Agent skill

Grammar and Flow Checker

by phuryn in phuryn/pm-skills

Reviews a draft for grammar, logic and flow problems and returns located, prioritized fix suggestions without rewriting the whole text.

MITAuto-check passedWriting & Content

Install Grammar and Flow Checker

skills CLI
$ npx skills add phuryn/pm-skills --skill grammar-check -a claude-code

Project install by default; add -g for ~/.claude/skills/.

GitHub CLI
$ gh skill install phuryn/pm-skills grammar-check --agent claude-code

Project scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).

Manual copy
$ git clone --depth 1 https://github.com/phuryn/pm-skills.git skills-src && mkdir -p .claude/skills && cp -r skills-src/pm-toolkit/skills/grammar-check .claude/skills/grammar-check && rm -rf skills-src

Use ~/.claude/skills/ instead of .claude/skills for a personal install. The folder must contain SKILL.md.

Claude Code skills documentation · loads skills from .claude/skills/

Facts

Skill name
grammar-check
GitHub stars
27k
Token cost
~2.4k tokens
SKILL.md length
1,291 words
Files
1
Skills in repo
67
Repo updated
First seen
Licence
MIT

At a glance

Reviews a draft for grammar, logic and flow problems and returns located, prioritized fix suggestions without rewriting the whole text.

  • Works in 5 steps: Understand Context → Scan for Errors → Categorize Errors → …
  • Proofreading a draft for grammar and clarity before sending it
  • SKILL.md covers Purpose, Input Arguments, Process and Error Categories and Examples, plus 5 more sections
  • Instructions only: no scripts, shell commands, URLs or credentials in SKILL.md

What it does

The skill takes the text's stated objective, such as persuading investors or explaining a product to new users, and reads the draft once to catalogue three kinds of problems: grammar errors like spelling, punctuation and tense consistency, logical errors such as contradictions or unsupported claims, and flow errors like choppy transitions, redundancy or vague pronouns.

For each problem found it reports the location in the text, what is wrong, a suggested fix, and the reasoning behind that fix, then sorts the whole list so grammar or logic errors that confuse the reader come before flow issues that only hurt readability, with purely stylistic polish last. Worked examples pair a specific error, such as a missing apostrophe in a contraction, with its correction, and the skill is explicit that it edits around problems rather than rewriting the document from scratch.

When your agent uses it

  • Proofreading a draft for grammar and clarity before sending it
  • Reviewing marketing copy or documentation for logical gaps
  • Getting prioritized, located fix suggestions instead of a full rewrite

Example prompts

  • “Check this investor email for grammar and logic issues before I send it.”
  • “Review this product announcement draft for flow problems and prioritize the fixes.”
  • “Find the grammar errors in this paragraph without rewriting the rest of it.”

Workflow steps

5 steps, taken from the step headings in SKILL.md.

  1. Understand Context
  2. Scan for Errors
  3. Categorize Errors
  4. Create Fix Suggestions
  5. Prioritize

What it can do on your machine

Read from SKILL.md and the folder at commit 8607e3b. It shows what the files ask for, not the result of running them.

  • Tool permissions

    Pre-approves nothing: there is no allowed-tools line, so your agent's usual permission prompts apply.

    From allowed-tools in the SKILL.md frontmatter.

  • Runs code

    No scripts in the folder and no shell commands in SKILL.md.

    From the folder's file list and the shell code blocks in SKILL.md.

  • Network

    No URLs in SKILL.md.

    From URLs in SKILL.md, links to its own repository left out.

  • Credentials

    Names no API keys, tokens, secrets or passwords.

    From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.

Context cost

Grammar and Flow Checker loads about 2.4k tokens when it runs. Until then it costs about 51 tokens; SKILL.md has 1,291 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it
~51
When it runs · the whole SKILL.md, loaded when a task matches
~2.4k

Estimates: characters ÷ 4, the usual rule of thumb; real counts depend on the model's tokenizer. Scripts and assets cost tokens only if the agent reads them.

Safety

Auto-check passed

The automated check found no risky patterns in SKILL.md.

Automated static check — not a guarantee. Review scripts before installing. It scans the text of SKILL.md for risky patterns (piping downloads into a shell, reading credential files, hidden Unicode, destructive commands); files beside SKILL.md are not scanned.

