Skills message-split

长消息自动拆分 skill。当回复内容超过渠道限制时,自动将消息拆分为多条有序发送,避免截断或丢消息。Auto-split long messages into smaller chunks before sending, with sequence markers.

install
source · Clone the upstream repo
git clone https://github.com/openclaw/skills
Claude Code · Install into ~/.claude/skills/
T=$(mktemp -d) && git clone --depth=1 https://github.com/openclaw/skills "$T" && mkdir -p ~/.claude/skills && cp -r "$T/skills/54meteor/message-split" ~/.claude/skills/openclaw-skills-message-split && rm -rf "$T"
OpenClaw · Install into ~/.openclaw/skills/
T=$(mktemp -d) && git clone --depth=1 https://github.com/openclaw/skills "$T" && mkdir -p ~/.openclaw/skills && cp -r "$T/skills/54meteor/message-split" ~/.openclaw/skills/openclaw-skills-message-split && rm -rf "$T"
manifest: skills/54meteor/message-split/SKILL.md
source content

Message Split Skill

Problem

Many messaging channels (Feishu, Telegram, etc.) have a per-message character limit (~4000 chars for Feishu). When a response exceeds this limit, it either gets truncated or silently fails, leaving the user with no feedback.

Solution

Before sending any message, check its length and split if necessary.

Usage

def send_long_message(text, channel="{active_channel}"):
    """
    Send a message, splitting it into multiple chunks if it exceeds the length limit.
    
    Args:
        text: The message text to send
        channel: Target channel (feishu/telegram/discord/whatsapp/signal/imessage/openclaw-weixin)
    
    Returns:
        Number of chunks sent
    """
    MAX_LEN = 3600  # Feishu limit with margin
    CHUNK_HEADER = "[{i}/{total}]\n"
    
    if len(text) <= MAX_LEN:
        message(action="send", channel=channel, message=text)
        return 1
    
    chunks = split_text(text, MAX_LEN)
    total = len(chunks)
    
    for i, chunk in enumerate(chunks, 1):
        header = f"[{i}/{total}]\n" if total > 1 else ""
        message(action="send", channel=channel, message=header + chunk)
    
    return total


def split_text(text, max_len):
    """
    Split text into chunks of at most max_len characters.
    Attempts to split at sentence boundaries or line breaks for readability.
    """
    import re
    
    # Try to split at sentence-ending punctuation first
    sentence_split = re.split(r'(?<=[。!?.!?])\s+', text)
    
    chunks = []
    current = ""
    
    for sentence in sentence_split:
        if len(current) + len(sentence) + 1 <= max_len:
            current += (" " + sentence if current else sentence)
        else:
            if current:
                chunks.append(current)
            # If single sentence exceeds limit, split by words/characters
            if len(sentence) > max_len:
                for i in range(0, len(sentence), max_len - 100):
                    chunks.append(sentence[i:i + max_len - 100])
                current = ""
            else:
                current = sentence
    
    if current:
        chunks.append(current)
    
    return chunks

Channel Limits Reference

ChannelMax chars (approx)Notes
Feishu4000Hard limit
Telegram4096
Discord2000Embed limit 6000
WhatsApp65000But relayed messages get truncated
Signal700Very low
iMessage~4000Via macOS relay

Notes

  • Always use
    MAX_LEN = 3600
    as a safe default (leaves room for header)
  • If channel is unknown, default to feishu behavior
  • Splitting is done on word/sentence boundaries when possible to preserve readability
  • Sequence headers
    [{i}/{total}]
    are only added when
    total > 1