research-refine-pipeline

Compare original and translation side by side

🇺🇸

Original

English

🇨🇳

Translation

Chinese

Research Refine Pipeline: End-to-End Method and Experiment Planning

Research Refine 工作流：端到端方法与实验规划

Refine and concretize: $ARGUMENTS

优化并具体化：$ARGUMENTS

Overview

概述

Use this skill when the user does not want to stop at a refined method. The goal is to produce a coherent package that includes:

a problem-anchored, elegant final proposal
the review history explaining why the method is focused
a detailed experiment roadmap tied to the paper's claims
a compact pipeline summary that says what to run next

This skill composes two existing workflows:

```
research-refine
```
for method refinement
```
experiment-plan
```
for claim-driven validation planning

For stage-specific detail, read these sibling skills only when needed:

```
../research-refine/SKILL.md
```
```
../experiment-plan/SKILL.md
```

当用户不满足于仅优化方法时，可使用本技能。目标是生成一套完整的成果包，包括：

以问题为锚点、简洁清晰的最终提案
说明方法为何聚焦的评审历史
与论文主张紧密关联的详细实验路线图
说明下一步执行内容的简洁工作流摘要

本技能整合了两个现有工作流：

用于方法优化的
```
research-refine
```
用于基于主张的验证规划的
```
experiment-plan
```

如需了解各阶段的详细信息，仅在必要时查看以下姊妹技能文档：

```
../research-refine/SKILL.md
```
```
../experiment-plan/SKILL.md
```

Core Rule

核心规则

Do not plan a large experiment suite on top of an unstable method. First stabilize the thesis. Then turn the stable thesis into experiments.

不要基于不稳定的方法规划大规模实验套件。首先要稳固研究主题，再将稳固后的主题转化为实验。

Default Outputs

默认输出

```
refine-logs/FINAL_PROPOSAL.md
```
```
refine-logs/REVIEW_SUMMARY.md
```
```
refine-logs/REFINEMENT_REPORT.md
```
```
refine-logs/EXPERIMENT_PLAN.md
```
```
refine-logs/EXPERIMENT_TRACKER.md
```
```
refine-logs/PIPELINE_SUMMARY.md
```

```
refine-logs/FINAL_PROPOSAL.md
```
```
refine-logs/REVIEW_SUMMARY.md
```
```
refine-logs/REFINEMENT_REPORT.md
```
```
refine-logs/EXPERIMENT_PLAN.md
```
```
refine-logs/EXPERIMENT_TRACKER.md
```
```
refine-logs/PIPELINE_SUMMARY.md
```

Workflow

工作流

Phase 0: Triage the Starting Point

阶段0：评估起始点

Extract the problem, rough approach, constraints, resources, and target venue.
Check whether
```
refine-logs/FINAL_PROPOSAL.md
```
already exists and still matches the current request.
If the proposal is missing, stale, or materially different from the current request, run the full
```
research-refine
```
stage.
If the proposal is already strong and aligned, reuse it and jump to experiment planning.
If in doubt, prefer re-running
```
research-refine
```
rather than planning experiments for the wrong method.

提取问题、初步方法、约束条件、资源和目标发表场所。
检查
```
refine-logs/FINAL_PROPOSAL.md
```
是否已存在，且是否与当前请求匹配。
若提案缺失、过时，或与当前请求存在实质性差异，则运行完整的
```
research-refine
```
阶段。
若提案已完善且符合要求，则复用该提案并直接进入实验规划阶段。
若存在疑问，优先重新运行
```
research-refine
```
，而非为错误的方法规划实验。

Phase 1: Method Refinement Stage

阶段1：方法优化阶段

Run the

research-refine

workflow and keep its V3 philosophy intact:

preserve the Problem Anchor
prefer the smallest adequate mechanism
keep one dominant contribution
modernize only when it improves the paper

Exit this stage only when these are explicit:

the final method thesis
the dominant contribution
the complexity intentionally rejected
the key claims and must-run ablations
the remaining risks, if any

If the verdict is still

REVISE

, continue into experiment planning only if the remaining weaknesses are clearly documented.

运行

research-refine

工作流，并严格遵循其V3理念：

保留问题锚点
优先采用最小可行机制
聚焦一项核心贡献
仅在能提升论文质量时才引入现代化技术

仅当明确得到以下内容时，方可退出本阶段：

最终的方法主题
核心贡献
主动舍弃的复杂度
必须验证的关键主张和对照实验
若存在，剩余的风险

若最终结论仍为

REVISE

，仅当剩余缺陷已被清晰记录时，方可继续进入实验规划阶段。

Phase 2: Planning Gate

阶段2：规划校验门

Before the experiment stage, write a short gate check:

What is the final method thesis?
What is the dominant contribution?
What complexity was intentionally rejected?
Which reviewer concerns still matter for validation?
Is a frontier primitive central, optional, or absent?

If these answers are not crisp, tighten the final proposal first.

