Token导航 LogoToken导航

Agent Skill · 效率

discord-markdown(Discord Markdown 控制)

用于处理 Discord 服务器、频道、消息、成员和机器人交互。它适合让 Agent 辅助查询社区对话、整理频道内容、发布通知或管理基础协作流程。使用时需要确认 bot 权限、频道可见范围和服务器规则;涉及删除消息、管理成员、批量通知或读取私密频道时,应先获得明确授权并控制操作范围。

discord-markdown 是效率类 Agent Skill,可用宿主为 OpenClaw,通过ClawHub获取,权限为只读;许可证为 MIT-0,第三方扫描已通过,按安装量在效率类的 21,003 个 Skill 里排第 4,030。

总安装 14,629周安装 622GitHub Stars 1下载 5,125核验 2026-05-01

安装说明

本站只整理中文说明,不托管安装包,也不代用户安装。
GitHub
许可证
MIT-0
版本
1.0.0

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:discord-markdown(Discord Markdown 控制)
来源仓库:https://github.com/billchirico/discord-markdown
安装命令:
openclaw skills install discord-markdown
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 OpenClaw 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。

ClawHubOpenClaw
openclaw skills install discord-markdown

这个 Skill 是做什么的

效率类 Skill 把重复的整理、汇总、转换工作交给助手完成,减少手工复制粘贴。

将标准 Markdown 语法转换为 Discord 兼容格式。渲染代码块表格图片等富文本元素增强可读性。统一跨平台内容发布时的排版一致性体验。discord-markdown 属于效率类 Skill,可作为该场景下的辅助能力补充。某些扩展语法如 Mermaid 图仍需额外启用支持。

输出前建议预览效果防止样式错乱影响观感。

上手步骤

4 步
  1. 1

    确认自己的宿主工具

    公开资料标注支持 OpenClaw;先确认自己用的是其中之一,再按对应工具的 Skills 目录放置。

  2. 2

    拿到安装命令

    可以直接复制的命令是 openclaw skills install discord-markdown;命令里的占位符换成自己的路径或密钥再执行。

  3. 3

    安装后重启宿主

    命令执行完要完全退出宿主工具再打开,让新装的 Skill 被重新扫描到,否则列表里可能看不到。

  4. 4

    按最小权限试用

    它标注为只读,先用只读任务试一次,确认行为符合预期再扩大使用范围。

常见问题

6 条

discord-markdown 怎么安装?

在终端执行 openclaw skills install discord-markdown。装完完全退出宿主工具再打开,让它重新扫描本地 Skill。

discord-markdown 支持哪些 AI 工具?

公开资料标注支持 OpenClaw。其他工具只要能读取本地 Skill 目录,一般也能手动放进去,但要自己确认触发方式是否一致。

discord-markdown 需要什么权限?

权限级别是只读。该 Skill 主要提供规则、说明或参考内容,本身偏只读;真正读写文件、联网或执行命令仍取决于宿主 Agent 的任务。

discord-markdown 是免费的吗?

来源标注的许可证是 MIT-0。本站不代收任何费用,也不托管安装包;能否商用、要不要署名,以许可证原文为准。

discord-markdown 用的人多吗?

公开数据是累计安装 14,629 次,近一周安装 622 次,下载 5,125 次,GitHub 1 星。这些数字来自第三方目录统计,只能当作热度参考,不代表质量或安全性。

discord-markdown 安全吗?

第三方扫描结果为通过,但这只覆盖已知的静态检查项,不能替代自己读一遍源码和安装命令。

值得选的地方和要先想清楚的地方

值得选的地方

  • 专注 OpenClaw 一种宿主,触发方式和使用习惯不用来回切换。
  • 许可证明确为 MIT-0,商用和分发边界好判断。
  • 第三方扫描已通过,常见的高风险行为没有命中。
  • 标注为只读权限,试用阶段不容易误改本地文件。

先想清楚的地方

  • 第三方目录整理,版本更新和行为细节以来源仓库为准。

适不适合你

更适合

  • 已经在用 OpenClaw,想直接扩展它能力的人。
  • 需要处理效率类任务、又不想每次都手写提示词的人。
  • 需要许可证清楚、并且有第三方扫描结果的团队项目。

