New: 98,000+ skills indexed from GitHub repos with 100+ stars · every skill safety-checkedBrowse top skillsTop skills
Esc to closeBrowse all skills
Submit a skillBrowse skills
Submit a skillBrowse skills

Agent skill

Himalaya

by agentscope-ai in agentscope-ai/skills

通过 IMAP/SMTP 管理邮件的命令行工具。使用 himalaya 可以在终端中列出、阅读、撰写、回复、转发、搜索和整理邮件。支持多账户和使用 MML（MIME Meta Language）撰写邮件。

Apache-2.0Auto-check passedBackend & APIs

Install Himalaya

skills CLI
$ npx skills add agentscope-ai/skills --skill himalaya -a claude-code

Project install by default; add -g for ~/.claude/skills/.

GitHub CLI
$ gh skill install agentscope-ai/skills himalaya --agent claude-code

Project scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).

Manual copy
$ git clone --depth 1 https://github.com/agentscope-ai/skills.git skills-src && mkdir -p .claude/skills && cp -r skills-src/skills/himalaya-zh .claude/skills/himalaya && rm -rf skills-src

Use ~/.claude/skills/ instead of .claude/skills for a personal install. The folder must contain SKILL.md.

Claude Code skills documentation · loads skills from .claude/skills/

Facts

Skill name
himalaya
GitHub stars
130
Token cost
~1.4k tokens
SKILL.md length
204 words
Files
2 (incl. references)
Skills in repo
4
Repo updated
First seen
Licence
Apache-2.0

At a glance

通过 IMAP/SMTP 管理邮件的命令行工具。使用 himalaya 可以在终端中列出、阅读、撰写、回复、转发、搜索和整理邮件。支持多账户和使用 MML（MIME Meta Language）撰写邮件。

  • Works in 3 steps: Himalaya CLI - himalaya 二进制文件必须已在 PATH… → 配置文件位于 ~/.config/himalaya/config.toml → 已配置 IMAP/SMTP 凭据（密码安全存储）
  • Tasks that involve Transactional email
  • SKILL.md covers 参考资料, 前置条件, 配置设置 and 常用操作, plus 5 more sections
  • Instructions only: no scripts, shell commands, URLs or credentials in SKILL.md

What it does

Himalaya is an agent skill from agentscope-ai/skills. 通过 IMAP/SMTP 管理邮件的命令行工具。使用 himalaya 可以在终端中列出、阅读、撰写、回复、转发、搜索和整理邮件。支持多账户和使用 MML（MIME Meta Language）撰写邮件。

Its SKILL.md is about 1.4k tokens, which your agent loads only when the skill is triggered. The skill folder holds 2 other files, including reference files (for example `references/configuration.md`).

It sits in Backend & APIs, covering Transactional email. It works with Python. The repository describes itself as: A curated collection of skills around AgentScope ecosystem and CoPaw applications. The licence is Apache-2.0.

When your agent uses it

  • Tasks that involve Transactional email

Example prompts

  • “/himalaya”

Requirements

  • Python 3

Workflow steps

3 steps, taken from the first numbered list in SKILL.md.

  1. Himalaya CLI - himalaya 二进制文件必须已在 PATH 中。通过 himalaya --version 检查。
  2. 配置文件位于 ~/.config/himalaya/config.toml
  3. 已配置 IMAP/SMTP 凭据（密码安全存储）

What it can do on your machine

Read from SKILL.md and the folder at commit b533664. It shows what the files ask for, not the result of running them.

  • Tool permissions

    Pre-approves nothing: there is no allowed-tools line, so your agent's usual permission prompts apply.

    From allowed-tools in the SKILL.md frontmatter.

  • Runs code

    No scripts in the folder and no shell commands in SKILL.md (its code samples are bash, toml and python).

    From the folder's file list and the shell code blocks in SKILL.md.

  • Network

    No URLs in SKILL.md.

    From URLs in SKILL.md, links to its own repository left out.

  • Credentials

    Names no API keys, tokens, secrets or passwords.

    From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.

Context cost

Himalaya loads about 1.4k tokens when it runs, and up to ~2.4k if it reads all its reference files. Until then it costs about 28 tokens; SKILL.md has 204 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it
~28
When it runs · the whole SKILL.md, loaded when a task matches
~1.4k
With references · SKILL.md plus every file in references/, read only if the agent opens them
~2.4k

Estimates: characters ÷ 4, the usual rule of thumb; real counts depend on the model's tokenizer. Scripts and assets cost tokens only if the agent reads them.

Safety

Auto-check passed

The automated check found no risky patterns in SKILL.md.