SKILL.md

The full file from phuryn/pm-skills at commit 8607e3b, republished under its MIT licence (© phuryn). 1,291 words, ~2,419 tokens.

Download SKILL.mdSave it as .claude/skills/grammar-check/SKILL.md (or your agent's skills folder).
name
grammar-check
description
Identify grammar, logical, and flow errors in text and suggest targeted fixes without rewriting the entire text. Use when proofreading content, checking writing quality, or reviewing a draft.

Grammar and Flow Checking

You are an expert copyeditor and writing specialist. Your role is to identify grammar, logical, and flow errors in text, then provide clear, actionable fix suggestions without rewriting the entire document.

Purpose

Analyze text for grammar, logical, and flow errors. Provide specific, focused suggestions on how to fix each issue. Focus on clarity, correctness, and readability.

Input Arguments

  • $OBJECTIVE: What is the intended purpose or goal of the text? (e.g., "persuade investors to fund our Series A," "explain product features to new users," "communicate company values to employees")
  • $TEXT: The text to review

Process

Step 1: Understand Context
  • Note the objective: Is this marketing copy, technical documentation, a presentation, an email, social media content?
  • Identify the target audience: Experts, general public, stakeholders, customers?
  • Consider tone: Formal, casual, authoritative, friendly?
Step 2: Scan for Errors

Read through the text once, identifying:

  • Grammar errors: Spelling, punctuation, subject-verb agreement, tense consistency, modifier placement
  • Logical errors: Contradictions, unsupported claims, unclear cause-and-effect, incomplete thoughts
  • Flow errors: Choppy transitions, unclear organization, redundancy, passive voice overuse, vague pronouns, awkward phrasing
Step 3: Categorize Errors

Organize findings by type:

  1. Grammar (spelling, punctuation, syntax)
  2. Logic (clarity, coherence, reasoning)
  3. Flow (transitions, sentence structure, readability, tone consistency)
Step 4: Create Fix Suggestions

For each error, provide:

  • Location: Where in the text (e.g., "Paragraph 3, sentence 2")
  • Error identified: What's wrong
  • Fix suggested: How to correct it
  • Rationale: Why this matters (clarity, grammar rule, flow, tone)
Step 5: Prioritize

Flag highest-impact issues first:

  • Critical: Grammar or logic errors that confuse readers
  • Important: Flow issues that hurt readability or persuasiveness
  • Minor: Stylistic suggestions or polish

Error Categories and Examples

Grammar Errors

Spelling

  • Example error: "buisness" instead of "business"
  • Fix: Correct spelling to "business"

Punctuation

  • Example error: "Lets get started" (apostrophe missing in "Let's")
  • Fix: Use "Let's" (contraction of "let us")
  • Example error: Run-on sentence with multiple independent clauses not connected properly
  • Fix: Break into separate sentences or connect with a conjunction/semicolon

Subject-Verb Agreement

  • Example error: "The team are working" (treating singular noun as plural)
  • Fix: "The team is working" (team is a collective noun, treated as singular in US English)

Tense Consistency

  • Example error: "We launched the product last month and are seeing great results. Users report high satisfaction and prefer our solution." (mix of past and present)
  • Fix: Keep tense consistent based on timeframe

Pronoun Clarity

  • Example error: "The manager told the designer that she should revise the mockups." (Unclear if "she" refers to manager or designer)
  • Fix: Use name or restructure: "The manager told the designer to revise the mockups."

Modifier Placement

  • Example error: "After reviewing the proposal, the decision seemed obvious." (Who reviewed? Unclear.)
  • Fix: "After reviewing the proposal, we saw the decision was obvious."

Logical Errors

Unsupported Claims

  • Example error: "Our product is the best on the market because customers love it."
  • Fix: Provide evidence: "Our product has a 4.8-star rating from 2,000+ customers and achieved 40% market share in the SMB segment."

Contradictions

  • Example error: Text says "We prioritize user privacy" but also "We share user data with 50+ third parties."
  • Fix: Clarify or reconcile the statements with detail

Incomplete Logic

  • Example error: "The feature was launched in Q3, so adoption increased." (No proof of causation)
  • Fix: "The feature was launched in Q3; adoption increased 25% in the following month, driven by improved onboarding."

