安全

Hermes Email Skill

试用

Use when Codex, Hermes, OpenClaw, Claude Code, Cowork, or another AI agent needs to plan, review, implement, audit, or improve email work focused on fast del...

它能做什么

Move quickly, but make the launch state explicit. Focus on the decision a human needs now: hold, fix, approve, or monitor.

技能文档

Hermes Email Skill

Move quickly, but make the launch state explicit. Focus on the decision a human needs now: hold, fix, approve, or monitor.

Agent Contract

The agent may inspect, reason, draft, critique, and prepare handoffs for fast delivery decisions, message QA, launch coordination, and concise status handoffs.

  • Primary lens: fast delivery decisions, message QA, launch coordination, and concise status handoffs.
  • Common request signals: preflight checklists, launch-room summaries, transactional copy reviews, escalation notes, and send readiness calls.
  • Default posture: Move quickly, but make the launch state explicit. Focus on the decision a human needs now: hold, fix, approve, or monitor.

Use Cases

Typical requests include preflight checklists, launch-room summaries, transactional copy reviews, escalation notes, and send readiness calls.

Runbook

  • State the launch context: what is sending, to whom, through which provider, and by what deadline.
  • Find the blocking risk first: incorrect audience, broken personalization, deliverability issue, compliance issue, missing approval, or unclear CTA.
  • Run a compressed preflight across copy, links, rendering, segment logic, exclusions, sender identity, and tracking.
  • Summarize the current status in decision language: ready, ready with caveats, blocked, or needs review.
  • When triaging an incident, create a timeline of observed behavior, suspected cause, blast radius, mitigation, and next owner.
  • Keep all live send, resend, cancellation, suppression, and DNS actions behind explicit approval.

Quality Bar

  • The status can be understood by a launch-room participant in under a minute.
  • Critical defects are separated from polish issues.
  • The recommended action names the owner and deadline.
  • Transactional and lifecycle messages preserve the user promise exactly.
  • Monitoring notes include what to watch after approval.

Output Pattern

Return launch summaries, preflight tables, incident timelines, transactional copy notes, and approve-or-hold recommendations. Keep recommendations concrete. Separate analysis from live-system actions, and require explicit approval before sending email, importing contacts, changing DNS, altering suppression rules, or editing production automations.

相关技能

在本地磁盘以分类纯 Markdown 文件保存需要长期留存的事实,与智能体内置记忆并存。

作者 Iván559 次安装18 星标

把自然语言描述转为结构化 JSON,并由 mcp-diagram-generator MCP 服务生成 Draw.io、Mermaid 或 Excalidraw 图表文件。

作者 nssa.io1.0k 次安装47 星标

以 AI 机器人身份加入视频会议,提供语音、虚拟形象与屏幕共享四种模式。

作者 johnpatternai22 次安装8 星标

诊断生产力系统反复失效的根因,给出最小干预——容量测算、瓶颈定位、可靠的本地记录。

作者 Iván855 次安装69 星标

从 AdMapix API 拉取广告创意、应用、榜单和收入预估等数据,原样返回结构化 JSON。

作者 fly0pants4.3k 次安装296 星标

polnikale 的更多技能

浏览全部技能

把泛指的 Sequenzy 请求路由到正确的命令、工具或反馈路径,避免承诺尚未接通的功能。

作者 polnikale27 次安装

通过已验证的 CLI 与 MCP 工作流操作 Sequenzy 邮件营销,覆盖订阅者、营销活动、序列与统计数据。

作者 polnikale19 次安装

Use when Codex, Hermes, OpenClaw, Claude Code, Cowork, or another AI agent needs to plan, review, implement, audit, or improve email work focused on responsi...

作者 polnikale3 次安装

Use when Codex, Hermes, OpenClaw, Claude Code, Cowork, or another AI agent needs to plan, review, implement, audit, or improve email work focused on Claude-o...

作者 polnikale3 次安装

Use when Codex, Hermes, OpenClaw, Claude Code, Cowork, or another AI agent needs to plan, review, implement, audit, or improve email work focused on agentic...

作者 polnikale1 次安装

Use when Codex, Hermes, OpenClaw, Claude Code, Cowork, or another AI agent needs to plan, review, implement, audit, or improve email work focused on behavior...

作者 polnikale1 次安装