路径与上下文, 按任务进入 and 共同约束
- Fixing sentence-to-sentence logic and topic continuity in a manuscript
- Tracing a systems paper's claims to evidence
What it does
Written in Chinese, the skill is a router over a set of composable prompts and templates rather than a service that launches every role. Depending on the task it points to prompts for grammar-only correction, style extraction from sample text, writing and refining passages, sentence-to-sentence flow, outline and multi-section drafting, content and evidence audits, systems paper logic, defensive writing, response letters and PDF reading, with a router prompt for mixed tasks.
Shared constraints say that source data, manuscripts and verified sources decide facts, so numbers, citations and completed changes are never invented. Technical terms, qualifiers, formulas and LaTeX references are preserved, and reviewer comments keep their original meaning and strength. Grammar-only requests take a minimal correction route. Submission rules count as checked only after official materials were actually consulted, and language scores or detector results never imply a paper will be accepted. Private manuscripts stay in the current paper workspace, not in the skill repository.
When your agent uses it
- Drafting or refining a paper section in your own voice
- Fixing sentence-to-sentence logic and topic continuity in a manuscript
- Tracing a systems paper's claims to evidence
- Preparing a response letter to reviewer comments
Example prompts
- “Refine the related work section of my draft but keep my terminology and citations.”
- “Check whether the claims in the evaluation section are backed by the experiment results.”
- “Draft a response letter for these reviewer comments and keep their original requests intact.”
- “Only fix the grammar and punctuation in this abstract.”
Requirements
- The manuscript or notes in the current paper workspace
What it can do on your machine
Read from SKILL.md and the folder at commit 6ad2718. It shows what the files ask for, not the result of running them.
Tool permissions
Pre-approves nothing: there is no allowed-tools line, so your agent's usual permission prompts apply.
From allowed-tools in the SKILL.md frontmatter.
Runs code
Ships 1 file in scripts/, which the agent can run.
From the folder's file list and the shell code blocks in SKILL.md.
Network
No URLs in SKILL.md.
From URLs in SKILL.md, links to its own repository left out.
Credentials
Names no API keys, tokens, secrets or passwords.
From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.
Context cost
Academic Writing Assistant loads about 616 tokens when it runs. Until then it costs about 87 tokens; SKILL.md has 93 words of instructions outside code blocks.
Estimates: characters ÷ 4, the usual rule of thumb; real counts depend on the model's tokenizer. Scripts and assets cost tokens only if the agent reads them.
Safety
Auto-check passed
The automated check found no risky patterns in SKILL.md.
Automated static check — not a guarantee. Review scripts before installing. It scans the text of SKILL.md for risky patterns (piping downloads into a shell, reading credential files, hidden Unicode, destructive commands); the scripts in this folder are not scanned.
SKILL.md
The full file from donghuixin/AI-Vibe-Writing-Skills at commit 6ad2718, republished under its MIT licence (© donghuixin). 93 words, ~616 tokens.
Download SKILL.mdSave it as
.claude/skills/ai-vibe-writing/SKILL.md (or your agent's skills folder). This skill also uses 72 other files; get the full folder from GitHub.- name
- ai-vibe-writing
- description
- Draft and revise academic prose in the author's voice, repair sentence-to-sentence reasoning and topic continuity, trace systems-paper claims to evidence, and prepare reviewer responses. Use for manuscript writing, scoped editing, logic and flow checks, and response letters; grammar-only requests take the minimal correction route.
