New: 97,000+ skills indexed from GitHub repos with 100+ stars · every skill safety-checkedBrowse top skillsTop skills
Esc to closeBrowse all skills
Submit a skillBrowse skills
Submit a skillBrowse skills

Agent skill

General Atomisticskills Setup

by learningmatter-mit in learningmatter-mit/AtomisticSkills

Set up, check or troubleshoot how AtomisticSkills runs on this machine -- creating its Python environments, connecting its MCP servers, choosing uv or a container runtime, and configuring API keys.

MITAuto-check: notesAgent Workflows

Install General Atomisticskills Setup

skills CLI
$ npx skills add learningmatter-mit/AtomisticSkills --skill general-atomisticskills-setup -a claude-code

Project install by default; add -g for ~/.claude/skills/.

GitHub CLI
$ gh skill install learningmatter-mit/AtomisticSkills general-atomisticskills-setup --agent claude-code

Project scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).

Manual copy
$ git clone --depth 1 https://github.com/learningmatter-mit/AtomisticSkills.git skills-src && mkdir -p .claude/skills && cp -r skills-src/skills/general-atomisticskills-setup .claude/skills/general-atomisticskills-setup && rm -rf skills-src

Use ~/.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/

Facts

Skill name
general-atomisticskills-setup
GitHub stars
175
Token cost
~1.2k tokens
SKILL.md length
519 words
Files
1
Skills in repo
129
Repo updated
First seen
Licence
MIT

At a glance

Set up, check or troubleshoot how AtomisticSkills runs on this machine -- creating its Python environments, connecting its MCP servers, choosing uv or a container runtime, and configuring API keys.

  • Works in 4 steps: Check the machine → Create the environments → Configure API keys → …
  • Installing AtomisticSkills
  • SKILL.md covers Goal, How skills run, Instructions and Constraints
  • Calls uv, curl and sh; reaches astral.sh; needs MP_API_KEY and HF_TOKEN

What it does

General Atomisticskills Setup is an agent skill from learningmatter-mit/AtomisticSkills. Set up, check or troubleshoot how AtomisticSkills runs on this machine -- creating its Python environments, connecting its MCP servers, choosing uv or a container runtime, and configuring API keys. Use it when installing AtomisticSkills, when a skill command or MCP tool fails to start, or before a first research task.

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 Agent Workflows, covering MCP servers. It works with Model Context Protocol and Python. 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

  • Installing AtomisticSkills
  • A skill command
  • MCP tool fails to start
  • Before a first research task

Example prompts

  • “/general-atomisticskills-setup”

Requirements

  • Python 3
  • Docker
  • A credential in MP_API_KEY

Workflow steps

4 steps, taken from the step headings in SKILL.md.

  1. Check the machine
  2. Create the environments
  3. Configure API keys
  4. Verify with a real calculation

What it can do on your machine

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

    Shell commands in SKILL.md call:

    • uv
    • curl
    • sh

    From the folder's file list and the shell code blocks in SKILL.md.

  • Network

    Hosts in commands or code, which the agent is likely to contact:

    • astral.sh

    Also links to:

    • github.com

    From URLs in SKILL.md, links to its own repository left out.

  • Credentials

    Names these keys or tokens, usually read from environment variables:

    • MP_API_KEY
    • HF_TOKEN

    From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.

Context cost

General Atomisticskills Setup loads about 1.2k tokens when it runs. Until then it costs about 87 tokens; SKILL.md has 519 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it
~87
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: notes

The automated check noted patterns worth knowing about, such as sudo or a known installer.

  • NotePipes a well-known installer script into a shellSKILL.md:63
    | `uv is not installed` | `curl -LsSf https://astral.sh/uv/install.sh \| sh` (ask the user first) |

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 learningmatter-mit/AtomisticSkills at commit 7f2d86d, republished under its MIT licence (© learningmatter-mit). 519 words, ~1,171 tokens.