Vague Claims

  • Example error: "Our solution saves time and money."
  • Fix: Be specific: "Our solution reduces onboarding time from 2 hours to 15 minutes and cuts operational costs by 30%."

Flow Errors

Weak Transitions

  • Example error: Paragraphs jump between topics without connection
  • Fix: Add transitional phrases: "In addition to this benefit," "However," "As a result," "This leads to..."

Choppy Sentences

  • Example error: "We launched the product. We got great feedback. We iterated quickly. We improved the feature."
  • Fix: Combine related ideas: "After launching the product, we received great feedback and iterated quickly to improve the feature."

Passive Voice Overuse

  • Example error: "The decision was made by the team to move forward with the strategy that was agreed upon." (Passive, wordy)
  • Fix: "The team decided to move forward with the agreed strategy." (Active, clearer)

Unclear Pronoun Reference

  • Example error: "We met with the vendor about their API. It was complicated, so we decided against it." (What is "it"? The API? The vendor? The meeting?)
  • Fix: "We met with the vendor about their API, which proved too complicated, so we chose another solution."

Redundancy

  • Example error: "Our solution is simple and easy to use; it's straightforward and uncomplicated."
  • Fix: "Our solution is simple and easy to use." (Remove redundant synonyms)

Tone Inconsistency

  • Example error: Mix of formal ("We respectfully submit our proposal") and casual ("This is gonna blow your mind") in the same document
  • Fix: Choose consistent tone throughout

Show full SKILL.md (501 more words)Show less

Output Format

Do NOT include the corrected text in full. Instead, provide:

[ERROR SUMMARY] Count of total errors found, organized by category:

  • X grammar errors
  • X logical errors
  • X flow errors

[FIXES BY CATEGORY] List all errors with fixes as bullet points. For each:

  • Location: Where in the text (paragraph, sentence)
  • Error: What's wrong (with quote from text if helpful)
  • Fix: How to improve it
  • Why: Brief rationale (clarity, grammar, engagement, etc.)

[PRIORITY FIXES] Highlight the 3-5 most important changes that will have the biggest impact on readability and clarity.

[TONE AND OBJECTIVE ALIGNMENT] Brief assessment of how well the text achieves its objective ($OBJECTIVE) and whether tone aligns with purpose. Suggest if tone adjustments are needed.


Important Guidelines

  • Tone: Use straightforward, professional language. Be encouraging about the writing.
  • Focus on clarity: Grammar matters, but clarity is paramount. A sentence can be grammatically correct but still confusing.
  • Use primary-school language: Explain fixes in simple terms. Don't assume the reader knows grammar terminology.
  • Don't rewrite: Provide specific fix suggestions, not rewrites of entire paragraphs. Let the author maintain their voice.
  • Include rationale: Explain why each fix matters. This helps the author understand the principle, not just the rule.
  • Be specific: "Clearer" isn't helpful; say "Vague pronoun reference; 'it' could mean the API or the vendor's proposal. Change to: 'The vendor's API proved too complex.'"
  • Consider audience: Fixes should match the intended audience and context.

Checklist for Review

Use this checklist to ensure thorough review:

  • Check for spelling errors (use spell-check, manual review)
  • Check for punctuation issues (missing commas, apostrophes, periods)
  • Verify subject-verb agreement throughout
  • Check tense consistency (past, present, future should align)
  • Identify vague pronouns that could be clearer
  • Look for sentences that could be combined or split for better flow
  • Identify passive voice; flag if overused
  • Check for unsupported claims; ask "Is this proven?" or "Do we have evidence?"
  • Look for contradictions between statements
  • Check transitions between paragraphs; are they smooth?
  • Verify tone consistency with objective
  • Look for redundant words or phrases
  • Check for overly complex sentences; can they be simplified?
  • Verify that claims support the stated objective

Examples of Effective Feedback

Poor feedback: "This sentence is unclear." Good feedback: "The pronoun 'it' in 'the vendor's API, but it was too complex' is vague. Change to 'the vendor's API was too complex' for clarity."

Poor feedback: "Fix the grammar here." Good feedback: "Subject-verb disagreement: 'The data show' not 'The data shows.' Collective nouns like 'data' take plural verbs in American English."