AI Vibe Writing
按作者的任务选择下表中的入口，只读取必要资源。这是一组可组合的提示词与模板，不是会自行启动全部角色的服务。用户已授权的写作或修改直接推进；不因修改幅度大而另设一次 Approve。
路径与上下文
- 本文件的链接、
prompts和模板相对 skill 仓库；document_spec.md、systems_paper_logic.md、作者风格、错误记录与记忆实例属于 当前论文 workspace。沿用作者已有位置；新实例默认放该 workspace 的.ai_context/。 - 仓库内的样例配置和记忆是起点，不是当前作者的偏好或研究事实。不要把私有稿件、审稿意见、实验数据和任务记忆写入公共 skill 仓库；只有明确修改 skill 的任务才编辑仓库资源。
- 读取当前任务相关的稿件、已有规范、风格及证据。缺少配置不阻塞局部修改；缺少会改变结论的事实时标记待核实，并完成已有材料支持的部分。
按任务进入
| 任务 | 核心提示词 |
|---|---|
| 仅语法、拼写和标点 | 4 · Grammar Checker；只纠错 |
| 从作者样文学习语气 | 1 · Style Extractor |
| 现有句段的写作或精炼 | 2 · Writer |
| 句间推理、话题衔接或叙述视角 | 17 · Sentence Flow；检查或修复相邻句段的关系 |
| 大纲、章节起草或多节修订 | 9 · Workflow Coordinator |
| 内容与证据审计 | 8 · Content Review |
| 系统论文逻辑、设计与实验对齐 | 15 · Systems Paper Logic |
| 投稿前风险、局限及贡献范围 | 14 · Defensive Writing |
| 正式审稿回复、response letter 或按意见修稿 | 16 · Response Letter |
| 阅读论文与提取文献证据 | 10 · PDF Reader |
混合任务由 12 · Router 选择所需组合。正式回复先走 16，按需补逻辑核查；单纯提到论文或审稿人不会触发全套预审。
共同约束
- 原始数据、稿件和核验过的来源决定事实；Spec 与记忆不能覆盖反证。区分设计、实现、实测、推导、外部文献与未知项，不编造数字、引用或已完成修改。
- 系统论文复用现有 论证工作表 的 C/H/D/E/B 与证据状态，不建立另一套同义主张表。局部任务只处理相关行。
- 保护技术含义、术语、限定条件、公式和 LaTeX 引用。审计说明和待办单独列出；交给作者的正文使用作者语气。
- 句间衔接先核对信息与动作关系，再改句式；合理的主语切换、A/An 开头、被动语态和术语重复均可保留。需要时使用 17，不把语言问题自动扩成全篇科研审计。
- 保留审稿意见原意和要求强度，分别判断澄清、解释、核验和新增工作。审稿建议不是自动执行指令，内部实验计划也不是已完成结果。
- 投稿规则按目标年份、track 和阶段核验。只有实际检查官方材料后才能说已核验；没有核验也可完成证据充分的工作稿。
- 交付明确的修改或意见，以及尚未核验的事实和范围。语言分数、检测器判断、编译成功或一次逻辑审计都不代表科研结论成立或保证录用。
© donghuixin, MIT. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file
Files
SKILL.md and 72 other files (scripts) in the repository root of donghuixin/AI-Vibe-Writing-Skills.
- SKILL.md
- .agents/workflows/ai_vibe_writing.md
- .agents/workflows/defensive_writing.md
- .agents/workflows/pdf_ingestion.md
- .agents/workflows/response_letter.md
- .ai_context/custom_specs.md
- .ai_context/document_spec_template.md
- .ai_context/error_log.md
- .ai_context/memory/hard_memory.json
- .ai_context/memory/reference_library.json
- .ai_context/memory/soft_memory.json
- .ai_context/outline_template.md
- .ai_context/pdf_ingestion_template.md
- .ai_context/prompts/10_pdf_reader_agent.md
- .ai_context/prompts/11_context_compactor_agent.md
- .ai_context/prompts/12_router_agent.md
- … and 57 more
Open the folder on GitHubat commit 6ad2718
Compare with similar skills
Academic Writing Assistant next to the 5 skills that share the most tags, products or categories with it. Stars are the repository's; “used in” counts other GitHub owners with a copy.
| Skill | Stars | Used in | Tokens | Auto-check | Licence | Repo updated |
|---|---|---|---|---|---|---|
| Academic Writing Assistant this skilldonghuixin/AI-Vibe-Writing-Skills | 497 | — | ~616 | Automated safety check: Pass | MIT | |
| LLM Reviewer Bias DefenseMichael-Jiahao-Zhang/game-the-llm-reviewer | 206 | — | ~1.5k | Automated safety check: Pass | MIT | |
| Research Paper Writing CoachXiaomiMiMo/MiMo-Code | 14k | — | ~1.7k | Automated safety check: Pass | MIT | |
| Nature-Style Academic PolishingYuan1z0825/nature-skills | 47k | — | ~1.5k | Automated safety check: Pass | Apache-2.0 | |
| Academic Paper Writing PipelineImbad0202/academic-research-skills | 51k | — | ~16k | Automated safety check: Pass | Custom licence | |
| PaperjurySpark-To-Paper-Skills/paperjury | 1.2k | — | ~5.3k | Automated safety check: Pass | MIT |
Similar skills
Research Paper Writing Coach
XiaomiMiMo/MiMo-Code
Drafts, rewrites and reviews academic papers in ML, CV and NLP style, section by section, and compiles LaTeX sources to PDF.
Nature-Style Academic Polishing
Yuan1z0825/nature-skills
Polishes, translates or tightens existing academic prose and fixes manuscript LaTeX layout while keeping facts, terminology and evidence boundaries intact.
