Getting it into your agent
One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.
npx skills add Theia-pro/email-mentor --skill skillgit clone --depth 1 https://github.com/Theia-pro/email-mentorWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/skills/theia-pro/email-mentor/skill)<a href="https://agentmods.dev/skills/theia-pro/email-mentor/skill"><img src="https://agentmods.dev/badge/skills/theia-pro/email-mentor/skill.svg" alt="Measured on agentmods" height="20"></a>What it costs to keep this loaded
Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00136 | $0.01685 |
| Opus 5 | $0.00068 | $0.00843 |
| Sonnet 5 | $0.00027 | $0.00337 |
| Haiku 4.5 | $0.00014 | $0.00169 |
Grade A, and why
email-mentor scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 7d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 113 lines — stays where its author put it; the contents beside it link to each section on GitHub.
邮件管家（Email Mentor）
概述
处理用户邮箱中的邮件（以英文邮件为主）：翻译、分类、标注发件人、提取关键词与处理截止时间（DDL），输出中文整理清单和日历文件，并定期生成汇总报告。本 skill 只读整理，绝不回复、不删除、不发送任何邮件。
目录约定
首次运行时先检查以下目录，不存在则创建：
- 邮件数据：优先自动发现 Thunderbird 的本地数据（见第 1 步）；备选目录
~/Documents/EmailMentor/inbox/存放用户手动放入的*.eml或*.txt/*.md ~/Documents/EmailMentor/output/：输出目录整理清单_YYYY-MM-DD.md：每次整理的邮件清单deadlines.ics：DDL 日历文件（可导入飞书/Outlook/Google 日历）processed/processed.jsonl：历史处理记录（累积所有已处理邮件的分类、翻译、DDL 等信息）weekly_report.md/monthly_report.md：定期汇总报告
工作流程
第 1 步：定位并解析邮件
先自动定位 Thunderbird 邮件数据（用户若已按 thunderbird_setup.md 配置好）：
python scripts/find_thunderbird.py --json
- 输出
"found": true时，取第一个mail_dirs路径作为解析输入 - 输出
"found": false时，提示用户：a) 先启动一次 Thunderbird 完成登录；b) 或把.eml/.txt邮件放入~/Documents/EmailMentor/inbox/
然后运行解析脚本，把邮件转成 JSON：
python scripts/parse_mailbox.py --input "<Thunderbird Mail 目录或 inbox 路径>" --output "<输出>/emails.json" [--since YYYY-MM-DD]
--input可直接传 Thunderbird 的 Mail 目录（内含无扩展名 mbox，脚本自动识别），也可传 mbox/.eml/文本文件或文件夹--since传入上次处理日期，只处理新邮件- 若用户指定了邮件路径，优先使用用户指定的路径
第 2 步：逐封整理（LLM 核心工作）
读取 emails.json，对每一封邮件执行：
- 翻译：把正文翻译成通顺的中文，保留关键信息（时间、地点、数字、金额、链接、截止日期）
- 分类：按 分类体系 归入唯一类别
- 发件人：标注发件人身份（如"课程教授""学校财务处""公司 HR"），帮助用户判断重要性
- 关键词：提取 3-5 个关键词
- 重要性：高 / 中 / 低（结合 DDL 紧迫度与发件人身份判断）
- DDL：若邮件明确包含截止时间/会议时间/回复期限，提取为
ddl（title、start、end，格式YYYY-MM-DD HH:MM）；没有则留空
整理结果写入 processed/processed.jsonl，结构示例见 处理结果格式。
第 3 步：生成整理清单
输出 整理清单_YYYY-MM-DD.md，包含每封邮件的：日期、发件人（含身份）、主题、翻译摘要、分类、重要性、关键词、DDL。按 DDL 临近程度排序。
第 4 步：生成日历文件
从本次有 DDL 的邮件生成 .ics 文件：
python scripts/make_calendar.py --input "<输出>/emails_ddl.json" --output "<输出>/deadlines.ics"
emails_ddl.json只包含本次整理中有 DDL 的邮件（脚本会自动提取其中的ddl字段，也可直接传入整个 processed.jsonl）- 生成后提示用户导入飞书日历，导入方法见 飞书导入
第 5 步：定期汇总
当用户要求"周报/月报/汇总"时运行：
What ships with it
12 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
- agents/openai.yaml 197 B
- examples/sample_report.md 2.2 KB
- examples/sample_整理清单.md 1.3 KB
- references/categories.md 1.1 KB
- references/data_format.md 2.8 KB
- references/feishu_import.md 1.5 KB
- references/thunderbird_setup.md 2.1 KB
- scripts/find_thunderbird.py 4.1 KB runs code
- scripts/make_calendar.py 5.0 KB runs code
- scripts/make_html.py 14 KB runs code
- scripts/make_report.py 7.2 KB runs code
- scripts/parse_mailbox.py 8.0 KB runs code
What this file has done since we first saw it
Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.
- 7d ago First seen · 113 lines · 136 tokens per session scan A ffa38dfbf020
email-mentor is a skill published in the GitHub repository Theia-pro/email-mentor (4 stars, last pushed 1mo ago), licensed MIT. It adds 136 tokens to every session and 1,685 once invoked, about $0.0007 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.
Other skills, from other repositories
stage-and-commit
Stage changed files and create a commit following the repo's translation, formatting, and git workflow rules. Use when the user asks to stage, commit, or both.
alibaba-cloud-translation-manager
Manage Alibaba Cloud TongyiTranslate (AnyTrans) via OpenAPI/SDK. Use whenever the user needs translation service resource operations in Alibaba Cloud, including list/create/update actions, task status checks, and troubleshooting AnyTrans API workflows.
concierge
Skill "concierge" from markmhendrickson/ateles, covering identity, principals, what you own, autonomy posture and runtime.
libretranslate-markdown-i18n
Machine-translate Markdown / Obsidian / Quartz content into other languages using a self-hosted LibreTranslate instance, preserving frontmatter, headings, emojis, bold/italic, wikilinks (![[...]]/[[...]]) and internal links. Use whenever a user wants to auto-translate a Markdown vault, Obsidian notes, or a…
german-technical-writing
Use when writing German-language prose longer than one sentence for Jira tickets, internal German wiki/spec docs, or team-chat to German-speaking colleagues (Slack, Matrix, Teams). Invoke BEFORE composing. Covers anglicism verbs (failt, triggern, returnen), calqued collocations and idioms (blockiert auf, macht Sinn…
regime-audit
Workflow composite that runs change-point-detector + hurst-exponent on SPY plus the 11 SPDR sector ETFs. Reports per-name the last detected regime shift, current persistence classification (meanreverting / randomwalk / trending), and cross-sector summary (broadregimeshift / localizedregimeshift / trenddominated /…