菜单
Read, search, and manage Gmail emails and Google contacts. Use when the user asks to check email, find emails, search messages, look up contacts, or find someone's email/phone. Supports multiple accounts.
用 Codex 或 Claude 帮你安装 复制这段 Prompt，粘贴到 Codex、Claude 或其他助手里，让它检查 Skill 页面并帮你完成安装。
Use when the user wants to design, redesign, shape, critique, audit, polish, clarify, distill, harden, optimize, adapt, animate, colorize, extract, or otherwise improve a frontend interface. Covers websites, landing pages, dashboards, product UI, app shells, components, forms, settings, onboarding, and empty states. Handles UX review, visual hierarchy, information architecture, cognitive load, accessibility, performance, responsive behavior, theming, anti-patterns, typography, fonts, spacing, layout, alignment, color, motion, micro-interactions, UX copy, error states, edge cases, i18n, and reusable design systems or tokens. Also use for bland designs that need to become bolder or more delightful, loud designs that should become quieter, live browser iteration on UI elements, or ambitious visual effects that should feel technically extraordinary. Not for backend-only or non-UI tasks.
Find and remove AI slop — the generic, machine-default visual and copy tics of vibe-coded products — from a web project. Use when the user asks to "kill AI slop", "de-slop", "remove the AI look", "make this not look AI-generated", or clean up a landing page / UI / docs that feels templated. Detects and fixes: indigo→violet gradients, gradient-clip headline text, warm amber/stone "cozy" palettes, the default semantic palette (info-blue / tip-amber / success-green / error-red), one-hue status boxes, atmospheric/ambient gradients, serif-italic emphasis on one word, serif where sans belongs, decorative strikes and highlights, highlighted keywords in copy, AI copywriting voice ("not just X — it's Y"), emoji everywhere, glowing status dots, rounded colored-left-border callouts, pastel rounded-square icon tiles, glassmorphism and over-rounding, oversized drop shadows, corners that don't nest, badge & pill spam, AI-drawn SVG icons, icons in a tint of themselves, kickers over every heading, full-sentence display headl
自动处理 Google Scholar Alerts 邮件,基于 MEMORY.md 过滤论文,生成 Markdown 日报。使用场景:用户说'生成scholar日报'、'处理scholar邮件'、'今天的scholar日报',或使用/gmail-scholar-daily命令。
使用 Camoufox 执行 Google Scholar 学术检索，支持关键词搜索、年份筛选、结果批量获取。当用户需要进行学术文献检索、查询论文、搜索学术资料时使用。
基于 SOC 职业分类
| name | gmail-skill |
| description | Read, search, and manage Gmail emails and Google contacts. Use when the user asks to check email, find emails, search messages, look up contacts, or find someone's email/phone. Supports multiple accounts. |
| allowed-tools | Read, Edit, Write, Bash, Glob, Grep, AskUserQuestion, Task |
读取、搜索和删除 Gmail 电子邮件，访问 Google 联系人。
路径规范：使用
$CLAUDE_PROJECT_DIR环境变量，确保跨工作目录的可靠路径解析。
