Agent skill

AI Research Writing

by Citrus-bit in Citrus-bit/Anaxa

A skill your agent uses when the user wants academic writing prompts, paper polishing workflows, translation/rewrite guidance, reviewer-style paper critique, experiment write-up help, title/caption…

MITAuto-check passedAI & LLM Engineering

Install AI Research Writing

skills CLI
$ npx skills add Citrus-bit/Anaxa --skill ai-research-writing -a claude-code

Project install by default; add -g for ~/.claude/skills/.

GitHub CLI
$ gh skill install Citrus-bit/Anaxa ai-research-writing --agent claude-code

Project scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).

Manual copy
$ git clone --depth 1 https://github.com/Citrus-bit/Anaxa.git skills-src && mkdir -p .claude/skills && cp -r skills-src/skills/public/ai-research-writing .claude/skills/ai-research-writing && rm -rf skills-src

Use ~/.claude/skills/ instead of .claude/skills for a personal install. The folder must contain SKILL.md.

Claude Code skills documentation · loads skills from .claude/skills/

Facts

Skill name
ai-research-writing
GitHub stars
120
Token cost
~886 tokens
SKILL.md length
389 words
Files
3
Skills in repo
15
Repo updated
First seen
Licence
MIT

At a glance

A skill your agent uses when the user wants academic writing prompts, paper polishing workflows, translation/rewrite guidance, reviewer-style paper critique, experiment write-up help, title/caption…

  • Works in 5 steps: Translation → Polishing → Logic Audit → …
  • The user wants academic writing prompts
  • SKILL.md covers Scope, Working Method, Output Modes and Suggested Response Pattern, plus 1 more section
  • Instructions only: no scripts, shell commands, URLs or credentials in SKILL.md

What it does

AI Research Writing is an agent skill from Citrus-bit/Anaxa. Use when the user wants academic writing prompts, paper polishing workflows, translation/rewrite guidance, reviewer-style paper critique, experiment write-up help, title/caption drafting, or practical AI-assisted research writing support. This skill adapts the prompt library and usage guidance curated in the awesome-ai-research-writing repository into a MedrixFlow-compatible writing workflow.

Its SKILL.md is about 890 tokens, which your agent loads only when the skill is triggered. The skill folder holds 2 other files (for example `README.md` and `THIRD_PARTY_NOTICE.md`).

It sits in AI & LLM Engineering, covering Translation, Prompt engineering and Scientific writing. It works with LaTeX. The repository describes itself as: Anaxa 是一个面向科研工作流的开源智能体系统。它不是单纯的聊天机器人,也不是无人监管的自动发论文机器,而是把文献检索、证据审计、实验执行、论文写作、同行评审式检查和最终产物打包放进同一个可追踪的研究生命周期中。 The licence is MIT.

When your agent uses it

  • The user wants academic writing prompts
  • Paper polishing workflows
  • Translation/rewrite guidance
  • Reviewer-style paper critique

Example prompts

  • “/ai-research-writing”

Workflow steps

5 steps, taken from the step headings in SKILL.md.

  1. Translation
  2. Polishing
  3. Logic Audit
  4. Reviewer Critique
  5. Titles and Captions

What it can do on your machine

Read from SKILL.md and the folder at commit d57c708. 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

    No scripts in the folder and no shell commands in SKILL.md.

    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

AI Research Writing loads about 886 tokens when it runs. Until then it costs about 104 tokens; SKILL.md has 389 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it
~104
When it runs · the whole SKILL.md, loaded when a task matches
~886

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); files beside SKILL.md are not scanned.

SKILL.md

The full file from Citrus-bit/Anaxa at commit d57c708, republished under its MIT licence (© Citrus-bit). 389 words, ~886 tokens.

Download SKILL.mdSave it as .claude/skills/ai-research-writing/SKILL.md (or your agent's skills folder). This skill also uses 2 other files; get the full folder from GitHub.
name
ai-research-writing
description
Use when the user wants academic writing prompts, paper polishing workflows, translation/rewrite guidance, reviewer-style paper critique, experiment write-up help, title/caption drafting, or practical AI-assisted research writing support. This skill adapts the prompt library and usage guidance curated in the awesome-ai-research-writing repository into a MedrixFlow-compatible writing workflow.
author
Leey21-inspired MedrixFlow adaptation
version
1.0.0

AI Research Writing

This skill adapts the practical academic-writing prompt collection from the awesome-ai-research-writing repository into a MedrixFlow-compatible workflow.

Use it when the user asks for:

  • Chinese-to-English or English-to-Chinese academic translation
  • paper polishing or de-AI-ification
  • logic checking for manuscript sections
  • title or caption drafting
  • reviewer-style critique of a paper draft
  • experiment analysis write-up support
  • research-writing prompt recommendations

Scope

This is a writing-support skill, not an execution-heavy tool skill.

