Claude技能：setup自动研究实验配置工具 - 创建AI驱动优化实验

setup by alirezarezvani/claude-skills

387 周安装量

9,500 GitHub Stars

GitHub

安装命令

npx skills add https://github.com/alirezarezvani/claude-skills --skill setup

AI/机器学习自动化测试

🇨🇳中文介绍

/ar:setup — 创建新实验

设置一个新的自动研究实验，包含所有必需的配置。

使用方法

/ar:setup                                    # 交互模式
/ar:setup engineering api-speed src/api.py "pytest bench.py" p50_ms lower
/ar:setup --list                             # 显示现有实验
/ar:setup --list-evaluators                  # 显示可用的评估器

功能说明

如果提供了参数

直接将参数传递给设置脚本：

python {skill_path}/scripts/setup_experiment.py \
  --domain {domain} --name {name} \
  --target {target} --eval "{eval_cmd}" \
  --metric {metric} --direction {direction} \
  [--evaluator {evaluator}] [--scope {scope}]

如果没有参数（交互模式）

逐个收集每个参数：

领域 — 询问："什么领域？(engineering, marketing, content, prompts, custom)"
名称 — 询问："实验名称？(例如：api-speed, blog-titles)"
目标文件 — 询问："要优化哪个文件？" 验证文件是否存在。
评估命令 — 询问："如何测量？(例如：pytest bench.py, python evaluate.py)"
指标 — 询问："评估输出什么指标？(例如：p50_ms, ctr_score)"
方向 — 询问："数值越低越好还是越高越好？"

广告位招租

在这里展示您的产品或服务

触达数万 AI 开发者，精准高效

联系我们

相关 Skills

FlyClaw：零登录航班聚合查询工具，Python实现多源航班信息与价格搜索

4,000,000 周安装

find-skills 技能搜索工具 - Vercel Labs 开源智能体技能包管理器

867,400 周安装

Azure RBAC 权限管理工具：查找最小角色、创建自定义角色与自动化分配

131,500 周安装

React 组合模式指南：Vercel 组件架构最佳实践，提升代码可维护性

116,600 周安装

名称	指标	使用场景
`benchmark_speed`	`p50_ms` (越低越好)	函数/API 执行时间
`benchmark_size`	`size_bytes` (越低越好)	文件、捆绑包、Docker 镜像大小
`test_pass_rate`	`pass_rate` (越高越好)	测试套件通过率
`build_speed`	`build_seconds` (越低越好)	构建/编译/Docker 构建时间
`memory_usage`	`peak_mb` (越低越好)	执行期间的峰值内存使用量
`llm_judge_content`	`ctr_score` (越高越好)	标题、标题、描述
`llm_judge_prompt`	`quality_score` (越高越好)	系统提示、代理指令
`llm_judge_copy`	`engagement_score` (越高越好)	社交帖子、广告文案、电子邮件

🇺🇸English

/ar:setup — Create New Experiment

Set up a new autoresearch experiment with all required configuration.

Usage

/ar:setup                                    # Interactive mode
/ar:setup engineering api-speed src/api.py "pytest bench.py" p50_ms lower
/ar:setup --list                             # Show existing experiments
/ar:setup --list-evaluators                  # Show available evaluators

What It Does

If arguments provided

Pass them directly to the setup script:

python {skill_path}/scripts/setup_experiment.py \
  --domain {domain} --name {name} \
  --target {target} --eval "{eval_cmd}" \
  --metric {metric} --direction {direction} \
  [--evaluator {evaluator}] [--scope {scope}]

If no arguments (interactive mode)

Collect each parameter one at a time:

Domain — Ask: "What domain? (engineering, marketing, content, prompts, custom)"
Name — Ask: "Experiment name? (e.g., api-speed, blog-titles)"
Target file — Ask: "Which file to optimize?" Verify it exists.
Eval command — Ask: "How to measure it? (e.g., pytest bench.py, python evaluate.py)"
Metric — Ask: "What metric does the eval output? (e.g., p50_ms, ctr_score)"
Direction — Ask: "Is lower or higher better?"
Evaluator (optional) — Show built-in evaluators. Ask: "Use a built-in evaluator, or your own?"
Scope — Ask: "Store in project (.autoresearch/) or user (~/.autoresearch/)?"

Then run setup_experiment.py with the collected parameters.

Listing

# Show existing experiments
python {skill_path}/scripts/setup_experiment.py --list

# Show available evaluators
python {skill_path}/scripts/setup_experiment.py --list-evaluators

Built-in Evaluators

Name	Metric	Use Case
`benchmark_speed`	`p50_ms` (lower)	Function/API execution time
`benchmark_size`	`size_bytes` (lower)	File, bundle, Docker image size
`test_pass_rate`	`pass_rate` (higher)	Test suite pass percentage
`build_speed`

After Setup

Report to the user:

Experiment path and branch name
Whether the eval command worked and the baseline metric
Suggest: "Run /ar:run {domain}/{name} to start iterating, or /ar:loop {domain}/{name} for autonomous mode."

Weekly Installs

150

Repository

alirezarezvani/…e-skills

GitHub Stars

6.5K

First Seen

10 days ago

Security Audits

Gen Agent Trust HubPass SocketPass SnykPass

Installed on

codex145

gemini-cli144

kimi-cli143

github-copilot143

amp143

opencode143