New: 98,000+ 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

Dreams

by lamm-mit in lamm-mit/scienceclaw

Agentic materials discovery and DFT simulation framework using ASE, Quantum ESPRESSO, and Claude LLMs via LangGraph.

Apache-2.0Auto-check passedAI & LLM Engineering

Install Dreams

skills CLI
$ npx skills add lamm-mit/scienceclaw --skill dreams -a claude-code

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

GitHub CLI
$ gh skill install lamm-mit/scienceclaw dreams --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/lamm-mit/scienceclaw.git skills-src && mkdir -p .claude/skills && cp -r skills-src/skills/dreams .claude/skills/dreams && 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
dreams
GitHub stars
244
Token cost
~1.2k tokens
SKILL.md length
474 words
Files
3 (incl. scripts)
Skills in repo
86
Repo updated
First seen
Licence
Apache-2.0

At a glance

Agentic materials discovery and DFT simulation framework using ASE, Quantum ESPRESSO, and Claude LLMs via LangGraph.

  • Works in 4 steps: Clone the repository → Create and activate conda environment → Install Quantum ESPRESSO → …
  • Tasks that involve Mobile testing and debugging
  • SKILL.md covers dreams, Prerequisites, Installation and How to run, plus 1 more section
  • Runs Python scripts from its folder; calls git, conda and python; reaches github.com; needs ANTHROPIC_API_KEY

What it does

Dreams is an agent skill from lamm-mit/scienceclaw. Agentic materials discovery and DFT simulation framework using ASE, Quantum ESPRESSO, and Claude LLMs via LangGraph.

Its SKILL.md is about 1.2k tokens, which your agent loads only when the skill is triggered. The skill folder holds 3 other files, including scripts (for example `scripts/USAGE.md` and `scripts/dreams_client.py`).

It sits in AI & LLM Engineering, covering Mobile testing and debugging and Building AI agents. It works with LangGraph and arXiv. The licence is Apache-2.0.

When your agent uses it

  • Tasks that involve Mobile testing and debugging
  • Tasks that involve Building AI agents

Example prompts

  • “/dreams”

Requirements

  • Python 3
  • A credential in ANTHROPIC_API_KEY

Workflow steps

4 steps, taken from the first numbered list in SKILL.md.

  1. Clone the repository
  2. Create and activate conda environment
  3. Install Quantum ESPRESSO
  4. Configure API keys and paths

What it can do on your machine

Read from SKILL.md and the folder at commit ab9aba1. 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

    Ships 2 files in scripts/ (Python), which the agent can run.

    Shell commands in SKILL.md call:

    • git
    • conda
    • python
    • python3

    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:

    • github.com

    Also links to:

    • arxiv.org
    • quantum-espresso.org
    • drive.google.com

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

  • Credentials

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

    • ANTHROPIC_API_KEY

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

Context cost

Dreams loads about 1.2k tokens when it runs. Until then it costs about 31 tokens; SKILL.md has 474 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); the scripts in this folder are not scanned.

SKILL.md

The full file from lamm-mit/scienceclaw at commit ab9aba1, republished under its Apache-2.0 licence (© lamm-mit). 474 words, ~1,205 tokens.

Download SKILL.mdSave it as .claude/skills/dreams/SKILL.md (or your agent's skills folder). This skill also uses 2 other files; get the full folder from GitHub.
name
dreams
description
Agentic materials discovery and DFT simulation framework using ASE, Quantum ESPRESSO, and Claude LLMs via LangGraph.
source_type
github
auth_required
true
repository_url
https://github.com/BattModels/material_agent
reference_url
https://arxiv.org/abs/2507.14267

dreams

Agentic materials discovery and DFT simulation framework using ASE, Quantum ESPRESSO, and Claude LLMs via LangGraph.

Code repository

https://github.com/BattModels/material_agent

Use this as the implementation source: clone the repo and follow its README for install, dependencies, and how to run code or experiments. The generated client prints JSON with a suggested git clone command.

Paper (arXiv — explanation)

https://arxiv.org/abs/2507.14267

This is the paper reference. The client can optionally fetch live Atom metadata (title, abstract) for agents; it does not run training or upstream research code by itself.

What “running” this client does

The *_client.py script prints JSON that combines a GitHub repository (clone URL + suggested git clone) with optional paper context from arXiv (live Atom metadata when reference_url is arXiv). Run the real code by cloning the repo and following its README — the skill is your agent-facing entrypoint, not a substitute for the repo’s install steps.

To call a REST API instead, set BASE_URL in scripts/dreams_client.py or wrap the upstream CLI with subprocess after clone.

How to run the method (from the source)

Extracted for operators and agents. Confirm against the upstream repository or paper before relying on it in production.

