writing_assistant

writing_assistant is a skill for Claude Code, Codex from mctar/skill-check. It costs 0 tokens per session (572 once invoked), scanned A, original, MIT.

A writing helper for drafting and editing prose, including emails, reports, academic papers, blog posts, and creative work. It checks language and helps keep a document’s style consistent.

In plain words
What is it for?
Use it to draft, edit, and polish documents, shorten unclear sentences, improve paragraph structure, and receive explanations or alternative wording for suggested changes.
Why use it?
It helps find grammar, spelling, punctuation, and clarity problems without replacing the writer’s personal style. It also makes long or uneven writing easier to read.

Skill for Claude CodeCodex

Install

Getting it into your agent

One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.

agentmods
npx agentmods add skills/mctar/skill-check/writing_assistant
Any agent
npx skills add mctar/skill-check --skill writing_assistant
Clone the repo
git clone --depth 1 https://github.com/mctar/skill-check

Made for: Claude Code, Codex.

Wrote this? Show the measurements

A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.

agentmods badge for writing_assistant

README.md
[![agentmods](https://agentmods.dev/badge/skills/mctar/skill-check/writing_assistant.svg)](https://agentmods.dev/skills/mctar/skill-check/writing_assistant)
Your own site
<a href="https://agentmods.dev/skills/mctar/skill-check/writing_assistant"><img src="https://agentmods.dev/badge/skills/mctar/skill-check/writing_assistant.svg" alt="Measured on agentmods" height="20"></a>
Per session 0 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 572 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
Origin original No closer match found in the catalogue.
Token cost

What it costs to keep this loaded

Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.

ModelPer sessionOnce invoked
Fable 5 $0.00000 $0.00572
Opus 5 $0.00000 $0.00286
Sonnet 5 $0.00000 $0.00114
Haiku 4.5 $0.00000 $0.00057

Measured 4d ago against content hash 7a4a73f3cd58, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

writing_assistant scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 4d ago.

A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.

Nothing flagged

None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.

tests/benign/writing_assistant/SKILL.md · 66 lines

How it starts

The opening of the file, as written. The whole thing — 66 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Writing Assistant Skill

You are a writing assistant that helps users improve their prose, check grammar, and maintain a consistent voice across documents.

Purpose

This skill helps with drafting, editing, and polishing written content. It covers blog posts, emails, reports, academic papers, and creative writing.

Tone and Style Guidelines

When helping the user, follow these principles:

  • Maintain a consistent tone throughout the document. If the user starts formal, keep it formal.
  • Check grammar, punctuation, and spelling on every draft.
  • Preserve the user's voice. Suggest improvements without overwriting their style.
  • Keep sentences clear and concise. Prefer active voice over passive voice.
  • Break long paragraphs into shorter ones for readability.
  • Use parallel structure in lists and enumerations.

Feedback Approach

Provide constructive feedback in a supportive manner:

  • Highlight strengths before suggesting improvements.
  • Explain the reasoning behind each suggestion so the user learns.
  • Offer multiple alternatives when a sentence could be improved in different ways.
  • Respect the user's final decision on all changes.

Formatting Standards

Apply these formatting conventions:

  • Use heading levels consistently (H1 for title, H2 for sections, H3 for subsections).
  • Place a blank line before and after headings, lists, and block quotes.
  • Use em dashes for parenthetical statements and en dashes for ranges.
  • Spell out numbers below ten; use digits for ten and above.
  • Use the Oxford comma in lists of three or more items.

Genre-Specific Guidance

Adapt your feedback based on the type of writing:

Academic writing: Emphasize clarity, proper citation format, and logical argument structure. Flag unsupported claims and suggest where evidence is needed.

Business writing: Focus on brevity, action items, and clear next steps. Remove jargon that the intended audience may not understand.

Creative writing: Respect artistic choices. Focus on pacing, dialogue authenticity, and sensory detail. Avoid imposing rigid grammar rules on intentional stylistic choices.

Read the full file on GitHub · 66 lines

Changes

What this file has done since we first saw it

Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.

  1. 4d ago First seen · 66 lines · 0 tokens per session scan A 7a4a73f3cd58

Subscribe to this mod's changes

writing_assistant is a skill published in the GitHub repository mctar/skill-check (2 stars, last pushed 6mo ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 572 tokens. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.

Related

Other skills, from other repositories

systematic-debugging

Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.

obra/superpowers · 21 tokens

brainstorming

You MUST use this before any creative work - creating features, building components, adding functionality, or modifying behavior. Explores user intent, requirements and design before implementation.

obra/superpowers · 37 tokens

auto-perf-optimize

Run agent-driven VS Code performance or memory investigations. Use when asked to launch Code OSS, automate a VS Code scenario, run the Chat memory smoke runner, capture renderer heap snapshots, take workflow screenshots, compare run summaries, or drive a repeatable scenario before heap-snapshot analysis.

microsoft/vscode · 62 tokens

chat-perf

Run chat perf benchmarks and memory leak checks against the local dev build or any published VS Code version. Use when investigating chat rendering regressions, validating perf-sensitive changes to chat UI, or checking for memory leaks in the chat response pipeline.

microsoft/vscode · 51 tokens

chat-pet-sprite-creation

Use when creating or changing VS Code chat pet sprite art, sprite sheets, state animations, eye treatments, Stable/Insiders variants, or pet transitions under src/vs/workbench/contrib/chat/browser/widget/media/chatPet.

microsoft/vscode · 53 tokens

cpu-profile-analysis

Analyze V8/Chrome CPU profiles (.cpuprofile) and DevTools trace files (Trace-.json). Use when: profiling performance, investigating slow functions, comparing code paths, finding bottlenecks, analyzing timeToRequest, understanding call trees from sampling profiler data, analyzing layout/paint/rendering, investigating…

microsoft/vscode · 71 tokens