Is the Scholar Deep Research skill free?

Yes. The skill itself is free from Agents365-ai/scholar-deep-research. SkillProof publishes the install command and an independent test verdict at no cost.

What is the Scholar Deep Research SkillProof Score?

9.2/10 — installs cleanly 5/5, triggers reliably 5/5, output vs. baseline 9/10, docs & honesty 4/5.

How do I install Scholar Deep Research?

Copy the install command from this page, run it in your terminal, and restart Claude Code. Skills live in ~/.claude/skills/ (global) or .claude/skills/ inside a project.

Can I use Scholar Deep Research with Cursor, Copilot, Gemini CLI, Codex or other AI tools?

The SKILL.md format is native to Claude (Claude Code, Desktop, claude.ai). The instructions inside adapt to other assistants: Cursor rules, GitHub Copilot instructions, Windsurf rules, Custom GPTs, AGENTS.md for OpenAI Codex, and GEMINI.md for Google Gemini CLI — our conversion guides cover each, and the free converter on the tools page does the wrapping for you.

Scholar Deep Research

8-phase, script-driven literature review across 7 scholarly APIs with a DOI-anchored bibliography.

by Agents365-ai · Agents365-ai/scholar-deep-research

Tested · Works

Install — copy the command Download source ↗

Test report

Verdict: Tested · Works
Score: 9.2/10
Tested: Jul 14, 2026
Environment: Claude Code 2.x (agent harness)
Upstream re-checked: Aug 10, 2026 · 3b718f6

Ran Phase 0→2 for real against live OpenAlex/arXiv/Crossref: got a ranked, DOI-anchored top-10 with real 2023-2026 LLM-agent survey papers and a rendered report scaffold with a verifiable bibliography — a memory-only baseline risks fabricated DOIs on exactly this kind of task. Caught one real bug: the SKILL.md's own Phase-2 example `research_state.py select --state research_state.json --top 20` fails (arg order); `--state` must precede the subcommand, as Phase-0's `init` example correctly shows.

Scored on four weighted criteria — install, triggering, output vs. baseline, docs. How scoring works

Installs cleanly 5/5
Triggers reliably 5/5
Output vs. baseline 9/10
Docs & honesty 4/5

What Scholar Deep Research does

Turns a research question into a cited literature review by running Python scripts against OpenAlex, arXiv, Crossref, PubMed, DBLP, bioRxiv and Exa, deduping and transparently ranking results, then chasing citations and forcing a self-critique pass before rendering a report with footnote anchors tied to real papers. Trigger on literature review / state-of-the-art / "what's known about X" / comparative-analysis requests; skip for tutorials or code debugging.

How to install Scholar Deep Research

git clone https://github.com/Agents365-ai/scholar-deep-research.git
cd scholar-deep-research
mkdir -p ~/.claude/skills
cp -r skills/scholar-deep-research ~/.claude/skills/scholar-deep-research

Skills live in ~/.claude/skills/ (global) or .claude/skills/ (per-project). Restart Claude Code after installing.

Commands — how to trigger Scholar Deep Research

/scholar-deep-research 8-phase, script-driven literature review across 7 scholarly APIs with a DOI-anchored bibliography.

It also activates on plain-language prompts like these:

Do a literature review on LLM agents for automated research
Find and rank papers on retrieval-augmented generation for me
Build me a DOI-anchored bibliography on this research question

Frequently asked questions

Is the Scholar Deep Research skill free?: Yes. The skill itself is free from Agents365-ai/scholar-deep-research. SkillProof publishes the install command and an independent test verdict at no cost.
Does Scholar Deep Research work with Claude Code?: We tested it with Claude Code 2.x (agent harness) on Jul 14, 2026. Verdict: Tested · Works. Ran Phase 0→2 for real against live OpenAlex/arXiv/Crossref: got a ranked, DOI-anchored top-10 with real 2023-2026 LLM-agent survey papers and a rendered report scaffold with a verifiable bibliography — a memory-only baseline risks fabricated DOIs on exactly this kind of task. Caught one real bug: the SKILL.md's own Phase-2 example `research_state.py select --state research_state.json --top 20` fails (arg order); `--state` must precede the subcommand, as Phase-0's `init` example correctly shows.
What is the Scholar Deep Research SkillProof Score?: 9.2/10 — installs cleanly 5/5, triggers reliably 5/5, output vs. baseline 9/10, docs & honesty 4/5.
How do I install Scholar Deep Research?: Copy the install command from this page, run it in your terminal, and restart Claude Code. Skills live in ~/.claude/skills/ (global) or .claude/skills/ inside a project.
Can I use Scholar Deep Research with Cursor, Copilot, Gemini CLI, Codex or other AI tools?: The SKILL.md format is native to Claude (Claude Code, Desktop, claude.ai). The instructions inside adapt to other assistants: Cursor rules, GitHub Copilot instructions, Windsurf rules, Custom GPTs, AGENTS.md for OpenAI Codex, and GEMINI.md for Google Gemini CLI — our conversion guides cover each, and the free converter on the tools page does the wrapping for you.