Download SKILL.mdSave it as .claude/skills/general-atomisticskills-setup/SKILL.md (or your agent's skills folder).
name
general-atomisticskills-setup
description
Set up, check or troubleshoot how AtomisticSkills runs on this machine -- creating its Python environments, connecting its MCP servers, choosing uv or a container runtime, and configuring API keys. Use it when installing AtomisticSkills, when a skill command or MCP tool fails to start, or before a first research task.
metadata.category
general
metadata.venv
cpu, mlip

AtomisticSkills Setup and Runtime

Goal

Make every AtomisticSkills skill and MCP tool runnable on the current machine, and know how they run: which environment a command uses, where results go, and what to do when something fails to start.

How skills run

  • Commands. Every skill command starts through the launcher ${CLAUDE_SKILL_DIR}/../../venv/run <env> ..., where <env> is cpu, mlip (MACE, MatGL) or fairchem, sometimes with an extra such as cpu+openmm. Run commands exactly as a skill writes them; the launcher picks the environment, and creates it on first use.
  • Backends. The launcher uses uv on this machine when it can, and otherwise a container image built from the same lock (Docker, Podman, Apptainer), with the same paths. ATOMISTIC_RUNTIME (or the plugin's runtime option) forces one.
  • MCP tools. Skills write MCP tools as server.tool, e.g. mace.relax_structure. If a server is not connected, the same tool runs from the shell; tools named in one command share a process, so a loaded model stays loaded: ${CLAUDE_SKILL_DIR}/../../venv/run mlip python -m src.mcp_server.cli mace load_model relax_structure structure_data=POSCAR. --list shows a server's tools and arguments.
  • Results. Scripts and MCP servers write into the current project: a research task gets its own research/<date>_<topic>/ directory (base.create_research_dir), and later outputs default to it. Never write results inside the skill or plugin directory.

Instructions

1. Check the machine
bash
${CLAUDE_SKILL_DIR}/../../venv/run --doctor

It reports the host (architecture, glibc, uv, container runtimes, GPU and driver) and, per environment, whether it runs with uv or a container and whether it is ready.

2. Create the environments
bash
${CLAUDE_SKILL_DIR}/../../venv/run --setup

This creates cpu, mlip and fairchem -- several GB for the GPU environments, so warn the user and use a long timeout. Name environments to create only some (--setup cpu mlip). On aarch64 with a container runtime, --setup generative also fetches the image behind the adit, diffcsp and mattergen servers.

If --doctor reports a missing prerequisite, fix it before retrying:

ReportFix
uv is not installedcurl -LsSf https://astral.sh/uv/install.sh | sh (ask the user first)
needs glibc >= … or needs a C compilerinstall a container runtime (Apptainer on HPC, Docker elsewhere); auto then uses it
MCP server "being created in the background"wait for --setup (or the background log it names) to finish, then reconnect the server with /mcp
Show full SKILL.md (155 more words)Show less
3. Configure API keys

Settings live in ~/.config/atomistic_skills.yaml (environment variables of the same name take precedence). Ask the user for the keys they need -- never invent them:

yaml
MP_API_KEY: "..."        # Materials Project
HF_TOKEN: "..."          # gated Hugging Face models, e.g. FairChem UMA
ATOMISTIC_RUNTIME: auto  # or uv, docker, podman, apptainer
4. Verify with a real calculation
bash
${CLAUDE_SKILL_DIR}/../../venv/run cpu python -m src.mcp_server.cli base --list
${CLAUDE_SKILL_DIR}/../../venv/run mlip python -c "import torch; print('CUDA available:', torch.cuda.is_available())"

Then, with the MCP servers connected, relax a small structure: mace.load_model followed by mace.relax_structure on a two-atom silicon cell should finish in seconds on a GPU.

Constraints

  • Platforms: native environments need Linux on x86_64 or aarch64; other hosts use the container fallback. PyMOL, SCINE/ORCA and fpocket exist for x86_64 only.
  • Research stacks: the generative models, ICEBERG, React-OT and SCD each have their own uv project, created on first use like the shared ones; several are x86_64 only, and on aarch64 the generative MCP servers run from the generative container image. venv/run --doctor lists what this host runs.
  • Installing software: ask the user before installing uv, a container runtime or system packages, and before downloading multi-GB environments.

