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 agentmods add instructions/tanshilongmario/articleskill/claude-mdgit clone --depth 1 https://github.com/TanShilongMario/ArticleSkillWrote 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/instructions/tanshilongmario/articleskill/claude-md)<a href="https://agentmods.dev/instructions/tanshilongmario/articleskill/claude-md"><img src="https://agentmods.dev/badge/instructions/tanshilongmario/articleskill/claude-md.svg" alt="Measured on agentmods" height="20"></a>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 | $0.02819 | $0.02819 |
| Opus 5 | $0.01409 | $0.01409 |
| Sonnet 5 | $0.00564 | $0.00564 |
| Haiku 4.5 | $0.00282 | $0.00282 |
Grade A, and why
ArticleSkill CLAUDE.md 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 5d 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 — 279 lines — stays where its author put it; the contents beside it link to each section on GitHub.
CLAUDE.md
本文件为 Claude Code (claude.ai/code) 在此代码库中工作时提供指导。
系统概述
这是一个中文文章写作 Skill 系统,专为公众号内容创作设计。它提供了一个综合性的 AI 辅助写作工作流程,能够学习作者风格并生成高质量、引人入胜的文章。
系统由多个 Markdown "技能文件"组成,它们协同工作,而非独立工具。
核心系统要求
最重要的原则:当用户请求文章创作时,AI 必须:
- 同时读取所有技能文件 - 绝不依赖单一技能文件
- 学习作者的写作风格 - 从
作者配置.md和现有文章中学习 - 搜索相关热点话题 - 使用 WebSearch 确保内容时效性
- 保持人设一致性 - 严格遵循作者配置
核心架构
技能文件位置
skills/ 目录包含所有技能文件:
作者配置.md(作者配置 - 模板:作者配置模板.md)公众号爆款写作.md(核心写作方法论)深度认知写作.md(认知升级型内容框架)文章创作工作流程.md(完整工作流程 - AI 必须遵循)热点分析工具.md(热点话题分析)写作辅助工具.md(实用命令)去AI化润色.md(去AI化文本润色)快速参考.md(快速查询卡片)
文件组织结构
skills/
├── 作者配置.md # 作者人设和风格(必读)
├── 系统说明.md # 系统架构说明
├── README.md # 使用指南
└── [其他技能文件].md # 写作方法论文件
作者配置系统
首次使用设置:
用户必须复制 作者配置模板.md 为 作者配置.md 并填写:
- 基本信息(笔名、身份、领域、背景)
- 人设标签(亲和力强、专业严谨、幽默风趣、极简干货)
- 内容特点(痛点驱动、产品思维等)
- 价值主张
- 情绪表达习惯
- 自嘲风格
- 写作偏好(开头方式、段落长度、术语使用)
AI 行为规则:
- 如果
作者配置.md存在:读取并提取人设特征 - 如果缺失:引导用户填写或询问核心人设问题
- 始终引用此文件以保持风格一致性
写作工作流程
当用户说"我要写一篇关于[主题]的文章"时:
第一阶段:资源加载(必须)
- 检查
作者配置.md是否存在 - 读取
skills/中的所有技能文件 - 从 2-3 篇现有文章中学习作者风格
- 使用 WebSearch 搜索热点话题
第二阶段:标题生成
生成 4 种类型的爆款标题:
- 冲突对比型:"我都不知道自己写了什么代码,但它在Github上火了"
- 疑问引导型:"AI工具,到底是一个均衡器,还是一个放大器?"
- 数字+效果型:"600星背后:我的AI工具开发日记"
- 否定+反转型:"别再用关键词试错了!MJ风格库+NanoBanana"
第三阶段:结构生成
三种文章模板:
- 工具介绍型:开头(150) → 痛点(350) → 方案(700) → 创作故事(500) → 迭代(350) → 价值升华(250) → 行动号召(100) = 2000-3000字
- 方法教程型:金句开场(100) → 问题分析(350) → 工具介绍(550) → 实操演示(700) → 效果(250) → 总结(200) → 互动(100) = 2000-2500字
- 深度思考型:问题引入(200) → 背景(450) → 历史(300) → 核心分析(900) → 深度追问(300) → 留白(100) = 2500-3500字
第四阶段:内容创作
关键要求:
- 使用作者的声音(第一人称"我",如适用)
- 分享失败和挫折(真实感)
- 情绪表达(符合作者配置)
- 适度自嘲(根据风格)
- 赋能读者:"连我也能做到"
- 关键:减少条目式输出 - 使用流畅的段落
第五阶段:优化与质量检查
- 内容优化(风格调整)
- 去AI化处理(去除AI味)
- 爆款要素检查
- 风格一致性检查
核心写作原则
减少条目式输出
这是最重要的原则。
避免使用:
1. 首先,你要做A
2. 然后,你要做B
3. 最后,你要做C
采用:
做这件事的时候,大多数人会直接从A开始。但我的建议是,先花点时间
想清楚B,然后再回头做A。为什么?因为[原因]。至于C,那是水到渠成
的事,不用急。
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.
- 5d ago First seen · 279 lines · 2,819 tokens per session scan A 320276e8d3dc
ArticleSkill CLAUDE.md is an instructions file published in the GitHub repository TanShilongMario/ArticleSkill (168 stars, last pushed 7mo ago), licensed MIT. It adds 2,819 tokens to every session, about $0.0141 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 instructions, from other repositories
next.js AGENTS.md
AGENTS.md instructions for vercel/next.js, covering next.js development guide, codebase structure, monorepo overview, core package: packages/next and other important packages.
codex AGENTS.md
AGENTS.md instructions for openai/codex, covering rust/codex-rs, the codex-core crate, code review rules, crate api surface and model visible context.
vscode buildNext.instructions.md
Working notes and architecture documentation for the new esbuild-based build system in build/next. Use when making changes to the new build pipeline (transpile/bundle commands, NLS plugin, source-map handling, resource copying, or self-hosting watch tasks).
spec-kit AGENTS.md
AGENTS.md instructions for github/spec-kit, covering agents.md, about spec kit and specify, quickstart — add a new integration in 5 steps, integration architecture and integrationmanifest — file tracking.
langchain AGENTS.md
AGENTS.md instructions for langchain-ai/langchain, covering global development guidelines for the langchain monorepo, corridor security analysis, project architecture and context, monorepo structure and development tools & commands.
vscode oss-third-party-notices.instructions.md
Instructions for microsoft/vscode, covering vs code oss third-party-notices pipeline, architecture, pipeline flow in ci, applying the notice (cutover) and fallback chain (never fail the build).