Install the "general-deep-research" agent skill from https://github.com/learningmatter-mit/AtomisticSkills/tree/main/skills/general-deep-research into .claude/skills/general-deep-research/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "general-deep-research", 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.
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 learningmatter-mit/AtomisticSkills --skill general-deep-research -a codex
Project install goes to .agents/skills/; add -g for ~/.codex/skills/.
Install the "general-deep-research" agent skill from https://github.com/learningmatter-mit/AtomisticSkills/tree/main/skills/general-deep-research into .agents/skills/general-deep-research/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "general-deep-research", 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 learningmatter-mit/AtomisticSkills --skill general-deep-research -a cursor
Project install goes to .agents/skills/; add -g for ~/.cursor/skills/.
Install the "general-deep-research" agent skill from https://github.com/learningmatter-mit/AtomisticSkills/tree/main/skills/general-deep-research into .cursor/skills/general-deep-research/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "general-deep-research", 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.
--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 learningmatter-mit/AtomisticSkills --skill general-deep-research -a gemini-cli
Project install goes to .agents/skills/; add -g for ~/.gemini/skills/.
Install the "general-deep-research" agent skill from https://github.com/learningmatter-mit/AtomisticSkills/tree/main/skills/general-deep-research into .gemini/skills/general-deep-research/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "general-deep-research", 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.
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 learningmatter-mit/AtomisticSkills --skill general-deep-research -a github-copilot
Project install goes to .agents/skills/; add -g for ~/.copilot/skills/.
Install the "general-deep-research" agent skill from https://github.com/learningmatter-mit/AtomisticSkills/tree/main/skills/general-deep-research into .github/skills/general-deep-research/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "general-deep-research", 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 learningmatter-mit/AtomisticSkills --skill general-deep-research -a opencode
OpenCode documents no install command of its own. Project install goes to .agents/skills/; add -g for ~/.config/opencode/skills/.
Install the "general-deep-research" agent skill from https://github.com/learningmatter-mit/AtomisticSkills/tree/main/skills/general-deep-research into .opencode/skills/general-deep-research/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "general-deep-research", 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
general-deep-research
GitHub stars
175
Token cost
~1.2k tokens
SKILL.md length
550 words
Files
1
Skills in repo
129
Repo updated
First seen
Licence
MIT
At a glance
Perform iterative, deep, and comprehensive literature research on a specific materials/chemistry topic.
Works in 5 steps: Query Formulation & Planning → Iterative Literature Search → Information Extraction & Synthesis → …
Tasks that involve Deep research
SKILL.md covers Goal, Instructions, Constraints and Examples
Instructions only: no scripts, shell commands, URLs or credentials in SKILL.md
What it does
General Deep Research is an agent skill from learningmatter-mit/AtomisticSkills. Perform iterative, deep, and comprehensive literature research on a specific materials/chemistry topic.
Its SKILL.md is about 1.2k tokens, which your agent loads only when the skill is triggered. It is a single SKILL.md file with no bundled scripts.
It sits in Research & Science, covering Deep research. It works with Model Context Protocol. The repository describes itself as: Integrating AtomisticSkills into Agentic IDEs (Cursor, Claude Code, Codex, Google Antigravity, Hermes Agent, etc). The licence is MIT.
When your agent uses it
Tasks that involve Deep research
Example prompts
“/general-deep-research”
Requirements
Python 3
Workflow steps
5 steps, taken from the step headings in SKILL.md.
Read from SKILL.md and the folder at commit 7f2d86d. 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).
From the folder's file list and the shell code blocks in SKILL.md.
Network
Links to these hosts (documentation or services it may open):
github.com
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
General Deep Research loads about 1.2k tokens when it runs. Until then it costs about 31 tokens; SKILL.md has 550 words of instructions outside code blocks.
Always· name and description, kept in context so the agent knows when to use it
~31
When it runs· the whole SKILL.md, loaded when a task matches
~1.2k
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.
Download SKILL.mdSave it as .claude/skills/general-deep-research/SKILL.md (or your agent's skills folder).
name
general-deep-research
description
Perform iterative, deep, and comprehensive literature research on a specific materials/chemistry topic.
metadata.category
general
metadata.venv
cpu
Deep Research
<!-- mcp-tools-note -->
[!NOTE]
Steps written server.tool are MCP tool calls: base.search_literature is the search_literature
tool of the base server (mcp__base__search_literature, or
mcp__plugin_atomistic-skills_base__search_literature when installed as a plugin).
Without a connected server, run the same tools from the shell. Tools named in
one command share a process, so a model loaded by load_model stays loaded:
bash
${CLAUDE_SKILL_DIR}/../../venv/run cpu python -m src.mcp_server.cli base search_literature key=value create_research_dir key=value
Goal
To perform an in-depth, iterative, and comprehensive literature and web research campaign to answer complex scientific questions (e.g., "What are the synthesis methods and solid-state electrolyte performance of LiInCl3?"). This skill produces a high-quality, synthesized research report with citations, significantly exceeding the depth of a single simple literature query.
Instructions
When the user requests deep research on a topic, the agent MUST follow this multi-step iterative protocol. Do not implement this as a python script, but rather execute these steps logically using your own tool-calling capabilities.
Step 1: Query Formulation & Planning
Break down the user's broad research topic into 3-5 specific sub-queries.
