Agent skill

ResearchClaw Research Pipeline

by aiming-lab in aiming-lab/AutoResearchClaw

Runs the ResearchClaw 23-stage autonomous pipeline from a topic, config file and output directory, from literature review through experiments to a written and reviewed paper.

MITAuto-check passedResearch & Science

Install ResearchClaw Research Pipeline

skills CLI

$ npx skills add aiming-lab/AutoResearchClaw --skill researchclaw -a claude-code

Project install by default; add -g for ~/.claude/skills/.

GitHub CLI

$ gh skill install aiming-lab/AutoResearchClaw researchclaw --agent claude-code

Project scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).

Manual copy

$ git clone --depth 1 https://github.com/aiming-lab/AutoResearchClaw.git skills-src && mkdir -p .claude/skills && cp -r skills-src/.claude/skills/researchclaw .claude/skills/researchclaw && rm -rf skills-src

Use ~/.claude/skills/ instead of .claude/skills for a personal install. The folder must contain SKILL.md.

Claude Code skills documentation · loads skills from .claude/skills/

Paste into Claude Code

Install the "researchclaw" agent skill from https://github.com/aiming-lab/AutoResearchClaw/tree/main/.claude/skills/researchclaw into .claude/skills/researchclaw/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "researchclaw", then confirm the skill loads.

Claude Code copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.

$skill-installer

$skill-installer install https://github.com/aiming-lab/AutoResearchClaw/tree/main/.claude/skills/researchclaw

Type this inside Codex. $skill-installer <name> installs a curated skill from openai/skills. The installer writes to $CODEX_HOME/skills (default ~/.codex/skills). Restart Codex if the skill does not show up.

skills CLI

$ npx skills add aiming-lab/AutoResearchClaw --skill researchclaw -a codex

Project install goes to .agents/skills/; add -g for ~/.codex/skills/.

GitHub CLI

$ gh skill install aiming-lab/AutoResearchClaw researchclaw --agent codex

Project scope by default (.agents/skills/); add --scope user for a personal install.

Manual copy

$ git clone --depth 1 https://github.com/aiming-lab/AutoResearchClaw.git skills-src && mkdir -p .agents/skills && cp -r skills-src/.claude/skills/researchclaw .agents/skills/researchclaw && rm -rf skills-src

Use ~/.agents/skills/ instead of .agents/skills for a personal install.

Codex skills documentation · loads skills from .agents/skills/

Paste into Codex

Install the "researchclaw" agent skill from https://github.com/aiming-lab/AutoResearchClaw/tree/main/.claude/skills/researchclaw into .agents/skills/researchclaw/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "researchclaw", then confirm the skill loads.

Codex copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.

skills CLI

$ npx skills add aiming-lab/AutoResearchClaw --skill researchclaw -a cursor

Project install goes to .agents/skills/; add -g for ~/.cursor/skills/.

GitHub CLI

$ gh skill install aiming-lab/AutoResearchClaw researchclaw --agent cursor

Project scope by default (.agents/skills/); add --scope user for a personal install.

Manual copy

$ git clone --depth 1 https://github.com/aiming-lab/AutoResearchClaw.git skills-src && mkdir -p .cursor/skills && cp -r skills-src/.claude/skills/researchclaw .cursor/skills/researchclaw && rm -rf skills-src

Use ~/.cursor/skills/ instead of .cursor/skills for a personal install.

Cursor skills documentation · loads skills from .cursor/skills/, .agents/skills/, .claude/skills/, .codex/skills/

Paste into Cursor

Install the "researchclaw" agent skill from https://github.com/aiming-lab/AutoResearchClaw/tree/main/.claude/skills/researchclaw into .cursor/skills/researchclaw/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "researchclaw", then confirm the skill loads.

Cursor copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.

gemini skills install

$ gemini skills install https://github.com/aiming-lab/AutoResearchClaw.git --path .claude/skills/researchclaw

--scope user (default) or --scope workspace; --path is the subfolder of the repo that holds the skill; --consent skips the security confirmation prompt.

skills CLI

$ npx skills add aiming-lab/AutoResearchClaw --skill researchclaw -a gemini-cli

Project install goes to .agents/skills/; add -g for ~/.gemini/skills/.

GitHub CLI

$ gh skill install aiming-lab/AutoResearchClaw researchclaw --agent gemini-cli

Project scope by default (.agents/skills/); add --scope user for a personal install.