It should help the agent:

  • choose an appropriate writing mode
  • structure the task before editing
  • apply concise academic-writing constraints
  • return polished output plus brief rationale when useful

Working Method

  1. Identify the writing intent first:
    • translation
    • polishing
    • logic audit
    • reviewer critique
    • title/caption generation
    • experiment analysis
  2. Preserve factual meaning. Do not invent claims, citations, results, or novelty.
  3. If the user provides draft text, work directly on that text rather than answering abstractly.
  4. If the user asks for publication-grade wording, prefer concise, natural, reviewer-resistant academic prose over flashy wording.
  5. For full paper/manuscript generation, default to LaTeX source and PDF output. Use exact BibTeX keys from references.bib, call manuscript_export for final delivery, and avoid \nocite{*} unless explicitly requested.
  6. If the user is writing in Chinese, you may explain decisions in Chinese, but produce the requested target-language result exactly as asked.

Output Modes

1. Translation
  • Keep technical meaning stable.
  • Preserve formulas, symbols, and explicit numeric claims.
  • Escape LaTeX-sensitive characters only when the user wants LaTeX-ready output.
Show full SKILL.md (154 more words)Show less
2. Polishing
  • Remove awkward AI-style phrasing.
  • Prefer precise verbs, concrete logical connectors, and shorter sentences.
  • Do not over-intensify novelty claims.
3. Logic Audit
  • Flag missing assumptions, unsupported jumps, repeated points, and vague conclusions.
  • Prefer reviewer-style comments tied to the specific text.
4. Reviewer Critique
  • Evaluate contribution clarity, methodological trust, evidence sufficiency, limitation handling, and writing clarity.
  • Separate major issues from minor issues when helpful.
5. Titles and Captions
  • Optimize for specificity and information density.
  • Avoid hype and vague adjectives.

Suggested Response Pattern

When editing concrete text, prefer:

  1. the revised output
  2. a short list of the main fixes if the user would benefit

When auditing text, prefer:

  1. key issues
  2. a revised version or repair strategy

References

The source repository also contains a broader prompt library and usage notes for research writing. This adaptation is intentionally lightweight so the skill can be loaded by MedrixFlow's native skill loader without requiring external tooling.

© Citrus-bit, 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 2 other files in skills/public/ai-research-writing of Citrus-bit/Anaxa.

  • SKILL.md
  • README.md
  • THIRD_PARTY_NOTICE.md

Open the folder on GitHubat commit d57c708

Compare with similar skills

AI Research Writing 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.

AI Research Writing compared with similar skills
SkillStarsUsed inTokensAuto-checkLicenceRepo updated
AI Research Writing this skillCitrus-bit/Anaxa120—~886Automated safety check: PassMIT
Nature-Style Academic PolishingYuan1z0825/nature-skills47k—~1.5kAutomated safety check: PassApache-2.0
Paper SkillcLin-c/paper-skill119—~2.6kAutomated safety check: PassMIT
Academic Paperbrycewang-stanford/Auto-Empirical-Research-Skills4.6k—~7.3kAutomated safety check: PassCustom licence
Academic Writing Assistantdonghuixin/AI-Vibe-Writing-Skills497—~616Automated safety check: PassMIT
Academic Paper PolishHKUSTDial/Supervisor-Skills8.8k—~3.1kAutomated safety check: PassCC-BY-NC-SA-4.0

Similar skills

  • 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.

    47k GitHub stars~1.5k tokensUpdated today
    Writing & ContentAuto-check passed
  • Paper Skill

    cLin-c/paper-skill

    End-to-end, Chinese-first academic research and publication workflow for reading papers, literature reviews, research framing, manuscript planning and writing, Chinese-English translation, LaTeX…

    119 GitHub stars~2.6k tokensUpdated 14 days ago
    Research & ScienceAuto-check passed
  • Academic Paper

    brycewang-stanford/Auto-Empirical-Research-Skills

    Academic paper writing skill with 12-agent pipeline. An agent skill from brycewang-stanford/Auto-Empirical-Research-Skills.

    4.6k GitHub stars~7.3k tokensUpdated 5 days ago
    Documents & OfficeAuto-check passed
  • Academic Writing Assistant

    donghuixin/AI-Vibe-Writing-Skills

    Drafts and revises academic prose in the author's voice, repairs sentence flow, traces systems-paper claims to evidence and prepares reviewer responses.

    497 GitHub stars~616 tokensUpdated 28 days ago
    Writing & ContentAuto-check passed
  • Academic Paper Polish

    HKUSTDial/Supervisor-Skills

    Polishes academic prose without changing its meaning: grammar and flow fixes, tone matched to the evidence, AI-tone removal and Chinese-to-English rewriting for submission.

