来源信息
- 仓库
- ApiliumCode/mayros
- 最近来源活动
- 2026年2月26日 12:53
- 检测到的 SKILL.md 语言
- 英语
- 星标
- 12
- 分支
- 1
安装方式
默认使用会先检查来源的 Prompt；你也可以切换为直接命令，或下载本地副本。
检查来源文件
决定是否安装前，请先阅读 SKILL.md，以及 SkillsMP 当前展示的配套文件。
文件资源管理器
10 个文件正在显示 SKILL.md
SKILL.md
来源说明 · 只读预览- name
- model-advisor
- description
- Recommends the optimal Claude model based on task requirements and cost analysis
- type
- semantic
- user-invocable
- true
- semantic
- {"skillVersion":1,"permissions":{"graph":["read"],"memory":["recall"]},"queries":[{"predicate":"advisor:recommendation","scope":"agent"}]}
# model-advisor
Recommends the optimal Claude model based on task requirements, complexity analysis, and cost efficiency.
## When to Use
Use when choosing between Claude models for a specific task, when optimizing API costs, or when you need guidance on which model best fits a workload profile.
## Supported Models
| Model | Input | Output | Best For |
| ---------- | ---------- | -------- | ------------------------------------------------------------------------------------- |
| Opus 4.6 | $15/MTok | $75/MTok | Complex reasoning, research, multi-step analysis, code architecture, creative writing |
| Sonnet 4.6 | $3/MTok | $15/MTok | Coding, general tasks, data analysis, moderate complexity |
| Haiku 4.5 | $0.80/MTok | $4/MTok | Classification, extraction, simple Q&A, high volume, low latency |
## Instructions
1. Recall any previous model recommendations with `skill_memory_context`
2. Analyze the task description from query results for complexity indicators
3. Match task keywords against model strengths to determine the best fit
4. Return the recommended model with rationale and cost comparison
在 GitHub 查看