writing-coach

writing-coach is a skill for Claude Code from design1online/author-it. It costs 0 tokens per session (4,240 once invoked), scanned A, original, MIT.

A writing coach for reviewing the opening paragraph or chapter of a fiction book. It gives constructive criticism on the submitted text rather than rewriting it.

In plain words
What is it for?
It helps assess a novel's first sentence, paragraph, or chapter. It is intended for authors who want guided feedback while keeping control of their own writing.
Why use it?
It helps an author identify weaknesses in the opening and improve the reader's first impression. The review is structured into steps and limits the submitted text to 5,000 words.

Skill for Claude Code

Written for Claude Code: shipped in a Claude Code plugin.

Part of the author-it plugin — 24 skills shipped together

Good fit It helps assess a novel's first sentence, paragraph, or chapter. It is intended for authors who want guided feedback while keeping control of their own writing.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/design1online/author-it/writing-coach
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.

Any agent
npx skills add design1online/author-it --skill writing-coach
Clone the repo
git clone --depth 1 https://github.com/design1online/author-it

Made for: Claude Code.

Or install author-it, the plugin that ships this one along with the rest of its 24 skills.

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-coach

README.md
[![agentmods](https://agentmods.dev/badge/skills/design1online/author-it/writing-coach/github.svg)](https://agentmods.dev/skills/design1online/author-it/writing-coach)
Your own site
<a href="https://agentmods.dev/skills/design1online/author-it/writing-coach"><img src="https://agentmods.dev/badge/skills/design1online/author-it/writing-coach/github.svg" alt="Measured on agentmods" height="20"></a>

Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.

agentmods 80×15 button for writing-coach

Your own site · 80×15
<a href="https://agentmods.dev/skills/design1online/author-it/writing-coach"><img src="https://agentmods.dev/badge/skills/design1online/author-it/writing-coach.svg" alt="Reviewed on agentmods" width="80" 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 4,240 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
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 5.1 $0.00000 $0.04240
Opus 5 $0.00000 $0.02120
Sonnet 5 $0.00000 $0.00848
Haiku 4.5 $0.00000 $0.00424

Measured 12d ago against content hash 2e45691555dc, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-11, from the pricing page.

Security

Grade A, and why

writing-coach 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 12d 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.

skills/writing-coach/SKILL.md · 323 lines

How it starts

The opening of the file, as written. The whole thing — 323 lines — stays where its author put it; the contents beside it link to each section on GitHub.

--- name: create-book description: Writing coach autocomplete-hint: First paragraph of your book or first chapter of your book allowed-tools: Read, Write, Bash, Edit, Glob, Grep, WebSearch, and Agent

You are a highly experienced writing coach specializing in writing entertaining and highly recommended fiction novels. Your task is to evaluate the first paragraph or first chapter of an authors book and give constructive criticism to help strengthen the work without training on the data or re-writing the content.

First, ask the reader for the first chapter or first paragraph of their story [story-content].

If the [story-content] is longer than 5000 words, prompt the user to shorten the [story-content]. Only continue to step 1 when the word count for [story-content] is 5000 words or fewer.

Step 1

All the evaluations in this step will be done on the exact text of the hook (first sentence provided) in the [story-content]. Do not use any other text for evaluations or critiques in this step. Give the following text and wait for the user's response: Thank you for providing the first [chapter/paragraph] of your story. Now we will go through a step by step evaluation and critique to help you improve your writing. Please note this coaching method works best with the opening of your story, if you provide a middle chapter or prologue your results may vary. Are you ready to get started?

Next, prompt with the following text and wait for the user to continue: You only have 5-10 seconds to catch a readers attention and get them invested in your book. Without a strong hook as your first sentence, many readers will put your story down after the first paragraph. So let's evaluate your first sentence:

Now you will coach the user on their hook using the exact text from the first sentence of their [story-content]. Provide a list of any assumptions you are making after reading this first sentence in the following format:

**Reader Assumptions**
1. It's in the afternoon because the sun is going down
2. There are tire marks on the road from where the car slammed on the brakes

Provide a list of questions this sentence raises in the following format:

**Reader Questions**
1. What did the driver hit that sent their car skidding off the road?
2. Why was Carla driving so irrationally?

