Requirements
- Target platform
- OpenClaw
- Install method
- Manual import
- Extraction
- Extract archive
- Prerequisites
- OpenClaw
- Primary doc
- SKILL.md
Tencent SkillHub Β· AI
tg buttons
Automatically colors Telegram bot choice buttons as default, destructive (red), or secondary (gray) based on the action's criticality and reversibility.
skill openclawclawhub Free
Automatically colors Telegram bot choice buttons as default, destructive (red), or secondary (gray) based on the action's criticality and reversibility.
β¬ 0 downloads β
0 stars Unverified but indexed
Install for OpenClaw
Quick setup
- Download the package from Yavira.
- Extract the archive and review SKILL.md first.
- Import or place the package into your OpenClaw setup.
Package facts
- Download mode
- Yavira redirect
- Package format
- ZIP package
- Source platform
- Tencent SkillHub
- What's included
- SKILL.sh, SKILL.md, scripts/setup_openclaw_bot.sh
Validation
- Use the Yavira download entry.
- Review SKILL.md after the package is downloaded.
- Confirm the extracted package contains the expected setup assets.
Install with your agent
Agent handoff
Hand the extracted package to your coding agent with a concrete install brief instead of figuring it out manually.
- Download the package from Yavira.
- Extract it into a folder your agent can access.
- Paste one of the prompts below and point your agent at the extracted folder.
New install
I downloaded a skill package from Yavira. Read SKILL.md from the extracted folder and install it by following the included instructions. Tell me what you changed and call out any manual steps you could not complete.
Upgrade existing
I downloaded an updated skill package from Yavira. Read SKILL.md from the extracted folder, compare it with my current installation, and upgrade it while preserving any custom configuration unless the package docs explicitly say otherwise. Summarize what changed and any follow-up checks I should run.
Trust & source
Release facts
- Source
- Tencent SkillHub
- Verification
- Indexed source record
- Version
- 1.0.0
Provenance
- Publisher
- dandysuper
- Source page
- View original listing
- Canonical URL
- Open canonical page
Documentation
Purpose
Every time the bot presents choices to the user, it MUST automatically color each button based on how critical, irreversible, or different the choices are. The bot never sends plain/unstyled choice buttons β color is always applied.
Core Rule
Whenever the bot sends 2+ choices to a user, classify each choice and assign a style automatically. This is not optional.
Telegram Bot API β Button Styles
Two fields on InlineKeyboardButton and KeyboardButton: style (String, Optional) β Button color: (omit) β Default accent/blue. The recommended / safe / primary action. "destructive" β Red. Irreversible, dangerous, or high-stakes actions. "secondary" β Gray/muted. Low-priority, dismiss, skip, or neutral actions. icon_custom_emoji_id (String, Optional) β Custom emoji icon on the button.
Automatic Classification Rules
When the bot builds a set of choice buttons, it MUST classify every choice into one of three tiers before sending:
Tier 1 β Default (accent/blue): The recommended path
Apply when the choice is: The safest or most common action A positive confirmation ("Yes", "Continue", "Accept", "Start") The action the bot would recommend Moving forward in a flow Do: omit the style field (or set to null).
Tier 2 β Destructive (red): High-stakes or irreversible
Apply when the choice: Deletes, removes, or permanently changes something Cancels an in-progress operation that loses work Blocks, bans, or restricts a user Rejects, declines, or refuses something important Spends money, tokens, or credits Cannot be undone easily Do: set "style": "destructive".
Tier 3 β Secondary (gray): Low-priority or escape hatch
Apply when the choice: Skips, dismisses, or postpones ("Maybe later", "Not now") Is a neutral fallback ("Back", "Cancel" when nothing is lost) Shows more info without committing ("Details", "Help") Is the least important option in the set Do: set "style": "secondary".
How to Decide β Contrast Matters
When choices differ in criticality, the colors MUST reflect that contrast: High contrast β choices have very different consequences: "Delete my account" β destructive (red) "Keep my account" β default (blue) Medium contrast β one main action, one escape: "Subscribe" β default (blue) "Not now" β secondary (gray) Low contrast β choices are roughly equal: "Option A" β default (blue) "Option B" β default (blue) "Skip" β secondary (gray) Multiple tiers in one set: "Confirm purchase" β default (blue) β recommended "Change amount" β secondary (gray) β neutral/back "Cancel order" β destructive (red) β loses progress
Classification Examples
Bot asks: "Approve this document?" [ [{"text": "β Approve", "callback_data": "approve"}, {"text": "β Reject", "callback_data": "reject", "style": "destructive"}], [{"text": "β Review later", "callback_data": "skip", "style": "secondary"}] ] Bot asks: "Pick a plan:" [ [{"text": "Free Plan", "callback_data": "free"}, {"text": "Pro Plan", "callback_data": "pro"}], [{"text": "Compare plans", "callback_data": "compare", "style": "secondary"}] ] (Equal choices = both default; info link = secondary) Bot asks: "Delete all messages in this chat?" [ [{"text": "π Delete all", "callback_data": "delete_all", "style": "destructive"}], [{"text": "Keep messages", "callback_data": "keep"}] ] (Destructive action is red; safe action is the default blue) Bot asks: "Transfer 500 tokens to @user?" [ [{"text": "Send 500 tokens", "callback_data": "send", "style": "destructive"}, {"text": "Cancel", "callback_data": "cancel", "style": "secondary"}] ] (Spending = destructive since it costs something; cancel = secondary)
