
Scientific Manuscript Review
Takes your research manuscript through eight systematic passes, from extracting the core message to checking journal formatting compliance. Built around the IMRaD structure with specific templates for each section: the Introduction funnel (broad to gap to hypothesis), Results paragraphs (question, approach, finding, interpretation), and Discussion flow (findings to context to limitations). Catches common manuscript problems like buried gap statements, data dumps without interpretation, and overclaiming in discussions. Includes hedging language guidelines and a clarity checklist that verifies claims match evidence strength. Honestly, the structured approach is what makes this work. It stops you from doing vague holistic feedback and forces specific evaluation of whether each section does its job.
- skills.sh installs
- 484
- GitHub stars
- 193
- last updated
- Aug 21, 2026
Install
$ npx -y skills add lyndonkl/claude --skill scientific-manuscript-review --agent claude-codeInstalls into .claude/skills of the current project.
Files
Scientific Manuscript Review
Table of Contents
Related skills: Grant proposals → grant-proposal-assistant | Recommendation letters → academic-letter-architect | Emails → scientific-email-polishing
Core Principles
Seven foundational beliefs guiding manuscript review:
- Clarity over cleverness: Scientific clarity is more important than stylistic elegance
- Narrative shapes comprehension: Structure and story arc determine reader understanding
- Audience dictates tone: Expert vs. general audience requires different depth and framing
- Format signals credibility: Professional formatting reflects scientific rigor
- Claims require evidence: Strong assertions need strong data and appropriate hedging
- Each section has a job: Introduction sells the problem, Results show the data, Discussion interprets
- Constraints shape structure: Word limits and journal guidelines determine emphasis
Workflow
Sponsors
Details
- Repository
- github.com/lyndonkl/claude
- Categories
- Git & Pull Requests, Documentation, Code Review & Quality, Data Science & ML
- First seen
- Jun 3, 2026