skills/claude-skills-open/skills/agents/email-outreach-run/SKILL.md
Automatic email outreach agent run
npx skillsauth add aaaaqwq/agi-super-skills email-outreach-runInstall 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.
Send mass email campaigns with personalization and approval workflow
google-auth skill if needed)sales/crm/)CRM Segment Mode:
cd $AGENTS_PATH/email-outreach
python3 email-outreach_agent.py \
--segment "stage=new AND product_id=prod-labeling" \
--template templates/cold_outreach.txt
Manual CSV Mode:
python3 email-outreach_agent.py \
--recipients /path/to/recipients.csv \
--template templates/training_reminder.txt
AI-Generated Mode:
python3 email-outreach_agent.py \
--segment "stage=qualified" \
--ai-mode \
--subject "Following up on our conversation"
python3 email-outreach_agent.py \
--segment "..." \
--template templates/cold_outreach.txt \
--dry-run
Agent shows:
Options:
[A] - Approve and send[T] - Send test to [email protected][C] - Cancel (save draft)# Summary
ls -lh $GOOGLE_TOOLS_PATH/data/email_outreach_summaries/
# Agent log
cat $GOOGLE_TOOLS_PATH/data/email_outreach_log.json | jq '.[-1]'
# CRM activities
tail -10 $CRM_PATH/activities.csv
Available templates in agents/email-outreach/templates/:
cold_outreach.txt - For new leadsfollow_up.txt - Follow-up to previous contacttraining_reminder.txt - Event/training remindersPlaceholders:
{name} - Full name{first_name} - First name{last_name} - Last name{company} / {company_name} - Company name{role} - Job roleFilter CRM leads:
# New leads for specific product
--segment "stage=new AND product_id=prod-labeling"
# Qualified leads
--segment "stage=qualified"
# Custom filters
--segment "stage=new AND product_id=prod-training"
| Error | Action |
|-------|--------|
| "Gmail credentials not found" | Run google-auth skill |
| "Daily limit reached" | Wait until tomorrow |
| "No recipients match" | Check segment query, verify CRM data |
| "Invalid email" | Check CSV, emails will be skipped |
email,first_name,last_name,company_name
[email protected],John,Doe,Example Corp
[email protected],Jane,Smith,Test Inc
Required: email
Optional: first_name, last_name, company_name, person_id, product_id
python3 email-outreach_agent.py \
--segment "stage=new AND product_id=prod-labeling" \
--template templates/cold_outreach.txt \
--campaign-name "Q1 Cold Outreach - Labeling"
# Create CSV with participants
cat > participants.csv << 'EOF'
email,first_name
[email protected],John
[email protected],Jane
EOF
python3 email-outreach_agent.py \
--recipients participants.csv \
--template templates/training_reminder.txt
python3 email-outreach_agent.py \
--segment "stage=qualified" \
--ai-mode \
--subject "Following up on data labeling project"
# Run unit tests
cd $AGENTS_PATH/email-outreach
python3 test_email_outreach.py
# Dry-run test
python3 email-outreach_agent.py \
--recipients test_data/test_recipients.csv \
--template test_data/test_template.txt \
--dry-run
google-tools/data/email_outreach_summaries/YYYY-MM-DD.mdgoogle-tools/data/email_outreach_log.jsonsales/crm/activities.csv (appended)google-tools/data/email_outreach_drafts/google-auth (if Gmail auth needed)change-review for CRM updates# Check Gmail API
python3 -c "from google.oauth2.credentials import Credentials; print(Credentials.from_authorized_user_file('$GOOGLE_TOOLS_PATH/token.json'))"
# Re-auth if needed
# Run google-auth skill
# Check CSV has the required columns
head -1 recipients.csv
# Placeholders case-sensitive: {name} not {Name}
# Check send log
cat $GOOGLE_TOOLS_PATH/data/email_send_log.json | jq '[.[] | select(.date == "2026-02-12")] | length'
# Wait until tomorrow or increase limit in config.json
✅ Human approval required for ALL outreach
✅ Rate limit: 50/day max
✅ Logs to CRM activities
✅ Dry-run flag mandatory for testing
✅ Uses claude -p --model haiku (not API key)
✅ Idempotent (re-run safe)
$AGENTS_PATH/email-outreach/email-outreach_agent.py$AGENTS_PATH/email-outreach/config.json$AGENTS_PATH/email-outreach/templates/$AGENTS_PATH/specs/email-outreach.spec.mdgoogle-auth - Gmail API authtelegram-send - Parallel outreach channeladd-lead - Add new contactslog-activity - Manual activity loggingtesting
AI驱动的智能浏览器自动化工具。使用LLM理解页面并自动执行任务,比传统Playwright更智能、更省token。适用于复杂交互、动态页面、需要智能决策的浏览器操作。Chrome浏览器优先。
tools
网页登录态管理。使用 fast-browser-use (fbu) 管理各平台登录状态,定期检查可用性,新平台授权时自动保存 profile。
development
Monitor and report on API provider quotas, balances, and usage. Query official providers (Moonshot, DeepSeek, xAI, Google AI Studio) and relay/proxy providers (Xingjiabiapi, Aixn, WoW) via their billing APIs. Also checks subscription services (Brave Search, OpenRouter). Generates quota reports. Triggers on "查额度", "API余额", "quota check", "billing report", "api balance", "供应商额度", "中转站余额", "费用报告", "check balance", "how much credit".
development
# A股基金监控 Skill A股基金净值监控,支持实时估值和盘后净值,自动判断交易日/节假日。 ## 用法 ### 快速监控(命令行) ```bash # 默认配置,输出到控制台 bash ~/clawd/skills/a-fund-monitor/scripts/monitor.sh # 推送到群(使用--push参数) bash ~/clawd/skills/a-fund-monitor/scripts/monitor.sh --push # 监控指定基金 bash ~/clawd/skills/a-fund-monitor/scripts/monitor.sh --codes "000979 002943" ``` ### Agent调用 ``` 执行A股基金监控任务。 1. 读取配置文件: ~/clawd/skills/a-fund-monitor/config.json 2. 获取实时净值数据 3. 非交易日自动切换为简短报告 配置文件格式: { "funds": [ {"code": "000979", "name": "景顺长城沪港深精选股票