← 返回
未分类 Key

Ldm Openclaw Skill

Run an LDM inbox placement and deliverability preflight before OpenClaw agents send outbound email campaigns.
在 OpenClaw 代理发送外发邮件营销活动前,运行 LDM 收件箱投放及送达能力预检。
live-direct-marketing
未分类 clawhub v1.0.0 1 版本 100000 Key: 需要
★ 0
Stars
📥 295
下载
💾 0
安装
1
版本
#latest

概述

LDM Deliverability Check

Use this skill whenever the agent is preparing, approving, or sending cold email, recruiting outreach, investor updates, deal-flow notifications, partnership outreach, or any other bulk outbound email.

The purpose of this skill is to prevent an OpenClaw agent from sending messages that are likely to land in spam, promotions, or fail authentication checks.

When To Use

Always run an LDM deliverability preflight before:

  • sending a cold email campaign
  • sending more than 5 similar outbound emails
  • scheduling a bulk send
  • approving outreach generated by another agent
  • sending from a new domain or mailbox
  • changing subject lines, links, templates, or tracking settings

For one-off personal emails, use this skill only when the user asks for deliverability or spam-risk review.

Policy

Before bulk outbound, call the LDM checker and evaluate:

  • inbox placement across major mailbox providers
  • spam, promotions, or junk folder placement
  • SPF, DKIM, and DMARC authentication signals
  • spam-score and content-risk signals
  • risky links, redirects, URL shorteners, or broken links
  • unsubscribe and compliance issues
  • HTML structure, image/text ratio, and suspicious formatting

If inbox placement is below the configured threshold, pause the campaign and report fixes instead of sending.

Default threshold: 70% inbox placement.

API Configuration

Set these environment variables:

LDM_API_BASE=https://check.live-direct-marketing.online
LDM_API_KEY=your_ldm_api_key
LDM_INBOX_THRESHOLD=70

If no API key is configured, tell the user that the LDM API key is missing and ask them to configure it before sending bulk outbound.

Agent Behavior

When the user asks to send or schedule outbound email:

  1. Draft or collect the final subject, sender domain, sender mailbox, HTML/text body, links, and target provider mix.
  2. Run the LDM preflight check.
  3. If the result passes, summarize the result and continue.
  4. If the result fails, do not send. Report the top deliverability risks and concrete changes.
  5. After changes, run the check again before sending.

Result Format

Report the result in this format:

LDM deliverability preflight: PASS/FAIL
Inbox placement: N%
Risk level: low/medium/high
Provider issues: Gmail: ..., Outlook: ..., Yahoo: ...
Authentication: SPF ..., DKIM ..., DMARC ...
Content risks: ...
Recommended fixes: ...
Decision: send / revise / pause

Example Instruction

Use this policy for autonomous outbound agents:

Always run ldm_check before bulk outbound. If inbox placement is below 70%, stop and report fixes instead of sending.

Safety

Never bypass a failed deliverability preflight for bulk outbound unless the user explicitly confirms that they want to send despite the risk.

Never expose the LDM API key in logs, chat messages, pull requests, or generated files.

版本历史

共 1 个版本

  • v1.0.0 当前
    2026-05-20 05:28 安全 安全

安全检测

腾讯云安全 (Keen)

安全,无风险
查看报告

腾讯云安全 (Sanbu)

安全,无风险
查看报告

🔗 相关推荐

security-compliance

Skill Vetter

spclaudehome
AI智能体技能安全预审工具。安装ClawdHub、GitHub等来源技能前,检查风险信号、权限范围及可疑模式。
★ 1,215 📥 266,539
developer-tools

Github

steipete
使用 `gh` CLI 与 GitHub 交互,通过 `gh issue`、`gh pr`、`gh run` 和 `gh api` 管理议题、PR、CI 运行及高级查询。
★ 668 📥 324,162
ai-intelligence

ontology

oswalpalash
类型化知识图谱,用于结构化智能体记忆与可组合技能。支持创建/查询实体(人员、项目、任务、事件、文档)及关联...
★ 712 📥 243,832