不太适合

  • 需要厂商级技术支持和 SLA 的生产系统。

效率类 Skill 对比

6 个同类
Skill总安装GitHub 星权限许可证扫描
github

GitHub 代码协作 · OpenClaw

7,632,918545需要联网MIT-0通过
nano-pdf

Nano PDF 文档 · OpenClaw

4,249,476231需要联网MIT-0通过
auto-updater

自动更新程序 · OpenClaw

2,964,063386操作浏览器MIT-0通过
video-frames

视频帧 · OpenClaw

2,621,304112需要联网MIT-0通过
gemini

Gemini 助手 · OpenClaw

2,547,39648需要联网MIT-0有提醒
discord-markdown

Discord Markdown 控制 · 本页

14,6291只读MIT-0通过

按安装量取同分类前几名;数字来自第三方目录统计,只作热度参考,不代表质量结论。

SKILL.md 原文

name
discord-markdown
description
Format text for Discord using markdown syntax. Use when composing Discord messages, bot responses, embed descriptions, forum posts, webhook payloads, or any content destined for Discord's chat interface. Triggers on requests mentioning Discord formatting, Discord messages, Discord bots, Discord embeds, or when the user needs text styled for Discord's rendering engine. Covers bold, italic, underline, strikethrough, spoilers, code blocks with syntax highlighting, headers, subtext, lists, block quotes, masked links, timestamps, and mentions. Always presents Discord-ready messages inside fenced code blocks so the user can copy-paste them directly into Discord with all markdown formatting preserved.

Discord Markdown Formatting

Format text for Discord's chat rendering engine. Discord uses a modified subset of Markdown with some unique additions (spoilers, timestamps, subtext, guild navigation).

Output Presentation — CRITICAL

When composing a Discord message for the user, always present the final message inside a fenced code block so the user can copy-paste it directly into Discord with all markdown formatting intact.

Why: Claude's chat interface renders markdown (e.g., **bold** becomes bold). If the user copies rendered text, the markdown syntax is stripped and the message loses its formatting when pasted into Discord. A code block preserves the raw syntax.

How to Present Discord Messages

Always wrap the final copy-paste-ready message in a fenced code block with the markdown language tag:

🚀 Announcement

This is bold and ~~this is struck~~ and ||this is a spoiler||

Block quote here

-# Subtext footer

Rules

  1. Always use a fenced code block — Triple backticks with markdown language identifier
  2. The ENTIRE message goes in ONE block — Everything the user will paste into Discord lives inside a single fenced code block. No part of the Discord message should ever appear outside the block as rendered markdown
  3. Explain outside the block — Put any notes, options, or context _before_ or _after_ the code block, never inside it
  4. Handle nested code blocks — If the Discord message itself contains code blocks, use four backticks (``````) as the outer fence so the inner triple backticks are preserved. The user copies everything between the outer fence — the inner triple backticks are part of the Discord message:

Here's some code:

console.log("hello");

Pretty cool right?

  1. Multiple messages = multiple blocks — If providing alternatives or a multi-message sequence, use a separate code block for each with a label above it
  2. Message metadata summary — Always display a metadata summary table immediately after every Discord message code block (see below)
  3. Templates too — When presenting templates from the reference files, they should also be in copyable code blocks following these same rules
  4. Never partially render — Do NOT put headers, bold text, code snippets, or any other Discord-formatted content outside the code block. If it's part of the Discord message, it goes inside the block. The user should never have to assemble a message from rendered markdown and code blocks

Message Metadata Summary

After every Discord message code block, include a summary table with the following stats:

StatDescriptionHow to Count
CharactersTotal character count of the messageCount all characters inside the code block. Show as X / 2,000 for chat messages or X / 4,096 for embed descriptions
SectionsNumber of header-delimited sectionsCount all #, ##, ### headers. If no headers, show 0
User MentionsUsers mentioned via <@USER_ID> or <@!USER_ID>Count unique <@...> patterns (not role mentions)
Role MentionsRoles mentioned via <@&ROLE_ID>Count unique <@&...> patterns. Include @everyone and @here
Channel MentionsChannels linked via <#CHANNEL_ID> or <id:...>Count unique <#...> and <id:...> patterns
URLsLinks in the messageCount raw URLs and masked links [text](url)
Code BlocksCode blocks with language infoIf the message contains fenced code blocks, list languages used (e.g., javascript, bash). Show — if none

Format the summary as a compact table directly below the code block:

| Stat               | Value          |
|--------------------|----------------|
| Characters         | 437 / 2,000    |
| Sections           | 3              |
| User Mentions      | 1              |
| Role Mentions      | 1 (@everyone)  |
| Channel Mentions   | 0              |
| URLs               | 0              |
| Code Blocks        | —              |

Notes:

  • For role mentions, parenthetically note if @everyone or @here is included since those ping the entire server
  • For code blocks, list each language, e.g. javascript, bash — or (no lang) if the block has no language identifier
  • If characters exceed 80% of the limit, add a ⚠️ warning
  • If characters exceed the limit, add a 🚫 and suggest splitting the message

Example Interaction

User: "Write me a Discord announcement about a new SDK release that includes code examples"

Claude's response should look like:

Here's your SDK announcement:

# 🚀 Volvox SDK v2.0 — Breaking Changes

Hey @everyone — we just shipped **v2.0** of the SDK and there are a few things you need to know before upgrading.

## What Changed

The `createJar` method now accepts an options object instead of positional arguments:

**Before:**

const jar = createJar("Lunch Spots", ["Chipotle", "Sweetgreen"], true);


**After:**

const jar = createJar({ name: "Lunch Spots", options: ["Chipotle", "Sweetgreen"], allowDuplicates: true, });


## New: Shake Events

jar.on("shake", (result) => { console.log(🎉 Selected: ${result.option}); });


> 💡 Full migration guide pinned in <#dev-resources>

Drop questions in <#sdk-support> — <@core-team> is standing by. 🫡

-# v2.0.0 • <t:1770537600:D>
StatValue
Characters659 / 2,000
Sections3
User Mentions1
Role Mentions1 (@everyone)
Channel Mentions2
URLs0
Code Blocks3 — ts, ts, ts

Key: Notice the outer fence uses four backticks (``````) because the Discord message contains inner triple-backtick code blocks. The user copies everything between the outer fence — inner backticks are part of the message.


Quick Reference

StyleSyntaxRenders As
Bold**text**text
Italic*text* or _text__text_
Underline__text__underlined text
Strikethrough~~text~~~~text~~
Spoiler`\\text\\`hidden until clicked
Inline code` code `monospaced
Bold italic***text***_text_
Underline italic__*text*__underlined italic
Underline bold__**text**__underlined bold
Underline bold italic__***text***__all three
Strikethrough bold~~**text**~~struck bold

Text Formatting

Emphasis

*italic* or _italic_
**bold**
***bold italic***
__underline__
~~strikethrough~~
||spoiler text||

Combining Styles

Nest formatting markers from outside in. Discord resolves them in this order: underline → bold → italic → strikethrough.

__**bold underline**__
__*italic underline*__
__***bold italic underline***__
~~**bold strikethrough**~~
~~__**bold underline strikethrough**__~~
||**bold spoiler**||

Escaping

Prefix any markdown character with \ to display it literally:

\*not italic\*
\*\*not bold\*\*
\|\|not a spoiler\|\|

Headers

Headers require # at the start of a line followed by a space. Only three levels are supported.

# Large Header
## Medium Header
### Small Header

Important: Headers do not work inline. The # must be the first character on the line.

Subtext

Small, muted gray text below content. Useful for footnotes, disclaimers, or attribution.