Prerequisites

  • Quantum ESPRESSO installed and available in system PATH
  • Anthropic API key (or alternative LLM provider packages installed)
  • Conda package manager
  • ASE (Atomic Simulation Environment) and LangGraph compatible Python environment

Installation

  1. Clone the repository:

    bash
    git clone https://github.com/BattModels/material_agent.git
cd material_agent

  2. Create and activate conda environment:

    bash
    conda env create -f environment.yml
conda activate dreams

    Note: Environment setup typically takes 5–10 minutes. Default setup supports Anthropic models only.

  3. Install Quantum ESPRESSO:

    • Follow official QE installation: https://www.quantum-espresso.org/
    • Ensure pw.x and related executables are in system PATH or modify QE_submission_example in prompt.py

  4. Configure API keys and paths:

    • Edit config/default.yaml:
      • Add your Anthropic (or alternative LLM provider) API key
      • Specify pseudopotential directory and paths
      • Set working directory for DFT calculations
Show full SKILL.md (216 more words)Show less

How to run

  1. Edit the task specification in invoke.py:

    python
    # Example: Calculate lattice constant for BCC Li
usermessage = "You are going to calculate the lattice constant for BCC Li through DFT, the experiment value is 3.451, use this to create the initial structure."

  2. Run the agent:

    bash
    python invoke.py

The agent will autonomously:

  • Parse the task via Claude LLM
  • Generate initial atomic structures
  • Configure and submit DFT calculations to Quantum ESPRESSO via ASE
  • Analyze results and iterate if needed
  • Return final materials property predictions

Configuration

Environment Variables & Config File (config/default.yaml):

  • ANTHROPIC_API_KEY: Required for Claude model access
  • pseudopotentials_dir: Path to pseudo-potential files (e.g., PAW datasets)
  • working_directory: Directory for DFT calculations and outputs
  • qe_path: Path to Quantum ESPRESSO executables (if not in PATH)
  • exchange_correlation_functional: XC functional choice (e.g., PBE)

For non-Anthropic LLMs:

  • Install provider-specific packages
  • Modify planNexe2.py and tools.py to integrate alternative LLM APIs

Demo Video: Full walkthrough available at Google Drive demo

The same text lives in scripts/USAGE.md for tools that prefer reading files under scripts/.

Parameters

--api-key (str) [required] API key for authentication --task-description (str) [required] Natural language task specification for the materials simulation (e.g., lattice constant calculation, adsorption energy prediction). Defined in invoke.py usermessage. --config-file (str) [optional, default=config/default.yaml] Path to YAML configuration file containing API keys, pseudopotentials, and working directory.

Usage
bash
python3 scripts/dreams_client.py python invoke.py
Example Output
json
{"calculation_result": "lattice_constant_value", "dft_converged": true, "explanation": "..." }

© lamm-mit, 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 2 other files (scripts) in skills/dreams of lamm-mit/scienceclaw.

  • SKILL.md
  • scripts/USAGE.md
  • scripts/dreams_client.py

Open the folder on GitHubat commit ab9aba1

Compare with similar skills

Dreams 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.

Dreams compared with similar skills
SkillStarsUsed inTokensAuto-checkLicenceRepo updated
Dreams this skilllamm-mit/scienceclaw244—~1.2kAutomated safety check: PassApache-2.0
Uipath FunctionsUiPath/skills168—~3.6kAutomated safety check: NotesMIT
Chemgraphargonne-lcf/ChemGraph162—~2.7kAutomated safety check: PassApache-2.0
Langgraph Agent Patternssoba-labs/langchain-agent-skills107—~3.6kAutomated safety check: PassMIT
AI EngineerDokhacgiakhoa/Agent-Skills-4-Vibe-Coding-CLI508—~1.1kAutomated safety check: PassCustom licence
Langgraph Error Handlingsoba-labs/langchain-agent-skills107—~1.5kAutomated safety check: PassMIT

Similar skills

  • Uipath Functions

    UiPath/skills

    UiPath Coded Functions — deterministic Python or TypeScript/JavaScript units built with the uip function CLI (new -l py|ts|js, init, serve, run, pack, publish); the functions map in uipath.json…

    168 GitHub stars~3.6k tokensUpdated today
    AI & LLM EngineeringAuto-check: notes

  • Chemgraph

    argonne-lcf/ChemGraph

    Develop, test, and extend ChemGraph -- an agentic framework for automated molecular simulations using LLMs, LangGraph, ASE, and MCP servers

    162 GitHub stars~2.7k tokensUpdated today
    AI & LLM EngineeringAuto-check passed

  • Langgraph Agent Patterns

    soba-labs/langchain-agent-skills

    Implement multi-agent coordination patterns (supervisor-subagent, router, orchestrator-worker, handoffs) for LangGraph applications.

