本文へスキップ
TakoAPI
スキル一覧に戻る

ask-council

jeadland 作

Web & Frontend Development
402ダウンロード数はclawskills.shが公開している値です
0閲覧数
0件のいいねサインインするとこのスキルにいいねできます
—まだ評価がありません
あなたの評価

概要

Ask LLM Council a question directly from Telegram/chat — get the chairman's synthesized answer without opening.

説明

このスキルでできること

Sends a question to a running LLM Council backend and returns the Chairman's synthesized answer via chat command. Runs through a three-stage deliberation process: individual model responses, peer ranking, and final synthesis. Takes 30-60 seconds per query.

Gives access to multi-model consensus from any chat interface without spinning up or navigating a web UI.

使いどころ

  • Quick architectural decision from mobile
  • Getting a consensus answer without opening a browser
  • Asking a tech or finance question mid-conversation
  • Comparing language/framework tradeoffs on the fly
  • Running a fast headless council query from Telegram

ワークフロー例

入力

User asks: /council Is Python or Go better for a new microservice?

エージェント
  1. 1

    Runs ask-council.sh with the question as argument

  2. 2

    Creates a new conversation via the LLM Council API

  3. 3

    Polls Stage 1 until all models have responded

  4. 4

    Polls Stage 2 until models have ranked each other

  5. 5

    Extracts and returns the Chairman's Stage 3 synthesis

出力

Chairman's synthesized answer recommending Python for team velocity or Go for high-throughput services, plus a link to the full web discussion

要件

  • LLM Council backend running locally (install via /install-llm-council)

インストール

clawhub install jeadland/ask-council

CLIコマンドを実行するか、Claude Code、Cursor、Codexなどお使いのコーディングエージェントにプロンプトを貼り付けてください。

リンク