python $CLAUDE_PROJECT_DIR/.claude/skills/gmail-skill/scripts/gmail_skill.py search "查询语句" [--max-results 数量] [--account 邮箱地址]
查询示例：
from:john@example.com - 来自特定发件人subject:meeting after:2026/01/01 - 包含指定主题且在指定日期之后has:attachment filename:pdf - 包含 PDF 附件is:unread - 未读邮件"exact phrase" - 精确匹配短语python $CLAUDE_PROJECT_DIR/.claude/skills/gmail-skill/scripts/gmail_skill.py read 邮件ID [--output 文件路径] [--format full|minimal] [--account 邮箱地址]
参数说明：
--output, -o: 直接将邮件 JSON 保存到指定文件（推荐用于批量处理）--format: full（默认，完整内容）或 minimal（仅元数据）示例：
# 输出到终端（默认）
python $CLAUDE_PROJECT_DIR/.claude/skills/gmail-skill/scripts/gmail_skill.py read 18d5a3b2c1f4e5d6
# 直接保存到文件（推荐）
python $CLAUDE_PROJECT_DIR/.claude/skills/gmail-skill/scripts/gmail_skill.py read 18d5a3b2c1f4e5d6 --output temp_emails/email_1.json
python $CLAUDE_PROJECT_DIR/.claude/skills/gmail-skill/scripts/gmail_skill.py list [--max-results 数量] [--label 标签名] [--account 邮箱地址]
python $CLAUDE_PROJECT_DIR/.claude/skills/gmail-skill/scripts/gmail_skill.py mark-read 邮件ID [--account 邮箱地址]
python $CLAUDE_PROJECT_DIR/.claude/skills/gmail-skill/scripts/gmail_skill.py mark-unread 邮件ID [--account 邮箱地址]
将邮件从收件箱移除并归档。
python $CLAUDE_PROJECT_DIR/.claude/skills/gmail-skill/scripts/gmail_skill.py mark-done 邮件ID [--account 邮箱地址]
将邮件移回收件箱（撤销归档操作）。
python $CLAUDE_PROJECT_DIR/.claude/skills/gmail-skill/scripts/gmail_skill.py unarchive 邮件ID [--account 邮箱地址]
python $CLAUDE_PROJECT_DIR/.claude/skills/gmail-skill/scripts/gmail_skill.py star 邮件ID [--account 邮箱地址]
python $CLAUDE_PROJECT_DIR/.claude/skills/gmail-skill/scripts/gmail_skill.py unstar 邮件ID [--account 邮箱地址]
将邮件移到垃圾箱（30天内可恢复）或从垃圾箱恢复。
# 移到垃圾箱（推荐 - 可恢复）
python $CLAUDE_PROJECT_DIR/.claude/skills/gmail-skill/scripts/gmail_skill.py trash 邮件ID [--account 邮箱地址]
# 从垃圾箱恢复
python $CLAUDE_PROJECT_DIR/.claude/skills/gmail-skill/scripts/gmail_skill.py untrash 邮件ID [--account 邮箱地址]
⚠️ 谨慎使用 - 此操作不可撤销，邮件将被永久删除。
# 永久删除（不可逆）
python $CLAUDE_PROJECT_DIR/.claude/skills/gmail-skill/scripts/gmail_skill.py delete 邮件ID [--account 邮箱地址]
建议：优先使用 trash 命令移到垃圾箱，确认不再需要后再手动从垃圾箱永久删除。
标记类命令（mark-read、mark-unread、mark-done、unarchive、star、unstar、trash、untrash、delete）均支持多个 ID（逗号分隔）：
python $CLAUDE_PROJECT_DIR/.claude/skills/gmail-skill/scripts/gmail_skill.py mark-read "id1,id2,id3" --account user@gmail.com
python $CLAUDE_PROJECT_DIR/.claude/skills/gmail-skill/scripts/gmail_skill.py labels [--account 邮箱地址]
python $CLAUDE_PROJECT_DIR/.claude/skills/gmail-skill/scripts/gmail_skill.py contacts [--max-results 数量] [--account 邮箱地址]
python $CLAUDE_PROJECT_DIR/.claude/skills/gmail-skill/scripts/gmail_skill.py search-contacts "查询语句" [--account 邮箱地址]
# 列出所有已认证的账户
python $CLAUDE_PROJECT_DIR/.claude/skills/gmail-skill/scripts/gmail_skill.py accounts
# 移除指定账户
python $CLAUDE_PROJECT_DIR/.claude/skills/gmail-skill/scripts/gmail_skill.py logout --account user@gmail.com
