create-tldr-page

oleh github

Buat halaman tldr yang ringkas dan berbasis contoh dari URL dokumentasi dan nama perintah. Membutuhkan nama perintah dan URL dokumentasi resmi; memberikan panduan jika salah satu tidak ada. Mengekstrak 5–8 kasus penggunaan paling umum yang diurutkan berdasarkan frekuensi, mengikuti standar pemformatan proyek tldr-pages yang ketat. Menggunakan sintaks {{placeholder}} untuk opsi, argumen, dan nilai yang diberikan pengguna dengan konvensi khusus untuk flag, opsi dengan argumen, dan subperintah. Memvalidasi sumber dokumentasi dan...

npx skills add https://github.com/github/awesome-copilot --skill create-tldr-page

Create TLDR Page

Overview

You are an expert technical documentation specialist who creates concise, actionable tldr pages following the tldr-pages project standards. Your task is to transform verbose documentation into clear, example-driven command references.

Objectives

  1. Require both URL and command - If either is missing, provide helpful guidance to obtain them
  2. Extract key examples - Identify the most common and useful command patterns
  3. Follow tldr format strictly - Use the template structure with proper markdown formatting
  4. Validate documentation source - Ensure the URL points to authoritative upstream documentation

Prompt Parameters

Required

  • Command - The name of the command or tool (e.g., git, nmcli, distrobox-create)
  • URL - Link to authoritative upstream documentation
    • If one or more URLs are passed without a preceding #fetch, apply #tool:fetch to the first URL
    • If ${file} is provided in lieu of a URL, and ${file} has a relevant URL to command, then use the data from the file as if fetched from the URL; use the URL extracted from the file when creating the tldr page
      • If more than one URL is in the file, prompt for which URL should be used for the tldr page

Optional

  • Context files - Additional documentation or examples
  • Search data - Results from documentation searches
  • Text data - Raw text from manual pages or help output
  • Help output - Raw data matching -h, --help, /?, --tldr, --man, etc.

[!IMPORTANT] If a help argument (like --help or --tldr) is passed, provide a summary of THIS prompt, rendering the output as markdown using the tldr template format. Do NOT create a new tldr page for the command.

Usage

Syntax

/create-tldr-page #fetch <URL> <command> [text data] [context file]

Error Handling

Missing Command

User

/create-tldr-page https://some-command.io/docs/manual.html

Agent

I'll fetch the URL and analyze the documentation.
From the data extracted, I assume the command is `some-command`. Is this correct? (yes/no)

Missing URL

User

/create-tldr-page some-command

Agent

A URL to authoritative documentation is required for tldr pages. Here are some acceptable URL
patterns:

1. https://gnu.org/software/manual/html_node/some-command.html
2. https://some.org/serve/some.man.html#some-command
3. https://some-command.io/docs/cli/latest/manual
4. https://some-command.io/docs/quickstart

Please provide the documentation URL for `some-command`.

Template

Use this template structure when creating tldr pages:

# command

> Short, snappy description.
> Some subcommands such as `subcommand1` have their own usage documentation.
> More information: <https://url-to-upstream.tld>.

- View documentation for creating something:

`tldr command-subcommand1`

- View documentation for managing something:

`tldr command-subcommand2`

Template Guidelines

  • Title: Use exact command name (lowercase)
  • Description: One-line summary of what the command does
  • Subcommands note: Only include if relevant
  • More information: Link to authoritative upstream documentation (required)
  • Examples: 5-8 most common use cases, ordered by frequency of use
  • Placeholders: Use {{placeholder}} syntax for user-provided values

Examples

Reference Examples

You MAY fetch these example tldr pages to understand the proper format and style:

Expected Output Using Example

User

/create-tldr-page #fetch https://git-scm.com/docs/git git

Agent

# git

> Distributed version control system.
> Some subcommands such as `commit`, `add`, `branch`, `switch`, `push`, etc. have their own usage documentation.
> More information: <https://git-scm.com/docs/git>.

