Arxiv MCP Server
blazickjp/arxiv-mcp-server
A skill your agent uses when finding, comparing, reading, or monitoring arXiv papers, including requests for abstracts, citation graphs, original LaTeX, section-level technical details, or…
Use ChemGraph Python and CLI workflows, agent-written batch scripts, and attached chemistry MCP tools.
Install Chemgraph
$ npx skills add argonne-lcf/ChemGraph --skill chemgraph -a claude-codeProject install by default; add -g for ~/.claude/skills/.
$ gh skill install argonne-lcf/ChemGraph chemgraph --agent claude-codeProject scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).
$ git clone --depth 1 https://github.com/argonne-lcf/ChemGraph.git skills-src && mkdir -p .claude/skills && cp -r skills-src/src/chemgraph/skills/chemgraph .claude/skills/chemgraph && rm -rf skills-srcUse ~/.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/
Install the "chemgraph" agent skill from https://github.com/argonne-lcf/ChemGraph/tree/main/src/chemgraph/skills/chemgraph into .claude/skills/chemgraph/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "chemgraph", 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 install https://github.com/argonne-lcf/ChemGraph/tree/main/src/chemgraph/skills/chemgraphType 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.
$ npx skills add argonne-lcf/ChemGraph --skill chemgraph -a codexProject install goes to .agents/skills/; add -g for ~/.codex/skills/.
$ gh skill install argonne-lcf/ChemGraph chemgraph --agent codexProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/argonne-lcf/ChemGraph.git skills-src && mkdir -p .agents/skills && cp -r skills-src/src/chemgraph/skills/chemgraph .agents/skills/chemgraph && rm -rf skills-srcUse ~/.agents/skills/ instead of .agents/skills for a personal install.
Codex skills documentation · loads skills from .agents/skills/
Install the "chemgraph" agent skill from https://github.com/argonne-lcf/ChemGraph/tree/main/src/chemgraph/skills/chemgraph into .agents/skills/chemgraph/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "chemgraph", 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.
$ npx skills add argonne-lcf/ChemGraph --skill chemgraph -a cursorProject install goes to .agents/skills/; add -g for ~/.cursor/skills/.
$ gh skill install argonne-lcf/ChemGraph chemgraph --agent cursorProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/argonne-lcf/ChemGraph.git skills-src && mkdir -p .cursor/skills && cp -r skills-src/src/chemgraph/skills/chemgraph .cursor/skills/chemgraph && rm -rf skills-srcUse ~/.cursor/skills/ instead of .cursor/skills for a personal install.
Cursor skills documentation · loads skills from .cursor/skills/, .agents/skills/, .claude/skills/, .codex/skills/
Install the "chemgraph" agent skill from https://github.com/argonne-lcf/ChemGraph/tree/main/src/chemgraph/skills/chemgraph into .cursor/skills/chemgraph/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "chemgraph", 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 https://github.com/argonne-lcf/ChemGraph.git --path src/chemgraph/skills/chemgraph--scope user (default) or --scope workspace; --path is the subfolder of the repo that holds the skill; --consent skips the security confirmation prompt.
$ npx skills add argonne-lcf/ChemGraph --skill chemgraph -a gemini-cliProject install goes to .agents/skills/; add -g for ~/.gemini/skills/.
$ gh skill install argonne-lcf/ChemGraph chemgraph --agent gemini-cliProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/argonne-lcf/ChemGraph.git skills-src && mkdir -p .gemini/skills && cp -r skills-src/src/chemgraph/skills/chemgraph .gemini/skills/chemgraph && rm -rf skills-srcUse ~/.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/
Install the "chemgraph" agent skill from https://github.com/argonne-lcf/ChemGraph/tree/main/src/chemgraph/skills/chemgraph into .gemini/skills/chemgraph/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "chemgraph", 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.
$ gh skill install argonne-lcf/ChemGraph chemgraphInstalls 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).
