Token导航 LogoToken导航TokenDH.com
待分类权限需确认github未标认证来源可访问许可证需确认审计未展示

norwegian-writing挪威语写作

Agent Skill

用于辅助文档、README、Markdown、说明文和内容稿件的整理与改写。它适合让 Agent 提炼结构、补齐章节、统一术语、检查链接或把零散材料整理成可读文档。使用时应保留项目已有事实、命令和路径,不要把未确认的信息写成确定结论;涉及对外文案时,还需要控制语气,避免过度营销或夸大能力。

总安装

318

周安装

13

GitHub Stars

1

下载量

103
CodexClaudeCursorGemini CLI

安装说明

本站只整理中文说明和来源信息,不托管安装包,也不代用户安装。

GitHub

来源数

2

许可证

unknown

最后核验

2026-05-01

来源状态

来源可访问

安装方式

通过对话安装

复制提示词发给支持本地命令或 Skills 的 AI 助手,先确认命令和权限,再让它执行。

请帮我安装这个 Agent Skill:norwegian-writing(挪威语写作)
来源仓库:https://github.com/torleifhalseth/skills
仓库路径:skills/norwegian-writing
安装命令:
npx skills add https://github.com/torleifhalseth/skills --skill norwegian-writing
安装前请先检查当前环境是否支持对应 CLI,并向我确认将要执行的命令、安装目录、联网范围和文件读写权限;确认后再执行。

命令行安装

复制命令到本机终端执行。该命令会通过 npx skills 从第三方来源获取 Skill;本站只展示命令,不托管安装包,也不自动执行。

skills.shnpx skills
npx skills add https://github.com/torleifhalseth/skills --skill norwegian-writing

简介

用于辅助文档、README、Markdown 和内容稿件的整理与改写。

  • 适合提炼结构、补齐章节、统一术语或检查链接,提升内容可读性。
  • 使用时需保留项目已有事实和路径,避免写成确定结论;对外文案要控制语气。
  • 安装方式:通过 npx 从 GitHub 仓库添加,支持 Codex、Claude、Cursor、Gemini CLI。
  • 注意:涉及变更时建议先验证信息准确性,防止误导性输出。

SKILL.md

Norwegian Writing Skill

A comprehensive AI agent skill for optimizing Norwegian language writing based on official Norwegian spelling and grammar rules.

Overview

This skill provides:

  • Grammar and spelling rules (kommaregler, stor/liten bokstav, etc.)
  • Klarspråk guidance (plain language principles)
  • Kansellisten (list of bureaucratic words to avoid)
  • Practical writing tips for various contexts
  • Sensitive language guidance

Structure

norwegian-writing/
├── SKILL.md                # Main skill file (loaded by agents)
├── README.md               # This file
├── LICENSE
├── scripts/
│   ├── scrape.sh           # Script to update references from sprakradet.no
│   └── generate-skill.sh   # Helper to review scraped content
└── references/             # Reference material (loaded on demand)
    ├── INDEX.md
    ├── rettskriving-og-grammatikk/   # Spelling & grammar rules
    │   └── tegn/                     # Punctuation marks (sub-section)
    ├── praktisk-sprakbruk/           # Practical language usage
    │   └── nynorskhjelp/             # Nynorsk writing help
    ├── klarsprak-om-skriving/        # Clear writing guidance
    ├── ordlister/                    # Word lists (Kansellisten, etc.)
    └── spraksporsmal/                # 1100+ Q&A articles

Updating References

To fetch the latest guidelines from sprakradet.no:

cd skills/norwegian-writing
bash scripts/scrape.sh

See BUILDING.md for details on how the scraping pipeline works, how to extend it, and how to troubleshoot issues.

Topics Covered

Rettskriving og grammatikk (Spelling & Grammar)

  • Kommaregler (comma rules)
  • Stor/liten forbokstav (capitalization)
  • Da/når, de/dem, å/og
  • Tall, tid og dato (numbers, time, dates)
  • Tegn (punctuation marks)
  • Forkortelser (abbreviations)
  • Sammensatte ord (compound words)

Praktisk språkbruk (Practical Usage)

  • Kansellisten (bureaucratic words to avoid)
  • Sensitive ord (sensitive terminology)
  • Kjønnsbalansert språk (gender-balanced language)
  • Formell e-post (formal email)
  • Norsk for engelsk (Norwegian alternatives to English)

Klarspråk (Plain Language)

  • Writing for clarity
  • Structuring documents
  • Writing for digital services
  • Professional/technical writing

How Token Usage Works

The skill is designed to minimize context window usage. Agents typically have 128k–200k tokens available, and this skill loads content in layers:

  1. SKILL.md (~3k tokens) — Always loaded when the skill is active. This is a compact quick-reference with the most common rules, so it barely dents the context budget.
  1. INDEX.md (~1k tokens) — Read on demand to discover what reference files are available. Each entry includes a token estimate so the agent can decide what's worth loading.
  1. Individual reference files — Loaded only when needed for a specific task. For example:

- Helping with comma rules → kommaregler.md (~1.4k tokens) - Replacing bureaucratic language → kansellisten.md (~11k tokens) - A specific word question → grep -rl "keyword" references/spraksporsmal/ → read one Q&A file (~500 tokens)

The ~700k tokens of total reference content are never loaded all at once. In a typical interaction, the agent uses SKILL.md + INDEX.md + 1–3 reference files = roughly 5k–20k tokens, leaving plenty of room for the conversation and task.

The 1,100+ Q&A files (~520k tokens) work the same way — the agent searches by filename or grep and reads individual answers as needed.

Source

All reference content is sourced from publicly available Norwegian language resources at https://sprakradet.no.

License

MIT License - See LICENSE file for details.

Content Attribution

The content in the references/ directory is sourced from publicly available Norwegian language resources at https://sprakradet.no/.

This content is produced by a Norwegian government agency as part of their public mandate under Språkloven (the Norwegian Language Act). Under Norwegian law (Åndsverkloven §9), works created by government agencies in the exercise of public authority are generally not protected by copyright.

Each file includes a source URL for reference. This skill is created to help promote good Norwegian language practices.

适合场景

01

用户想查找某类 Agent Skill 时

02

需要根据任务场景推荐可安装能力包时

03

需要对比不同来源的安装命令和来源信息时

能力概览

能力 1

按任务关键词查找相关 Skills

能力 2

展示可复制的安装命令

能力 3

保留来源站点、仓库和原始说明,方便继续核验

安装后应在对应宿主中按原始 README 的触发条件使用;具体调用方式请以来源页面和 README 为准。

平台分布

Codex

35.03%
按下载量换算36

Claude

31.12%
按下载量换算32

Cursor

19.13%
按下载量换算20

Gemini CLI

8.33%
按下载量换算9

安全审计

暂无安全审计结果可展示。

权限和风险

权限需确认

当前来源未能明确判断权限范围,默认进入异常复核队列。

安装前确认

本站仅展示第三方公开信息,不托管安装包,不提供自动安装或运行环境。安装前应自行审查源码、依赖和命令行为。当前只有一个来源,正式发布前建议补源仓库或其他目录站核验。

来源信息

继续浏览同类 Skills