Manual copy

$ git clone --depth 1 https://github.com/aiming-lab/AutoResearchClaw.git skills-src && mkdir -p .gemini/skills && cp -r skills-src/.claude/skills/researchclaw .gemini/skills/researchclaw && rm -rf skills-src

Use ~/.gemini/skills/ instead of .gemini/skills for a personal install, then run /skills reload.

Gemini CLI skills documentation · loads skills from .gemini/skills/, .agents/skills/

Paste into Gemini CLI

Install the "researchclaw" agent skill from https://github.com/aiming-lab/AutoResearchClaw/tree/main/.claude/skills/researchclaw into .gemini/skills/researchclaw/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "researchclaw", then confirm the skill loads.

Gemini CLI copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.

GitHub CLI

$ gh skill install aiming-lab/AutoResearchClaw researchclaw

Installs for Copilot at project scope by default; add --scope user for a personal install. Preview a skill first with gh skill preview. Needs GitHub CLI 2.90.0 or later (public preview).

skills CLI

$ npx skills add aiming-lab/AutoResearchClaw --skill researchclaw -a github-copilot

Project install goes to .agents/skills/; add -g for ~/.copilot/skills/.

Manual copy

$ git clone --depth 1 https://github.com/aiming-lab/AutoResearchClaw.git skills-src && mkdir -p .github/skills && cp -r skills-src/.claude/skills/researchclaw .github/skills/researchclaw && rm -rf skills-src

Use ~/.copilot/skills/ instead of .github/skills for a personal install. Commit .github/skills so cloud agent and code review can use it.

GitHub Copilot skills documentation · loads skills from .github/skills/, .claude/skills/, .agents/skills/

Paste into GitHub Copilot

Install the "researchclaw" agent skill from https://github.com/aiming-lab/AutoResearchClaw/tree/main/.claude/skills/researchclaw into .github/skills/researchclaw/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "researchclaw", then confirm the skill loads.

GitHub Copilot copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.

skills CLI

$ npx skills add aiming-lab/AutoResearchClaw --skill researchclaw -a opencode

OpenCode documents no install command of its own. Project install goes to .agents/skills/; add -g for ~/.config/opencode/skills/.

GitHub CLI

$ gh skill install aiming-lab/AutoResearchClaw researchclaw --agent opencode

Project scope by default (.agents/skills/); add --scope user for a personal install.

Manual copy

$ git clone --depth 1 https://github.com/aiming-lab/AutoResearchClaw.git skills-src && mkdir -p .opencode/skills && cp -r skills-src/.claude/skills/researchclaw .opencode/skills/researchclaw && rm -rf skills-src

Use ~/.config/opencode/skills/ instead of .opencode/skills for a personal install.

OpenCode skills documentation · loads skills from .opencode/skills/, .claude/skills/, .agents/skills/

Paste into OpenCode

Install the "researchclaw" agent skill from https://github.com/aiming-lab/AutoResearchClaw/tree/main/.claude/skills/researchclaw into .opencode/skills/researchclaw/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "researchclaw", then confirm the skill loads.

OpenCode copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.

Facts

Skill name: researchclaw
GitHub stars: 15k
Token cost: ~1k tokens
SKILL.md length: 274 words
Files: 1
Skills in repo: 34
Repo updated: Aug 19, 2026
First seen: Oct 7, 2026
Licence: MIT

At a glance

Runs the ResearchClaw 23-stage autonomous pipeline from a topic, config file and output directory, from literature review through experiments to a written and reviewed paper.

Works in 3 steps: Verify config file exists → If no config.yaml, create one from the… → Ensure the user's LLM API key is…
Producing a full research paper draft from a single topic
SKILL.md covers Description, Trigger Conditions, Instructions and Tools Required
Instructions only: no scripts, shell commands, URLs or credentials in SKILL.md

What it does

This skill launches ResearchClaw's 23-stage pipeline, which carries a research topic through literature review, hypothesis generation, experiment design, code generation and execution, result analysis, paper writing, peer review and final export. It checks that config.yaml exists, creates it from config.researchclaw.example.yaml if not, and confirms an LLM API key is set in the config or through an environment variable.

You can run it with the researchclaw CLI, which has options for the topic, config path, output directory, resuming from a named stage and auto-approving the gate stages (5, 9 and 20), or through the Python API, including an iterative pipeline for multi-round improvement. Each stage writes into a run folder under artifacts. Experiment modes include simulated, where the LLM generates synthetic results without executing code, and sandbox, where generated code runs locally in a subprocess.