$ npx skills add argonne-lcf/ChemGraph --skill chemgraph -a github-copilotProject install goes to .agents/skills/; add -g for ~/.copilot/skills/.
$ git clone --depth 1 https://github.com/argonne-lcf/ChemGraph.git skills-src && mkdir -p .github/skills && cp -r skills-src/src/chemgraph/skills/chemgraph .github/skills/chemgraph && rm -rf skills-srcUse ~/.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/
Install the "chemgraph" agent skill from https://github.com/argonne-lcf/ChemGraph/tree/main/src/chemgraph/skills/chemgraph into .github/skills/chemgraph/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "chemgraph", 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.
$ npx skills add argonne-lcf/ChemGraph --skill chemgraph -a opencodeOpenCode documents no install command of its own. Project install goes to .agents/skills/; add -g for ~/.config/opencode/skills/.
$ gh skill install argonne-lcf/ChemGraph chemgraph --agent opencodeProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/argonne-lcf/ChemGraph.git skills-src && mkdir -p .opencode/skills && cp -r skills-src/src/chemgraph/skills/chemgraph .opencode/skills/chemgraph && rm -rf skills-srcUse ~/.config/opencode/skills/ instead of .opencode/skills for a personal install.
OpenCode skills documentation · loads skills from .opencode/skills/, .claude/skills/, .agents/skills/
Install the "chemgraph" agent skill from https://github.com/argonne-lcf/ChemGraph/tree/main/src/chemgraph/skills/chemgraph into .opencode/skills/chemgraph/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "chemgraph", 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
chemgraph- GitHub stars
- 162
- Token cost
- ~743 tokens
- SKILL.md length
- 344 words
- Files
- 5 (incl. references)
- Skills in repo
- 3
- Repo updated
- First seen
- Licence
- Apache-2.0
At a glance
Use ChemGraph Python and CLI workflows, agent-written batch scripts, and attached chemistry MCP tools.
- Works in 6 steps: Identify the requested calculation,… → Use native chemistry tools for supported… → For Python or CLI setup, read interface… → …
- Molecular simulations
- Instructions only: no scripts, shell commands, URLs or credentials in SKILL.md
- ASE calculations
What it does
Chemgraph is an agent skill from argonne-lcf/ChemGraph. Use ChemGraph Python and CLI workflows, agent-written batch scripts, and attached chemistry MCP tools. Use for molecular simulations, ASE calculations, staging structures, tracking calculations, and reporting computed results.
Its SKILL.md is about 740 tokens, which your agent loads only when the skill is triggered. The skill folder holds 5 other files, including reference files (for example `references/ase-batch.md`, `references/mcp-workflows.md` and `references/python-and-cli.md`).
It sits in Research & Science, covering MCP servers and Physical and earth sciences. It works with Python and Model Context Protocol. The repository describes itself as: Agentic framework for computational chemistry and materials science workflows. The licence is Apache-2.0.
When your agent uses it
- Molecular simulations
- ASE calculations
- Staging structures
- Tracking calculations
Example prompts
- “/chemgraph”
Requirements
- Python 3
Workflow steps
6 steps, taken from the first numbered list in SKILL.md.
- Identify the requested calculation, input structures, calculator/model,
- Use native chemistry tools for supported local operations. When discovery is
- For Python or CLI setup, read interface guidance.
- Establish where every file lives: the agent's virtual filesystem, its shell,
- Submit the requested calculation once. Save returned job or batch identifiers.
- Report actual tool results, including failures, units, calculator/model, and
What it can do on your machine
Read from SKILL.md and the folder at commit e890eb3. 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.
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
Chemgraph loads about 743 tokens when it runs, and up to ~3.8k if it reads all its reference files. Until then it costs about 59 tokens; SKILL.md has 344 words of instructions outside code blocks.
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 argonne-lcf/ChemGraph at commit e890eb3, republished under its Apache-2.0 licence (© argonne-lcf). 344 words, ~743 tokens.
