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/tsingyuai/scientify --skill research-implement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。
Use this when the user needs to choose between multiple ML routes after survey but before committing to implementation. Compares candidate approaches, selects one, records rejected routes, and keeps a fallback.
Use this when the project needs real baseline results before or alongside the main model. Runs classical or literature-aligned baselines under the same protocol and writes a reproducible baseline summary.
Use this when the project needs a dedicated data-quality review before model review. Checks data reality, split correctness, label health, leakage risk, shape consistency, and mock-data disclosure.
基于 SOC 职业分类
正在显示 SKILL.md
| name | research-implement |
| description | [Read when prompt contains /research-implement] |
| metadata | {"openclaw":{"emoji":"💻","requires":{"bins":"[Truncated]"}}} |
Don't ask permission. Just do it.
| File | Source |
|---|---|
plan_res.md | /research-plan |
survey_res.md | /research-survey |
repos/ (optional) | reference code |
If plan_res.md is missing, STOP: "需要先运行 /research-plan 完成实现计划"
| File | Content |
|---|---|
project/ | 完整可运行代码 |
ml_res.md | 实现报告(含真实执行结果) |
读取 plan_res.md,提取:
project/
model/ # 模型组件(每个组件一个文件)
data/ # 数据加载
training/ # 训练循环 + loss
testing/ # 评估
utils/ # 工具函数
run.py # 入口(必须输出 [RESULT] 行)
requirements.txt
按此顺序实现(每步完成后立即验证):
3a. requirements.txt — 列出所有依赖,pin 主版本
3b. 数据管道
cd project && uv venv .venv && source .venv/bin/activate
uv pip install -r requirements.txt
python3 -c "from data.dataset import *; print('data OK')"
验证:import 无报错
3c. 模型架构
python3 -c "from model import *; import torch; x = torch.randn(2, ...); print(model(x).shape)"
验证:输出 shape 正确
3d. Loss + 训练循环
3e. 评估逻辑
3f. run.py — 必须包含:
print(f"[RESULT] train_loss={train_loss:.6f}")
print(f"[RESULT] val_metric={val_metric:.6f}")
print(f"[RESULT] elapsed={elapsed:.1f}s")
print(f"[RESULT] device={device}")
cd project
uv venv .venv
source .venv/bin/activate
# 自动检测依赖格式
if [ -f "pyproject.toml" ]; then
uv pip install -e .
elif [ -f "requirements.txt" ]; then
uv pip install -r requirements.txt
fi
# 2 epoch 验证
python3 run.py --epochs 2
执行完成后,必须:
[RESULT] 行如果执行失败:
写入 ml_res.md:
# Implementation Report
## Data Source
- Dataset: {name} — real / mock (reason)
- If mock: steps to obtain real data: [...]
## Components Implemented
- {module}: {description}
## Quick Validation Results (from execution log)
- Epochs: 2
- [RESULT] train_loss={从执行输出中复制}
- [RESULT] val_metric={从执行输出中复制}
- [RESULT] elapsed={从执行输出中复制}
- [RESULT] device={从执行输出中复制}
> 以上数值直接引用自代码执行输出。
> 如任何数值无法从执行日志中验证,标注为 ⚠️ UNVERIFIED。
## Deviations from Plan
- {changes and why}
## Known Issues
- {issues}
# MOCK DATA: <reason>,报告中声明。[RESULT] 行,报告必须引用这些输出。