skills/claude-skills-open/skills/channels/mass-outreach/SKILL.md
Multi-channel outreach via Telegram/Email/WhatsApp
npx skillsauth add aaaaqwq/claude-code-skills mass-outreachInstall this skill globally with one command. Works with Claude Code, Cursor, and Windsurf.
3 of 9 scanners reported clean
Some scanners were skipped, did not run, or reported a non-clean status. Review each row below.
Mass message sending via Telegram, Email, WhatsApp with lessons learned from previous mistakes.
Mistake: Asked people to write an intro who had already done so.
Solution:
ALWAYS check via Telegram API who has already posted in the "Introduction" topic
DO NOT rely on old CSV data
Mistake: Marked a person as "IN GROUP" when they were not in the group.
Solution:
ALWAYS verify membership via client.get_participants(group)
DO NOT rely on notes in CRM
Mistake: Wrong dates in the message (Sunday 9, Monday 10 instead of 8 and 9).
Solution:
from datetime import datetime, timedelta
today = datetime.now()
# Find the nearest Sunday
days_until_sunday = (6 - today.weekday()) % 7
if days_until_sunday == 0:
days_until_sunday = 7
next_sunday = today + timedelta(days=days_until_sunday)
next_monday = next_sunday + timedelta(days=1)
print(f"Sunday: {next_sunday.strftime('%d.%m')}")
print(f"Monday: {next_monday.strftime('%d.%m')}")
Mistake: Did not check sent message history before the campaign.
Solution:
ALWAYS before sending:
1. Get the list of all potential recipients
2. Check outgoing messages for the last N days
3. Exclude those who have already been contacted
4. Show to the user for confirmation
Rules for Telegram:
Rules for Email:
[ ] 1. Dates verified (day of week = date)
[ ] 2. Recipient list verified via API
[ ] 3. Checked who has already received messages
[ ] 4. Checked who has written an intro (if relevant)
[ ] 5. Template shown to user and approved
[ ] 6. Rate limits configured
[ ] 7. There is a plan in case of error
# 1. Data verification
def verify_recipients(group_name, check_intro=True):
# Get all group participants
participants = client.get_participants(group)
# If needed -- check who has written an intro
if check_intro:
intro_messages = client.get_messages(group, limit=2000)
intro_authors = extract_intro_authors(intro_messages)
# Check who has already been contacted
already_sent = check_sent_messages(participants, days=3)
return {
'all': participants,
'with_intro': intro_authors if check_intro else [],
'already_sent': already_sent,
'to_send': [p for p in participants if p not in already_sent]
}
# 2. Sending with rate limiting
def send_with_delay(recipients, message_template, delay=45):
for i, recipient in enumerate(recipients):
try:
message = personalize(message_template, recipient)
client.send_message(recipient, message)
print(f"✓ {i+1}/{len(recipients)} - sent")
if i < len(recipients) - 1:
time.sleep(delay)
except FloodWaitError as e:
print(f"FloodWait: sleeping {e.seconds}s")
time.sleep(e.seconds)
except Exception as e:
print(f"✗ Error: {e}")
log_error(recipient, e)
| What | Path |
|------|------|
| Telegram sessions | $SALES_PATH/telegram/sessions/ |
| CRM contacts | $CRM_PATH/contacts/ |
| Activities | $CRM_PATH/activities.csv |
| Communities | $CRM_PATH/communities/ |
testing
通用自媒体文章自动发布工具。支持百家号、搜狐号、知乎、微信公众号、小红书、抖音号六个平台的自动化发布流程。使用Playwright自动化实现平台导航和发布,支持通过storageState管理Cookie实现账号切换。
development
# SKILL.md - Model Configuration Status (mcstatus) ## 触发条件 - `/mcstatus` 命令 - 用户询问模型配备、模型配置、model status、模型列表等 ## 功能 实时生成 Agent + Cron 的模型配置报告,展示当前所有 agent 的主模型/fallback链和所有 cron 任务的模型分配。 ## 执行步骤 ### Step 1: 收集 Agent 模型配置 读取各 agent 的 models.json 获取主模型和 fallback 链: ```bash for agent in main ops code quant data research content market finance pm law product sales batch; do config=$(cat ~/.openclaw/agents/$agent/agent/models.json 2>/dev/null) if [ -n "$config" ]; then echo "=== $agent
tools
MCP 服务器智能管理助手。自动检测 MCP 可用性、智能开关、功能问答,提供人性化的 MCP 管理体验。
tools
从GitHub搜索并自动安装配置MCP(Model Context Protocol)服务器工具到Claude配置文件。当用户需要安装MCP工具时触发此技能。工作流程:搜索GitHub上的MCP项目 -> 提取npx配置 -> 添加到~/.claude.json -> 处理API密钥(如有)。