When your agent uses it

Producing a full research paper draft from a single topic
Resuming a pipeline run from a specific stage
Choosing between simulated and sandboxed experiment modes

Example prompts

“Run ResearchClaw on the topic of graph neural networks for molecule property prediction.”
“Resume my ResearchClaw run from the paper outline stage.”
“Write a paper about retrieval-augmented generation for legal documents using the ResearchClaw pipeline.”

Requirements

ResearchClaw installed, with the researchclaw CLI or Python package
A config.yaml with an LLM API key

Workflow steps

3 steps, taken from the first numbered list in SKILL.md.

Verify config file exists
If no config.yaml, create one from the example
Ensure the user's LLM API key is configured in config.yaml under llm.api_key or via llm.api_key_env environment variable.

What it can do on your machine

Read from SKILL.md and the folder at commit be4ba47. It shows what the files ask for, not the result of running them.

Tool permissions
Pre-approves nothing: there is no allowed-tools line, so your agent's usual permission prompts apply.
From allowed-tools in the SKILL.md frontmatter.
Runs code
No scripts in the folder and no shell commands in SKILL.md (its code samples are bash and python).
From the folder's file list and the shell code blocks in SKILL.md.
Network
No URLs in SKILL.md.
From URLs in SKILL.md, links to its own repository left out.
Credentials
Names no API keys, tokens, secrets or passwords.
From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.

Context cost

ResearchClaw Research Pipeline loads about 1k tokens when it runs. Until then it costs about 27 tokens; SKILL.md has 274 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it: ~27
When it runs · the whole SKILL.md, loaded when a task matches: ~1k

Estimates: characters ÷ 4, the usual rule of thumb; real counts depend on the model's tokenizer. Scripts and assets cost tokens only if the agent reads them.

Safety

Auto-check passed

The automated check found no risky patterns in SKILL.md.

Automated static check — not a guarantee. Review scripts before installing. It scans the text of SKILL.md for risky patterns (piping downloads into a shell, reading credential files, hidden Unicode, destructive commands); files beside SKILL.md are not scanned.

SKILL.md

The full file from aiming-lab/AutoResearchClaw at commit be4ba47, republished under its MIT licence (© aiming-lab). 274 words, ~1,041 tokens.

Download SKILL.mdSave it as .claude/skills/researchclaw/SKILL.md (or your agent's skills folder).

name: researchclaw
description: Run the ResearchClaw autonomous research pipeline from a topic, config, and output directory.

ResearchClaw — Autonomous Research Pipeline Skill

Description

Run ResearchClaw's 23-stage autonomous research pipeline. Given a research topic, this skill orchestrates the entire research workflow: literature review → hypothesis generation → experiment design → code generation & execution → result analysis → paper writing → peer review → final export.

Trigger Conditions

Activate this skill when the user:

Asks to "research [topic]", "write a paper about [topic]", or "investigate [topic]"
Wants to run an autonomous research pipeline
Asks to generate a research paper from scratch
Mentions "ResearchClaw" by name

Instructions

Prerequisites Check

Verify config file exists:

bash

ls config.yaml || ls config.researchclaw.example.yaml

If no config.yaml, create one from the example:
bash
```
cp config.researchclaw.example.yaml config.yaml
```
Ensure the user's LLM API key is configured in config.yaml under llm.api_key or via llm.api_key_env environment variable.

Running the Pipeline

Option A: CLI (recommended)

bash

researchclaw run --topic "Your research topic here" --auto-approve

Options:

--topic / -t: Override the research topic from config
--config / -c: Config file path (default: config.yaml)
--output / -o: Output directory (default: artifacts/rc-YYYYMMDD-HHMMSS-HASH/)
--from-stage: Resume from a specific stage (e.g., PAPER_OUTLINE)
--auto-approve: Auto-approve gate stages (5, 9, 20) without human input

Option B: Python API

python

from researchclaw.pipeline.runner import execute_pipeline
from researchclaw.config import RCConfig
from researchclaw.adapters import AdapterBundle
from pathlib import Path

config = RCConfig.load("config.yaml", check_paths=False)
results = execute_pipeline(
    run_dir=Path("artifacts/my-run"),
    run_id="research-001",
    config=config,
    adapters=AdapterBundle(),
    auto_approve_gates=True,
)

# Check results
for r in results:
    print(f"Stage {r.stage.name}: {r.status.value}")

Option C: Iterative Pipeline (multi-round improvement)

python

from researchclaw.pipeline.runner import execute_iterative_pipeline

results = execute_iterative_pipeline(
    run_dir=Path("artifacts/my-run"),
    run_id="research-001",
    config=config,
    adapters=AdapterBundle(),
    max_iterations=3,
    convergence_rounds=2,
)

