telegram-formatting
Telegram HTML and MarkdownV2 formatting reference for clawq message code
- License 许可
- Unlicense
- 最近更新
- 2026-11-12
- Stars
- ★ 0
- Forks
- 0
01 前言 Front Matter
- name
- telegram-formatting
- description
- Telegram HTML and MarkdownV2 formatting reference for clawq message code
03 SKILL.md 正文
Telegram Formatting Skill
Use this skill when writing or modifying code that produces Telegram-formatted messages in clawq.
HTML Mode (preferred for structured output)
Tags
<b>bold</b>,<i>italic</i>,<u>underline</u>,<s>strikethrough</s><code>inline code</code>,<pre>code block</pre><pre><code class="language-python">highlighted</code></pre><a href="URL">link text</a><blockquote>quote</blockquote>,<blockquote expandable>collapsible</blockquote><tg-spoiler>hidden</tg-spoiler>
Escaping (outside tags)
<→<,>→>,&→&
MarkdownV2 Mode (used for agent responses)
Syntax
- Bold:
*text*, Italic:_text_, Code:`text` - Code block:
```lang\n...\n``` - Quote:
>line(per line), Expandable:**>line||(per line)
Must-escape characters
_ * [ ] ( ) ~ ` > # + - = | { } . !
Expandable Blockquote Pattern
Best practice for fitting large content into a single message:
<b>Result:</b> Brief summary here.
<blockquote expandable>
1. Step one details
2. Step two details
3. Step three details
</blockquote>
clawq Conventions
- Max message length: 4096 chars (split via
chunk_textintelegram.ml) send_chunked— sends with optional?parse_mode, splits automaticallysend_chunked_html_with_fallback— sends as HTML, falls back to plain text per chunk on errortelegram_delegate_prompt— wraps user prompt with HTML formatting instructions for delegate/forktelegram_format.ml— MarkdownV2 escaping helpers (escape_mdv2,bold,italic,code_block, etc.)/toolsuses HTML mode with<blockquote expandable>for tool listings- Agent chat responses use MarkdownV2 via
telegram_format.ml - Delegate/fork responses use HTML with fallback
04 同仓库更多 Skills
run-task
Runs a backlog item (bug, feature, task, epic, milestone, phase) end-to-end by gathering context, constructing a startup prompt, spawning a worktree-backed subagent, and managing the claim/done/review cycle. Use when the user wants to execute a backlog target like B123, F456, P2.M4.E3, etc.
pipeline-designer
Design and create structured output pipelines. Gathers requirements, designs step sequences with output schemas, generates valid YAML pipeline definitions, and validates them.
idea
Log a planning idea to the backlog. Use when the user has a feature idea, enhancement suggestion, or brainstorm they want tracked.
feature
Automate the creation of a new feature for clawq. Gathers requirements, discovers existing capabilities, decomposes into implementation layers, gates risky work behind approval, and delegates implementation. Prefers skills/rigs/cron/templates over OCaml code changes.
pag-review-via-team
review work using teams + review-and-fix
clawq-version-bump
Bump clawq version, commit, tag, push, and create a GitHub release