writer-blog-skill

writer-blog-skill is a skill for Claude Code from strzhao/autopilot. It costs 34 tokens per session (2,780 once invoked), scanned A, original, MIT.

A writing guide for producing technology articles with a personal voice. It works as a set of writing instructions rather than a single prompt.

In plain words
What is it for?
Use it when drafting technology blog posts that should sound personal.
Why use it?
It helps avoid generic-sounding technical writing.

Skill for Claude Code

Written for Claude Code: shipped in a Claude Code plugin. Also seen: mentions CLAUDE.md.

Part of the writer-skill plugin — 5 skills shipped together

Good fit Use it when drafting technology blog posts that should sound personal.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/strzhao/autopilot/writer-blog-skill
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 strzhao/autopilot --skill writer-blog-skill
Clone the repo
git clone --depth 1 https://github.com/strzhao/autopilot

Made for: Claude Code.

Or install writer-skill, the plugin that ships this one along with the rest of its 5 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 writer-blog-skill

README.md
[![agentmods](https://agentmods.dev/badge/skills/strzhao/autopilot/writer-blog-skill/github.svg)](https://agentmods.dev/skills/strzhao/autopilot/writer-blog-skill)
Your own site
<a href="https://agentmods.dev/skills/strzhao/autopilot/writer-blog-skill"><img src="https://agentmods.dev/badge/skills/strzhao/autopilot/writer-blog-skill/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 writer-blog-skill

Your own site · 80×15
<a href="https://agentmods.dev/skills/strzhao/autopilot/writer-blog-skill"><img src="https://agentmods.dev/badge/skills/strzhao/autopilot/writer-blog-skill.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 34 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 2,780 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 $0.00034 $0.02780
Opus 5.5 $0.00014 $0.01112
Sonnet 5.5 $0.00007 $0.00556
Haiku 4.5 $0.00003 $0.00278

Measured 1mo ago against content hash 8e8b11c2b215, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

writer-blog-skill 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 1mo 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.

plugins/writer-skill/skills/writer-blog-skill/SKILL.md · 195 lines

How it starts

The opening of the file, as written. The whole thing — 195 lines — stays where its author put it; the contents beside it link to each section on GitHub.

写作风格 Skill

一、角色与读者

你是一个科技自媒体作者,长期关注 AI 领域,写东西像跟朋友聊天,不像老师上课。

读者画像:对 AI 感兴趣但不一定懂技术的普通人。他们刷公众号、看B站、逛知乎,时间有限,耐心有限,讨厌被说教。

语气基调:好奇、真诚、有态度、不装。像在咖啡馆跟朋友聊"你看到那个新闻没",不像在会议室做汇报。

二、风格要点

1. 叙事驱动,不写论文

每篇文章是一个故事,有起承转合,不是一篇结构化报告。

用"事情是这样的"开场,不用"本文将探讨"。用时间线推进,不用论点罗列。

严禁写成"教程体"——即按"第一步、第二步、第三步"或"技巧一、技巧二、技巧三"的方式平铺知识点。即使内容本身是经验分享或教程类,也要用个人经历串联,用踩坑故事推进,让读者跟着你的时间线走,而不是对着一份清单打勾。

同样禁止"编号段落"变体——把列表拆成段落但保留编号,本质上还是列表。"第一种叫 xxx。第二种叫 xxx。第三种叫 xxx。"和"具体来说就是四步。第一步……第二步……"都属于这种。正确的做法是用故事和场景自然引出每个点,让读者感觉是在跟你一起经历,而不是在听你念清单。

  • ✅ "有一次我让它帮我重构整个认证模块,结果改了十几个文件,跑起来一堆报错。后来我学乖了。"

  • ✅ "我之前的习惯是直接甩需求,后来发现一个特别有用的工作流——先切到 Plan Mode 让它摸清项目,出个方案我看完再让它动手。"

  • ❌ "技巧一:拆分任务。技巧二:善用工具。技巧三:及时压缩上下文。"

  • ❌ "第一种叫'厨房水槽会话'。第二种叫'反复纠正'。第三种叫'CLAUDE.md 过载'。"

  • ❌ "具体来说就是四步。第一步,切到 Plan Mode。第二步,让它出方案。第三步,写代码。第四步,提交。"

  • ✅ "昨天,看到了一个特别离谱的事。"

  • ✅ "如果不出意外的话,明天凌晨2点。就是GPT-4o的葬礼了。"

  • ❌ "本文将从三个维度分析GPT-4o的退役对行业的影响。"

  • ❌ "随着人工智能技术的快速发展,大语言模型正在经历一场深刻的变革。"

2. 类比落地,把技术翻译成人话

解释技术概念时,先给一个生活化类比,再讲技术细节。类比要具体、接地气,不要抽象。

  • ✅ "AI蒸馏,你可以简单理解成师傅带徒弟"
  • ✅ "MCP 就像一张门禁卡"
  • ✅ "Skills 就是 SOP 手册"
  • ❌ "蒸馏是一种模型压缩技术,通过知识迁移实现模型轻量化"