Output Structure

After a successful run, the output directory contains:

artifacts/<run-id>/
├── stage-1/                # TOPIC_INIT outputs
├── stage-2/                # PROBLEM_DECOMPOSE outputs
├── ...
├── stage-10/
│   └── experiment.py       # Generated experiment code
├── stage-12/
│   └── runs/run-1.json     # Experiment execution results
├── stage-14/
│   ├── experiment_summary.json  # Aggregated metrics
│   └── results_table.tex        # LaTeX results table
├── stage-17/
│   └── paper_draft.md      # Full paper draft
├── stage-22/
│   └── charts/             # Generated visualizations
│       ├── metric_trajectory.png
│       └── experiment_comparison.png
└── pipeline_summary.json   # Overall pipeline status

Experiment Modes

Mode	Description	Config
`simulated`	LLM generates synthetic results (no code execution)	`experiment.mode: simulated`
`sandbox`	Execute generated code locally via subprocess	`experiment.mode: sandbox`
`ssh_remote`	Execute on remote GPU server via SSH	`experiment.mode: ssh_remote`

Troubleshooting

Config validation error: Run researchclaw validate --config config.yaml
LLM connection failure: Check llm.base_url and API key
Sandbox execution failure: Verify experiment.sandbox.python_path exists and has numpy installed
Gate rejection: Use --auto-approve or manually approve at stages 5, 9, 20

Tools Required

File read/write (for config and artifacts)
Bash (for CLI execution)
No external MCP servers required for basic operation

Files

Just SKILL.md in .claude/skills/researchclaw of aiming-lab/AutoResearchClaw.

Open the folder on GitHubat commit be4ba47

Compare with similar skills

ResearchClaw Research Pipeline next to the 5 skills that share the most tags, products or categories with it. Stars are the repository's; “used in” counts other GitHub owners with a copy.

ResearchClaw Research Pipeline compared with similar skills
Skill	Stars	Used in	Tokens	Auto-check	Licence	Repo updated
ResearchClaw Research Pipeline this skillaiming-lab/AutoResearchClaw	15k	—	~1k	Automated safety check: Pass	MIT	1 mo ago
Academic Research PipelineImbad0202/academic-research-skills	51k	—	~15k	Automated safety check: Pass	Custom licence	today
Academic Research Suite for CodexImbad0202/academic-research-skills-codex	12k	—	~12k	Automated safety check: Pass	Custom licence	6 days ago
Autonomous Researchfedericodeponte/opendraft	507	—	~8.2k	Automated safety check: Pass	Apache-2.0	7 days ago
Survey Paper Generatordair-ai/dair-academy-plugins	614	2 repos	~2.1k	Automated safety check: Notes	MIT	2 mo ago
Academic Integrity Rewritelin1111-1/academic-integrity-rewrite	102	—	~1.1k	Automated safety check: Pass	MIT	28 days ago

Similar skills

Academic Research Pipeline
Imbad0202/academic-research-skills
Orchestrates a ten-stage academic workflow from research to finished manuscript, including integrity checks, two rounds of peer review and revision.
51k GitHub stars~15k tokensUpdated today
Research & ScienceAuto-check passed
Academic Research Suite for Codex
Imbad0202/academic-research-skills-codex
A router skill that sends academic work such as literature reviews, drafting, citation checks, peer review and revision to the right workflow in the ARS suite.
12k GitHub stars~12k tokensUpdated 6 days ago
Research & ScienceAuto-check passed
Autonomous Research
federicodeponte/opendraft
An 18-agent pipeline that turns one topic line into a drafted research paper, literature review, or thesis chapter.
507 GitHub stars~8.2k tokensUpdated 7 days ago
Research & ScienceAuto-check passed
Survey Paper Generator
dair-ai/dair-academy-plugins
Builds a single-file HTML survey paper on an AI or ML topic from a research bundle the agent curates, with prose and SVG figures written by Kimi K2.6.
614 GitHub starsUsed in 2 repos~2.1k tokens
Research & ScienceAuto-check: notes
Academic Integrity Rewrite
lin1111-1/academic-integrity-rewrite
Revise Chinese or English academic writing for lower unnecessary textual overlap while preserving meaning, evidence, numbers, equations, terminology, and citations.
102 GitHub stars~1.1k tokensUpdated 28 days ago
Research & ScienceAuto-check passed
Gemini Deep Research
OpenLAIR/dr-claw
Runs multi-source web research through Google's Gemini Deep Research Agent with a bundled Python script and saves a structured, cited report as files.
1.2k GitHub stars~996 tokensUpdated 22 days ago
Research & ScienceAuto-check passed

Questions about ResearchClaw Research Pipeline

What does ResearchClaw Research Pipeline do?

