Agent Plugins Marketplace
← All plugins

auto-research

v1.0.0

Full pipeline for AI/ML research papers (CCF-A venues) with live experiment dashboard. Covers Phase 0–12: setup, ideation, pilot, experiments, analysis, writing, rebuttal.

Claude Code5 Skills

By linweiLicense: MIT0 GitHub starsUpdated 6 months ago

Directory evidence

Runtimes
Claude Code
Parsed components
5 skill or MCP entries
Source updated
Apr 10, 2026
Manifest status
Canonical path parsed

The directory validates manifest shape and source location. It does not execute the plugin or provide a security endorsement. Review the indexing methodology →

Install auto-research for Claude Code

Installs for the current user
claude plugin marketplace add IchenDEV/agent-plugin-mkt
claude plugin marketplace update agent-plugin-marketplace
claude plugin install auto-research@agent-plugin-marketplace

Paste and run these commands in a terminal with Claude Code. They add and refresh the PluginsMP catalog, then install this plugin.

The installer fetches third-party code from the source repository shown on this page. This directory validates manifest structure and source location, but does not perform a security audit; review the manifest, components, and source before installing.

Get the source manually
git clone https://github.com/Linwei94/claude-auto-research

Clone the source repository, then follow its setup instructions to add the plugin to a compatible client. The repository root is the plugin root.

Plugin files

auto-research/
├── .claude-plugin/plugin.json
├── skills/dashboard/SKILL.md
├── skills/dashboard-update/SKILL.md
├── skills/ideation/SKILL.md
├── skills/lab/SKILL.md
└── skills/pipeline/SKILL.md

Included Skills5

dashboardskills/dashboard/SKILL.md

Open the Research Dashboard in the browser. Shows live experiment status (running/done/pending), host/GPU info, results table. Triggers on "open dashboard", "打开dashboard", "看实验进度", "看看实验", "/autoresearch-dashboard", "dashboard".

dashboard-updateskills/dashboard-update/SKILL.md

Update the project dashboard with human-readable content — table names, method labels, insights, current findings. Reads research context (proposal, results, synthesis) and writes dashboard/meta.json. Triggers on "update dashboard", "更新dashboard", "dashboard更新", "写dashboard", "/auto-research:dashboard-update".

ideationskills/ideation/SKILL.md

Ideation Agent — AI/ML research literature review and idea generation (Phase 1-2). Spawned by Pipeline Agent as a team member. Can also run standalone. Triggers on "ideation", "literature review", "idea generation", "文献调研", "想法生成", "找文献".

labskills/lab/SKILL.md

Lab Agent — experiment orchestrator for AI/ML research (Phase 3-8). Spawned by Pipeline Agent as a team member. Plans experiments, writes code, spawns Execution Sub-agents (one per experiment), collects results. Triggers on "lab", "experiments", "run experiments", "跑实验", "实验执行".

pipelineskills/pipeline/SKILL.md

Full pipeline for AI/ML research papers targeting CCF-A venues (ICML, ICLR, NeurIPS, CVPR, etc.). Use this skill whenever the user wants to explore a research idea, do literature review, write a research proposal, plan experiments, design figures, or write a conference paper. Triggers on keywords like "research idea", "paper writing", "literature review", "experiment plan", "NeurIPS/ICML/ICLR/CVPR submission", or any AI research workflow. Always produces a full paper — no research-only mode.

Plugin manifests1

.claude-plugin/plugin.json
{
  "name": "auto-research",
  "description": "Full pipeline for AI/ML research papers (CCF-A venues) with live experiment dashboard. Covers Phase 0–12: setup, ideation, pilot, experiments, analysis, writing, rebuttal.",
  "version": "1.0.0",
  "author": {
    "name": "linwei"
  },
  "license": "MIT"
}

For maintainers

If you maintain this plugin, link to this source-backed listing from your README so users can review its manifest and indexed components.

[auto-research on Agent Plugins Marketplace](https://pluginsmp.com/plugins/auto-research)