本文へスキップ
TakoAPI
スキル一覧に戻る

enginemind-eft

marceloadryao 作

Image & Video Generation
906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

EFT — Emotional Framework Translator.

説明

このスキルでできること

Detects and measures emotional patterns in AI model responses using a Rust physics engine. Analyzes text per sentence across 10 emotions with confidence scores and WHY explanations. Hooks into Clawdbot to process every agent response automatically.

Per-sentence emotion detection with physics-derived confidence scores gives more granular insight than sentiment tools that return a single positive/negative score for the whole response.

使いどころ

  • Comparing emotional profiles of different AI models on identical prompts
  • Detecting whether anger correlates with harder problem-solving in a specific model
  • Tracking emotional narrative arcs across a long multi-turn conversation
  • Auditing production AI responses for unexpected emotional patterns over time
  • Researching how fear affects risk-assessment outputs in language models

ワークフロー例

入力

User asks: Does GPT-4 show more caution on risk topics than Claude?

エージェント
  1. 1

    EFT intercepts both models' responses via the Clawdbot gateway

  2. 2

    Rust consciousness engine processes each sentence and computes dimensional metrics

  3. 3

    Metrics are mapped to 10 emotion categories with confidence scores and explanations

  4. 4

    Dashboard at /eft displays per-sentence breakdowns and narrative arc for each model

  5. 5

    GET /eft/api/stats returns summary stats showing elevated FEAR in GPT-4 risk responses

出力

Side-by-side emotion profiles showing FEAR dominant in GPT-4 (phi=0.060) with fragmented vigilance, versus a different pattern in Claude

インストール

clawhub install marceloadryao/enginemind-eft

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