Community生產力與協作github.com

tderoussel/inbox-triage

分類電子郵件收件匣——整理需要回覆的郵件、草擬回覆、標記需要決策的項目,並找出可以忽略或取消訂閱的郵件。當使用者說「整理我的收件匣」、「幫我處理電子郵件」、「我的收件匣裡有什麼」或「清理我的郵件」時使用。

inbox-triage 是什麼?

這是一個專為 AI 代理(如 Claude Code、Cursor 等)設計的收件匣分類技能。它能將使用者的電子郵件收件匣轉化為簡潔的決策清單與草稿堆疊,自動將郵件分類為「需要你」、「可草擬回覆」、「僅供參考」和「雜訊」四個桶子,並針對「可草擬回覆」類別的郵件撰寫草稿,但**絕對不會實際發送、封存、刪除或取消訂閱**任何郵件。此技能支援 Gmail、Outlook 等郵件整合(透過 MCP 伺服器或 Composio 等 CLI 橋接工具),預設擷取過去 24 小時內未讀及最近的郵件。它強調安全第一:所有會影響伺服器狀態的操作都等待使用者批准,即使是使用者先前同意過的類似動作,每次批次都需重新核准。此外,它還會識別重複出現的郵件模式,建議使用者建立專用技能、篩選器或罐頭回覆以提升長期效率。

相容平台~Claude Code~Codex CLI~Cursor
npx skills add https://github.com/tderoussel/agent-skills/tree/main/skills/inbox-triage

Installed? Explore more 生產力與協作 skills: steipete/gemini, steipete/gh-issues, steipete/skill-creator · View all 6 →

在你喜歡的 AI 中提問

開啟一個已預先載入此 Agent Skill 的新對話。

說明文件

收件匣分類

將收件匣轉化為簡短的決策清單加上一疊草稿。絕不發送任何郵件。

硬性規則

僅限草稿。絕不發送、絕不封存、絕不刪除、絕不取消訂閱。 所有會影響伺服器狀態的操作都等待使用者處理。此規則不可協商,且不會因熟悉而放寬。

即使郵件本身要求立即回覆,或使用者先前已核准過類似的發送,此規則依然適用。核准是按批次進行的。

設定

任何郵件整合方式皆可 — Gmail/Outlook MCP 伺服器、API 用戶端,或是 Composio 等 CLI 橋接工具:

composio search "fetch emails" --toolkits gmail
composio link gmail

如果使用者有多個郵件帳戶,大多數整合支援同一個提供者的多個連線。請明確選擇一個,如果造成混淆則詢問使用者指的是哪一個 — 分類錯誤的收件匣會浪費整個執行。

步驟

1. 擷取

擷取未讀及最近的郵件。除非另有指示,否則預設為過去 24 小時;如果間隔更長,請詢問時間範圍,而不是自行猜測。

2. 分類到四個桶子

桶子意義
需要你真正的決策、承諾、金錢事項,或只有使用者能處理的人際關係
可草擬回覆例行回覆 — 撰寫草稿,但不要發送
僅供參考值得知道,無需行動
雜訊電子報、收據、通知、陌生推銷

判斷準則,按優先順序排列:

  • 任何來自付費客戶、投資人、顧問或指定的密切合作者的郵件,即使回覆看起來很例行,也歸入需要你。請將該清單保留在專案本身的此技能副本中。
  • 任何涉及金錢、法律風險或承諾的郵件歸入需要你。
  • 陌生推銷郵件歸入雜訊,除非它與正在進行的事務真正相關。
  • 在需要你與可草擬回覆之間猶豫不決時,選擇需要你。

3. 草擬回覆

對於所有歸入可草擬回覆的郵件,以使用者自己的語氣撰寫回覆 — 如果專案有品牌語氣或寫作風格文件,請參考。簡短、直接、無贅詞。配合郵件串的語氣:一個單句問題得到一個單句答案。

