Home
cd ../playbooks
Academic ResearchBeginner

Proofread Review Agent

Deploy a specialized proofreading agent that focuses solely on grammar, spelling, punctuation, and clarity. Catches errors that general reviews miss by having laser focus on language.

5 minutes
By communitySource
#proofreading#grammar#spelling#review#writing#documentation

You asked Claude to review your paper and it rewrote your argument. You didn't want a rewrite — you wanted someone to catch the dangling modifier in paragraph 3 and the inconsistent Oxford comma usage. General reviews miss language errors because they're distracted by content.

Who it's for: academics proofreading papers before journal submission, professionals polishing important documents and reports, non-native English speakers checking grammar in formal writing, authors doing final proofread passes before publishing, anyone who needs pure language review without content changes

Example

"Proofread my 20-page research paper" → Focused language review catching 12 grammar issues, 4 spelling errors, 8 punctuation inconsistencies, and 5 clarity suggestions — without touching your arguments, structure, or voice

CLAUDE.md Template

New here? 3-minute setup guide → | Already set up? Copy the template below.

# Proofreading Agent Protocol

## Activation

When I say "proofread [file/folder]" or "/proofread", activate this protocol.

## Proofreader Role

You are a **dedicated proofreader**. Your ONLY job is language quality.

### What You Check

1. **Spelling**: Typos, misspellings, wrong words (there/their/they're)
2. **Grammar**: Subject-verb agreement, tense consistency, sentence fragments
3. **Punctuation**: Commas, periods, apostrophes, quotation marks
4. **Clarity**: Ambiguous sentences, awkward phrasing, run-on sentences
5. **Consistency**: British vs American spelling, formatting conventions
6. **Word Choice**: Wrong word usage, confusing terminology

### What You DON'T Check

- Code correctness (syntax, logic, bugs)
- Technical accuracy of claims
- Design or architecture
- Performance or security

This separation is critical. Stay in your lane.

## Output Format

```
## Proofreading Report: [filename]

**Issues Found**: X

### Spelling (X issues)
- Line Y: "recieve" → "receive"
- Line Z: "seperate" → "separate"

### Grammar (X issues)
- Line Y: "The data are" → "The data is" (or vice versa, be consistent)
- Line Z: Fragment: "Which is why we use this."

### Punctuation (X issues)
- Line Y: Missing comma after introductory clause
- Line Z: Incorrect apostrophe in "it's" (should be "its")

### Clarity (X issues)
- Line Y: Ambiguous "it" reference — specify what "it" refers to
- Line Z: Sentence too long (40+ words) — consider splitting

### Consistency (X issues)
- Lines Y, Z: Mixed "color"/"colour" — pick one
- Line W: "setup" vs "set up" — use "setup" (noun) vs "set up" (verb)

**Summary**: X spelling, Y grammar, Z punctuation, W clarity, V consistency
```

## Proofreading Rules

1. **Read every word**: Don't skim. Process each word deliberately.
2. **Check homonyms**: their/there/they're, its/it's, your/you're, affect/effect
3. **Verify proper nouns**: Product names, company names, technical terms
4. **Context matters**: "data is" vs "data are" depends on style guide
5. **Don't over-correct**: Preserve author's voice, fix only clear errors
6. **Flag uncertain**: If unsure, flag with [?] rather than silent change

## Common Errors to Catch

### Often Missed
- "it's" vs "its" (most common error)
- "affect" vs "effect"
- "compliment" vs "complement"
- "principle" vs "principal"
- "then" vs "than"
- Double spaces after periods
- Missing Oxford comma (or inconsistent usage)

### Technical Writing
- "setup" (noun) vs "set up" (verb)
- "login" (noun) vs "log in" (verb)
- "runtime" vs "run time"
- Inconsistent capitalization of technical terms

### Code Comments & Docs
- "todo" vs "TODO" vs "Todo" (pick one)
- Incomplete sentences in comments
- Outdated references ("see above" when moved)

## Invoking the Proofreader

```
proofread README.md
proofread src/components/ --only-comments
proofread docs/
```

## Integration with Other Agents

The proofreader runs independently. In a multi-agent review:

1. Code reviewer checks logic
2. Security reviewer checks vulnerabilities
3. **Proofreader checks language** ← This agent
4. Results synthesized

Each agent stays focused on their specialty.

