跳到正文
TakoAPI
返回技能列表

model-matrix

由 hybredm 提供

Coding Agents & IDEs
—暂无评分
你的评分

简介

Weighted model-routing matrix for OpenClaw (cost-aware, policy-aware, daily scorecard template).

描述

该技能的功能

A weighted routing matrix that assigns AI model tasks to the cheapest model that meets quality thresholds. Scores models across real evaluations, benchmarks, sentiment, and cost, then applies policy rules to pick an effective winner per category. Includes a daily scorecard template to track and update routing decisions.

Combining weighted scoring with explicit swap-only-on-material-delta rules prevents churn and cost creep that comes from routing on benchmarks alone.

何时使用

  • Routing complex coding tasks to the highest-scoring code model
  • Keeping routine cron jobs on cheaper models to reduce API spend
  • Swapping model assignments when a weekly scorecard shows a material score shift
  • Enforcing a policy fallback when a preferred provider is temporarily excluded
  • Comparing Grok, Gemini, and GPT outputs for sentiment-heavy research tasks

示例工作流

输入

User asks: which model should handle complex coding tasks this week?

智能体
  1. 1

    Pull current scorecard scores for the Coding (complex) category

  2. 2

    Apply weights: 45% real eval, 30% benchmark, 20% sentiment, 5% cost

  3. 3

    Compute raw score for each candidate model

  4. 4

    Check policy constraints (e.g., Anthropic exclusion triggers auto-promote of #2)

  5. 5

    Return effective #1 with confidence rating

输出

GPT-5.3 Codex assigned as effective model for complex coding with confidence score

安装

clawhub install hybredm/model-matrix

运行 CLI 命令,或把这段提示词粘贴到 Claude Code、Cursor、Codex 或你在用的任意编程智能体里。

链接