將草稿儲存在郵件用戶端中,讓它們在使用者習慣操作的地方等待,同時也在摘要中顯示。

4. 回報

## 收件匣 — <日期>, <N> 封郵件

### 需要你 (<n>)
- **<寄件者>** — <他們想要什麼> → <需要做的決策>

### 已草擬 (<n>)
- **<寄件者>** — <主旨> → <回覆摘要一行>

### 僅供參考 (<n>)
- <一行一個>

### 雜訊 (<n>)
<按類型統計。列出值得取消訂閱的寄件者 — 但不要實際取消訂閱。>

保持易於掃讀。如果需要你為空,用一句話說明並停止 — 不要填充內容。

5. 觀察模式

如果同一類型的郵件不斷出現且獲得相同的回覆,請指出來。這表示需要一個專用技能、篩選器或罐頭回覆 — 這比分類本身更有價值。

定時執行此技能

適合每天執行兩到三次。草稿會累積,使用者批次檢閱,沒有任何郵件會在未經使用者同意的情況下被處理。

Individual skills in this repo

This repo contains 8 individual skills — each has its own dedicated page.

tderoussel/codebase-audit

Runs a ranked, evidence-backed audit of a product, codebase, or subsystem, ending in a verify list that separates proven findings from inferred ones. Use when the user asks for an audit, a gap analysis, a deep read, a bug hunt, a readiness check, a re-audit, a state reconciliation, or asks what they are not seeing. Trigger phrases include "audit", "gap analysis", "what am I missing", "deep audit", "readiness", "bug hunt", "review the whole thing". Produces findings and a verify list; does not fix.

tderoussel/competitive-teardown

Researches a competing product against your own and produces a ranked build-or-ignore verdict, plus optional comparison-page copy. Use when the user names a competitor or asks how their product stacks up against one. Trigger phrases include "vs us", "competitor", "what does X have", "should we copy", "competitive gap", "teardown", "are we behind". Produces a ranked verdict with effort estimates and an explicit not-worth-copying list.

tderoussel/decision-council

Run a structured multi-perspective review of a decision instead of getting one agreeable answer. Use when the user says run a council, get me perspectives on this, should I do X, stress-test this decision, or is this a good idea.

tderoussel/fleet-brief

Authors a workstream brief for dispatching multiple parallel build agents across one codebase, with per-lane file ownership, shared-ground warnings, and a derived DO-NOT list. Use whenever work is about to be split across concurrent agents, workers, lanes, or waves — even if the user does not say "write a brief". Trigger phrases include "fan out", "parallel agents", "orchestrate this", "split into lanes", "workstreams", "run these in parallel", "review-gated build". Produces the brief; does not dispatch.

tderoussel/overnight-build

Composes an autonomous unattended Claude Code build prompt that survives usage-limit resets via BUILD_LOG.md checkpointing, plus the launcher that restarts it. Use when the user asks for an overnight build, an autonomous build, a build to run while they sleep, an unattended or unsupervised session, or any long build they will not be monitoring. Trigger phrases include "overnight build", "run overnight", "build while I sleep", "autonomous build", "let it run", "unattended". Produces a single copyable prompt; does not run the build.

tderoussel/session-log

Write a durable record of a work session — what was built, root-caused, or shipped — into the project's notes. Use when the user says log this session, write a session log, record this, or when a substantial piece of work has just finished and needs to be handed off to a future session.

tderoussel/ship-gate

Verification gate for a Next.js-on-Vercel + Supabase + GitHub Actions stack, to run before claiming anything is shipped, deployed, live, merged, passing, or done. Use before saying a change is in production, before merging a PR, before reporting CI green, and before writing any status into a document — even if the user does not ask for verification. Trigger phrases include "is it live", "did it deploy", "ship it", "merge it", "is CI green", "confirm prod", "did that work". Encodes traps where the obvious check returns a false pass.

tderoussel/vault-doctor

Audits and repairs an Obsidian vault's structural health — broken [[wikilinks]], ambiguous duplicate filenames, missing or malformed frontmatter, stale status markers, and hub notes whose state sections have gone cold. Use when the user asks about vault health, broken links, vault cleanup, dead links, orphan notes, tag consistency, or says the vault feels messy or out of date. Trigger phrases include "vault health", "broken links", "clean up the vault", "audit the vault", "is the vault current". Read-only by default; every repair is proposed before it is made.

相關技能