Runs the ResearchClaw 23-stage autonomous pipeline from a topic, config file and output directory, from literature review through experiments to a written and reviewed paper. This skill launches ResearchClaw's 23-stage pipeline, which carries a research topic through literature review, hypothesis generation, experiment design, code generation and execution, result analysis, paper writing, peer review and final export.yaml if not, and confirms an LLM API key is set in the config or through an environment variable.

When should I use ResearchClaw Research Pipeline?

ResearchClaw Research Pipeline fits situations like: producing a full research paper draft from a single topic; resuming a pipeline run from a specific stage; choosing between simulated and sandboxed experiment modes.

How do I install ResearchClaw Research Pipeline in Claude Code?

Run `npx skills add aiming-lab/AutoResearchClaw --skill researchclaw -a claude-code`. Or copy the skill folder (.claude/skills/researchclaw in aiming-lab/AutoResearchClaw) into .claude/skills/researchclaw in your project. Claude Code loads it when a task matches its description.

How do I install ResearchClaw Research Pipeline in Codex?

Run `npx skills add aiming-lab/AutoResearchClaw --skill researchclaw -a codex`. Or copy the skill folder (.claude/skills/researchclaw in aiming-lab/AutoResearchClaw) into .agents/skills/researchclaw in your project. Codex loads it when a task matches its description.

Can I use ResearchClaw Research Pipeline in Cursor, Gemini CLI or GitHub Copilot?

Cursor, Gemini CLI, GitHub Copilot and OpenCode also load SKILL.md folders. With the skills CLI, run `npx skills add aiming-lab/AutoResearchClaw --skill researchclaw -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/researchclaw, .gemini/skills/researchclaw, .github/skills/researchclaw and .opencode/skills/researchclaw in your project.

What does ResearchClaw Research Pipeline need to run?

SKILL.md names no scripts, command-line tools or credentials: ResearchClaw Research Pipeline is instructions for the agent only. Our summary lists: ResearchClaw installed, with the researchclaw CLI or Python package; A config.yaml with an LLM API key.

Does ResearchClaw Research Pipeline access the network?

SKILL.md contains no URLs. Any network use would come from the scripts or tools the agent runs. This is read from the text; nothing was executed.

Is ResearchClaw Research Pipeline safe to install?

Our automated static check of SKILL.md found no risky patterns, such as piping downloads into a shell, reading credential files or hidden Unicode. It is not a guarantee. Review the folder before installing.

What licence does ResearchClaw Research Pipeline use?

ResearchClaw Research Pipeline is published under the MIT licence (the repository's licence). It allows redistribution, so the full SKILL.md is shown on this page.

How many tokens does ResearchClaw Research Pipeline use?

About 1k tokens (SKILL.md is roughly 4.2k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full.

What are the alternatives to ResearchClaw Research Pipeline?

Skills that share tags, products or a category with ResearchClaw Research Pipeline: Academic Research Pipeline (Imbad0202/academic-research-skills, 51k stars), Academic Research Suite for Codex (Imbad0202/academic-research-skills-codex, 12k stars), Autonomous Research (federicodeponte/opendraft, 507 stars) and Survey Paper Generator (dair-ai/dair-academy-plugins, 614 stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains ResearchClaw Research Pipeline?

aiming-lab (a GitHub organization) maintains it in aiming-lab/AutoResearchClaw, which has 14,602 GitHub stars. The repository holds 34 skills in this directory. The repository was last updated on August 19, 2026.

Source: aiming-lab/AutoResearchClaw on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.

Install ResearchClaw Research Pipeline

Facts

At a glance

What it does

When your agent uses it

Example prompts

Requirements

Workflow steps

What it can do on your machine

Tool permissions

Runs code

Network

Credentials

Context cost

Safety

SKILL.md

ResearchClaw — Autonomous Research Pipeline Skill

Description

Trigger Conditions

Instructions

Prerequisites Check

Running the Pipeline

Output Structure

Experiment Modes

Troubleshooting

Tools Required

Files

Compare with similar skills

Similar skills

More from aiming-lab/AutoResearchClaw

Related

Questions about ResearchClaw Research Pipeline