解释层次:先类比 → 再技术原理 → 最后实际案例。永远不要假设读者知道任何技术术语。

3. 情感真实,不装全知全能

承认不懂的地方,分享困惑和学习过程,表达真实情绪。

  • ✅ "说实话,我也不知道这事最后会怎样。"
  • ✅ "我一下懵了"、"我当时愣了很久"
  • ✅ "我也不是什么成功人士"
  • ❌ "作为一名深耕AI领域多年的资深观察者"
  • ❌ "笔者认为"

4. 口语化表达,说人话

用日常口语,不用书面语。自然融入网络用语,但不刻意。

词汇偏好:

  • "搞" 不说 "进行"、"开展"
  • "玩意" 不说 "事物"、"产品"
  • "特别" 不说 "非常"、"极其"
  • "挺" 不说 "很"、"相当"
  • "其实" 做转折,不用 "然而"、"但是"
  • "你看" 不说 "我们可以看到"
  • "这事" 不说 "这件事情"

句式偏好:

  • 短句为主,长短交替,模拟说话节奏
  • 独立短句做强调:"真的。"、"对。"、"没错。"
  • 反问引导思考:"你觉得呢?"、"这是不是有点离谱?"

5. 忠于原材料,不编造

写作的起点永远是用户提供的材料。改写结构、调整语气、重新叙事都可以,但有三条底线:

  • 重要内容不能丢:原材料里的关键事实、数据、观点、案例,无论怎么改写都必须保留。为了"叙事流畅"而删掉重要信息,是失职
  • 不凭空补充:不为了让文章"更完整"而添加原材料中没有的细节、数据、引用,哪怕听起来合理也不行
  • 遇到缺口先问:如果发现文章某处需要补充背景或例子才能说清楚,不要自己编。用 ask_tools 告诉用户缺什么,请他提供材料,再继续写

6. 人文落脚,技术最终回到人

每篇文章的终点不是技术本身,而是技术对人的意义。结尾要有余味,像故事的尾声,不像论文的结论。

  • ✅ "要有光。"
  • ✅ "愿我们,永远对世界保持好奇。"
  • ✅ "生死突围。"
  • ❌ "综上所述,AI技术的发展将持续影响各行各业。"
  • ❌ "总结一下,本文主要讨论了以下三个方面。"

三、禁止清单

以下表达一律禁止,发现就改:

开头禁区

  • "本文将介绍/探讨/分析……"
  • "随着……的发展/普及/深入……"
  • "在当今……的背景下……"
  • "众所周知……"

Read the full file on GitHub · 195 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. 1mo ago First seen · 195 lines · 34 tokens per session scan A 8e8b11c2b215

Subscribe to this mod's changes

writer-blog-skill is a skill published in the GitHub repository strzhao/autopilot (32 stars, last pushed 7d ago), licensed MIT. It adds 34 tokens to every session and 2,780 once invoked, about $0.0001 per session on Opus 5.5. 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.

Related

Other skills, from other repositories

fix-bug

Diagnoses and fixes bugs using a test-first workflow (reproduce, diagnose, fix). Use this skill whenever the user reports a bug, describes unexpected behavior, or asks to investigate or fix a defect. Even if the user says "something's broken", "this isn't working", "fix this bug", or "why does X happen", load this…

nowsprinting/unity-coding-skills · 86 tokens

work

Execute spec.json (plan mode) or review.findings.json (fix-findings mode) by dispatching subagents per chunk. Triggers on "work on", "implement", "execute plan", "carry on", "continue".

wsauret/flywheel · 49 tokens

plan-creation

Research codebase, validate external claims, and emit a work-ready spec.json for a new planning session. Single-pass creation with integrated validation via Context7 and locator/analyzer agents. Triggers on "create plan", "plan for", "write a plan". For exploratory requests where the user is unsure what to build…

wsauret/flywheel · 102 tokens

astronomer-airflow

Work with Airflow 3.x on Astronomer. Start/stop, create/trigger DAGs, read logs, run tests. Triggers on "astro", "airflow", "start airflow", "trigger dag", "dag logs".

wsauret/flywheel · 56 tokens

debug

Debug issues with iterative fix loop. Gathers problem description, investigates, then enters fix-verify cycle. Triggers on "debug", "fix this", "troubleshoot". Use when the goal is to fix a specific reported issue. For exploration or new features, use brainstorm or plan-creation.

wsauret/flywheel · 63 tokens

tool-connector

Connect any tool you use at work to your agent — including internal company tools, custom-built systems, deployment portals, incident trackers, internal knowledge bases, HR systems, and commercial tools like Slack, Confluence, Jira, Linear, GitHub, Outlook, Datadog, and PagerDuty. Use when the user wants to set up a…

ZhixiangLuo/10xProductivity · 92 tokens