npm package discovery and stats viewer.

Discover Tips

  • General search

    [free text search, go nuts!]

  • Package details

    pkg:[package-name]

  • User packages

    @[username]

Sponsor

Optimize Toolset

I’ve always been into building performant and accessible sites, but lately I’ve been taking it extremely seriously. So much so that I’ve been building a tool to help me optimize and monitor the sites that I build to make sure that I’m making an attempt to offer the best experience to those who visit them. If you’re into performant, accessible and SEO friendly sites, you might like it too! You can check it out at Optimize Toolset.

About

Hi, 👋, I’m Ryan Hefner  and I built this site for me, and you! The goal of this site was to provide an easy way for me to check the stats on my npm packages, both for prioritizing issues and updates, and to give me a little kick in the pants to keep up on stuff.

As I was building it, I realized that I was actually using the tool to build the tool, and figured I might as well put this out there and hopefully others will find it to be a fast and useful way to search and browse npm packages as I have.

If you’re interested in other things I’m working on, follow me on Twitter or check out the open source projects I’ve been publishing on GitHub.

I am also working on a Twitter bot for this site to tweet the most popular, newest, random packages from npm. Please follow that account now and it will start sending out packages soon–ish.

Open Software & Tools

This site wouldn’t be possible without the immense generosity and tireless efforts from the people who make contributions to the world and share their work via open source initiatives. Thank you 🙏

© 2026 – Pkg Stats / Ryan Hefner

@mulou/skills-for-gpt

v1.0.0

Published

Concise-response skills (English + Chinese) that constrain LLM output: conclusion-first, plain language, no filler. For Claude Code / Codex agents

Readme

skills-for-gpt

约束 LLM 输出风格的 skill 集合。当前包含一对内容完全对齐的中英文 skill,用于让模型的回答精简、结论先行、可直接使用

Skills that constrain LLM output style. Currently contains a pair of fully-aligned English/Chinese skills that make model answers concise, conclusion-first, and ready to use.

安装 / Install

通过 npm 下载 / Download via npm:

npm install @mulou/skills-for-gpt

安装后把 SKILL.md 复制到你的 agent skills 目录 / After install, copy the SKILL.md files into your agent's skills folder:

# Claude Code (英文版 / English)
cp -r node_modules/@mulou/skills-for-gpt/concise-response ~/.claude/skills/
# Claude Code (中文版 / Chinese)
cp -r node_modules/@mulou/skills-for-gpt/concise-response-zh ~/.claude/skills/

Codex 用户把目标改为 ~/.codex/skills/。不想装依赖,可用 npm pack @mulou/skills-for-gpt 下载 tarball,解压即得两个 SKILL.md。 Codex users: target ~/.codex/skills/ instead. To grab the files without a dependency, run npm pack @mulou/skills-for-gpt and unpack the tarball.

Skills

| Skill | 语言 / Language | 说明 / Description | |---|---|---| | concise-response | English | Concise, conclusion-first answering style | | concise-response-zh | 中文 | 精简回答风格(与英文版内容一致) |

核心规则 / Core Rules

两个 skill 强制执行同一套规则 / Both skills enforce the same rules:

  1. 结论先行 — 第一句话直接给答案,再解释必要原因。 Conclusion first — the first sentence is the answer; reasons come after.
  2. 语言简单准确 — 不堆砌术语,术语首次出现时解释。 Plain, precise language — no jargon stacking; explain terms on first use.
  3. 简单问题 1~3 句话 — 不加背景、免责声明或"另外"段落。 Simple questions get 1–3 sentences — no padding.
  4. 解释用「结论 → 原因 → 怎么做」结构。 Explanations follow Conclusion → Reason → What to do.
  5. 不注水 — 不复述问题、不重复结论、不扩展无关背景。 No filler — don't restate the question, repeat the conclusion, or add unrelated background.
  6. 不知道就明说 — 信息不足时说"目前无法确定",并指出缺什么。 Admit uncertainty — say what exactly is missing instead of guessing.
  7. 报告文字可直接使用 — 只给最终正式文本,不加元说明。 Report text is paste-ready — final formal wording only.
  8. 给一个答案,不给菜单 — 除非用户要求,不给长列表、大表格或多套方案。 One answer, not a menu — no Plan A/B/C unless asked.
  9. 风险警告是精简的例外 — 涉及安全、数据或工程风险时加必要警告,但保持一两句话。 Risk warnings are the exception — necessary, but kept to a sentence or two.

每个 skill 还包含发送前自检清单反面模式(禁止出现的典型写法),把风格要求变成可核对的动作。 Each skill also includes a pre-send checklist and anti-patterns section that turn the style rules into checkable actions.

使用方法 / Usage

将 skill 目录放入你的 agent 的 skills 目录(例如 Codex 的 ~/.codex/skills/,或 Claude Code 的 .claude/skills/)。每个 skill 是一个包含 SKILL.md 的目录,frontmatter 中的 description 描述了触发条件,供 agent 自动匹配加载。

Place a skill directory into your agent's skills folder (e.g. ~/.codex/skills/ for Codex, or .claude/skills/ for Claude Code). Each skill is a directory containing a SKILL.md; the frontmatter description states the trigger conditions for automatic loading.

按需选择语言版本:面向中文对话用 concise-response-zh,面向英文对话用 concise-response,也可以两个都装。

Pick the version matching your conversation language — or install both.