community-automations/deep-research

研究與情報

PublicClaude 子代理

深度研究 Agent

真正的研究，代表數十次搜尋、一大片開啟的分頁，還有做到一半就散掉的筆記。Deep Research 會自動跑完這整個流程，並分多輪進行。

sonnet1 週Brave SearchFirecrawlOpenAIPostgres
ClaudeClaude
ROI for
README.md

為什麼選擇此子代理

真正的研究，代表數十次搜尋、一大片開啟的分頁，還有做到一半就散掉的筆記。Deep Research 會自動跑完這整個流程，並分多輪進行。

它會規劃子問題、閱讀來源，並在每一輪結束後儲存檢查點，讓長時間的執行能從中斷處接續，而不必重頭來過。產出是一份附引用的報告，每個論點都連結到其來源，來源之間的歧異也會被標出來，而不是被模糊帶過。

運作方式

    • Read

      Used at step 01 to kick off the pipeline.

    • Write

      Used at step 01 to kick off the pipeline.

    • WebFetch

      Used at step 01 to kick off the pipeline.

    • WebSearch

      Used at step 01 to kick off the pipeline.

輸出範例

json
// Sample output
// (generated when the pipeline finishes)

Research the question across multiple rounds; produce a report where every claim carries an inline citation, and surface contradictions instead of hiding them.

Unlock the rest

The full agent definition, install snippet, and starter task are gated for community members.

Members get the full `.md` agent file, the npm / pnpm install one-liners, a starter prompt that we've tuned against real runs, and the open-source repo when this automation ships there. One email, magic link, done.