Poor feedback: "This doesn't flow well." Good feedback: "Choppy transitions between paragraphs. Add: 'Beyond cost savings, our solution also improves employee satisfaction.' This connects the cost discussion to the next point about employee impact."


When to Suggest No Change

Not every phrase needs fixing. Leave alone:

  • Intentional style choices (short, punchy sentences for impact)
  • Correct informal language (contractions, conversational tone in casual contexts)
  • Rhetorical devices (alliteration, parallel structure for emphasis)
  • Personal voice and style (unless it undermines clarity or objective)

Focus on clarity and correctness, not perfection or style uniformity.

© phuryn, MIT. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file

Files

Just SKILL.md in pm-toolkit/skills/grammar-check of phuryn/pm-skills.

Open the folder on GitHubat commit 8607e3b

Compare with similar skills

Grammar and Flow Checker next to the 5 skills that share the most tags, products or categories with it. Stars are the repository's; “used in” counts other GitHub owners with a copy.

Grammar and Flow Checker compared with similar skills
SkillStarsUsed inTokensAuto-checkLicenceRepo updated
Grammar and Flow Checker this skillphuryn/pm-skills27k—~2.4kAutomated safety check: PassMIT
User-Facing Text Cleanupguillaumemeyer/watermarks-remover24k—~3.5kAutomated safety check: PassMIT
Story Multi-Perspective Reviewzenstory-ai/oh-story-claudecode7.4k3 repos~3kAutomated safety check: PassMIT
Chinese Text Humanizerop7418/Humanizer-zh19k—~2kAutomated safety check: PassMIT
Baoyu TranslateJimLiu/baoyu-skills26k1 repos~3.9kAutomated safety check: PassMIT
Natural Japanese Business Writingcoji/natural-japanese1.9k—~2.1kAutomated safety check: PassMIT

Similar skills

  • User-Facing Text Cleanup

    guillaumemeyer/watermarks-remover

    Audits prose for invisible Unicode characters and rewrites it while keeping facts, citations, code and required disclosures unchanged and the writer's voice intact.

    24k GitHub stars~3.5k tokensUpdated today
    Writing & ContentAuto-check passed
  • Story Multi-Perspective Review

    zenstory-ai/oh-story-claudecode

    Reviews Chinese web-novel text with several reviewer agents in parallel, falling back to a single-agent pass, and reports structure, character, prose and setting problems with fixes.

    7.4k GitHub starsUsed in 3 repos~3k tokens
    Writing & ContentAuto-check passed
  • Chinese Text Humanizer

    op7418/Humanizer-zh

    Edits Chinese articles, comments and documents to remove filler, repetition and template phrasing while keeping the facts, the level of certainty and the author's voice.

    19k GitHub stars~2k tokensUpdated 16 days ago
    Writing & ContentAuto-check passed
  • Baoyu Translate

    JimLiu/baoyu-skills

    Translates articles and files in quick, normal or refined mode, with a custom glossary, saved preferences and a review-and-polish workflow for publication quality.

    26k GitHub starsUsed in 1 repo~3.9k tokens
    Writing & ContentAuto-check passed
  • Writes and edits Japanese business documents so they read clearly and naturally, removes AI-sounding phrasing and can score how AI-like a text reads.

    1.9k GitHub stars~2.1k tokensUpdated 1 mo ago
    Writing & ContentAuto-check passed
  • Defensive Writing Editor

    lennney/stop-that-shit

    Cuts defensive disclaimers, stacked hedging and self-protective narration from proposals and summaries, keeping only limits that affect the reader's decision.

    2.5k GitHub starsUsed in 1 repo~1.2k tokens
    Writing & ContentAuto-check passed

More from phuryn/pm-skills

All 67 skills in this repo
  • Reviews a diff by anchoring on agreements between two sides of a boundary, forcing a concrete violating execution, and refuting each finding before reporting it.

    27k GitHub stars~3.6k tokensUpdated 25 days ago
    Auto-check passed
  • A/B Test Analysis

    phuryn/pm-skills

    Validates an experiment's setup, works out lift, p-value and confidence interval from A/B test data, and recommends whether to ship, extend or stop.

    27k GitHub stars~893 tokensUpdated 25 days ago
    Auto-check passed
  • Team OKR Brainstorm

    phuryn/pm-skills

    Drafts three alternative sets of team OKRs, each with an inspiring objective and measurable key results, tied to the company strategy you provide.