Download SKILL.mdSave it as
.claude/skills/chemgraph/SKILL.md (or your agent's skills folder). This skill also uses 4 other files; get the full folder from GitHub.- name
- chemgraph
- description
- Use ChemGraph Python and CLI workflows, agent-written batch scripts, and attached chemistry MCP tools. Use for molecular simulations, ASE calculations, staging structures, tracking calculations, and reporting computed results.
- license
- Apache-2.0
- metadata.authors
- Thang Pham
- metadata.maintainers
- tdpham2
Use ChemGraph
- Identify the requested calculation, input structures, calculator/model, execution system, and output location. Inspect attached tool schemas before selecting arguments. Ask for missing scientific choices rather than inventing them; do not replace the requested calculator with another one silently.
- Use native chemistry tools for supported local operations. When discovery is
available, search/load the needed tools before considering scripts or reading
their implementation source. Scripts can reuse ChemGraph's Python APIs when
a capability is unavailable or a separate batch script is needed.
When inputs need construction, read
local structure preparation, including
on-demand tool loading when available. For direct PBS jobs, read the ASE batch example
and the
pbs-hpcskill; no chemistry MCP server or Parsl is required. Preserve an explicitly requested execution method. Report missing dependencies. This skill does not grant tools or override approvals. - For Python or CLI setup, read interface guidance. For calculations through attached tools, read MCP workflow guidance.
- Establish where every file lives: the agent's virtual filesystem, its shell,
the MCP server, or the compute worker. A path readable with
read_fileneed not exist on another host. Use existing staging tools when files must move. - Submit the requested calculation once. Save returned job or batch identifiers. When a calculation is pending, poll the available status tools or return the identifier and pending state; do not resubmit merely because it is unfinished.
- Report actual tool results, including failures, units, calculator/model, and
output paths. For ASE, prefer
potential_energy;single_point_energyis a legacy compatibility field. Distinguish optimization convergence from job completion. Never invent numerical results or label pending work successful.
For scheduler scripts or allocations, also read the pbs-hpc skill from the
available skill catalog. Facility-specific values belong in user configuration.
Resource paths
Resolve these relative references against this SKILL.md's directory using file
tools. /chemgraph-skills/ is a virtual, read-only resource route. To use a
template or future helper with execute, first write/copy it into the execution
backend's workspace and use that environment's actual path. State/store files
are not automatically visible to a shell or an MCP server.
© argonne-lcf, Apache-2.0. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file
Files
SKILL.md and 4 other files (references) in src/chemgraph/skills/chemgraph of argonne-lcf/ChemGraph.
- SKILL.md
- references/ase-batch.md
- references/mcp-workflows.md
- references/python-and-cli.md
- references/structure-preparation.md
Open the folder on GitHubat commit e890eb3
Compare with similar skills
Chemgraph 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.
| Skill | Stars | Used in | Tokens | Auto-check | Licence | Repo updated |
|---|---|---|---|---|---|---|
| Chemgraph this skillargonne-lcf/ChemGraph | 162 | — | ~743 | Automated safety check: Pass | Apache-2.0 | |
| Arxiv MCP Serverblazickjp/arxiv-mcp-server | 3.2k | — | ~353 | Automated safety check: Pass | Apache-2.0 | |
| Deep Research MCP Guidepminervini/deep-research-mcp | 113 | — | ~5.8k | Automated safety check: Pass | MIT | |
| Research Biomedical Databasesaws-samples/amazon-bedrock-agents-healthcare-lifesciences | 274 | — | ~3.1k | Automated safety check: Pass | MIT-0 | |
| Setup MedsciAperivue/medsci-skills | 331 | — | ~960 | Automated safety check: Pass | MIT | |
| Literature Review Toolsbrycewang-stanford/Auto-Empirical-Research-Skills | 4.5k | — | ~2.5k | Automated safety check: Notes | Custom licence |
Similar skills
Deep Research MCP Guide
pminervini/deep-research-mcp
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.