Automated static check — not a guarantee. Review scripts before installing. It scans the text of SKILL.md for risky patterns (piping downloads into a shell, reading credential files, hidden Unicode, destructive commands); files beside SKILL.md are not scanned.

SKILL.md

The full file from agentscope-ai/skills at commit b533664, republished under its Apache-2.0 licence (© agentscope-ai). 204 words, ~1,367 tokens.

Download SKILL.mdSave it as .claude/skills/himalaya/SKILL.md (or your agent's skills folder). This skill also uses 1 other file; get the full folder from GitHub.
name
himalaya
description
通过 IMAP/SMTP 管理邮件的命令行工具。使用 `himalaya` 可以在终端中列出、阅读、撰写、回复、转发、搜索和整理邮件。支持多账户和使用 MML（MIME Meta Language）撰写邮件。
homepage
https://github.com/pimalaya/himalaya
metadata.builtin_skill_version
1.3

Himalaya 邮件命令行工具

Himalaya 是一个命令行邮件客户端，可以通过 IMAP、SMTP、Notmuch 或 Sendmail 后端在终端中管理邮件。

参考资料

  • references/configuration.md（配置文件设置 + IMAP/SMTP 认证）

前置条件

  1. Himalaya CLI - himalaya 二进制文件必须已在 PATH 中。通过 himalaya --version 检查。
    • 推荐使用 v1.2.0 或更新版本。 旧版本在某些 IMAP 服务器上可能会失败；v1.2.0+ 包含了相关修复。
  2. 配置文件位于 ~/.config/himalaya/config.toml
  3. 已配置 IMAP/SMTP 凭据（密码安全存储）

配置设置

运行交互式向导来设置账户（将 default 替换为你想要的名称，例如 gmail、work）：

bash
himalaya account configure default

或手动创建 ~/.config/himalaya/config.toml：

toml
[accounts.personal]
email = "you@example.com"
display-name = "Your Name"
default = true

backend.type = "imap"
backend.host = "imap.example.com"
backend.port = 993
backend.encryption.type = "tls"
backend.login = "you@example.com"
backend.auth.type = "password"
backend.auth.cmd = "pass show email/imap"  # 或使用 keyring

message.send.backend.type = "smtp"
message.send.backend.host = "smtp.example.com"
message.send.backend.port = 587
message.send.backend.encryption.type = "start-tls"
message.send.backend.login = "you@example.com"
message.send.backend.auth.type = "password"
message.send.backend.auth.cmd = "pass show email/smtp"

如果你使用的是 163 邮箱账户，请在配置文件中添加 backend.extensions.id.send-after-auth = true 以确保正常运作。

常用操作

列出文件夹
bash
himalaya folder list
列出邮件

列出收件箱（默认）中的邮件：

bash
himalaya envelope list

列出指定文件夹中的邮件：

bash
himalaya envelope list --folder "Sent"

分页列出：

bash
himalaya envelope list --page 1 --page-size 20

如果遇到错误，请尝试：

bash
himalaya envelope list -f INBOX -s 1
搜索邮件
bash
himalaya envelope list from john@example.com subject meeting
阅读邮件

通过 ID 阅读邮件（显示纯文本）：

bash
himalaya message read 42

导出原始 MIME：

bash
himalaya message export 42 --full
发送 / 撰写邮件

推荐方式： 使用 template write | template send 管道来发送简单邮件。

发送一封简单邮件：

bash
export EDITOR=cat
himalaya template write \
  -H "To: recipient@example.com" \
  -H "Subject: Email Subject" \
  "Email body content" | himalaya template send

发送带多个头字段的邮件：

bash
export EDITOR=cat
himalaya template write \
  -H "To: recipient@example.com" \
  -H "Cc: cc@example.com" \
  -H "Subject: Email Subject" \
  "Email body content" | himalaya template send

发送带附件的邮件（使用 Python）：

对于带附件的邮件，请使用 Python 的 smtplib 和 email.mime 模块：

python
import smtplib
from email.mime.multipart import MIMEMultipart
from email.mime.text import MIMEText
from email.mime.base import MIMEBase
from email import encoders

msg = MIMEMultipart()
msg['From'] = 'sender@163.com'
msg['To'] = 'recipient@example.com'
msg['Subject'] = 'Email with attachment'

msg.attach(MIMEText('Email body', 'plain'))

# 添加附件
with open('/path/to/file.pdf', 'rb') as f:
    part = MIMEBase('application', 'octet-stream')
    part.set_payload(f.read())
    encoders.encode_base64(part)
    part.add_header('Content-Disposition', 'attachment; filename="file.pdf"')
    msg.attach(part)

server = smtplib.SMTP_SSL('smtp.163.com', 465)
server.login('sender@163.com', 'password')
server.send_message(msg)
server.quit()