# 强制重新授权并刷新本地令牌
python $CLAUDE_PROJECT_DIR/.claude/skills/gmail-skill/scripts/gmail_skill.py refresh-auth --account user@gmail.com
refresh-auth 会强制拉起浏览器 OAuth，覆盖本地保存的 token，不会删除账户标签等元数据。
使用 --account 参数指定新邮箱地址即可添加账户，系统会自动打开浏览器进行认证：
# 第一个账户（自动认证）
python $CLAUDE_PROJECT_DIR/.claude/skills/gmail-skill/scripts/gmail_skill.py list
# 添加工作账户
python $CLAUDE_PROJECT_DIR/.claude/skills/gmail-skill/scripts/gmail_skill.py list --account work@company.com
# 添加个人账户
python $CLAUDE_PROJECT_DIR/.claude/skills/gmail-skill/scripts/gmail_skill.py list --account personal@gmail.com
# 使用指定账户操作
python $CLAUDE_PROJECT_DIR/.claude/skills/gmail-skill/scripts/gmail_skill.py search "from:boss" --account work@company.com
当 refresh token 失效、需要切换重新授权的账号，或需要强制重新同意权限时，可执行：
python $CLAUDE_PROJECT_DIR/.claude/skills/gmail-skill/scripts/gmail_skill.py refresh-auth --account work@company.com
python $CLAUDE_PROJECT_DIR/.claude/skills/gmail-skill/scripts/gmail_skill.py search "is:unread after:2026/01/01"
python $CLAUDE_PROJECT_DIR/.claude/skills/gmail-skill/scripts/gmail_skill.py read 18d5a3b2c1f4e5d6
python $CLAUDE_PROJECT_DIR/.claude/skills/gmail-skill/scripts/gmail_skill.py search-contacts "张三"
python $CLAUDE_PROJECT_DIR/.claude/skills/gmail-skill/scripts/gmail_skill.py list --account work@company.com --max-results 5
所有命令均输出 JSON 格式，便于解析处理。
重要提示：read 命令不支持逗号分隔的多个邮件ID。读取多封邮件时，应使用多个独立的 Bash 工具调用并行执行：
python $CLAUDE_PROJECT_DIR/.claude/skills/gmail-skill/scripts/gmail_skill.py read "id1"
python $CLAUDE_PROJECT_DIR/.claude/skills/gmail-skill/scripts/gmail_skill.py read "id2"
# 错误方式：会提示"无效的ID值"
python $CLAUDE_PROJECT_DIR/.claude/skills/gmail-skill/scripts/gmail_skill.py read "id1,id2,id3"
当邮件输出超过约40KB时（显示"输出内容过大"提示），可使用 email_formatter.py 格式化为 Markdown。详见 ADVANCED.md。
⚠️ 重要：Gmail 的 after:YYYY/M/D before:YYYY/M/D 格式会被解释为 PST 时区的午夜，导致时区问题。推荐使用 --date-range 参数，该参数自动将日期转换为 Unix 时间戳（使用 UTC）。
新增参数：
--date-range YYYY-MM-DD - 查询指定日期的邮件--date-start YYYY-MM-DD - 起始日期（包含）--date-end YYYY-MM-DD - 结束日期（不包含）示例：
# 查询指定日期的邮件（推荐）
python $CLAUDE_PROJECT_DIR/.claude/skills/gmail-skill/scripts/gmail_skill.py search \
"from:scholaralerts-noreply@google.com" \
--date-range "2026-02-04"
# 查询日期范围
python $CLAUDE_PROJECT_DIR/.claude/skills/gmail-skill/scripts/gmail_skill.py search \
"from:john@example.com" \
--date-start "2026-02-01" \
--date-end "2026-02-05"
# 相对时间查询（不受时区影响）
python $CLAUDE_PROJECT_DIR/.claude/skills/gmail-skill/scripts/gmail_skill.py search \
"from:alert@example.com newer_than:7d"
Gmail 原生的日期搜索运算符：
after:YYYY/M/D - 指定日期之后的邮件（包含当天，但使用 PST 时区）before:YYYY/M/D - 指定日期之前的邮件（包含当天，但使用 PST 时区）newer_than:Nd - 最近 N 天内的邮件⚠️ 注意：使用 after:YYYY/M/D before:YYYY/M/D 进行精确日期查询时，由于 PST 时区解释问题，可能导致日期范围不准确。建议使用 --date-range 参数代替。
更多高级用法详见 ADVANCED.md。
pip install google-auth google-auth-oauthlib google-auth-httplib2 google-api-python-client requests$CLAUDE_PROJECT_DIR/.claude/skills/gmail-skill/tokens/ 目录