
Paper Writing Section
This does the structured work of writing individual academic paper sections with field-appropriate conventions. It pulls context from your existing LaTeX files and experimental logs, then writes sections like abstracts, methods, or results with inline planning comments before each paragraph. The two-pass refinement is the practical part: first it fixes technical errors like unenclosed math and broken references, then it compresses and removes redundancy. You get LaTeX fragments ready to drop into your paper, no preamble or placeholders. The quality checklist enforces things reviewers actually care about: proper math delimiters, valid citations, no hype language, numbers that match your logs. It assumes you have supporting files for section-specific tips and refinement prompts, so you'll want those reference files in place to get the full benefit.
- skills.sh installs
- 1.8K
- GitHub stars
- 459
- last updated
- Aug 21, 2026
Install
$ npx -y skills add lingzhi227/agent-research-skills --skill paper-writing-section --agent claude-codeInstalls into .claude/skills of the current project.
Files
Paper Section Writer
Write a publication-quality section for an academic paper.
Input
$0— Section name:abstract,introduction,background,related-work,methods,experimental-setup,results,discussion,conclusion$1— (Optional) Path to context file (research plan, results, prior sections)
Workflow
Step 1: Gather Context
Read the paper's existing .tex files, experiment logs, result files, and any provided context. Understand: title, contributions, methodology, key results, figures, tables.
Step 2: Write the Section
Load section-specific tips from references/section-tips.md. Before every paragraph, include a brief plan as a LaTeX comment (% Plan: ...).
Step 3: Two-Pass Refinement
Apply both refinement passes from references/refinement-prompts.md:
- Pass 1: Fix errors (unenclosed math, broken refs, hallucinated numbers, duplicate labels)
- Pass 2: Remove redundancies, compress, ensure smooth transitions
References
Sponsors
Details
- Repository
- github.com/lingzhi227/agent-research-skills
- Categories
- Documentation, AI & Agent Building, Data Science & ML
- First seen
- Jun 3, 2026
More from lingzhi227/agent-research-skills
All 31- Paper Revision1.8K
- Experiment Design1.8K
- Github Research1.8K
- Research Planning1.8K
- Survey Generation1.8K
- Algorithm Design1.7K
- Rebuttal Writing1.7K
- Code Debugging1.7K
- Related Work Writing1.7K
- Table Generation1.7K
- Self Review1.7K
- Slide Generation1.7K
- Paper Compilation1.7K
- Atomic Decomposition1.6K
- Paper To Code1.6K
- Experiment Code1.6K
- Paper Assembly1.6K
- Symbolic Equation1.6K
- Excalidraw Skill1.6K
- Literature Review4.1K
- Literature Search2.7K
- Figure Generation2.3K
- Latex Formatting2.3K
- Backward Traceability2.3K