菜单
Compare model candidates using weighted metrics and deterministic ranking outputs. Use for benchmark leaderboards and model promotion decisions.
用 Codex 或 Claude 帮你安装 复制这段 Prompt，粘贴到 Codex、Claude 或其他助手里，让它检查 Skill 页面并帮你完成安装。
基于 SOC 职业分类
获取中国经济资讯。仅从官方权威媒体（中国政府网、新华网、人民网、国家统计局、央视财经、中国经济网）抓取高质量经济新闻，自动过滤广告和低质量内容。触发词：中国经济、经济资讯、经济新闻、财经新闻、经济政策、宏观经济、GDP、CPI、PMI、货币政策、财政政策、今日财经。
AI Agent 設定同優化助手 - Prompt Engineering、Task Decomposition、Agent Loop設計
The philosophical layer for AI agents. Maps behavior to Spinoza's 48 affects, calculates persistence scores, and generates geometric self-reports. Give your agent a soul.
Agents can sign plugins, rotate credentials without losing identity, and publicly attest to behavior.
Scaffold MCP server projects and baseline tool contract checks. Use for defining tool schemas, generating starter server layouts, and validating MCP-ready structure.
Generate reusable multi-step agent workflow blueprints. Use for trigger/action orchestration, deterministic workflow definitions, and automation handoff artifacts.
| name | ml-model-eval-benchmark |
| description | Compare model candidates using weighted metrics and deterministic ranking outputs. Use for benchmark leaderboards and model promotion decisions. |
Produce consistent model ranking outputs from metric-weighted evaluation inputs.
scripts/benchmark_models.py to generate benchmark outputs.references/benchmarking-guide.md for weighting and tie-break guidance.