    8.8k GitHub stars~3.1k tokensUpdated 1 mo ago
    Writing & ContentAuto-check passed
  • Prompts Collection

    Norman-bury/research-writing-skill

    A skill your agent uses for translation, polishing, or de-AI-ification of academic text - provides ready-to-use prompt templates

    3.4k GitHub stars~1k tokensUpdated 4 mo ago
    Writing & ContentAuto-check passed

More from Citrus-bit/Anaxa

All 15 skills in this repo
  • Nature Figure

    Citrus-bit/Anaxa

    Submission-grade Nature/high-impact journal figure workflow for Python or R.

    120 GitHub starsUsed in 2 repos~2.7k tokens
    Auto-check passed
  • Chart Visualization

    Citrus-bit/Anaxa

    A skill your agent uses whenever the user wants a chart, graph, plot, dashboard visual, or asks to visualize structured numbers, trends, comparisons, proportions, distributions, correlations…

    120 GitHub stars~2.4k tokensUpdated 1 mo ago
    Auto-check passed
  • Claude To Medrixflow

    Citrus-bit/Anaxa

    Interact with MedrixFlow AI agent platform via its HTTP API.

    120 GitHub stars~1.7k tokensUpdated 1 mo ago
    Auto-check passed
  • Fireworks Tech Graph

    Citrus-bit/Anaxa

    A skill your agent uses when the user wants to create any technical diagram - architecture, data flow, flowchart, sequence, agent/memory, or concept map - and export as SVG+PNG.

    120 GitHub stars~5.4k tokensUpdated 1 mo ago
    Auto-check passed
  • Bootstrap

    Citrus-bit/Anaxa

    Generate a personalized SOUL.md through a warm, adaptive onboarding conversation.

    120 GitHub stars~1.2k tokensUpdated 1 mo ago
    Auto-check passed
  • Deep Research

    Citrus-bit/Anaxa

    A skill your agent uses for general web research that needs current online information, multiple source angles, and synthesis, when no more specific research skill applies.

    120 GitHub stars~1.9k tokensUpdated 1 mo ago
    Auto-check passed

Works with

Questions about AI Research Writing

What does AI Research Writing do?

A skill your agent uses when the user wants academic writing prompts, paper polishing workflows, translation/rewrite guidance, reviewer-style paper critique, experiment write-up help, title/caption…. AI Research Writing is an agent skill from Citrus-bit/Anaxa. Use when the user wants academic writing prompts, paper polishing workflows, translation/rewrite guidance, reviewer-style paper critique, experiment write-up help, title/caption drafting, or practical AI-assisted research writing support.

When should I use AI Research Writing?

AI Research Writing fits situations like: the user wants academic writing prompts; paper polishing workflows; translation/rewrite guidance; reviewer-style paper critique.

How do I install AI Research Writing in Claude Code?

Run `npx skills add Citrus-bit/Anaxa --skill ai-research-writing -a claude-code`. Or copy the skill folder (skills/public/ai-research-writing in Citrus-bit/Anaxa) into .claude/skills/ai-research-writing in your project. Claude Code loads it when a task matches its description.

How do I install AI Research Writing in Codex?

Run `npx skills add Citrus-bit/Anaxa --skill ai-research-writing -a codex`. Or copy the skill folder (skills/public/ai-research-writing in Citrus-bit/Anaxa) into .agents/skills/ai-research-writing in your project. Codex loads it when a task matches its description.

Can I use AI Research Writing 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 Citrus-bit/Anaxa --skill ai-research-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-research-writing, .gemini/skills/ai-research-writing, .github/skills/ai-research-writing and .opencode/skills/ai-research-writing in your project.

What does AI Research Writing need to run?

SKILL.md names no scripts, command-line tools or credentials: AI Research Writing is instructions for the agent only.

Does AI Research Writing 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 AI Research Writing 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. Review the folder before installing.

What licence does AI Research Writing use?

AI Research Writing is published under the MIT licence (the repository's licence). It allows redistribution, so the full SKILL.md is shown on this page.

How many tokens does AI Research Writing use?

About 886 tokens (SKILL.md is roughly 3.5k 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 AI Research Writing?

Skills that share tags, products or a category with AI Research Writing: Nature-Style Academic Polishing (Yuan1z0825/nature-skills, 47k stars), Paper Skill (cLin-c/paper-skill, 119 stars), Academic Paper (brycewang-stanford/Auto-Empirical-Research-Skills, 4.6k stars) and Academic Writing Assistant (donghuixin/AI-Vibe-Writing-Skills, 497 stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains AI Research Writing?

Citrus-bit (a GitHub user) maintains it in Citrus-bit/Anaxa, which has 120 GitHub stars. The repository holds 15 skills in this directory. The repository was last updated on September 7, 2026.

Source: Citrus-bit/Anaxa on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.