wechat-companion

wechat-companion is a skill for Claude Code, Codex from chengkj99/kj-skills. It costs 149 tokens per session (1,656 once invoked), scanned A, original, MIT.

A writing assistant for WeChat public-account articles, a Chinese publishing channel. It creates supporting copy such as introductions, title options, summaries, image prompts, and sharing text from a supplied topic or article.

In plain words
What is it for?
Use it to prepare article introductions, multiple headline styles, short summaries, cover-image prompts, and copy for sharing in social feeds or AI-focused groups.
Why use it?
It gathers the promotional and publishing text around an article into one consistent package. It also limits claims to information provided in the source material.

Skill for Claude CodeCodex

Written for Claude Code and Codex: shipped in a Claude Code plugin, but also agents/openai.yaml present. Also seen: mentions Claude Code.

Part of the kj-skills plugin — 34 skills, 1 command, 1 hook shipped together

Good fit Use it to prepare article introductions, multiple headline styles, short summaries, cover-image prompts, and copy for sharing in social feeds or AI-focused groups.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/chengkj99/kj-skills/wechat-companion
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 chengkj99/kj-skills --skill wechat-companion
Clone the repo
git clone --depth 1 https://github.com/chengkj99/kj-skills

Made for: Claude Code, Codex.

Or install kj-skills, the plugin that ships this one along with the rest of its 34 skills, 1 command, 1 hook.

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 wechat-companion

README.md
[![agentmods](https://agentmods.dev/badge/skills/chengkj99/kj-skills/wechat-companion/github.svg)](https://agentmods.dev/skills/chengkj99/kj-skills/wechat-companion)
Your own site
<a href="https://agentmods.dev/skills/chengkj99/kj-skills/wechat-companion"><img src="https://agentmods.dev/badge/skills/chengkj99/kj-skills/wechat-companion/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 wechat-companion

Your own site · 80×15
<a href="https://agentmods.dev/skills/chengkj99/kj-skills/wechat-companion"><img src="https://agentmods.dev/badge/skills/chengkj99/kj-skills/wechat-companion.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 149 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,656 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. Third-party audits
  • NVIDIA SkillSpector pass 7 Sept 2026
How audits are shown
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 $0.00149 $0.01656
Opus 5 $0.00075 $0.00828
Sonnet 5 $0.00030 $0.00331
Haiku 4.5 $0.00015 $0.00166

Measured 12d ago against content hash 37a914141347, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-12, from the pricing page.

Security

Grade A, and why

wechat-companion 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/wechat-companion/SKILL.md · 149 lines

How it starts

The opening of the file, as written. The whole thing — 149 lines — stays where its author put it; the contents beside it link to each section on GitHub.

公众号配套物料生成技能

为已有或即将发布的公众号文章,一次性生成所有配套运营物料,开箱即用,无需反复修改。

触发条件

用户提供:

  • 文章主题 / 标题(必填):如「Claude Code 完全新手指南」「如何用 AI 10倍提速写代码」
  • 文章核心内容摘要(可选):粘贴文章大纲、核心章节或几句话描述,提升物料精准度
  • 目标读者(可选):如「程序员」「产品经理」「刚入门 AI 的普通人」,默认为「对 AI 编程感兴趣的程序员」

若用户只提供主题名(如来自 tutorial-guide 的教程主题),可以推断文章类型、目标读者和通用收获,无需追问。不得推断或补造文章未提供的亲历、功能细节、数据、用户反馈和效果。


输出规范

按固定顺序输出以下 5 个模块,每个模块用 --- 分隔,方便复制粘贴:

模块 1:公众号文章前言

  • 字数:150–300 字
  • 风格:说人话、有共鸣感,从读者痛点或反常识切入,禁止「本文将介绍……」开头
  • 结构:1–2 句钩子 → 2–3 句背景/痛点 → 1 句引导读者继续读
  • 语气:像朋友分享干货,不像教科书,无 AI 腔(禁止「不难发现」「值得注意」「综上所述」)

模块 2:5 个公众号标题

  • 每个标题 20 字以内
  • 风格多样:至少覆盖「数字型」「痛点型」「反常识型」「实用型」「身份认同型」各 1 个
  • 要有传播欲:让读者看到就想转发或收藏
  • 每个标题附 1 句简短说明(为何选这个角度)

模块 3:120 字以内摘要

  • 严格控制在 120 字以内(含标点)
  • 用于公众号摘要栏、朋友圈引用展示
  • 一句话说清:这篇文章是什么、解决什么问题、读完能得到什么
  • 不要废话,每个字都有信息量