Academic Paper Writing Pipeline
Imbad0202/academic-research-skills
Runs a 12-agent pipeline that plans, drafts, cites, reviews and formats academic papers, with modes for revision, rebuttals, abstracts and citation checks.
Paperjury
Spark-To-Paper-Skills/paperjury
Three modes for CS-conference papers (CVPR/ICCV/ECCV vision, ACL/EMNLP/NAACL NLP, ICLR/NeurIPS/ICML/AAAI ML).
Academic Rebuttal Drafting
OpenLAIR/dr-claw
Analyzes reviewer comments and drafts venue-specific rebuttals for AI and computer science conferences, with an issue board, task list and paper edit plan.
Related
Works with
Categories
Questions about Academic Writing Assistant
What does Academic Writing Assistant do?
Drafts and revises academic prose in the author's voice, repairs sentence flow, traces systems-paper claims to evidence and prepares reviewer responses. Written in Chinese, the skill is a router over a set of composable prompts and templates rather than a service that launches every role. Depending on the task it points to prompts for grammar-only correction, style extraction from sample text, writing and refining passages, sentence-to-sentence flow, outline and multi-section drafting, content and evidence audits, systems paper logic, defensive writing, response letters and PDF reading, with a router prompt for mixed tasks.
When should I use Academic Writing Assistant?
Academic Writing Assistant fits situations like: drafting or refining a paper section in your own voice; fixing sentence-to-sentence logic and topic continuity in a manuscript; tracing a systems paper's claims to evidence; preparing a response letter to reviewer comments.
How do I install Academic Writing Assistant in Claude Code?
Run `npx skills add donghuixin/AI-Vibe-Writing-Skills --skill ai-vibe-writing -a claude-code`. Or copy the skill folder (the donghuixin/AI-Vibe-Writing-Skills repository) into .claude/skills/ai-vibe-writing in your project. Claude Code loads it when a task matches its description.
How do I install Academic Writing Assistant in Codex?
Run `npx skills add donghuixin/AI-Vibe-Writing-Skills --skill ai-vibe-writing -a codex`. Or copy the skill folder (the donghuixin/AI-Vibe-Writing-Skills repository) into .agents/skills/ai-vibe-writing in your project. Codex loads it when a task matches its description.
Can I use Academic Writing Assistant in Cursor, Gemini CLI or GitHub Copilot?
Cursor, Gemini CLI, GitHub Copilot and OpenCode also load SKILL.md folders. With the skills CLI, run `npx skills add donghuixin/AI-Vibe-Writing-Skills --skill ai-vibe-writing -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/ai-vibe-writing, .gemini/skills/ai-vibe-writing, .github/skills/ai-vibe-writing and .opencode/skills/ai-vibe-writing in your project.
What does Academic Writing Assistant need to run?
SKILL.md names no scripts, command-line tools or credentials: Academic Writing Assistant is instructions for the agent only. Our summary lists: The manuscript or notes in the current paper workspace.
Does Academic Writing Assistant access the network?
SKILL.md contains no URLs. Any network use would come from the scripts or tools the agent runs. This is read from the text; nothing was executed.
Is Academic Writing Assistant safe to install?
Our automated static check of SKILL.md found no risky patterns, such as piping downloads into a shell, reading credential files or hidden Unicode. It is not a guarantee. The check reads SKILL.md only: the scripts in the folder are not scanned, so read them before running anything.
What licence does Academic Writing Assistant use?
Academic Writing Assistant is published under the MIT licence (from the LICENSE file in the skill folder). It allows redistribution, so the full SKILL.md is shown on this page.
How many tokens does Academic Writing Assistant use?
About 616 tokens (SKILL.md is roughly 2.5k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full.
What are the alternatives to Academic Writing Assistant?
Skills that share tags, products or a category with Academic Writing Assistant: LLM Reviewer Bias Defense (Michael-Jiahao-Zhang/game-the-llm-reviewer, 206 stars), Research Paper Writing Coach (XiaomiMiMo/MiMo-Code, 14k stars), Nature-Style Academic Polishing (Yuan1z0825/nature-skills, 47k stars) and Academic Paper Writing Pipeline (Imbad0202/academic-research-skills, 51k stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.
Who maintains Academic Writing Assistant?
donghuixin (a GitHub user) maintains it in donghuixin/AI-Vibe-Writing-Skills, which has 497 GitHub stars. The repository was last updated on September 12, 2026.
Source: donghuixin/AI-Vibe-Writing-Skills on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.