注意：MML 附件限制： 使用 MML 格式的 template send 命令在处理 multipart/附件时可能会失败，报错 "cannot parse MML message: empty body"。这是 himalaya v1.1.0 的已知问题。发送附件请使用 Python 方式。

注意：避免在自动化中使用 message write： himalaya message write 命令需要交互式 TUI 选择（Edit/Discard/Quit），在非交互式环境中会挂起。

注意：message send 的限制： 直接使用 himalaya message send <raw_email> 可能会因头字段解析问题而失败，报错 "cannot send message without a recipient"。请改用 template send。

配置要求： 确保在 config.toml 中设置了 message.send.save-to-folder，以避免 "Folder not exist" 错误：

toml
[accounts.163]
# ... 其他配置 ...
message.send.save-to-folder = "Sent"

对于 163 邮箱账户，如果已发送文件夹不存在，请先创建：

bash
himalaya folder create Sent
移动/复制邮件

移动到文件夹：

bash
himalaya message move 42 "Archive"

复制到文件夹：

bash
himalaya message copy 42 "Important"
删除邮件
bash
himalaya message delete 42
管理标记

添加标记：

bash
himalaya flag add 42 --flag seen

移除标记：

bash
himalaya flag remove 42 --flag seen

多账户

列出账户：

bash
himalaya account list

使用指定账户：

bash
himalaya --account work envelope list

附件

保存邮件中的附件：

bash
himalaya attachment download 42

保存到指定目录：

bash
himalaya attachment download 42 --dir ~/Downloads

输出格式

大多数命令支持 --output 来获取结构化输出：

bash
himalaya envelope list --output json
himalaya envelope list --output plain

调试

启用调试日志：

bash
RUST_LOG=debug himalaya envelope list

完整跟踪和回溯：

bash
RUST_LOG=trace RUST_BACKTRACE=1 himalaya envelope list

提示

  • 使用 himalaya --help 或 himalaya <command> --help 查看详细用法。
  • 邮件 ID 是相对于当前文件夹的；切换文件夹后需要重新列出。
  • 要撰写带附件的富文本邮件，请使用 MML 语法（参见 references/message-composition.md）。
  • 使用 pass、系统 keyring 或输出密码的命令来安全存储密码。
  • 自动化场景： 始终使用 template write | template send 管道，并设置 export EDITOR=cat。
  • 163 邮箱用户： 在配置中设置 backend.extensions.id.send-after-auth = true 和 message.send.save-to-folder = "Sent"。
  • 文件夹名称： 使用英文文件夹名称（例如 "Sent" 而非 "已发送"）以获得更好的兼容性。

© agentscope-ai, Apache-2.0. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file

Files

SKILL.md and 1 other file (references) in skills/himalaya-zh of agentscope-ai/skills.

  • SKILL.md
  • references/configuration.md

Open the folder on GitHubat commit b533664

Compare with similar skills

Himalaya next to the 5 skills that share the most tags, products or categories with it. Stars are the repository's; “used in” counts other GitHub owners with a copy.

Himalaya compared with similar skills
SkillStarsUsed inTokensAuto-checkLicenceRepo updated
Himalaya this skillagentscope-ai/skills130—~1.4kAutomated safety check: PassApache-2.0
Cloudflare Email Servicehodgef/apiker1272 repos~2kAutomated safety check: PassMIT
E2a Integratetokencanopy/e2a193—~840Automated safety check: PassApache-2.0
Google Workspaceericrisco/rsc-harness180—~3.2kAutomated safety check: PassMIT
Converting Email Templatesaiskillstore/marketplace433—~1.8kAutomated safety check: PassNone
Odoo Qweb Templatessickn33/agentic-awesome-skills47k2 repos~1kAutomated safety check: PassMIT

Similar skills

  • Cloudflare Email Service

    hodgef/apiker

    Send and receive transactional emails with Cloudflare Email Service (Email Sending + Email Routing).

    127 GitHub starsUsed in 2 repos~2k tokens
    Backend & APIsAuto-check passed

  • E2a Integrate

    tokencanopy/e2a

    A skill your agent uses when adding e2a email capabilities to an application or codebase: outbound sending, inbound signed webhooks, REST polling, or SDK integration.

    193 GitHub stars~840 tokensUpdated 5 days ago
    Backend & APIsAuto-check passed

  • Google Workspace

    ericrisco/rsc-harness

    A skill your agent uses when server-side code reads or writes Gmail, Drive, Calendar, or Sheets with a GCP service account and no human in the OAuth loop: picking the auth mode (app-owned vs…

    180 GitHub stars~3.2k tokensUpdated yesterday
    Backend & APIsAuto-check passed

  • Converting Email Templates

    aiskillstore/marketplace

    A skill your agent uses when converting or migrating email templates from another provider (SendGrid, Mailgun, Mandrill, Postmark, Brevo, Amazon SES) to Mailtrap-compatible Handlebars syntax.