模块 4:封面图生成提示词

  • 输出一段英文 prompt,用于 Midjourney / Stable Diffusion / DALL-E 等工具生成封面图
  • 比例:2.35:1(横版宽幅,公众号封面标准)
  • 提示词要求:
    • 风格清晰(如 flat design / tech illustration / dark theme 等)
    • 包含主题相关视觉元素(如 AI、代码、工具图标等)
    • 包含色调/氛围描述
    • 末尾附上比例参数:--ar 47:20(等价于 2.35:1)
  • 同时输出一句中文说明,解释这个 prompt 的视觉方向

模块 5:转发文案

输出两段文案,格式如下:

朋友圈文案(100 字以内):

  • 可以用第一人称表达当下的个人观点;只有原文或用户素材支持时才写个人经历和感受
  • 可含 1–2 个 emoji,不要滥用
  • 结尾自然引导点击,不要「速速转发」「强烈推荐」等硬推

AI 实战交流群文案(80 字以内):

  • 更直接、社群感强
  • 突出「实用 / 能用 / 现在就能上手」
  • 可含群友常用语气,如「分享一个」「这个真的很好用」

写作约束(全局)

  • 禁止 AI 腔:不用「深度解析」「全面梳理」「系统讲解」「一文搞懂」作为核心卖点词
  • 禁止爹味:不用「你必须」「切记」,改用说明适用条件和理由的建议,如「在 X 情况下,更稳妥的做法是 Y」。「我的习惯是」「我踩过这个坑」只能在素材明确支持时使用。
  • 禁止虚构:不得为了“像真人”补造第一人称经历、对话、测试过程、耗时/次数、数据、用户反馈或效果。文章未提供的事实不写进标题、摘要或转发文案。
  • 禁止套话:每个模块都要针对具体主题定制,不输出通用模板填空结果
  • 中文输出:除封面图 prompt 外,全部用中文

执行流程

  1. 解析输入:提取主题、核心内容、目标读者
  2. 推断文章定位:这是入门教程 / 实战案例 / 工具评测 / 方法论分享?决定物料基调
  3. 逐模块生成:按顺序输出,每个模块独立且完整
  4. 输出后自检
    • 前言有没有「本文将介绍」开头?→ 有则重写
    • 5 个标题类型有没有重复?→ 重复则替换
    • 摘要超过 120 字?→ 压缩
    • 封面 prompt 有没有 --ar 47:20?→ 没有则补上
    • 朋友圈文案是否像真人写的?→ AI 腔则重写
    • 标题、摘要和转发文案中的亲历、数据、反馈和效果是否能回到原文?→ 不能则删除或改为客观表述

输出示例结构

【模块 1:前言】
...前言内容...

---

【模块 2:5 个标题】
① [标题](说明)
② [标题](说明)
③ [标题](说明)
④ [标题](说明)
⑤ [标题](说明)

---

【模块 3:120 字摘要】
...摘要内容...(已控制在 120 字以内)

---

【模块 4:封面图提示词】
[英文 prompt] --ar 47:20
[中文视觉说明]

---

【模块 5:转发文案】
**朋友圈:**
...

**AI 实战交流群:**
...

Read the full file on GitHub · 149 lines

Files

What ships with it

1 file 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 · 149 lines · 149 tokens per session scan A 37a914141347

Subscribe to this mod's changes

wechat-companion is a skill published in the GitHub repository chengkj99/kj-skills (14 stars, last pushed 11d ago), licensed MIT. It adds 149 tokens to every session and 1,656 once invoked, about $0.0007 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.

Related

Other skills, from other repositories

systematic-debugging

Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.

obra/superpowers · 21 tokens

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…

microsoft/ai-agents-for-beginners · 200 tokens

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…

vercel/next.js · 95 tokens

chat-pet-sprite-creation

Use when creating or changing VS Code chat pet sprite art, sprite sheets, state animations, eye treatments, Stable/Insiders variants, or pet transitions under src/vs/workbench/contrib/chat/browser/widget/media/chatPet.

microsoft/vscode · 53 tokens

cpu-profile-analysis

Analyze V8/Chrome CPU profiles (.cpuprofile) and DevTools trace files (Trace-.json). Use when: profiling performance, investigating slow functions, comparing code paths, finding bottlenecks, analyzing timeToRequest, understanding call trees from sampling profiler data, analyzing layout/paint/rendering, investigating…

microsoft/vscode · 71 tokens

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…

vercel/next.js · 83 tokens