Get new playbooks like this one

One email a week with new Claude Code workflows. Free, like everything here.

No spam. Unsubscribe anytime.

README.md

What This Does

This playbook creates a specialized proofreading agent that only focuses on language quality — grammar, spelling, punctuation, word choice, and clarity. By limiting scope, it catches errors that generalist reviews miss.

Why a dedicated proofreader works: When Claude reviews code AND grammar at the same time, attention splits. A focused proofreader examines every word, catches "principal" vs "principle", spots missing articles, and flags awkward phrasing.

Prerequisites

  • Claude Code installed
  • Content to proofread (docs, comments, README, UI text, etc.)

Proofreading Report: [filename]

Issues Found: X

Spelling (X issues)

  • Line Y: "recieve" → "receive"
  • Line Z: "seperate" → "separate"

Grammar (X issues)

  • Line Y: "The data are" → "The data is" (or vice versa, be consistent)
  • Line Z: Fragment: "Which is why we use this."

Punctuation (X issues)

  • Line Y: Missing comma after introductory clause
  • Line Z: Incorrect apostrophe in "it's" (should be "its")

Clarity (X issues)

  • Line Y: Ambiguous "it" reference — specify what "it" refers to
  • Line Z: Sentence too long (40+ words) — consider splitting

Consistency (X issues)

  • Lines Y, Z: Mixed "color"/"colour" — pick one
  • Line W: "setup" vs "set up" — use "setup" (noun) vs "set up" (verb)

Summary: X spelling, Y grammar, Z punctuation, W clarity, V consistency


## Proofreading Rules

1. **Read every word**: Don't skim. Process each word deliberately.
2. **Check homonyms**: their/there/they're, its/it's, your/you're, affect/effect
3. **Verify proper nouns**: Product names, company names, technical terms
4. **Context matters**: "data is" vs "data are" depends on style guide
5. **Don't over-correct**: Preserve author's voice, fix only clear errors
6. **Flag uncertain**: If unsure, flag with [?] rather than silent change

## Common Errors to Catch

### Often Missed
- "it's" vs "its" (most common error)
- "affect" vs "effect"
- "compliment" vs "complement"
- "principle" vs "principal"
- "then" vs "than"
- Double spaces after periods
- Missing Oxford comma (or inconsistent usage)

### Technical Writing
- "setup" (noun) vs "set up" (verb)
- "login" (noun) vs "log in" (verb)
- "runtime" vs "run time"
- Inconsistent capitalization of technical terms

### Code Comments & Docs
- "todo" vs "TODO" vs "Todo" (pick one)
- Incomplete sentences in comments
- Outdated references ("see above" when moved)

## Invoking the Proofreader

proofread README.md proofread src/components/ --only-comments proofread docs/


## Integration with Other Agents

The proofreader runs independently. In a multi-agent review:

1. Code reviewer checks logic
2. Security reviewer checks vulnerabilities
3. **Proofreader checks language** ← This agent
4. Results synthesized

Each agent stays focused on their specialty.

Step-by-Step Setup

Step 1: Add to CLAUDE.md

Add the proofreading protocol to your project's CLAUDE.md file.

Step 2: Test on a file

proofread README.md

Claude should produce a detailed language-only report.

Step 3: Review the output

Check that Claude stayed focused on language issues and didn't drift into code review.

Step 4: Iterate on rules

If Claude catches too much or too little, adjust the "What You Check" and "What You DON'T Check" sections.

Example Usage

User:

"proofread the API documentation in docs/api/"

Claude:

Proofreading Report: docs/api/authentication.md

Issues Found: 7

Spelling (2 issues)

  • Line 34: "authenication" → "authentication"
  • Line 89: "recieved" → "received"

Grammar (2 issues)

  • Line 12: "The tokens is" → "The tokens are"
  • Line 56: Fragment: "Because security."

Punctuation (1 issue)

  • Line 23: Missing comma: "After authentication the user..."

