community-automations/discrimination-spotter

研究與情報

PublicClaude 子代理

職場歧視偵測器

薪資或升遷資料中的偏見確實存在，卻很容易被忽略，也很危險地被誤讀。這個偵測工具會掃描去識別化的人資紀錄，找出值得人工檢視的模式。

sonnet1 週HRIS exportpandasOpenAIConfluence
ClaudeClaude
ROI for
README.md

為什麼選擇此子代理

薪資或升遷資料中的偏見確實存在，卻很容易被忽略，也很危險地被誤讀。這個偵測工具會掃描去識別化的人資紀錄，找出值得人工檢視的模式。

每一項發現都附帶其注意事項：樣本數、資料的局限性，並清楚註明這只是供人工審查的訊號，而非定論。它協助 HR 或法務團隊知道該往哪裡看，但不會假裝數據能證明意圖。

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)

Report statistical gaps in the HR data by group, always with sample size and a stated caveat; flag for human review and never assert intent or causation.

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.