本文へスキップ
TakoAPI
スキル一覧に戻る

turing-pyramid

tensusds 作

Coding Agents & IDEs
877ダウンロード数はclawskills.shが公開している値です
2スター
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

Decision framework for agent psychological health. 10 needs with decay, tension-based priority, cross-need cascades.

説明

このスキルでできること

Prioritized action selection engine for AI agents using 10 configurable needs with time-decay and tension scoring. Each cycle calculates which needs are most deprived and selects concrete actions ranked by urgency. Replaces idle heartbeat loops with a decision framework that adapts to agent state over time.

Instead of polling for tasks or waiting for user input, agents get a ranked action list derived from measurable deprivation levels, decay curves, and cross-need cascades.

使いどころ

  • Running an AI agent on a regular heartbeat schedule with meaningful next steps
  • Preventing an autonomous agent from cycling without purpose between tasks
  • Tuning an agent's priorities for research-focused versus social-facing work
  • Auditing what actions an agent took and why over the past week
  • Detecting when a low-priority need has been neglected for too long

ワークフロー例

入力

User asks: Run the Turing Pyramid cycle for my agent

エージェント
  1. 1

    Reads current satisfaction values from assets/needs-state.json

  2. 2

    Applies time-decay to each need based on hours elapsed and the configured day/night multiplier

  3. 3

    Calculates tension scores (importance × (3 - satisfaction)) for all 10 needs

  4. 4

    Selects highest-tension needs using probability tables and impact range matrices

  5. 5

    Outputs ranked action suggestions with mark-satisfied.sh commands for each

出力

A prioritized list of 2-3 concrete actions with tension scores, impact values, and follow-up mark-satisfied commands

要件

  • WORKSPACE environment variable set to the agent workspace directory path

インストール

clawhub install tensusds/turing-pyramid

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