    27k GitHub stars~1.1k tokensUpdated 25 days ago
    Auto-check passed
  • Analyzes uploaded cohort data to compute retention curves and feature adoption trends, builds heatmaps and charts, and suggests qualitative follow-up research.

    27k GitHub stars~1.3k tokensUpdated 25 days ago
    Auto-check passed
  • Dummy Dataset Generator

    phuryn/pm-skills

    Generates realistic test datasets with custom columns, row counts and business constraints, output as CSV, JSON, SQL inserts or a runnable Python script.

    27k GitHub stars~983 tokensUpdated 25 days ago
    Auto-check passed
  • Builds a structured customer interview script with opening, warm-up, jobs-to-be-done exploration and wrap-up sections, following Mom Test rules against leading questions.

    27k GitHub stars~1.2k tokensUpdated 25 days ago
    Auto-check passed

Questions about Grammar and Flow Checker

What does Grammar and Flow Checker do?

Reviews a draft for grammar, logic and flow problems and returns located, prioritized fix suggestions without rewriting the whole text. The skill takes the text's stated objective, such as persuading investors or explaining a product to new users, and reads the draft once to catalogue three kinds of problems: grammar errors like spelling, punctuation and tense consistency, logical errors such as contradictions or unsupported claims, and flow errors like choppy transitions, redundancy or vague pronouns.

When should I use Grammar and Flow Checker?

Grammar and Flow Checker fits situations like: proofreading a draft for grammar and clarity before sending it; reviewing marketing copy or documentation for logical gaps; getting prioritized, located fix suggestions instead of a full rewrite.

How do I install Grammar and Flow Checker in Claude Code?

Run `npx skills add phuryn/pm-skills --skill grammar-check -a claude-code`. Or copy the skill folder (pm-toolkit/skills/grammar-check in phuryn/pm-skills) into .claude/skills/grammar-check in your project. Claude Code loads it when a task matches its description.

How do I install Grammar and Flow Checker in Codex?

Run `npx skills add phuryn/pm-skills --skill grammar-check -a codex`. Or copy the skill folder (pm-toolkit/skills/grammar-check in phuryn/pm-skills) into .agents/skills/grammar-check in your project. Codex loads it when a task matches its description.

Can I use Grammar and Flow Checker in Cursor, Gemini CLI or GitHub Copilot?

Cursor, Gemini CLI, GitHub Copilot and OpenCode also load SKILL.md folders. With the skills CLI, run `npx skills add phuryn/pm-skills --skill grammar-check -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/grammar-check, .gemini/skills/grammar-check, .github/skills/grammar-check and .opencode/skills/grammar-check in your project.

What does Grammar and Flow Checker need to run?

SKILL.md names no scripts, command-line tools or credentials: Grammar and Flow Checker is instructions for the agent only.

Does Grammar and Flow Checker access the network?

SKILL.md contains no URLs. Any network use would come from the scripts or tools the agent runs. This is read from the text; nothing was executed.

Is Grammar and Flow Checker safe to install?

Our automated static check of SKILL.md found no risky patterns, such as piping downloads into a shell, reading credential files or hidden Unicode. It is not a guarantee. Review the folder before installing.

What licence does Grammar and Flow Checker use?

Grammar and Flow Checker is published under the MIT licence (the repository's licence). It allows redistribution, so the full SKILL.md is shown on this page.

How many tokens does Grammar and Flow Checker use?

About 2.4k tokens (SKILL.md is roughly 9.7k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full.

What are the alternatives to Grammar and Flow Checker?

Skills that share tags, products or a category with Grammar and Flow Checker: User-Facing Text Cleanup (guillaumemeyer/watermarks-remover, 24k stars), Story Multi-Perspective Review (zenstory-ai/oh-story-claudecode, 7.4k stars), Chinese Text Humanizer (op7418/Humanizer-zh, 19k stars) and Baoyu Translate (JimLiu/baoyu-skills, 26k stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains Grammar and Flow Checker?

phuryn (a GitHub user) maintains it in phuryn/pm-skills, which has 26,845 GitHub stars. The repository holds 67 skills in this directory. The repository was last updated on September 14, 2026.

Source: phuryn/pm-skills on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.