-# This renders as subtext

Block Quotes

Single-line

> This is a single block quote

Multi-line

Everything after >>> (including subsequent lines) becomes quoted:

>>> This entire block
including this line
and this line
are all quoted

Lists

Unordered

Use - or * with a space. Indent with spaces for nesting:

- Item one
- Item two
  - Nested item
  - Another nested item
    - Deep nested

Ordered

1. First item
2. Second item
3. Third item

Auto-numbering trick: Discord auto-increments if you repeat 1.:

1. First
1. Second (renders as 2.)
1. Third (renders as 3.)

Code Blocks

Inline Code

Use `inline code` for short snippets

Multi-line Code Block

Wrap code with triple backticks on their own lines:

function hello() { return "world"; }

Syntax Highlighting

Add a language identifier after the opening backticks:

function hello() { return "world"; }

See references/syntax-highlighting.md for the full list of supported languages.

Commonly used languages: javascript, typescript, python, csharp, json, bash, css, html, sql, yaml, diff, markdown

Links

Masked Links

[Click here](https://example.com)

Note: Masked links work in embeds and some contexts, but regular chat may show a preview. Discord may suppress masked links from bots in certain conditions.

Auto-linking

Discord auto-links any valid URL pasted directly:

Check out https://example.com for more info

Suppressing Link Previews

Wrap a URL in angle brackets to prevent Discord from generating a preview embed:

<https://example.com>

Timestamps

Dynamic timestamps that display in each user's local timezone.

Format: <t:UNIX_TIMESTAMP:FORMAT_FLAG>

FlagOutput StyleExample
tShort time4:20 PM
TLong time4:20:30 PM
dShort date02/08/2026
DLong dateFebruary 8, 2026
fShort date/time (default)February 8, 2026 4:20 PM
FLong date/timeSunday, February 8, 2026 4:20 PM
RRelative2 hours ago

Example:

Event starts <t:1770537600:F>
That was <t:1770537600:R>

Tip: Use Math.floor(Date.now() / 1000) or date +%s to get the current Unix timestamp.

Mentions & References

<@USER_ID>          → @username mention
<@!USER_ID>         → @username mention (nickname format)
<@&ROLE_ID>         → @role mention
<#CHANNEL_ID>       → #channel link
<id:browse>         → Browse Channels link
<id:customize>      → Customize Community link
<id:guide>          → Server Guide link
<id:linked-roles>   → Linked Roles link

Emoji

:emoji_name:                    → Standard/custom emoji
<:emoji_name:EMOJI_ID>          → Custom emoji
<a:emoji_name:EMOJI_ID>         → Animated custom emoji

Discord-Specific Gotchas

  1. No nested block quotes — Discord does not support >> for nested quotes
  2. Headers need line start — # must be the first character on the line (not inline)
  3. Underline is NOT standard Markdown — __text__ underlines in Discord but bolds in standard Markdown
  4. Spoilers are Discord-only — ||text|| has no equivalent in standard Markdown
  5. Lists need a blank line — Start lists after a blank line or they may not render
  6. Embed markdown differs — Some formatting behaves differently in embeds vs chat messages
  7. 2000 character limit — Standard messages max at 2,000 characters; nitro users get 4,000
  8. Embed description limit — Embed descriptions max at 4,096 characters
  9. Code block language names are case-insensitive — JS, js, and JavaScript all work

Formatting for Different Contexts

Reminder: Regardless of context, always present the final Discord-ready message inside a fenced code block so the user can copy-paste it directly. See "Output Presentation" above.

Chat Messages

Full markdown support. 2,000 character limit (4,000 with Nitro).

Embed Descriptions

Full markdown support. 4,096 character limit. Masked links work reliably here.

Embed Field Values

Limited markdown. 1,024 character limit per field.

Bot Messages / Webhooks

Full markdown support. Same as chat messages. Use embeds for richer formatting.

Forum Posts

Full markdown support in the post body. Title is plain text only.

Resources

平台分布

OpenClaw

92.93%
按下载量换算4,763

安全审计

VirusTotal

通过

ClawScan

通过

Static analysis

未展示

权限和风险

只读

该 Skill 主要提供规则、说明或参考内容,本身偏只读;真正读写文件、联网或执行命令仍取决于宿主 Agent 的任务。

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。目前只有一个公开来源,建议同时核对源仓库。

继续浏览同类 Skills