community-automations/telegram-toxicity

銷售與 CRM

PublicClaude 子代理

Telegram 毒性偵測器

大型聊天群組很容易迅速變調,而真人管理員不可能在凌晨兩點讀完每一則訊息。這個偵測器會在每則訊息出現的當下,就針對騷擾、仇恨與威脅進行評分,並標記出越線的內容。

sonnet4 天Telegram Bot APIClaudePerspective APIPostgreSQL
ClaudeClaude
ROI for
README.md

為什麼選擇此子代理

大型聊天群組很容易迅速變調,而真人管理員不可能在凌晨兩點讀完每一則訊息。這個偵測器會在每則訊息出現的當下,就針對騷擾、仇恨與威脅進行評分,並標記出越線的內容。

管理員收到的警示會附上訊息脈絡與建議處置,而非一股腦的原始訊息洪流。累犯會被記錄下來,因此一連串游走邊緣的訊息會浮上檯面,而非一則則悄悄溜過。

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)

Score this message for toxicity from 0 to 1 across harassment, hate, and threats; return JSON with reasons.

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.