ResearAIResearAICommunity·21 Agent Skills Included

DeepScientist

Autonomous local research studio from baselines to paper drafts

Runs long-horizon research projects locally, from literature scouting and baseline reproduction to experiments, analysis, and paper writing. Eliminates scattered results, broken baseline setups, and lost context by storing every quest as one Git repository with durable artifacts and memory. Guides AI agents through staged skills like scout, baseline, experiment, write, review, and rebuttal so research keeps moving with human takeover anytime.
npx skills add ResearAI/DeepScientist --all -g -y
Available:

Tells the AI agent how to run the DeepScientist research loop: route work through stage skills, keep one quest per Git repository, and execute all terminal actions only through the approved bash_exec tool.

All Skills in This Repository (21)

Pure Emerald Level Indicators
📦 In Repo
ResearAIResearAI

write

Generate publication-ready paper drafts from validated quest evidence.

Community
Advanced
📦 In Repo
ResearAIResearAI

optimize

Shape and govern end-to-end optimization workflows for algorithm-first quests.

Community
Advanced
📦 In Repo
ResearAIResearAI

baseline

Standardize a reference object for quest evaluation with plan and checklist requirements.

Community
Advanced
📦 In Repo
ResearAIResearAI

analysis-campaign

Coordinate code-based follow-up analyses with campaign plans and per-slice runs.

Community
Advanced
📦 In Repo
ResearAIResearAI

scout

Clarify quest framing by outlining objectives, data requirements, and evaluation criteria.

Community
Advanced
📦 In Repo
ResearAIResearAI

idea

Convert a baseline and problem frame into literature-grounded research directions.

Community
Advanced
📦 In Repo
ResearAIResearAI

review

Audits drafts and papers for evidence-grounded critique and produces a revision plan.

Community
Advanced
📦 In Repo
ResearAIResearAI

figure-polish

Polish research figures using a render-inspect-revise workflow and Matplotlib style.

Community
Advanced
📦 In Repo
ResearAIResearAI

alphaxiv-paper-lookup

Fetch structured AI-generated overviews of arXiv papers from alphaxiv.org.

Community
Intermediate
📦 In Repo
ResearAIResearAI

experiment

Plan, execute, and log auditable quest experiments with PLAN.md and CHECKLIST.md.

Community
Advanced
📦 In Repo
ResearAIResearAI

decision

Creates canonical records for quest decisions with verdicts, actions, and evidence paths.

Community
Advanced
📦 In Repo
ResearAIResearAI

finalize

Consolidate final claims, limitations, recommendations, and graph exports for quest closure.

Community
Advanced

Frequently Asked Questions

FAQPage Schema
How to install DeepScientist?

Run `npx skills add ResearAI/DeepScientist --all -g -y` in your terminal to install the full skill suite globally.

What does DeepScientist actually do?

It is a local-first autonomous research studio that takes a paper, repo, or research question and drives it through baselines, experiments, analysis, and paper drafts on your own machine.

Can DeepScientist reproduce a baseline from a paper?

Yes. The baseline skill attaches, imports, or reproduces a comparator, verifies its metrics, and records a durable comparison contract before any experiment starts.

Which AI agents work with DeepScientist?

It ships built-in runners for Codex, Claude Code, Kimi Code, and OpenCode, and all skills follow the standard SKILL.md format.

Can I take over from the AI during a research quest?

Yes. You can pause, edit plans or code, inspect every artifact in the web workspace or TUI, and hand control back to the agent at any time.

Related Repositories in Education & Research

View All in Education & Research