academic-paper-polish
Skill56 starsChanged 3 months agoMITView on GitHub
Polish academic and research writing for clarity, structure, terminology, argumentation, and cautious claims without inventing evidence or citations.
In this repository34 other files it gives its agents.
- academic-pptxSkill
- academic-slidesSkill
- academic-writing-styleSkill
- analytics-data-analysisSkill
- chart-imageSkill
- content-analysisSkill
- content-research-writerSkill
- copywritingSkill
- creative-writingSkill
- dashboard-creatorSkill
- data-analyzerSkill
- deep-researchSkill
- document-converter-suiteSkill
- docxSkill
- domain-name-brainstormerSkill
- finance-news-analysisSkill
- finance-skillsSkill
- frontend-designSkill
- image-analyzerSkill
- imageSkill
- markdown-converterSkill
- natural-writingSkill
- netlify-deploySkill
- notion-infographicSkill
- pdfSkill
- pptxSkill
- rylai-pptSkill
- seoSkill
- skill-seekersSkill
- summarizationSkill
- ui-designerSkill
- video-generationSkill
- videoSkill
- xlsxSkill
The file
We split this skill into the rules it gives an agent
3 rules. About 0 are common, 3 are distinctive, and 0 are very specific to this project.
≈0
Common · estimate
Many files like this have a rule of this kind.
≈3
Distinctive · estimate
This author's own choices. Worth a look.
0
Very specific
Tied to their project's names, files or tools. Probably skip.
- Common
- Distinctive
- Very specific
- Distinctive: line 25
Check tools, packages, credentials, network access, and runtime capabilities before execution.
- Distinctive: line 48
Do not fabricate experiments, results, references, reviewer comments, or statistical significance.
- Distinctive: line 50
Keep author voice when the user supplies a style sample.
≈ “Common” is an estimate: at least 1 in 5 of the 350,495 skill files we read have a rule of the same kind, not the same words. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.
Files
Rylai Codex-Hermes-Claude Edition | Original portable workflow by Rylai
Runtime Compatibility
- Codex: install under
~/.agents/skills/academic-paper-polish. - Hermes: install under
~/.hermes/skills/academic-paper-polishor expose the bundle throughskills.external_dirs. - Claude Code: install under
~/.claude/skills/academic-paper-polishor<project>/.claude/skills/academic-paper-polish. - Claude.ai and Cowork: upload and enable the matching per-skill ZIP.
- Resolve bundled files relative to this skill directory; do not depend on paths from another machine.
- Check tools, packages, credentials, network access, and runtime capabilities before execution.
Academic Paper Polish
Improve an academic draft without changing its scientific meaning.
Workflow
- Identify the field, venue, audience, manuscript section, and requested level of editing.
- Preserve claims, equations, variable names, citations, and technical terminology.
- Improve argument order, paragraph logic, transitions, concision, and hedging.
- Flag claims that need evidence instead of inventing sources.
- Return either tracked suggestions, a revised passage, or both, according to the request.
- Perform a final consistency check for abbreviations, tense, terminology, figure references, and citation style.
Bundled References
references/section-phrases.md: section-specific rhetorical patterns.references/vocabulary.md: precise academic wording and weak-phrase replacements.references/ai-polish.md: reusable editing prompts and verification passes.
Boundaries
- Do not fabricate experiments, results, references, reviewer comments, or statistical significance.
- Distinguish language polishing from substantive scientific review.
- Keep author voice when the user supplies a style sample.
Does it work?
Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.
No reviews yet
People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.
- It worked
- Partly
- It didn't
Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.
Your trail
Files you open will collect here, so you can find them again.
Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.
Now do this for your own.
Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.

