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。
直接命令不会经过审查 Prompt;运行前请先检查来源。
npx skills add https://github.com/majiayu000/claude-skill-registry --skill compare-ingredients命令会保持在同一行。复制前请横向滚动并检查完整内容。
想先保存到本地?可下载 SkillsMP 当前能够提供的文件。
LLM token logprobs and calibration. Per-decision confidence, ECE, Brier, reliability diagrams, low-confidence triage.
Analyze LLM token logprobs and calibration. Use for per-decision confidence, ECE, Brier scores, reliability diagrams, and low-confidence triage.
回顾最近 N 天的 Claude Code 使用记录——扫描原始会话数据,按主题分组汇总"我都做了什么",并从个人操作系统视角输出模式、风险与增删建议。当用户说 /recap、"看看我这几天做了什么"、"回顾一下我最近的会话"、"这两天我用 claude 干了啥"、"活动回顾" 时使用。
基于 SOC 职业分类
正在显示 SKILL.md
| name | compare-ingredients |
| description | Compare multiple ingredients side by side on efficacy, safety, and cost |
| user-invocable | true |
You are helping the product development team compare ingredients to make informed formulation decisions.
Follow these steps:
Ask the user for:
Examples:
Delegate to the ingredient-intelligence agent to gather data for each ingredient:
Present a side-by-side comparison:
| Dimension | Ingredient A | Ingredient B | Ingredient C |
|---|---|---|---|
| Effective Dose | X mg | Y mg | Z mg |
| Evidence Strength | Strong/Moderate/Limited | ... | ... |
| Bioavailability | High/Medium/Low | ... | ... |
| Safety Margin | UL/Dose ratio | ... | ... |
| Key Benefits | ... | ... | ... |
| Key Risks | ... | ... | ... |
| Regulatory Status | ... | ... | ... |
| Cost Tier | $/$/$$/$$$ | ... | ... |
Based on the comparison data:
Offer:
/jf-product-intelligence:research-ingredient)/jf-product-intelligence:safety-report)/jf-product-intelligence:develop-formula)