进入实验阶段前，编写一份简短的校验清单：

最终的方法主题是什么？
核心贡献是什么？
主动舍弃了哪些复杂度？
哪些评审意见仍需在验证环节关注？
前沿基础组件是核心、可选还是未使用？

若上述问题的答案不够清晰，需先完善最终提案。

Phase 3: Experiment Planning Stage

阶段3：实验规划阶段

Run the

experiment-plan

workflow grounded in:

```
refine-logs/FINAL_PROPOSAL.md
```
```
refine-logs/REVIEW_SUMMARY.md
```
```
refine-logs/REFINEMENT_REPORT.md
```

Ensure the experiment plan covers:

the main anchor result
novelty isolation
a simplicity or deletion check
a frontier necessity check if applicable
run order, budget, and decision gates

基于以下文件运行

experiment-plan

工作流：

```
refine-logs/FINAL_PROPOSAL.md
```
```
refine-logs/REVIEW_SUMMARY.md
```
```
refine-logs/REFINEMENT_REPORT.md
```

确保实验规划涵盖：

核心锚点结果
创新性验证
简洁性或删减验证
若适用，前沿组件的必要性验证
执行顺序、预算和决策节点

Phase 4: Integration Summary

阶段4：整合摘要

Write

refine-logs/PIPELINE_SUMMARY.md

markdown

undefined

编写

refine-logs/PIPELINE_SUMMARY.md

：

markdown

undefined

Pipeline Summary

Problem: [problem] Final Method Thesis: [one sentence] Final Verdict: [READY / REVISE / RETHINK] Date: [today]

Final Deliverables

Proposal:
```
refine-logs/FINAL_PROPOSAL.md
```
Review summary:
```
refine-logs/REVIEW_SUMMARY.md
```
Experiment plan:
```
refine-logs/EXPERIMENT_PLAN.md
```
Experiment tracker:
```
refine-logs/EXPERIMENT_TRACKER.md
```

Proposal:
```
refine-logs/FINAL_PROPOSAL.md
```
Review summary:
```
refine-logs/REVIEW_SUMMARY.md
```
Experiment plan:
```
refine-logs/EXPERIMENT_PLAN.md
```
Experiment tracker:
```
refine-logs/EXPERIMENT_TRACKER.md
```

Contribution Snapshot

Dominant contribution:
Optional supporting contribution:
Explicitly rejected complexity:

Dominant contribution:
Optional supporting contribution:
Explicitly rejected complexity:

Must-Prove Claims

[Claim 1]
[Claim 2]

[Claim 1]
[Claim 2]

First Runs to Launch

[Run]
[Run]
[Run]

[Run]
[Run]
[Run]

Main Risks

[Risk]:
[Mitigation]:

[Risk]:
[Mitigation]:

Next Action

Proceed to
```
/run-experiment
```

undefined

Proceed to
```
/run-experiment
```

undefined

Phase 5: Present a Brief Summary to the User

阶段5：向用户展示简短摘要

Pipeline complete.

Method output:
- refine-logs/FINAL_PROPOSAL.md

Experiment output:
- refine-logs/EXPERIMENT_PLAN.md
- refine-logs/EXPERIMENT_TRACKER.md

Pipeline summary:
- refine-logs/PIPELINE_SUMMARY.md

Best next step:
- /run-experiment

Pipeline complete.

Method output:
- refine-logs/FINAL_PROPOSAL.md

Experiment output:
- refine-logs/EXPERIMENT_PLAN.md
- refine-logs/EXPERIMENT_TRACKER.md

Pipeline summary:
- refine-logs/PIPELINE_SUMMARY.md

Best next step:
- /run-experiment

Key Rules

关键规则

Large file handling: If the Write tool fails due to file size, immediately retry using Bash (
```
cat << 'EOF' > file
```
) to write in chunks. Do NOT ask the user for permission — just do it silently.
Do not let the experiment plan override the Problem Anchor.
Do not widen the paper story after method refinement unless a missing validation block is truly necessary.

Reuse the same claims across

FINAL_PROPOSAL.md

EXPERIMENT_PLAN.md

, and

PIPELINE_SUMMARY.md

Keep the main paper story compact.
If the method is intentionally simple, defend that simplicity in the experiment plan rather than adding new components.
If the method uses a modern LLM / VLM / Diffusion / RL primitive, make its necessity test explicit.
If the method does not need a frontier primitive, say that clearly and avoid forcing one.
Prefer the staged skills when the user only needs one stage; use this skill for the integrated flow.

大文件处理：若Write工具因文件大小失败，立即使用Bash（
```
cat << 'EOF' > file
```
）分块重试写入。无需向用户请求权限——直接静默执行。
不要让实验规划覆盖问题锚点。
方法优化完成后，除非确实需要补充验证模块，否则不要拓展论文的核心故事线。

在

FINAL_PROPOSAL.md

、

EXPERIMENT_PLAN.md

和

PIPELINE_SUMMARY.md

中复用相同的主张。

保持论文的核心故事线简洁紧凑。
若方法为刻意简化设计，需在实验规划中为这种简洁性辩护，而非添加新组件。
若方法使用了现代LLM / VLM / Diffusion / RL基础组件，需明确验证其必要性。
若方法无需前沿基础组件，需清晰说明，避免强行添加。
当用户仅需要单个阶段时，优先使用分阶段技能；本技能用于整合式流程。

Composing with Other Skills

与其他技能组合

/research-refine-pipeline -> one-shot method + experiment planning
/research-refine   -> method refinement only
/experiment-plan   -> experiment planning only
/run-experiment    -> execution

/research-refine-pipeline -> one-shot method + experiment planning
/research-refine   -> method refinement only
/experiment-plan   -> experiment planning only
/run-experiment    -> execution