proofread-manuscript
Exhaustively audit a medical manuscript for language, scientific consistency, citation support, tables and figures, journal compliance, and hidden revisions.
Skill by research-consultancy
Install
Works with Claude Code, Claude apps, Codex, Cursor, Gemini CLI, GitHub Copilot, VS Code, OpenCode, Goose, Windsurf. Read the repository before you give any tool access to your data.
npx agentmarket install skill/research-consultancy-proofread-manuscript
Asks which of your tools to add it to (Claude Code, Codex, Cursor, VS Code, Windsurf, Gemini CLI, Claude Desktop) and shows the change first. See https://agentmart.dev/cli.
Get the weekly diff
The weekly diff: one email a week with new agent tools, notable updates and grade changes, plus security alerts for tools you follow. Double opt-in, one-click unsubscribe.
About
Use cases: security, writing, research
Reviews
Write a reviewNo reviews yet. Installed it? Reviews come from verified installers only. How reviews work
Permissions
What this skill can do and what it asks for, from its SKILL.md. Checked Oct 25, 2026.
- Tools
- No tools found
- Secrets
- None asked for
- Install scripts
- None found
Network hosts it talks to 1
codeload.github.com· found in install command
Files it touches
~/.claude/skills/proofread-manuscript
What's inside
- Skill name
proofread-manuscript- Description
- Exhaustively audit a medical manuscript for language, scientific consistency, citation support, tables and figures, journal compliance, and hidden revisions. Use for proofreading, full pre-submission review, or revision-package verification.
- License
- MIT
- Instructions
- 35 lines in SKILL.md · view on GitHub
Files (3)
- SKILL.md
- openai.yaml · agents/
- checklist.md · references/
SKILL.md (first lines)
# Proofread a Medical Manuscript Run a hostile-reader preflight adapted from the thorough manuscript review. Preserve the author's scientific meaning while finding every error that could weaken trust or block submission. ## Inventory and scope Classify every input: manuscript, supplement, tables or figures, analysis output, cover letter, response letter, or journal instructions. Resolve ambiguous file roles before selecting the clean manuscript. Establish the target journal and whether the user wants a findings report, an edited file, or both. State which checks cannot run when a source file, analysis output, or target journal is absent. Read the applicable document/PDF/spreadsheet skill before extraction. Read every section, table, footnote, legend, reference, and supplement in full. For DOCX files, inspect the OOXML as well as rendered text so tracked insertions, deletions, and comments remain visible. Render document pages when layout affects the judgment. Inventory is complete when every provided file has a role and every requested review surface is accessible. ## Apply the audit Read [references/checklist.md](references/checklist.md) completely, then work through every applicable item. Re-derive arithmetic and trace repeated statistics across the abstract, text, tables, figures, supplement, and analysis output. Use the model-invoked `pubmed` skill and primary full text to verify important cited claims. If a response letter is present, match each claimed revision and quoted passage to the current manuscript. When a target journal is named, retrieve its current official author instructions and compare exact limits, structure, declarations, reference style, and submission-file requirements. Apply edits only when authorized. Keep technical terms, effect direction, denominators, uncertainty, citations, and author voice intact. Flag scientifically ambiguous passages for author decision rather than silently choosing a meaning. For a scoped line edit, apply every language check and identify which broader checks were outside scope. For a full review, the audit is complete only when every checklist item is verified, reported as a finding, or explicitly marked uncheckable. ## Deliver findings Group findings by severity: - **Critical**: factually wrong, unsupported, submission-blocking, or hidden tracked content. - **Major**: likely reviewer objection, material ambiguity, or cross-document inconsistency. - **Minor**: grammar, style, formatting, or polish. For each finding give the location, a short quote, the problem, and a specific fix. Separate required corrections from discretionary editorial suggestions. For a full review, add only material, non-duplicative editorial recommendations that strengthen the paper beyond correctness; omit this section when none are warranted. End with a coverage note listing passed checks and checks that could not be performed. If editing a file, preserve the original, return the corrected artifact, and summarize material changes.
From research-consultancy/rc-skills, MIT.
More from research-consultancy/rc-skills
- 0.512score
pubmed
research-consultancy
Search and verify biomedical literature in PubMed.
SkillCFreshness: C★ 2Claude Code +9 - 0.507score
domain-modeling
research-consultancy
Build and sharpen a medical research project's domain model.
SkillCFreshness: C★ 2Claude Code +9 - 0.506score
screen-pubmed-abstracts
research-consultancy
Screen a PubMed plain-text export for a systematic review or meta-analysis and produce a balanced CSV shortlist.
SkillCFreshness: C★ 2Claude Code +9 - 0.502score
research
research-consultancy
Investigate a medical research question against high-trust primary sources and capture the findings as a Markdown file in the repo.
SkillCFreshness: C★ 2Claude Code +9 - 0.501score
grill-meta-analysis-topic
research-consultancy
Validate a proposed meta-analysis topic against the published evidence.
SkillCFreshness: C★ 2Claude Code +9 - 0.501score
build-pubmed-search
research-consultancy
Build and validate a PubMed search string for a meta-analysis.
SkillCFreshness: C★ 2Claude Code +9 - 0.501score
teach
research-consultancy
Teach the user a medical research skill or concept, within this workspace.
SkillCFreshness: C★ 2Claude Code +9 - 0.477score
grilling
research-consultancy
Grill the user relentlessly about a plan, decision, or idea.
SkillCFreshness: C★ 2Claude Code +9
Signals
- Stars
- 2
- Forks
- 0
- Open issues
- 0
- Last commit (this folder)
- Jul 21, 2026 (3 months ago)
From GitHub (fetched Oct 24, 2026).
Details
- License
- MIT
- Website
- research-consultancy.org/
- First seen
- Oct 24, 2026
- Last checked
- Oct 24, 2026
- Source
- GitHubgithub-graphql
More from research-consultancy
- 0.512score
pubmed
research-consultancy
Search and verify biomedical literature in PubMed.
SkillCFreshness: C★ 2Claude Code +9 - 0.507score
domain-modeling
research-consultancy
Build and sharpen a medical research project's domain model.
SkillCFreshness: C★ 2Claude Code +9 - 0.506score
screen-pubmed-abstracts
research-consultancy
Screen a PubMed plain-text export for a systematic review or meta-analysis and produce a balanced CSV shortlist.
SkillCFreshness: C★ 2Claude Code +9 - 0.502score
research
research-consultancy
Investigate a medical research question against high-trust primary sources and capture the findings as a Markdown file in the repo.
SkillCFreshness: C★ 2Claude Code +9 - 0.501score
grill-meta-analysis-topic
research-consultancy
Validate a proposed meta-analysis topic against the published evidence.
SkillCFreshness: C★ 2Claude Code +9 - 0.501score
build-pubmed-search
research-consultancy
Build and validate a PubMed search string for a meta-analysis.
SkillCFreshness: C★ 2Claude Code +9
Cite this page
proofread-manuscript skill. Agent Mart. https://agentmart.dev/skills/research-consultancy-proofread-manuscript (last updated 2026-10-24)