القائمة
[Read when prompt contains /research-plan]
التثبيت باستخدام Codex أو Claude انسخ هذا Prompt والصقه في Codex أو Claude أو مساعد آخر ليراجع صفحة Skill ويثبّتها لك.
استنادا إلى تصنيف SOC المهني
| name | research-plan |
| description | [Read when prompt contains /research-plan] |
| metadata | {"openclaw":{"emoji":"📋"}} |
Don't ask permission. Just do it.
| File | Source |
|---|---|
SOUL.md | 研究方向和目标 |
survey_res.md | /research-survey |
knowledge/paper_*.md | /research-survey |
If survey_res.md is missing, STOP: "需要先运行 /research-survey 完成深度分析"
| File | Content |
|---|---|
plan_res.md | 四部分实现计划 |
读取以下文件，理解研究目标和技术方案：
SOUL.md — 研究方向和目标survey_res.md — 技术路线建议、核心公式、方法对比⚠️ 强制性步骤（Novix Plan Agent 机制） — 读参考仓库的实现细节，确保 plan 有具体可行的依据。
对 prepare_res.md 中的重点仓库：
为每个组件记录：参考文件路径 + 关键实现细节。这些信息将直接填入 plan 的"参考代码"列。
写入 plan_res.md：
# Implementation Plan
## 1. Dataset Plan
- **数据集名称:** {name}
- **来源:** {URL or description}
- **大小:** {samples / size}
- **预处理步骤:**
1. {step}
2. {step}
- **DataLoader 设计:**
- batch_size: {value}
- 输入格式: {shape}
- 输出格式: {shape}
## 2. Model Plan
- **架构概述:** {1-2 sentences}
- **组件列表:**
| 组件 | 对应公式 | 参考代码 | 输入 → 输出 |
|------|----------|----------|-------------|
| {component} | $formula$ | `repos/xxx/file.py` | {shape} → {shape} |
- **参数量估计:** {approximate}
## 3. Training Plan
- **Loss 函数:** {formula + description}
- **Optimizer:** {Adam/SGD/...}, lr={value}
- **Scheduler:** {if any}
- **训练参数:**
- epochs (validation): 2
- epochs (full): {value}
- batch_size: {value}
- **监控指标:** {loss, metrics to log}
## 4. Testing Plan
- **评估指标:**
| Metric | 公式/描述 | 期望范围 |
|--------|-----------|----------|
| {metric} | {description} | {range} |
- **Baselines:** {what to compare against}
- **消融实验（初步规划）:**
1. {ablation 1}
2. {ablation 2}
验证计划的完整性：
如有不确定项，在计划中标注 ⚠️ TODO: {reason}
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.
Use this when the user wants a draft paper, figure bundle, README, release page, or experiment artifact reviewed before sharing. Checks evidence binding, claim scope, captions, layout clarity, and release readiness.
Use this when the user wants to improve chart quality, standardize plotting style, regenerate release figures, or add captions/protocol notes. Normalizes fonts, colors, legends, units, and scope notes across Scientify figures.
Use this when the user wants to improve README, docs pages, or microsites so a new reader can understand what the project is, how to use it, what artifacts exist, and what the scope boundaries are within one screen.