Author: Bowen Deng Contact: GitHub @learningmatter-mit

© learningmatter-mit, MIT. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file

Files

Just SKILL.md in skills/general-atomisticskills-setup of learningmatter-mit/AtomisticSkills.

Open the folder on GitHubat commit 7f2d86d

Compare with similar skills

General Atomisticskills Setup 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 Atomisticskills Setup compared with similar skills
SkillStarsUsed inTokensAuto-checkLicenceRepo updated
General Atomisticskills Setup this skilllearningmatter-mit/AtomisticSkills175—~1.2kAutomated safety check: NotesMIT
MCP Server Builderanthropics/skills180k62 repos~2.3kAutomated safety check: PassApache-2.0
MCP Server BuildershareAI-lab/learn-claude-code78k5 repos~1.2kAutomated safety check: PassMIT
Fastmcp Client CLIPrefectHQ/fastmcp28k1 repos~823Automated safety check: PassApache-2.0
MemPalace Setup and OperationMemPalace/mempalace59k—~2.2kAutomated safety check: PassMIT
FastmcpTommy-yw/RunbookHermes5463 repos~2.1kAutomated safety check: PassMIT

Similar skills

  • MCP Server Builder

    anthropics/skills

    Official

    Guides the design and implementation of Model Context Protocol servers in TypeScript or Python, from tool naming and error messages to evaluation.

    180k GitHub starsUsed in 62 repos~2.3k tokens
    Agent WorkflowsAuto-check passed

  • MCP Server Builder

    shareAI-lab/learn-claude-code

    Walks through building MCP servers in Python or TypeScript that expose tools, resources and prompts to Claude, with templates, registration and testing.

    78k GitHub starsUsed in 5 repos~1.2k tokens
    Agent WorkflowsAuto-check passed

  • Fastmcp Client CLI

    PrefectHQ/fastmcp

    Query and invoke tools on MCP servers using fastmcp list and fastmcp call.

    28k GitHub starsUsed in 1 repo~823 tokens
    Agent WorkflowsAuto-check passed

  • MemPalace Setup and Operation

    MemPalace/mempalace

    Installs and configures MemPalace as a private local palace, a shared-brain hub or a client of an existing hub, including MCP registration and version-correct initialization.

    59k GitHub stars~2.2k tokensUpdated today
    Agent WorkflowsAuto-check passed

  • Fastmcp

    Tommy-yw/RunbookHermes

    Build, test, inspect, install, and deploy MCP servers with FastMCP in Python.

    546 GitHub starsUsed in 3 repos~2.1k tokens
    Agent WorkflowsAuto-check passed

  • Migrate To Archestra

    archestra-ai/archestra

    Migrate an existing agentic PoC/pilot (Claude Code project files, MCP configs, hooks, local tools, openclaw config, or similar hand-rolled setup artifacts) into an Archestra instance.

    4.3k GitHub stars~2.6k tokensUpdated today
    Agent WorkflowsAuto-check passed

More from learningmatter-mit/AtomisticSkills

All 129 skills in this repo

  • Drug Binding Site Definition

    learningmatter-mit/AtomisticSkills

    Define a docking search box (center coordinates + box dimensions in Angstroms) from a co-crystal ligand, binding-site residues, or a saved JSON specification.

    175 GitHub stars~2.9k tokensUpdated yesterday
    Auto-check passed

  • Drug Complex System Builder

    learningmatter-mit/AtomisticSkills

    Build a solvated, charge-neutralized protein-ligand complex for OpenMM molecular dynamics simulation.

    175 GitHub stars~2k tokensUpdated yesterday
    Auto-check passed

  • Drug Pocket Detection

    learningmatter-mit/AtomisticSkills

    Identify and rank ligandable pockets on a protein structure or model using geometry (fpocket) or an ML predictor (P2Rank).

