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.
npx skills add SpaceZephyr/cowrite --skill ai-writing-assistantgit clone --depth 1 https://github.com/SpaceZephyr/cowriteWrote 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.
[](https://agentmods.dev/skills/spacezephyr/cowrite/ai-writing-assistant)<a href="https://agentmods.dev/skills/spacezephyr/cowrite/ai-writing-assistant"><img src="https://agentmods.dev/badge/skills/spacezephyr/cowrite/ai-writing-assistant/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.
<a href="https://agentmods.dev/skills/spacezephyr/cowrite/ai-writing-assistant"><img src="https://agentmods.dev/badge/skills/spacezephyr/cowrite/ai-writing-assistant.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
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.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00035 | $0.02748 |
| Opus 5 | $0.00017 | $0.01374 |
| Sonnet 5 | $0.00007 | $0.00550 |
| Haiku 4.5 | $0.00003 | $0.00275 |
Grade A, and why
ai-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 10d 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.
How it starts
The opening of the file, as written. The whole thing — 309 lines — stays where its author put it; the contents beside it link to each section on GitHub.
AI Writing Assistant
Overview
Enables users to create compelling social media content through structured writing methods. This skill helps transform ideas into polished content by providing guided workflows tailored to different writing scenarios and challenges.
Quick Diagnosis
Before choosing a method, quickly assess the user's situation:
Key Questions to Ask:
- What type of content are you trying to create? (Article, post, reflection, tutorial)
- How much content/ideas do you already have? (None, some scattered thoughts, detailed outline, complete draft)
- What's your main challenge? (Getting started, organizing ideas, polishing quality, finding unique angles)
Based on answers, recommend the most suitable method from the 6 options below.
Writing Methods
Method 1: Conversational Writing (对话式创作)
Best for: Personal experience sharing, reflections, year-end summaries, project reviews
When to use: User has ideas but doesn't know how to start or organize them
Workflow:
-
Set the interview frame
我想写一篇关于【主题】的文章，但还没想清楚怎么写。 请你扮演一个资深编辑，通过提问帮我梳理思路。规则如下： 1. 一次只问一个问题 2. 根据我的回答追问细节 3. 问题要能挖掘我的真实经历和独特观点 4. 大概问 8-10 个问题 5. 问完后帮我整理成文章大纲 现在开始第一个问题。 -
Answer questions naturally - User responds conversationally without worrying about structure
-
Integrate into draft
根据我们的对话，请帮我： 1. 整理成一篇文章的初稿 2. 保留我的原话和表达风格 3. 补充必要的过渡段落 4. 标注哪些地方需要我补充细节 -
Manual polishing - User refines with personal touches, adjusts flow, adds vivid opening/closing
Key benefits: Extracts authentic personal experiences, maintains user's voice, reduces mental overhead
Method 2: Outline-Based Writing (大纲式创作)
Best for: Opinion pieces, tutorials, structured articles, technical documentation
When to use: User has clear ideas about what to say but needs help with expansion
Workflow:
- Create detailed outline with clear sections and key points for each part:
## 文章大纲：[主题] ### 一、开头 - 观点：[核心观点] - 预期反应：[读者可能的反应] - 承诺：[文章价值] ### 二、主体部分 - 观点1：[分论点1] - 案例：[支撑案例] - 观点2：[分论点2] - 案例：[支撑案例] ### 三、结论 - 总结观点 - 给出建议
What ships with it
4 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.
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.
- 10d ago First seen · 309 lines · 35 tokens per session scan A 9afff4fb0c66
ai-writing-assistant is a skill published in the GitHub repository SpaceZephyr/cowrite (91 stars, last pushed 1mo ago), licensed MIT. It adds 35 tokens to every session and 2,748 once invoked, about $0.0002 per session on Opus 5. 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 2026-08-30.
Other skills, from other repositories
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
local-ai-agents
Build local-first AI agents that run entirely on a developer workstation with Microsoft Foundry Local and Qwen function-calling models. Covers Small Language Models (SLMs), the OpenAI-compatible local endpoint, sandboxed local tools, local RAG with Chroma, local MCP servers, hybrid cloud/local routing, and the…
next-cache-components-adoption
Turn on Cache Components in a Next.js app and resolve the blocking routes it surfaces. Use when the user wants to enable, adopt, or migrate to Cache Components, flip the cacheComponents flag, work through a flood of blocking-prerender / instant validation errors, run the cache-components-instant-false codemod, or…
insight-error-page
Write or audit an insight-kind error page for the Next.js dev overlay. Use when creating a new errors/ .mdx page, auditing an existing one, or checking that a page matches the framework fix cards. Covers page structure, title alignment, FixCard cards with Copy prompt button, code snippets, terminology verification…
next-cache-components-optimizer
Drive a Next.js route to instant navigation by setting up an agentic loop, under Cache Components / PPR, on initial load (hard navigation) and client-side navigation (soft navigation). Encode the goal as a failing @next/playwright instant() e2e and work it to green, one verified route at a time; the shipped test then…
next-partial-prefetching-adoption
Turn on Partial Prefetching in a Next.js app and work through the insights it surfaces. Use when the user wants to enable or adopt Partial Prefetching, flip the partialPrefetching flag, opt routes in with export const prefetch = 'partial', audit Link prefetch={true} behavior, preserve existing prefetched UI with…