aibuildai-inc/aibuildai-llm-posttrain-agent/research-paper-writing
Claude Code and agent skill by aibuildai-inc/aibuildai-llm-posttrain-agent
- community
Checking that the SKILL.md file is still in the repository.
Improve academic paper writing quality for ML/CV/NLP-style papers with clear section structure, paragraph flow, and reviewer-facing presentation. Use when drafting or revising Abstract, Introduction, Related Work, Method, Experiments, or Conclusion; polishing figures/tables; checking claim-support alignment; or performing self-review before submission.
Install
npx vskill@latest install aibuildai-inc/aibuildai-llm-posttrain-agent/research-paper-writingSKILL.md
Research Paper Writing
Overview
Use this skill to rewrite a research paper into a reviewer-friendly, high-clarity draft. Prioritize first-impression quality (figures/tables/layout), logical flow, and evidence-backed claims.
The document is yours to build and compile
scaffold/ in this skill's own directory is the official NeurIPS 2024 submission template with its sample content removed: paper.tex as the conference ships it, and the unmodified neurips_2024.sty beside it. Copy the whole directory into your artifacts directory, rename the file to whatever your role was told to produce, and edit it freely. It is a mechanics starter, not a template you must follow: replace the preamble entirely if you prefer another class.
Compile it yourself with the tectonic on your PATH, from the directory holding the source:
A relative \input, \includegraphics{figures/name.png}, or \bibliography{references} resolves against that directory, and BibTeX runs as part of the same compile. Read what tectonic prints, fix your own source, and compile again as often as you need. Nothing compiles the document for you, and nothing writes any part of it.
Core Workflow
- Clarify the paper story before sentence-level edits.
- Use section-specific guidance in
references/. - Rewrite paragraph-by-paragraph with one message per paragraph.
- Run reverse outlining after writing each section.
- Check every major claim in Abstract/Introduction against experimental evidence.
- Run final-paper adversarial review with
references/paper-review.md.
Global Principles
- Keep one paragraph for one message only.
- State the paragraph message in the first sentence.
- Make nouns self-contained; define new terms before reusing them.
- Maintain sentence-to-sentence flow (cause, contrast, consequence, or refinement).
- Iterate with adversarial self-review: read as a skeptical reviewer.
- Treat visual quality as core content, not decoration.
- Use a clean teaser and pipeline figure.
- Use readable, minimal-ink tables.
- Keep formatting consistent and tidy.
Paragraph Clarity Check (Important)
Use this quick test whenever the user asks whether a paragraph "flows" or is clear.
- Read as an external reader:
- Does this paragraph have one explicit message?
- Does the first sentence state what this paragraph will do?
- Are all key nouns/terms readable without hidden context?
- Does each sentence connect to the previous one with a clear relation (cause, contrast, consequence, refinement, example)?
- Run reverse outlining for the current section:
- Write down thesis/main claim.
- Write down each paragraph topic sentence.
- Write down the evidence/explanation points under each paragraph.
- Check mapping: topic sentence -> thesis, and evidence -> topic sentence.
- Revise or remove any paragraph that cannot be mapped cleanly.
- If flow is still weak, add temporary section headers and explicit transition phrases during revision, then remove unnecessary headers before finalizing.
Source reference for this check:
references/does-my-writing-flow-source.md
Section Guides
Load only the needed section file:
- Introduction:
references/introduction.md - Abstract:
references/abstract.md - Related Work:
references/related-work.md - Method:
references/method.md - Experiments:
references/experiments.md - Conclusion:
references/conclusion.md - Data analysis:
references/data-analysis.md(mine each data property to a modeling consequence: why a method won or lost on this task) - Figures:
references/figures.md(figure catalogue mapped to its real artifact and the question it answers; generate from real data, never fabricate) - Results and metrics:
references/results-metrics.md(analyze each result as a root-cause question, isolating the one design dimension that drove the metric) - Inferential spine:
references/inference.md(turn flat reporting into question -> hypothesis -> test; mine the run's pre-registered predictions, earn every mechanism from an artifact, calibrate wording to uncertainty) - Paper review (Paper Rview):
references/paper-review.md - Paragraph clarity source:
references/does-my-writing-flow-source.md - Example bank index:
references/examples/index.md
Paper Review Core Points
Use references/paper-review.md for the full checklist and workflow.
- Add an end-of-draft self-review question list in five dimensions:
- contribution,
- writing clarity,
- experimental strength,
- evaluation completeness,
- method design soundness.
- Treat claim-evidence alignment as a hard constraint, especially for Abstract and Introduction.
- Perform adversarial writing: review as a skeptical reviewer and resolve every high-risk question.
- Revise until major rejection risks are explicitly addressed.
Execution Rules
- Build a mini-outline before drafting prose.
- For each subsection, explicitly include motivation, design, and technical advantage when applicable.
- Avoid writing style that looks like incremental patching of a naive baseline.
- Keep terminology stable across the full paper.
- If a claim cannot be supported by results, weaken or remove the claim.
- Before finalizing, append and answer a five-dimension self-review question list, then revise the paper based on unresolved items.
- Do not load all section references (Introduction/Abstract/Related Work/Method/Experiments/Conclusion) at once; load only the specific section guide needed for the current edit target.
Output Contract
When asked to rewrite or draft sections, return:
- A compact section outline (3-7 bullets).
- Revised paragraphs with explicit paragraph roles (opening/challenge/method/advantage/evidence/limitation).
- A short self-review checklist covering clarity, flow, terminology consistency, unsupported claims, and missing evidence.
- A claim-evidence map for each major claim in the revised text using
Claim: ... | Evidence: ... | Status: supported/needs evidence.
Security
- Security scanPassed, 100 of 100Pattern checks on the skill's files.
- Model reviewNot runA model review is scheduled for the next rescan.
Quality evaluation
- Task evaluationNot runNo evaluation yet. Run one in Skill Studio.
Source
- SKILL.md in the repositoryCheckingplugins/aibuildai-builtin-marketplace/aibuildai-builtin/skills/research-paper-writing/SKILL.md
Popularity
- 7-day trend score
- 0
Not refreshed yet.
Works with
Any agent vskill installs to: 56 targets in all. These 39 have a page on this site.
- Claude Code
- Cursor
- GitHub Copilot
- Windsurf
- Codex
- Gemini CLI
- Cline
- Amp
- Roo Code
- Goose
- Continue
- Kilo Code
- Junie
- Trae
- OpenHands
- Qwen Code
- AI Agent
- Tabnine Chat
- Sourcegraph Cody
- Amazon Q
- Firebase Genkit
- Sweep
- Devin
- Phind
- Mentat
- Claude Desktop
- Aider
- GPT Pilot
- Plandex
- bolt.new
- v0
- Replit Agent
- Anse
- TypingMind
- BetterChatGPT
- LibreChat
- Warp AI
- Pieces
- Fig AI
Embed badge
[](https://verified-skill.com/skills/aibuildai-inc/aibuildai-llm-posttrain-agent/research-paper-writing)