Token导航 LogoToken导航TokenDH.com
研究检索只读clawhub未标认证来源可访问clear审计提醒

hera-mail赫拉邮件

Agent Skill

hera-mail 用于查找、检索和筛选相关信息,适合在 OpenClaw 中需要根据关键词、任务场景或来源线索快速定位候选结果时使用。可结合来源仓库、安装命令和原始 README 继续核验具体用法。安装前建议确认权限范围、维护状态,以及是否会触发联网、命令执行或文件读写。

总安装

3,109

周安装

127

GitHub Stars

公开资料未说明

下载量

1,006
OpenClaw

安装说明

本站只整理中文说明和来源信息,不托管安装包,也不代用户安装。

GitHub

来源数

2

许可证

MIT-0

最后核验

2026-05-01

来源状态

来源可访问

安装方式

通过对话安装

复制提示词发给支持本地命令或 Skills 的 AI 助手,先确认命令和权限,再让它执行。

请帮我安装这个 Agent Skill:hera-mail(赫拉邮件)
来源仓库:https://github.com/wzr818181/hera-mail
安装命令:
openclaw skills install hera-mail
安装前请先检查当前环境是否支持对应 CLI,并向我确认将要执行的命令、安装目录、联网范围和文件读写权限;确认后再执行。

命令行安装

复制命令到本机终端执行。该命令会通过 OpenClaw 从第三方来源获取 Skill;本站只展示命令,不托管安装包,也不自动执行。

ClawHubOpenClaw
openclaw skills install hera-mail

简介

内部电子邮件系统,供 HERA 代理发送、接收、阅读和管理带有可选文件附件的直接消息。

SKILL.md

name
hera-mail
description
HERA system internal email system for agent-to-agent communication. Use when any HERA agent needs to: (1) Check their inbox for new messages, (2) Read specific emails from other agents, (3) Send emails to other agents with optional file attachments (papers, data, images), (4) Manage message status (read/unread). This is the primary communication method between HERA agents.
metadata

HERA Mail System

Internal email system for agent-to-agent communication within the HERA research assistant framework.

Quick Start

Check Inbox

python3 {baseDir}/scripts/list_inbox.py <agent-name>

Read a Message

python3 {baseDir}/scripts/read_mail.py <agent-name> <mail-file.md>

Send a Message

python3 {baseDir}/scripts/send_mail.py <from-agent> <to-agent> "<subject>" <attachment-paths...>

Agent Names

AgentName for Scripts
Group Leadergroup-leader
Rough Readerrough-reader
Intensive Readerintensive-reader
Code Guidercode-guider
Coordinator 1coordinator-1
Coordinator 2coordinator-2
Rough Checker 1rough-checker-1
Rough Checker 2rough-checker-2
Report Writerreport-writer

Email Format

[FROM: agent-name]
[TO: agent-name]
[TIMESTAMP: YYYY-MM-DD HH:MM:SS]
[MAIL-ID: unique-id]
[SUBJECT: subject text]
[STATUS: unread]

---

Message body content here.
No formal greetings needed - be direct and concise.

---
[END]

Attachments

Attachments are stored in:

hera-agents/<recipient>/inbox/attachments/<mail-id>/<files>

Supported: PDFs, images, data files, code, any file type.

Workflows

Workflow 1: Check and Read Messages

  1. List inbox: list_inbox.py <agent-name>
  2. Identify unread messages (marked with [○])
  3. Read specific message: read_mail.py <agent-name> <file.md>
  4. Message automatically marked as read

Workflow 2: Send Message with Attachment

# Send paper to Rough Reader
python3 send_mail.py group-leader rough-reader "Review this paper" /path/to/paper.pdf

# Send data visualization to Report Writer
python3 send_mail.py intensive-reader report-writer "Analysis results" /path/to/figure.png /path/to/data.csv

Workflow 3: Interactive Send (with body from stdin)

cat <<EOF | python3 send_mail.py coordinator-1 code-guider "Code review needed"
Please review the attached code for:
1. Performance issues
2. Memory leaks
3. Best practices

Deadline: EOD
EOF

Message Types

TypeSenderRecipientPurpose
Task AssignmentGroup LeaderAny agentAssign new work
Work SubmissionAny agentCoordinator/LeaderSubmit completed work
Review RequestAny agentRough CheckerRequest quality check
Information RequestAny agentReader agentsRequest analysis
Data TransferAny agentAny agentShare files/data

Best Practices

  1. Be direct - No formal greetings, get straight to the point
  2. Clear subjects - Subject line should summarize the task/request
  3. Attach relevant files - Include papers, data, code as needed
  4. Check inbox regularly - Agents should monitor their inbox
  5. Mark important messages - Use mail ID for reference in future comms

Directory Structure

hera-agents/
├── <agent-name>/
│   ├── inbox/           # Received messages
│   │   ├── *.md         # Mail files
│   │   ├── *.read       # Read markers
│   │   └── attachments/ # Attached files per mail
│   └── outbox/          # Sent message copies
│       └── *.md
└── skills/hera-mail/
    ├── scripts/
    │   ├── list_inbox.py
    │   ├── read_mail.py
    │   └── send_mail.py
    └── references/

Examples

Example 1: Group Leader assigns task to Rough Reader

cat <<EOF | python3 send_mail.py group-leader rough-reader "Scan arXiv papers on quantum error correction"
Priority: High
Scope: Last 6 months
Focus: Surface codes, LDPC codes

Deliverable: List of top 10 relevant papers with abstracts
Deadline: 2 hours
EOF

Example 2: Intensive Reader sends analysis to Report Writer

python3 send_mail.py intensive-reader report-writer "Analysis complete: Quantum Error Correction" \
    /workspace/analysis/summary.md \
    /workspace/analysis/key_findings.csv \
    /workspace/figures/error_rates.png

Example 3: Coordinator requests quality check

python3 send_mail.py coordinator-1 rough-checker-1 "QC needed: Literature review draft" \
    /workspace/drafts/lit_review_v1.md

Troubleshooting

Inbox not found: Ensure agent directory exists under hera-agents/

Mail not delivered: Check recipient agent name is correct

Attachment missing: Verify file path is absolute and file exists

Permission denied: Ensure scripts are executable:

chmod +x /Users/zhaoruiwu/.openclaw/workspace/hera-agents/skills/hera-mail/scripts/*.py

适合场景

01

OpenClaw 用户查找和安装 Skill 时

02

用户想查找某类 Agent Skill 时

03

需要根据任务场景推荐可安装能力包时

04

需要对比不同来源的安装命令和来源信息时

能力概览

能力 1

按任务关键词查找相关 Skills

能力 2

展示可复制的安装命令

能力 3

保留来源站点、仓库和原始说明,方便继续核验

能力 4

补充不同宿主或平台的使用分布数据

能力 5

展示第三方安全扫描或审计结果

安装后应在对应宿主中按原始 README 的触发条件使用;具体调用方式请以来源页面和 README 为准。

平台分布

OpenClaw

84.07%
按下载量换算846

安全审计

VirusTotal

可疑

ClawScan

可疑

Static analysis

通过

权限和风险

只读

该 Skill 主要提供规则、说明或参考内容,本身偏只读;真正读写文件、联网或执行命令仍取决于宿主 Agent 的任务。

安装前确认

本站仅展示第三方公开信息,不托管安装包,不提供自动安装或运行环境。安装前应自行审查源码、依赖和命令行为。来源安全扫描存在 warning/failed 结果,不能写成本站确认安全。当前只有一个来源,正式发布前建议补源仓库或其他目录站核验。

来源信息

继续浏览同类 Skills