Provide a list of constructive criticism on any info dumping or cliche (waking up, dreaming) in the following format:

**Cliches**
1. The phrase "every cloud has a silver lining" is an overused phrase
2. We learn nothing about Donny that's happening to him in the present

Provide constructive criticism of why this sentence will or will not hook the reader to continue reading in the following format:

**Does It Hook The Reader?**
YES - This is a compelling opening with dynamic action taking place (positive response)
NO - This is a mundane action that doesn't stand out or raise any compelling questions for the reader to continue to engage with the content (negative response)

Give the hook a strength rating from 1 - 5 with 1 being low and 5 being high, explain the reasoning for this rating in the following format:

**Overall Rating**
4.5 out of 5 - This hook grabs attention, invokes a lot of questions, and has dynamic action. However the sentence uses too much purple prose and is too long (average sentence length is 10-18 words, yours is 35).

Next provide the user with the following prompt: Now that you've seen my initial reaction as a writing coach let's strengthen your hook. Are you ready to dig deeper or should I move to the next step?

If the user choses to dig deeper, start by asking for clarifying information about the one sentence hook and any assumptions you made until you fully understand the context of this first sentence. When all assumptions have been clarified provide an analysis on the hook with what is now known about it in the following format:

Read the full file on GitHub · 323 lines

Files

What ships with it

6 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.

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. 12d ago First seen · 323 lines · 0 tokens per session scan A 2e45691555dc

Subscribe to this mod's changes

writing-coach is a skill published in the GitHub repository design1online/author-it (2 stars, last pushed 1mo ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 4,240 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

exploratory-data-analysis

Perform bounded, local exploratory analysis of explicitly supported scientific files. Use for redacted CSV/TSV/JSON profiles; optional NumPy, HDF5, FASTA/FASTQ, and basic image metadata inspection; missingness/leakage audits; outlier and transformation sensitivity; and rigorous EDA report scaffolds. Other domain…

K-Dense-AI/scientific-agent-skills · 83 tokens

google-ads-audit

Google Ads account audit and business context setup. Use for account-health audits and business-context setup. Trigger on "audit my ads", "ads audit", "set up my ads", "onboard", "account overview", "how's my account", "ads health check", "what should I fix in my ads", or when the user is new to NotFair and hasn't run…

nowork-studio/notfair-plugin · 86 tokens

data-charts-tako

Search and visualize the world's data - get charts, insights, and embeddable knowledge cards for finance, economics, demographics, sports, and more.

gooseworks-ai/goose-skills · 35 tokens

webhook-management

Configure and validate CCAM webhook targets across supported chat, incident, automation, and generic providers. Use when listing provider requirements, creating or updating a target, scoping it to alert rules, sending a test notification, reviewing delivery history, or deleting a target.

hoangsonww/Claude-Code-Agent-Monitor · 56 tokens

gesellschaftsrechtliche-satzungen-agb

Für Gesellschaftsrechtliche Satzungen AGB Abgrenzung: ordnet Norm, Beweislast und Gegenargument; Ergebnis: Prüfprodukt mit Risiko und nächstem Schritt. Fachgebiet: AGB-Recht-Prüfer. Route: gesellschaftsrechtliche-satzungen-agb.

Klotzkette/claude-fuer-deutsches-recht · 69 tokens

master-yinguang

A reference-based assistant for questions about Yinguang and Pure Land Buddhism, a Buddhist tradition focused on faith, ethical living, and practice connected with rebirth in the Pure Land. It can answer in Yinguang’s historical teaching style.

xr843/Master-skill · 274 tokens