Automate setup, configuration, execution, monitoring, and troubleshooting of AutoResearchClaw — the 23-stage autonomous research pipeline that generates conference-grade papers. Use when the user mentions ResearchClaw, wants to write a research paper autonomously, needs to set up or debug the pipeline, or says research paper, autonomous research, or paper generation.
Install with Codex or Claude Copy this prompt, paste it into Codex, Claude, or another assistant, and let it review the skill page and install it for you.
A direct command skips the review prompt. Inspect the source before running it.
Automate setup, configuration, execution, monitoring, and troubleshooting of AutoResearchClaw — the 23-stage autonomous research pipeline that generates conference-grade papers. Use when the user mentions ResearchClaw, wants to write a research paper autonomously, needs to set up or debug the pipeline, or says research paper, autonomous research, or paper generation.
license
MIT
user-invocable
true
compatibility
Requires Python 3.11+, Docker, and a LaTeX distribution. Works with Claude Code and compatible coding agents.
This skill wraps AutoResearchClaw, a 23-stage pipeline that takes a research topic and produces a conference-grade LaTeX paper with real citations, sandbox-executed experiments, multi-agent peer review, and citation verification.
Honesty policy: This skill does not fabricate capabilities. Every command maps to real upstream functionality. If something fails, the skill reports the actual error and suggests concrete fixes — it never pretends the problem does not exist.
Commands
Command
Purpose
/researchclaw
Show help and available subcommands
/researchclaw:setup
Check and install all prerequisites (Python, Docker, LaTeX, pip packages)
/researchclaw:config
Interactive config wizard — generates a working config.yaml
/researchclaw:run
Start a research pipeline run
/researchclaw:status
Check the status of a running or completed pipeline
/researchclaw:resume
Resume a pipeline from the last successful stage
/researchclaw:diagnose
Auto-detect and explain common failures
/researchclaw:validate
Validate config, dependencies, and connectivity before running
/researchclaw — Help
When invoked without a subcommand, display this command list and a one-line status summary:
Check if researchclaw CLI is installed: which researchclaw
Check if config.yaml exists in the current directory
Print the command table above
Suggest the most logical next step based on what is missing
/researchclaw:setup — Prerequisites Installation
MANDATORY: Ask the user before installing anything. Present what is missing and get explicit approval.
The script checks each dependency and outputs a JSON report. Based on the report:
Python 3.11+: Check python3 --version. If missing or too old, suggest pyenv install 3.11 or system package manager.
pip / uv: Check pip3 --version or uv --version. Suggest uv if not present (faster).
Docker: Check docker info. If Docker daemon is not running, tell the user honestly — this skill cannot start Docker for you on most systems.
LaTeX: Check pdflatex --version. If missing, suggest sudo apt-get install texlive-full (Linux) or brew install --cask mactex (macOS). Be honest: this is a large download (2-4 GB).
AutoResearchClaw: Check pip3 show researchclaw. If not installed:
pip3 install researchclaw
Or from source:
git clone https://github.com/aiming-lab/AutoResearchClaw.git
cd AutoResearchClaw
pip3 install -e ".[all]"
After installation, re-run the check script to verify everything passes.
What this skill CANNOT do:
Start the Docker daemon (requires system-level access)
Install LaTeX without sudo on Linux
Fix network/firewall issues blocking API access
Provide LLM API keys — the user must supply their own
Generate a working config.yaml by asking the user a series of questions. Use AskUserQuestion for each batch.
Batch 1 — Essential settings (MUST ask):
Research topic: What do you want to research? (free text)
LLM provider: Which LLM API? Options: openai, anthropic, azure, deepseek, local
API key: Provide your API key, or the environment variable name that holds it (e.g., OPENAI_API_KEY)
Model: Which model? Suggest defaults per provider:
openai: gpt-4o
anthropic: claude-sonnet-4-20250514
deepseek: deepseek-chat
Batch 2 — Experiment settings (ask with smart defaults):
Experiment mode: simulated (no code execution, fastest), sandbox (local execution), or ssh_remote (GPU server). Default: simulated
Auto-approve gates: Skip human approval at stages 5, 9, 20? Default: true for first run
Output directory: Where to save artifacts. Default: artifacts/
Batch 3 — Optional advanced settings (offer but don't require):
Paper template: neurips, icml, iclr, or generic. Default: neurips
Max iterations: For iterative pipeline mode. Default: 3
Literature sources: arxiv, semantic_scholar, or both. Default: both
After collecting answers, generate config.yaml using the template in assets/config-template.yaml. Write it to the current directory and show the user the generated file.
Validation: After generating, run:
researchclaw validate --config config.yaml
If validation fails, explain what went wrong and offer to fix it.
/researchclaw:run — Execute the Pipeline
Pre-flight checks (always run before starting):
Run /researchclaw:validate logic silently
If any check fails, report it and ask the user whether to proceed or fix first
Start the pipeline:
researchclaw run --topic "$ARGUMENTS" --config config.yaml --auto-approve 2>&1 | tee researchclaw-run.log
If $ARGUMENTS is empty, read the topic from config.yaml.
During execution:
The pipeline runs 23 stages. Each stage produces output in artifacts/<run-id>/stage-N/
Monitor progress by checking which stage directories exist
If the pipeline fails, capture the error output and run /researchclaw:diagnose logic automatically
After completion:
Report which stages succeeded and which failed
Show the path to the generated paper (typically artifacts/<run-id>/stage-17/paper_draft.md or the final PDF)
Show total execution time
/researchclaw:status — Pipeline Status
Check the current state of a pipeline run:
ls -la artifacts/ 2>/dev/null | tail -5
For the most recent run:
Find the latest artifacts/rc-* directory
Count completed stages: ls -d artifacts/rc-*/stage-* 2>/dev/null | wc -l
Check for pipeline_summary.json — if it exists, the run is complete
If no summary exists, check which stage was last modified to estimate current progress
Report: Stage X/23 complete. Current stage: [stage name]. Status: [running/failed/complete]
Stage name mapping (for human-readable output):
Stage
Name
1
Topic Initialization
2
Problem Decomposition
3
Literature Search
4
Literature Analysis
5
Research Direction (Gate)
6
Hypothesis Generation
7
Experiment Design
8
Experiment Plan Review
9
Experiment Approval (Gate)
10
Code Generation
11
Code Review
12
Experiment Execution
13
Result Collection
14
Result Analysis
15
Paper Outline
16
Section Writing
17
Paper Draft
18
Peer Review
19
Revision
20
Final Review (Gate)
21
Citation Verification
22
Visualization
23
Final Export
/researchclaw:resume — Resume a Failed Run
Resume from the last successful stage:
Find the latest run directory: ls -td artifacts/rc-* | head -1
Find the last completed stage: check pipeline_summary.json or find the highest-numbered stage-* directory with output files
Determine the next stage name from the stage mapping above
Run:
researchclaw run --config config.yaml --from-stage STAGE_NAME --output <run-dir> --auto-approve 2>&1 | tee researchclaw-resume.log
Known issue (upstream): The --from-stage flag may not work correctly in all versions. If resume fails, inform the user honestly and suggest:
Starting a fresh run
Manually copying successful stage outputs to a new run directory
/researchclaw:diagnose — Auto-Diagnose Failures
Read the most recent log and error output to identify the problem:
