深度解析长周期、多参与方、多线程的邮件往来记录。当用户发送 .eml 文件或粘贴邮件正文时自动触发。自动过滤社交辞令，梳理事件演进，定位决策点，清晰呈现各方执行动作与遗留事项。
13· 13·0 当前·0 累计
by @kevinsuzc下载技能包
最后更新
2026/4/24
安全扫描
OpenClaw
安全
high confidenceThe skill's instructions and requirements are internally consistent with its stated purpose: it expects email text (.eml or pasted bodies) and describes only parsing and analysis steps, without requesting credentials, installs, or access to unrelated system data.
评估建议
This skill is coherent and does what it says: it analyzes email text you provide and returns a structured report. Before using it on sensitive material, consider: (1) privacy — you must supply the email content (do not upload secrets, credentials, or NDAs unless you accept sharing them with the agent); (2) verify outputs — treat Medium/Low confidence items as needing human confirmation; (3) test with non-sensitive sample emails to confirm formatting/results; (4) check your platform's logging/pri...详细分析 ▾
✓ 用途与能力
The name/description (email chain analysis) matches the runtime instructions: parsing headers, reconstructing threads, extracting actions, and producing a structured report. No unexpected credentials, binaries, or config paths are requested.
✓ 指令范围
SKILL.md limits operations to the provided email_data input (extract headers, timeline, thread splitting, action extraction, confidence tagging). It does not instruct reading other files, environment variables, or transmitting data to external endpoints. The automatic-trigger wording is a behavioral description, not an instruction to access unrelated data.
✓ 安装机制
There is no install spec and no code files — this is an instruction-only skill, which minimizes disk-executed risk. No downloads, package installs, or extracted archives are present.
✓ 凭证需求
The skill declares no environment variables, credentials, or config paths. All required inputs are explicit (email_data, optional focus_keyword) and are proportionate to the analysis task.
✓ 持久化与权限
Flags show always=false and normal model invocation; the skill does not request permanent presence, nor does it instruct modifying other skills or system-wide settings.
安全有层次，运行前请审查代码。
运行时依赖
无特殊依赖
版本
latestv2.0.02026/4/24
v2.0: 多线程时间轴 / 矛盾标注 / 置信度 / 风险预警 / 附件清单
● Pending
安装命令
点击复制官方npx clawhub@latest install email-chronicle-analyst
镜像加速npx clawhub@latest install email-chronicle-analyst --registry https://cn.longxiaskill.com