CRITICAL: You must try different permutations and synonyms for the material or topic. For example, if the topic is LiInCl3, your queries must include variations like LiInCl3, Li-In-Cl, Lithium Indium Chloride, Li3InCl6, etc., to ensure no literature is missed.
Create a rough outline for the final research report in your task plan.
Step 2: Iterative Literature Search
For each sub-query, use the base.search_literature tool to search the OpenAlex database. Always set download=True to attempt downloading the full text of discovered papers.
CRITICAL: You must NOT rely solely on the literature search tool. You must ALSO perform a general web search using the search_web tool for all your queries. This captures recent publications, patents, reviews, and data that OpenAlex might miss.
bash
search_web(
query="Li-In-Cl solid state electrolyte review"
)
Step 3: Information Extraction & Synthesis
Do not just list papers. You must read the content (or the provided summaries/full texts from the MCP tool).
Extract specific numbers, methodologies, and limitations (e.g., "Conductivity is 1.2 mS/cm at RT", "Synthesized via mechanochemical milling followed by annealing at 250C").
If gaps in knowledge remain (e.g., you found the conductivity but not the stability window), perform another round of searching with refined queries targeting the missing information.
Show full SKILL.md (189 more words)Show less
Step 4: Report Generation
Draft a comprehensive, academic-style markdown report named deep_research_report.md inside the active research_dir (which should be created via base.create_research_dir).
The report must include:
Executive Summary: A high-level overview of the findings.
Detailed Findings: Categorized by sub-topics (e.g., Structure, Performance, Synthesis). Include specific data points and conflicting reports if any exist. CRITICAL: When summarizing each point, you MUST include the DOI reference or URL of the source where the info is coming from inline.
Methodologies: Common computational or experimental methods used in the literature.
Knowledge Gaps: What remains unknown or disputed in the current literature.
References: A cited list of the papers and URLs you drew information from, mapping to your inline citations.
Step 5: User Review
Once the report is generated, present it to the user.
bash
notify_user(
PathsToReview=["/absolute/path/to/research_dir/deep_research_report.md"],
BlockedOnUser=True,
Message="Deep research is complete. Please review the comprehensive report."
)
Constraints
Depth Over Speed: Take the time to run multiple tool calls to search and read. Do not stop after one search query.
Data Specificity: Extract quantitative data (values, temperatures, error margins) wherever possible rather than qualitative statements.
Resource Utilization: Use both base.search_literature and search_web.
Examples
To initiate deep research:
bash
# Agent internally executes Step 1 to Step 5.
# (No specific environment required since it's an agentic skill relying on MCP tools).
General Deep Research 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.
General Deep Research compared with similar skills
Skill
Stars
Used in
Tokens
Auto-check
Licence
Repo updated
General Deep Research this skilllearningmatter-mit/AtomisticSkills
Explains how to run, integrate and debug the deep-research-mcp project through its CLI, Python API or MCP server, with OpenAI, Gemini and DR-Tulu backends.
Deep web-research methodology for the interceptor browser surface — investigate a topic the way researchers, intelligence analysts, investigative journalists, private investigators, and OSINT…
Define a docking search box (center coordinates + box dimensions in Angstroms) from a co-crystal ligand, binding-site residues, or a saved JSON specification.
Perform iterative, deep, and comprehensive literature research on a specific materials/chemistry topic. General Deep Research is an agent skill from learningmatter-mit/AtomisticSkills. Perform iterative, deep, and comprehensive literature research on a specific materials/chemistry topic.
When should I use General Deep Research?
General Deep Research fits situations like: tasks that involve Deep research.
How do I install General Deep Research in Claude Code?
Run `npx skills add learningmatter-mit/AtomisticSkills --skill general-deep-research -a claude-code`. Or copy the skill folder (skills/general-deep-research in learningmatter-mit/AtomisticSkills) into .claude/skills/general-deep-research in your project. Claude Code loads it when a task matches its description.
How do I install General Deep Research in Codex?
Run `npx skills add learningmatter-mit/AtomisticSkills --skill general-deep-research -a codex`. Or copy the skill folder (skills/general-deep-research in learningmatter-mit/AtomisticSkills) into .agents/skills/general-deep-research in your project. Codex loads it when a task matches its description.
Can I use General Deep Research 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 learningmatter-mit/AtomisticSkills --skill general-deep-research -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/general-deep-research, .gemini/skills/general-deep-research, .github/skills/general-deep-research and .opencode/skills/general-deep-research in your project.
What does General Deep Research need to run?
SKILL.md names no scripts, command-line tools or credentials: General Deep Research is instructions for the agent only. Our summary lists: Python 3.
Does General Deep Research access the network?
SKILL.md names 1 domain. As links in the text: github.com. This is read from the text; nothing was executed.
Is General Deep Research 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 General Deep Research use?
General Deep Research 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 General Deep Research use?
About 1.2k tokens (SKILL.md is roughly 4.9k 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 General Deep Research?
Skills that share tags, products or a category with General Deep Research: Deep Research (jordan-gibbs/hyperresearch, 3.8k stars), Rival Search MCP (damionrashford/RivalSearchMCP, 132 stars), Deep Research MCP Guide (pminervini/deep-research-mcp, 112 stars) and Exa Search (majiayu000/claude-skill-registry, 666 stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.
Who maintains General Deep Research?
learningmatter-mit (a GitHub organization) maintains it in learningmatter-mit/AtomisticSkills, which has 175 GitHub stars. The repository holds 129 skills in this directory. The repository was last updated on October 6, 2026.