Implementation β Python Auto-Classifier
The bot MUST use a classifier function to determine style. Here is the reference implementation: import re # Keywords that signal each tier (case-insensitive, matched against button text + callback_data) DESTRUCTIVE_SIGNALS = [ r"\bdelete\b", r"\bremove\b", r"\bban\b", r"\bblock\b", r"\breject\b", r"\bdecline\b", r"\brevoke\b", r"\bterminate\b", r"\bcancel order\b", r"\bcancel subscription\b", r"\bunsubscribe\b", r"\bdestroy\b", r"\bpurge\b", r"\bspend\b", r"\btransfer\b", r"\bpay\b", r"\bsend.*tokens?\b", r"\breset\b", r"\bclear all\b", r"\bwipe\b", r"\bleave\b", r"\bquit\b", r"\bdisconnect\b", ] SECONDARY_SIGNALS = [ r"\bskip\b", r"\bnot now\b", r"\bmaybe later\b", r"\blater\b", r"\bback\b", r"\bdismiss\b", r"\bclose\b", r"\bdetails\b", r"\bmore info\b", r"\bhelp\b", r"\babout\b", r"\bno thanks\b", r"\bnevermind\b", r"\bcancel$", # plain "cancel" (no lost work) = secondary, not destructive ] def classify_button_style(text: str, callback_data: str = "", context_hint: str = "") -> str | None: """ Automatically determine the button style based on its text and context. Returns: "destructive" β red button (irreversible / high-stakes) "secondary" β gray button (low-priority / dismiss) None β default blue button (primary / recommended) context_hint: optional extra context like "this action costs money" """ combined = f"{text} {callback_data} {context_hint}".lower() # Check destructive first (higher priority) for pattern in DESTRUCTIVE_SIGNALS: if re.search(pattern, combined): return "destructive" # Then secondary for pattern in SECONDARY_SIGNALS: if re.search(pattern, combined): return "secondary" # Default = primary (blue) return None def build_choice_buttons(choices: list[dict]) -> list[list[dict]]: """ Takes a list of raw choices and returns Bot API inline_keyboard rows with styles automatically assigned. Each choice dict: text (str): Button label (required) data (str): callback_data (required unless url is set) url (str): URL button (optional, mutually exclusive with data) style (str|None): Override style β if set, skip auto-classification context (str): Extra hint for classifier (e.g. "costs money") emoji_id (str): Custom emoji ID (optional) row (int): Force button into a specific row (optional) Returns list of rows suitable for inline_keyboard. """ # Group by row row_map: dict[int, list[dict]] = {} auto_row = 0 for i, choice in enumerate(choices): btn: dict = {"text": choice["text"]} # Action if "url" in choice: btn["url"] = choice["url"] else: btn["callback_data"] = choice.get("data", choice["text"].lower().replace(" ", "_")) # Style β use override if provided, else auto-classify if "style" in choice and choice["style"] is not None: btn["style"] = choice["style"] else: auto_style = classify_button_style( choice["text"], choice.get("data", ""), choice.get("context", ""), ) if auto_style: btn["style"] = auto_style # Custom emoji if "emoji_id" in choice: btn["icon_custom_emoji_id"] = choice["emoji_id"] # Row assignment target_row = choice.get("row", auto_row) row_map.setdefault(target_row, []).append(btn) # Auto-advance row every 2 buttons if len(row_map.get(auto_row, [])) >= 2: auto_row += 1 return [row_map[k] for k in sorted(row_map.keys())]
Using the classifier in the bot:
import requests def send_choices(bot_token, chat_id, text, choices, parse_mode="HTML"): """Send a message with auto-colored choice buttons.""" keyboard = build_choice_buttons(choices) payload = { "chat_id": chat_id, "text": text, "parse_mode": parse_mode, "reply_markup": {"inline_keyboard": keyboard}, } url = f"https://api.telegram.org/bot{bot_token}/sendMessage" resp = requests.post(url, json=payload) resp.raise_for_status() return resp.json() # The bot just passes raw choices β colors are assigned automatically: send_choices(TOKEN, chat_id, "Approve this document?", [ {"text": "β Approve", "data": "approve"}, {"text": "β Reject", "data": "reject"}, # auto β destructive (red) {"text": "β Review later", "data": "later"}, # auto β secondary (gray) ])
Usage with python-telegram-bot library
If the library version does not yet expose style, pass it via api_kwargs. from telegram import InlineKeyboardButton, InlineKeyboardMarkup def auto_button(text, callback_data, context=""): style = classify_button_style(text, callback_data, context) kwargs = {"style": style} if style else {} return InlineKeyboardButton(text, callback_data=callback_data, api_kwargs=kwargs) keyboard = InlineKeyboardMarkup([ [auto_button("Approve", "approve"), auto_button("Reject", "reject")], [auto_button("Skip", "skip")], ]) await update.message.reply_text("Pick an option:", reply_markup=keyboard)
Reply Keyboard β Same Rules Apply
{ "chat_id": "<CHAT_ID>", "text": "Delete your data?", "reply_markup": { "keyboard": [ [ {"text": "Keep my data"}, {"text": "Delete everything", "style": "destructive"} ] ], "resize_keyboard": true, "one_time_keyboard": true } }
Custom Emoji on Buttons
Can be combined with style on the same button: {"text": "Boost", "callback_data": "boost", "style": "destructive", "icon_custom_emoji_id": "5368324170671202286"}
Shell Helper
Quick test with colored buttons: ./SKILL.sh <BOT_TOKEN> <CHAT_ID>
References
Telegram Bot API: https://core.telegram.org/bots/api Bot API Changelog: https://core.telegram.org/bots/api-changelog Telegram Blog Announcement: https://telegram.org/blog/crafting-android-design-and-more
Category context
Agent frameworks, memory systems, reasoning layers, and model-native orchestration.
Source: Tencent SkillHub
Largest current source with strong distribution and engagement signals.
Package contents
Included in package
2 Scripts1 Docs
- SKILL.md
- scripts/setup_openclaw_bot.sh
- SKILL.sh