slack-notification-triage

作者: openai

將最近的 Slack 活動分類為使用者的優先佇列或任務清單。

npx skills add https://github.com/openai/plugins --skill slack-notification-triage

Slack Notification Triage

Use this skill to produce a priority queue or task list for the user from recent Slack messages. It is for surfacing what the user likely needs to read, reply to, or do next.

Start Here

  • If the user provided a time window, use it. For requests like "today" or "this morning," resolve the user's timezone with slack_read_user_profile.
  • Treat this as best-effort triage over recent Slack activity, not an exact unread or notification-state view.

Workflow

  1. Treat this as personal triage for the user. Focus on messages directed at the user, messages likely needing a reply, and messages that create a concrete follow-up or task for the user.
  2. Resolve the current user with slack_read_user_profile so you have the user's Slack ID for mention-based searches.
  3. If the user provided channel names, DMs, people, or topic keywords, use that scope.
  4. Named channels: Resolve IDs through slack_search_channels, then call slack_read_channel with limit at 100 per channel.
  5. Named people or DMs: Resolve people through slack_search_users, then use slack_search_public_and_private with several small searches using filters from:<@USER_ID>, to:<@USER_ID>, or in:<@USER_ID> to surface relevant DM or person-specific activity.
  6. Named topics: Use slack_search_public_and_private, and if channels were also provided, keep the search inside those channels.
  7. No explicit scope: Search in this order:
    • unanswered direct conversations: run slack_search_public_and_private over channel_types="im", paging until you have a reasonable set of unique conversations, then dedupe and expand promising DMs with slack_read_channel
    • unanswered group DMs: repeat over channel_types="mpim", again preferring unique conversations over repeated hits from one chat
    • direct mentions: slack_search_public_and_private with query set to <@USER_ID>
    • threads with prior user participation: slack_search_public_and_private with query set to from:<@USER_ID> is:thread, then slack_read_thread
    • threads with prior user mention: slack_search_public_and_private with query set to <@USER_ID> is:thread, then slack_read_thread
  8. Use slack_read_thread when the thread could hold more necessary context.
  9. Prioritize messages that likely need a reply or could create a concrete follow-up or task for the user. Explicit asks, review or approval requests, blockers, and bumps should rank above casual questions, FYIs, or repeated snippets from the same conversation.
  10. Read the full ## Formatting Rules section below.
  11. Before sending the final answer, map the findings into the exact structure in Formatting Rules. Do not invent alternate section names or top-level layouts.
  12. If the user also asked to draft or send follow-ups from the triage results, use ../slack-outgoing-message/SKILL.md and align with the explicit intent:
  • explicit send/post/reply: write directly
  • explicit draft/review-first: draft
  • otherwise keep this skill analysis-only

Formatting Rules

  • For a concise Slack or chat summary, you MUST use exactly this structure unless the user explicitly requests a different format.
  • If you use ../slack-outgoing-message/SKILL.md to draft or send the final message, this output contract remains binding. The downstream skill does not relax or rename these sections.
**Slack Notification Triage - YYYY-MM-DD**
**Overview**
<1-2 sentence summary of what the user most likely needs to read, reply to, or do next>

**Tasks for you**
- ...

**Worth skimming**
- ...

**Can ignore for now**
- ...

**Notes**
- <gaps, caveats, or partial coverage>
  • Keep the triage compact; aim for 3–15 bullets total across all sections.
  • Treat Tasks for you as the primary section whenever the triage is meant to produce a personal todo list.
  • Include Can ignore for now only when the user explicitly asked to filter tasks.
  • Start each bullet with the key update, then add the action the user may need to take.
  • Preserve exact channel names and mention DMs explicitly.
  • Use Notes for coverage limits or sparse results.

來自 openai 的更多技能

user-context
openai
載入或管理資料分析插件的持久性來源路由偏好設定、入門邏輯、設定進度以及語義層註冊表。
official
notion-research-documentation
openai
研究Notion內容,並將其整合為結構化的簡報、報告或附有引用的比較分析。透過精準查詢搜尋並擷取Notion頁面,然後按主題組織發現,並附上內文來源引用及參考文獻章節。根據範圍與使用者目標,從四種輸出格式(快速簡報、研究摘要、比較分析、綜合報告)中選擇。使用內建範本建立與更新Notion頁面;直接連結來源,並在新資訊到來時追蹤變更。
official
rcsb-pdb-skill
openai
提交精簡的RCSB PDB請求以獲取核心元數據、Search API查詢及FASTA下載。當用戶需要簡潔的RCSB摘要時使用;保存原始JSON或…
official
pdf
openai
PDF 讀取、建立與驗證,支援視覺化渲染與程式化生成。使用 Poppler(pdftoppm)將 PDF 頁面渲染為 PNG,以便在交付前檢查版面、間距與排版。透過 reportlab 程式化生成 PDF,確保格式可靠;使用 pdfplumber 或 pypdf 提取文字與元資料。執行品質標準:無文字裁切、元素重疊、表格破損或渲染瑕疵;僅使用 ASCII 連字號,引用格式需具可讀性。使用...
official
test-coverage-improver
openai
Improve test coverage in the OpenAI Agents JS monorepo: run `pnpm test:coverage`, inspect coverage artifacts, identify low-coverage files and branches, propose…
official
playwright
openai
終端驅動的瀏覽器自動化,具備元素快照與互動式UI工作流程。透過playwright-cli包裝腳本運作(需npx),支援無頭模式與有頭模式以進行視覺化除錯。核心流程:開啟頁面、擷取快照以取得穩定元素參照、使用參照進行互動、在導航或DOM變更後重新擷取快照。包含表單填寫、點擊、輸入、多分頁管理、螢幕截圖/PDF擷取,以及流程除錯的軌跡記錄。元素參照(例如e3、e15)...
official
ukb-topmed-phewas-skill
openai
接受rsID、GRCh37或GRCh38輸入,解析為所需的GRCh38查詢,以獲取單一變異的簡潔UKB-TOPMed PheWAS摘要。當需要…時使用。
official
code-review-context
openai
模型可見上下文
official