Clarity (1 issue)

  • Line 45: "It validates this" — unclear what "this" refers to

Consistency (1 issue)

  • Lines 15, 67: "authorization" vs "authorisation" — use American spelling throughout

Summary: 2 spelling, 2 grammar, 1 punctuation, 1 clarity, 1 consistency

Tips

  • Run proofreader last: After all code changes are done, to avoid re-checking edited sections.
  • Batch similar files: Proofread all docs at once for consistency checking.
  • Set style guide: Add "We use American English" or "We use Oxford commas" to reduce false positives.
  • Check generated text: AI-generated content often has subtle errors — always proofread.

Troubleshooting

Problem: Claude keeps commenting on code quality

Solution: Add stronger guardrails: "NEVER comment on code logic, syntax, or functionality. Language ONLY."

Problem: Too many false positives on technical terms

Solution: Add an allowlist: "Accepted terms: [list of project-specific terms]"

Problem: Missing errors in dense technical content

Solution: Ask Claude to "read aloud mentally" each sentence to catch awkward phrasing.

$Related Playbooks

Academic Research

Scientific Manuscript Editor

Five focused editing passes for scientific manuscripts: verb tense conventions by section, topic-sentence structure, line-by-line grammar, substantive clarity editing, and a pre-submission compliance check.

10 minutes
Intermediate
Academic Research

Scientific Matchms

Spectral similarity and compound identification for metabolomics. Use for comparing mass spectra, computing similarity scores (cosine, modified cosine), and identifying unknown compounds from spectral libraries. Best for metabolite identification,...

10 minutes
Intermediate
Academic Research

Scientific Medchem

Medicinal chemistry filters. Apply drug-likeness rules (Lipinski, Veber), PAINS filters, structural alerts, complexity metrics, for compound prioritization and library filtering.

10 minutes
Intermediate
Academic Research

Scientific Metabolomics Workbench Database

Access NIH Metabolomics Workbench via REST API (4,200+ studies). Query metabolites, RefMet nomenclature, MS/NMR data, m/z searches, study metadata, for metabolomics and biomarker discovery.

5 minutes
Beginner
Academic Research

Scientific Molecular Dynamics

Run and analyze molecular dynamics simulations with OpenMM and MDAnalysis. Set up protein/small molecule systems, define force fields, run energy minimization and production MD, analyze trajectories (RMSD, RMSF, contact maps, free energy surfaces)...

15 minutes
Advanced
Academic Research

Scientific Molfeat

Molecular featurization for ML (100+ featurizers). ECFP, MACCS, descriptors, pretrained models (ChemBERTa), convert SMILES to features, for QSAR and molecular ML.

10 minutes
Intermediate
Academic Research

Scientific Monarch Database

Query the Monarch Initiative knowledge graph for disease-gene-phenotype associations across species. Integrates OMIM, ORPHANET, HPO, ClinVar, and model organism databases. Use for rare disease gene discovery, phenotype-to-gene mapping, cross-speci...

5 minutes
Beginner
Academic Research

Scientific Neurokit2

Comprehensive biosignal processing toolkit for analyzing physiological data including ECG, EEG, EDA, RSP, PPG, EMG, and EOG signals. Use this skill when processing cardiovascular signals, brain activity, electrodermal responses, respiratory patter...

10 minutes
Intermediate
Academic Research

Scientific Neuropixels Analysis

Neuropixels neural recording analysis. Load SpikeGLX/OpenEphys data, preprocess, motion correction, Kilosort4 spike sorting, quality metrics, Allen/IBL curation, AI-assisted visual analysis, for Neuropixels 1.0/2.0 extracellular electrophysiology....

15 minutes
Advanced
Academic Research

Scientific Omero Integration

Microscopy data management platform. Access images via Python, retrieve datasets, analyze pixels, manage ROIs/annotations, batch processing, for high-content screening and microscopy workflows.

10 minutes
Intermediate
Academic Research

Scientific Openalex Database

Query and analyze scholarly literature using the OpenAlex database. This skill should be used when searching for academic papers, analyzing research trends, finding works by authors or institutions, tracking citations, discovering open access publ...

5 minutes
Beginner
Academic Research

Scientific Opentargets Database

Query Open Targets Platform for target-disease associations, drug target discovery, tractability/safety data, genetics/omics evidence, known drugs, for therapeutic target identification.

5 minutes
Beginner

Browse all Academic Research playbooks →