claudegoodies
Skill

research-refine-pipeline

From wanshuiyin

Run an end-to-end workflow that chains `research-refine` and `experiment-plan`. Use when the user wants a one-shot pipeline from vague research direction to focused final proposal plus detailed experiment roadmap, or asks to \"\u4e32\u8d77\u6765\", build a pipeline, do it end-to-end, or generate both the method and experiment plan together.

Chains research-refine and experiment-plan skills into one pipeline from raw idea to method proposal plus experiment roadmap.

Use it when

  • Going from a vague research direction straight to a validated experiment plan
  • Need both a refined method thesis and a claim-driven experiment plan together
  • Already have a proposal and want to add an experiment plan without redoing method work

Skip it if

  • You only need one stage — use research-refine or experiment-plan directly instead
  • Your method thesis is still unstable; this pipeline requires stabilizing it first before planning experiments
  • You want quick output rather than a multi-file structured package (6 default output files)

Facts

Repository
wanshuiyin/Auto-claude-code-research-in-sleep
Status
Actively maintained
Last commit
Declared tools
Bash(*), Read, Write, Edit, Grep, Glob, WebSearch, WebFetch,
Source file
skills/research-refine-pipeline/SKILL.md

Source preview

The instructions Claude Code reads when this skill runs.

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

Refine and concretize: **$ARGUMENTS**

## Overview

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:

1. `research-refine` for method refinement
2. `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`

## Core Rule

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

## Default Outputs

- `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

### Phase 0: Triage the Starting Point

- 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
View full source on GitHub →

Other skills