- Official
Research Biomedical Databases
aws-samples/amazon-bedrock-agents-healthcare-lifesciences
A skill your agent uses when querying biomedical databases (UniProt, ClinVar, gnomAD, PDB, Reactome, Open Targets, etc.) via the Biomni AgentCore Gateway MCP server.
Setup Medsci
Aperivue/medsci-skills
A skill your agent uses when a skill fails for a missing tool or the environment needs checking.
Literature Review Tools
brycewang-stanford/Auto-Empirical-Research-Skills
Recommend AND run open-source AI tools, agents, Claude Code / Codex skills, and MCP servers for any stage of a literature review — searching, reading, extracting, synthesizing, screening…
Mat DB Mp
learningmatter-mit/AtomisticSkills
Query Materials Project database for crystal structures, computed properties, elastic/magnetic data, and structurally similar materials using the MP API.
More from argonne-lcf/ChemGraph
Pbs Hpc
argonne-lcf/ChemGraph
Prepare PBS HPC jobs, choose allocation and filesystem settings, submit and monitor jobs, and diagnose job output.
Chemgraph
argonne-lcf/ChemGraph
Develop, test, and extend ChemGraph -- an agentic framework for automated molecular simulations using LLMs, LangGraph, ASE, and MCP servers
Related
Works with
Categories
Questions about Chemgraph
What does Chemgraph do?
Use ChemGraph Python and CLI workflows, agent-written batch scripts, and attached chemistry MCP tools. Chemgraph is an agent skill from argonne-lcf/ChemGraph. Use ChemGraph Python and CLI workflows, agent-written batch scripts, and attached chemistry MCP tools.
When should I use Chemgraph?
Chemgraph fits situations like: molecular simulations; ASE calculations; staging structures; tracking calculations.
How do I install Chemgraph in Claude Code?
Run `npx skills add argonne-lcf/ChemGraph --skill chemgraph -a claude-code`. Or copy the skill folder (src/chemgraph/skills/chemgraph in argonne-lcf/ChemGraph) into .claude/skills/chemgraph in your project. Claude Code loads it when a task matches its description.
How do I install Chemgraph in Codex?
Run `npx skills add argonne-lcf/ChemGraph --skill chemgraph -a codex`. Or copy the skill folder (src/chemgraph/skills/chemgraph in argonne-lcf/ChemGraph) into .agents/skills/chemgraph in your project. Codex loads it when a task matches its description.
Can I use Chemgraph 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 argonne-lcf/ChemGraph --skill chemgraph -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/chemgraph, .gemini/skills/chemgraph, .github/skills/chemgraph and .opencode/skills/chemgraph in your project.
What does Chemgraph need to run?
SKILL.md names no scripts, command-line tools or credentials: Chemgraph is instructions for the agent only. Our summary lists: Python 3.
Does Chemgraph 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 Chemgraph 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 Chemgraph use?
Chemgraph is published under the Apache-2.0 licence (declared in SKILL.md). It allows redistribution, so the full SKILL.md is shown on this page.
How many tokens does Chemgraph use?
About 743 tokens (SKILL.md is roughly 3k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full. Its references folder adds about 3.1k tokens, read only when the agent opens those files.
What are the alternatives to Chemgraph?
Skills that share tags, products or a category with Chemgraph: Arxiv MCP Server (blazickjp/arxiv-mcp-server, 3.2k stars), Deep Research MCP Guide (pminervini/deep-research-mcp, 113 stars), Research Biomedical Databases (aws-samples/amazon-bedrock-agents-healthcare-lifesciences, 274 stars) and Setup Medsci (Aperivue/medsci-skills, 331 stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.
Who maintains Chemgraph?
argonne-lcf (a GitHub organization) maintains it in argonne-lcf/ChemGraph, which has 162 GitHub stars. The repository holds 3 skills in this directory. The repository was last updated on October 9, 2026.
Source: argonne-lcf/ChemGraph on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.