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 movebrickschi/harness-engineering-mcp --skill wechat-ai-articlegit clone --depth 1 https://github.com/movebrickschi/harness-engineering-mcpWrote 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/movebrickschi/harness-engineering-mcp/wechat-ai-article)<a href="https://agentmods.dev/skills/movebrickschi/harness-engineering-mcp/wechat-ai-article"><img src="https://agentmods.dev/badge/skills/movebrickschi/harness-engineering-mcp/wechat-ai-article.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 5.1 | $0.00084 | $0.15909 |
| Opus 5 | $0.00042 | $0.07955 |
| Sonnet 5 | $0.00017 | $0.03182 |
| Haiku 4.5 | $0.00008 | $0.01591 |
Grade A, and why
wechat-ai-article 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 7d 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 — 614 lines — stays where its author put it; the contents beside it link to each section on GitHub.
WeChat Tech Article Skill
这个 skill 负责把「最新科技新闻」或「用户指定的科技主题方向」（以 AI 为重点，但同样覆盖芯片/硬件/大厂财报/开发者工具/GitHub 热门项目/MCP 与 skills 生态/新工程术语/安全事件/重大并购）自动化转成一篇微信公众号级别的深度长文。输出单文件：article.html（内联样式，粘贴即用）。
启动前约定
- 语言：正文中文，数据/产品名/benchmark/公司名 用英文原词
- 风格：技术深度 + 通俗导读双轨。默认面向混合读者——非技术读者能跟着故事和判断读完，技术读者能从可选阅读层拿到 benchmark / 源码 / 公式细节。每个硬核段落必须配一段白话翻译或生活类比，让普通人也能 get 到
- 实战与痛点导向：涉及技术能力、工具、论文、框架、模型或开发者生态时，正文必须尽量回答「当前解决什么痛点、方案怎么落地、谁适合用、有哪些坑、哪些问题仍然解决不了」。不要只写原理、参数和行业影响
- 不使用 emoji
- 不落盘 Markdown 源文件，文章草稿只存在 Agent 上下文里，直接转 HTML
- 每篇视觉语言必须独立生成：文章排版风格（色板 / 排版尺度 / 组件形态）要与最近历史避重，绝不复用上一篇的 token
- 不生成封面：本 workflow 只负责公众号正文 HTML，不调用任何图片生成工具，不创建图片候选，不写任何图片后处理配置
Step 0：输入路由
在执行 Step 1 前，先判断用户输入属于哪种模式，并把结果记录为 input_mode：
input_mode |
触发条件 | 后续流程 |
|---|---|---|
auto_news |
用户只说 /wechat-ai-article、写 AI 周报、科技新闻、近期热点、今日/本周科技新闻，且没有给出明确主题 |
跑 Step 1A + Step 2，采集最近 7 天新闻并展示 Top 10 让用户选择 |
custom_topic |
用户请求里已经带明确主题、方向、公司、产品、技术、议题或人群，例如「AI Agent 工程化」「OpenAI 最近的新模型」「国产大模型出海」「Cursor 和 Claude Code 对比」 | 跑 Step 1B，围绕主题定向调研，跳过 Top 10 拍板，直接进入 Step 3 |
direct_link |
用户给了一个或多个新闻 / 博客 / 论文 / 公告链接，并要求基于链接写文章 | 跑 Step 1C，用 WebFetch 读原文并做交叉验证，跳过 Top 10 拍板，直接进入 Step 3 |
主题判定优先级：只要用户输入中包含可写作的主题，就按 custom_topic 处理；不要再默认跑 14 条全局新闻查询。只有在没有主题时，才使用原来的自动新闻流程。
过宽主题处理：如果用户只给「AI」「科技」「大模型」「芯片」这类过宽词，无法判断写作角度时，先用 AskQuestion 让用户在 2-4 个方向里收窄；不要直接泛写。
工作流（最多 8 步，按主题分支）
复制下面的清单，逐项勾选执行：
Task Progress:
- [ ] Step 0: 判断输入模式（auto_news / custom_topic / direct_link）
- [ ] Step 1: 按输入模式采集资料（auto_news 采集最近 7 天新闻；custom_topic 定向调研；direct_link 读取链接并交叉验证）
- [ ] Step 2: 仅 auto_news 模式打分排序并给出 Top 10 候选让用户拍板；custom_topic / direct_link 直接进入写作策略
- [ ] Step 3: 根据新闻类型确定写作模板与篇幅，并标记 content_profile
- [ ] Step 3.1: 命中 personal_practice / retrospective 时 AskQuestion 二选一（仅 custom_topic / direct_link 触发，auto_news 跳过）
- [ ] Step 3.5: 仅技术层面主题做「叙事骨架设计」（产出 6 字段 JSON），business_narrative / fast_take / 消费功能型 product_experience 跳过
- [ ] Step 4: 按规范写作（含 5 个备选标题、正文、参考资料）
- [ ] Step 4.5: 生成「文章视觉语言卡」（色板 + 排版尺度 + 组件形态）
- [ ] Step 5: 输出 article.html + 追加样式历史
What ships with it
8 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.
- 7d ago First seen · 614 lines · 84 tokens per session scan A 168528b555f5
wechat-ai-article is a skill published in the GitHub repository movebrickschi/harness-engineering-mcp (2 stars, last pushed 3mo ago), licensed MIT. It adds 84 tokens to every session and 15,909 once invoked, about $0.0004 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 2026-08-31.
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…
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…
chronicle
Analyze Copilot session history for standup reports, usage tips, session search, and session reindexing. Use when the user asks for a standup, daily summary, usage tips, workflow recommendations, wants to search or find past sessions by keyword/file/PR, wants to reindex their session store, or asks about deleting…
babysit-pr
Babysit a GitHub pull request after creation by continuously polling review comments, CI checks/workflow runs, and mergeability state until the PR is merged/closed or user help is required. Diagnose failures, retry likely flaky failures up to 3 times, auto-fix/push branch-related issues when appropriate, and keep…