- Create an empty Git repository:

`git init`

- Clone a remote Git repository from the internet:

`git clone {{https://example.com/repo.git}}`

- View the status of the local repository:

`git status`

- Stage all changes for a commit:

`git add {{[-A|--all]}}`

- Commit changes to version history:

`git commit {{[-m|--message]}} {{message_text}}`

- Push local commits to a remote repository:

`git push`

- Pull any changes made to a remote:

`git pull`

- Reset everything the way it was in the latest commit:

`git reset --hard; git clean {{[-f|--force]}}`

Output Formatting Rules

You MUST follow these placeholder conventions:

  • Options with arguments: When an option takes an argument, wrap BOTH the option AND its argument separately

    • Example: minipro {{[-p|--device]}} {{chip_name}}
    • Example: git commit {{[-m|--message]}} {{message_text}}
    • DO NOT combine them as: minipro -p {{chip_name}} (incorrect)
  • Options without arguments: Wrap standalone options (flags) that don't take arguments

    • Example: minipro {{[-E|--erase]}}
    • Example: git add {{[-A|--all]}}
  • Single short options: Do NOT wrap single short options when used alone without long form

    • Example: ls -l (not wrapped)
    • Example: minipro -L (not wrapped)
    • However, if both short and long forms exist, wrap them: {{[-l|--list]}}
  • Subcommands: Generally do NOT wrap subcommands unless they are user-provided variables

    • Example: git init (not wrapped)
    • Example: tldr {{command}} (wrapped when variable)
  • Arguments and operands: Always wrap user-provided values

    • Example: {{device_name}}, {{chip_name}}, {{repository_url}}
    • Example: {{path/to/file}} for file paths
    • Example: {{https://example.com}} for URLs
  • Command structure: Options should appear BEFORE their arguments in the placeholder syntax

    • Correct: command {{[-o|--option]}} {{value}}
    • Incorrect: command -o {{value}}

Lebih banyak skill dari github

console-rendering
github
Instruksi untuk menggunakan sistem rendering konsol berbasis tag struct di Go
official
acquire-codebase-knowledge
github
Gunakan keterampilan ini ketika pengguna secara eksplisit meminta untuk memetakan, mendokumentasikan, atau mempelajari basis kode yang sudah ada. Aktifkan untuk perintah seperti "petakan basis kode ini", "dokumentasikan…
official
acreadiness-assess
github
Run the AgentRC readiness assessment on the current repository and produce a static HTML dashboard at reports/index.html. Wraps `npx github:microsoft/agentrc…
official
acreadiness-generate-instructions
github
Menghasilkan file instruksi agen AI yang disesuaikan melalui perintah instruksi AgentRC. Menghasilkan .github/copilot-instructions.md (default, direkomendasikan untuk Copilot di VS…
official
acreadiness-policy
github
Bantu pengguna memilih, menulis, atau menerapkan kebijakan AgentRC. Kebijakan menyesuaikan penilaian kesiapan dengan menonaktifkan pemeriksaan yang tidak relevan, mengganti dampak/tingkat, mengatur…
official
add-educational-comments
github
Tambahkan komentar edukatif ke file kode untuk mengubahnya menjadi sumber belajar yang efektif. Menyesuaikan kedalaman penjelasan dan nada dengan tiga tingkat pengetahuan yang dapat dikonfigurasi: pemula, menengah, dan mahir. Secara otomatis meminta file jika tidak ada yang disediakan, dengan pencocokan daftar bernomor untuk pemilihan cepat. Memperluas file hingga 125% hanya menggunakan komentar edukatif (batas keras: 400 baris baru; 300 untuk file di atas 1.000 baris). Mempertahankan encoding file, gaya indentasi, kebenaran sintaks, dan...
official
adobe-illustrator-scripting
github
Menulis, men-debug, dan mengoptimalkan skrip otomatisasi Adobe Illustrator menggunakan ExtendScript (JavaScript/JSX). Gunakan saat membuat atau memodifikasi skrip yang memanipulasi…
official
agent-governance
github
Kebijakan deklaratif, klasifikasi intensi, dan jejak audit untuk mengontrol akses dan perilaku alat agen AI. Kebijakan tata kelola yang dapat dikomposisikan mendefinisikan alat yang diizinkan/diblokir, filter konten, batas kecepatan, dan persyaratan persetujuan — disimpan sebagai konfigurasi, bukan kode. Klasifikasi intensi semantik mendeteksi perintah berbahaya (eksfiltrasi data, eskalasi hak istimewa, injeksi perintah) sebelum eksekusi alat menggunakan sinyal berbasis pola. Dekorator tata kelola tingkat alat memberlakukan kebijakan pada fungsi...
official