    433 GitHub stars~1.8k tokensUpdated yesterday
    Backend & APIsAuto-check passed

  • Odoo Qweb Templates

    sickn33/agentic-awesome-skills

    Expert in Odoo QWeb templating for PDF reports, email templates, and website pages.

    47k GitHub starsUsed in 2 repos~1k tokens
    Documents & OfficeAuto-check passed

  • Stripe Projects

    fossasia/eventyay

    A skill your agent uses when the user wants to provision infrastructure or third-party services using Stripe Projects.

    1.7k GitHub starsUsed in 5 repos~2k tokens
    Backend & APIsAuto-check: notes

More from agentscope-ai/skills

  • Agentscope Skill

    agentscope-ai/skills

    Build and debug Python applications using AgentScope 2.x. An agent skill from agentscope-ai/skills.

    130 GitHub stars~2.5k tokensUpdated 1 mo ago
    Auto-check passed

  • News

    agentscope-ai/skills

    为用户从指定新闻网站查找最新新闻。提供政治、财经、社会、国际、科技、体育和娱乐类别的权威 URL。使用 browseruse 打开每个 URL 并通过 snapshot 获取内容，然后为用户总结。

    130 GitHub stars~366 tokensUpdated 1 mo ago
    Auto-check passed

  • Nano Memory

    agentscope-ai/skills

    Guidelines and workflows for the agent to maintain persistent memory using native file tools (readfile, writefile, editfile) and standard OS commands for searching.

    130 GitHub stars~1.2k tokensUpdated 1 mo ago
    Auto-check passed

Works with

Categories

Questions about Himalaya

What does Himalaya do?

通过 IMAP/SMTP 管理邮件的命令行工具。使用 himalaya 可以在终端中列出、阅读、撰写、回复、转发、搜索和整理邮件。支持多账户和使用 MML（MIME Meta Language）撰写邮件。. Himalaya is an agent skill from agentscope-ai/skills.

When should I use Himalaya?

Himalaya fits situations like: tasks that involve Transactional email.

How do I install Himalaya in Claude Code?

Run `npx skills add agentscope-ai/skills --skill himalaya -a claude-code`. Or copy the skill folder (skills/himalaya-zh in agentscope-ai/skills) into .claude/skills/himalaya in your project. Claude Code loads it when a task matches its description.

How do I install Himalaya in Codex?

Run `npx skills add agentscope-ai/skills --skill himalaya -a codex`. Or copy the skill folder (skills/himalaya-zh in agentscope-ai/skills) into .agents/skills/himalaya in your project. Codex loads it when a task matches its description.

Can I use Himalaya in Cursor, Gemini CLI or GitHub Copilot?

Cursor, Gemini CLI, GitHub Copilot and OpenCode also load SKILL.md folders. With the skills CLI, run `npx skills add agentscope-ai/skills --skill himalaya -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/himalaya, .gemini/skills/himalaya, .github/skills/himalaya and .opencode/skills/himalaya in your project.

What does Himalaya need to run?

SKILL.md names no scripts, command-line tools or credentials: Himalaya is instructions for the agent only. Our summary lists: Python 3.

Does Himalaya access the network?

SKILL.md contains no URLs. Any network use would come from the scripts or tools the agent runs. This is read from the text; nothing was executed.

Is Himalaya safe to install?

Our automated static check of SKILL.md found no risky patterns, such as piping downloads into a shell, reading credential files or hidden Unicode. It is not a guarantee. Review the folder before installing.

What licence does Himalaya use?

Himalaya is published under the Apache-2.0 licence (the repository's licence). It allows redistribution, so the full SKILL.md is shown on this page.

How many tokens does Himalaya use?

About 1.4k tokens (SKILL.md is roughly 5.5k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full. Its references folder adds about 1k tokens, read only when the agent opens those files.

What are the alternatives to Himalaya?

Skills that share tags, products or a category with Himalaya: Cloudflare Email Service (hodgef/apiker, 127 stars), E2a Integrate (tokencanopy/e2a, 193 stars), Google Workspace (ericrisco/rsc-harness, 180 stars) and Converting Email Templates (aiskillstore/marketplace, 433 stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains Himalaya?

agentscope-ai (a GitHub organization) maintains it in agentscope-ai/skills, which has 130 GitHub stars. The repository holds 4 skills in this directory. The repository was last updated on September 10, 2026.

Source: agentscope-ai/skills on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.