    175 GitHub stars~4k tokensUpdated yesterday
    Auto-check passed

  • Chem Bond Dissociation

    learningmatter-mit/AtomisticSkills

    Calculate homolytic and heterolytic bond dissociation energies (BDEs) for all single bonds in a molecule using MLIPs with RDKit fragmentation.

    175 GitHub stars~2.5k tokensUpdated yesterday
    Auto-check passed

  • Chem Conformer Search

    learningmatter-mit/AtomisticSkills

    Generate molecular conformers with RDKit ETKDG, relax with MLIPs, and rank by energy with Boltzmann weighting.

    175 GitHub stars~1.3k tokensUpdated yesterday
    Auto-check passed

  • Chem DB Mof

    learningmatter-mit/AtomisticSkills

    Query multiple MOF databases (QMOF via MPContribs; ARC-MOF DB7/Majumdar et al.

    175 GitHub stars~1.9k tokensUpdated yesterday
    Auto-check passed

Works with

Categories

Questions about General Atomisticskills Setup

What does General Atomisticskills Setup do?

Set up, check or troubleshoot how AtomisticSkills runs on this machine -- creating its Python environments, connecting its MCP servers, choosing uv or a container runtime, and configuring API keys. General Atomisticskills Setup is an agent skill from learningmatter-mit/AtomisticSkills. Set up, check or troubleshoot how AtomisticSkills runs on this machine -- creating its Python environments, connecting its MCP servers, choosing uv or a container runtime, and configuring API keys.

When should I use General Atomisticskills Setup?

General Atomisticskills Setup fits situations like: installing AtomisticSkills; A skill command; MCP tool fails to start; before a first research task.

How do I install General Atomisticskills Setup in Claude Code?

Run `npx skills add learningmatter-mit/AtomisticSkills --skill general-atomisticskills-setup -a claude-code`. Or copy the skill folder (skills/general-atomisticskills-setup in learningmatter-mit/AtomisticSkills) into .claude/skills/general-atomisticskills-setup in your project. Claude Code loads it when a task matches its description.

How do I install General Atomisticskills Setup in Codex?

Run `npx skills add learningmatter-mit/AtomisticSkills --skill general-atomisticskills-setup -a codex`. Or copy the skill folder (skills/general-atomisticskills-setup in learningmatter-mit/AtomisticSkills) into .agents/skills/general-atomisticskills-setup in your project. Codex loads it when a task matches its description.

Can I use General Atomisticskills Setup 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-atomisticskills-setup -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-atomisticskills-setup, .gemini/skills/general-atomisticskills-setup, .github/skills/general-atomisticskills-setup and .opencode/skills/general-atomisticskills-setup in your project.

What does General Atomisticskills Setup need to run?

Going by SKILL.md and its folder, General Atomisticskills Setup needs the command-line tools its instructions call (uv, curl and sh) and credentials named MP_API_KEY and HF_TOKEN. Our summary lists: Python 3; Docker; A credential in MP_API_KEY.

Does General Atomisticskills Setup access the network?

SKILL.md names 2 domains. In commands or code: astral.sh; the agent is likely to contact it when it follows the instructions. As links in the text: github.com. This is read from the text; nothing was executed.

Is General Atomisticskills Setup safe to install?

Our automated static check of SKILL.md found notes only (pipes a well-known installer script into a shell), nothing it rates as a warning. It is not a guarantee. Review the folder before installing.

What licence does General Atomisticskills Setup use?

General Atomisticskills Setup 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 Atomisticskills Setup use?

About 1.2k tokens (SKILL.md is roughly 4.7k 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 Atomisticskills Setup?

Skills that share tags, products or a category with General Atomisticskills Setup: MCP Server Builder (anthropics/skills, 180k stars), MCP Server Builder (shareAI-lab/learn-claude-code, 78k stars), Fastmcp Client CLI (PrefectHQ/fastmcp, 28k stars) and MemPalace Setup and Operation (MemPalace/mempalace, 59k stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains General Atomisticskills Setup?

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.

Source: learningmatter-mit/AtomisticSkills on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.