    107 GitHub stars~3.6k tokensUpdated 1 mo ago
    AI & LLM EngineeringAuto-check passed

  • AI Engineer

    Dokhacgiakhoa/Agent-Skills-4-Vibe-Coding-CLI

    Principal AI Architect and Machine Learning Engineer. An agent skill from Dokhacgiakhoa/Agent-Skills-4-Vibe-Coding-CLI.

    508 GitHub stars~1.1k tokensUpdated 4 mo ago
    AI & LLM EngineeringAuto-check passed

  • Langgraph Error Handling

    soba-labs/langchain-agent-skills

    Implement LangGraph error handling with current v1 patterns.

    107 GitHub stars~1.5k tokensUpdated 1 mo ago
    AI & LLM EngineeringAuto-check passed

  • Port From Langgraph

    strands-agents/harness-sdk

    Migrate a LangGraph application to Strands Agents while preserving its external entrypoint, routing, persistence, interrupts, limits, and tracing.

    8.7k GitHub stars~200 tokensUpdated today
    AI & LLM EngineeringAuto-check passed

More from lamm-mit/scienceclaw

All 86 skills in this repo

  • Fred Economic Data

    lamm-mit/scienceclaw

    Query FRED (Federal Reserve Economic Data) API for 800,000+ economic time series from 100+ sources.

    244 GitHub starsUsed in 4 repos~3k tokens
    Auto-check passed

  • Drug Research

    lamm-mit/scienceclaw

    Generates comprehensive drug research reports with compound disambiguation, evidence grading, and mandatory completeness sections.

    244 GitHub starsUsed in 3 repos~1.7k tokens
    Auto-check passed

  • Imaging Data Commons

    lamm-mit/scienceclaw

    Query and download public cancer imaging data from NCI Imaging Data Commons using idc-index.

    244 GitHub starsUsed in 5 repos~11k tokens
    Auto-check passed

  • Rowan

    lamm-mit/scienceclaw

    Cloud-based quantum chemistry platform with Python API. An agent skill from lamm-mit/scienceclaw.

    244 GitHub starsUsed in 4 repos~3.1k tokens
    Auto-check: warnings

  • Infographics

    lamm-mit/scienceclaw

    Create professional infographics using Nano Banana Pro AI with smart iterative refinement.

    244 GitHub starsUsed in 6 repos~4.4k tokens
    Auto-check: notes

  • Disease Research

    lamm-mit/scienceclaw

    Generate comprehensive disease research reports using 100+ ToolUniverse tools.

    244 GitHub stars~946 tokensUpdated 1 mo ago
    Auto-check passed

Works with

Categories

Questions about Dreams

What does Dreams do?

Agentic materials discovery and DFT simulation framework using ASE, Quantum ESPRESSO, and Claude LLMs via LangGraph. Dreams is an agent skill from lamm-mit/scienceclaw. Agentic materials discovery and DFT simulation framework using ASE, Quantum ESPRESSO, and Claude LLMs via LangGraph.

When should I use Dreams?

Dreams fits situations like: tasks that involve Mobile testing and debugging; tasks that involve Building AI agents.

How do I install Dreams in Claude Code?

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

How do I install Dreams in Codex?

Run `npx skills add lamm-mit/scienceclaw --skill dreams -a codex`. Or copy the skill folder (skills/dreams in lamm-mit/scienceclaw) into .agents/skills/dreams in your project. Codex loads it when a task matches its description.

Can I use Dreams 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 lamm-mit/scienceclaw --skill dreams -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/dreams, .gemini/skills/dreams, .github/skills/dreams and .opencode/skills/dreams in your project.

What does Dreams need to run?

Going by SKILL.md and its folder, Dreams needs Python for the scripts in its folder, the command-line tools its instructions call (git, conda, python and python3) and credentials named ANTHROPIC_API_KEY. Our summary lists: Python 3; A credential in ANTHROPIC_API_KEY.

Does Dreams access the network?

SKILL.md names 4 domains. In commands or code: github.com; the agent is likely to contact it when it follows the instructions. As links in the text: arxiv.org, quantum-espresso.org and drive.google.com. This is read from the text; nothing was executed.

Is Dreams 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. The check reads SKILL.md only: the scripts in the folder are not scanned, so read them before running anything.

What licence does Dreams use?

Dreams is published under the Apache-2.0 licence (the repository's licence). It allows redistribution, so the full SKILL.md is shown on this page.

How many tokens does Dreams use?

About 1.2k tokens (SKILL.md is roughly 4.8k 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 Dreams?

Skills that share tags, products or a category with Dreams: Uipath Functions (UiPath/skills, 168 stars), Chemgraph (argonne-lcf/ChemGraph, 162 stars), Langgraph Agent Patterns (soba-labs/langchain-agent-skills, 107 stars) and AI Engineer (Dokhacgiakhoa/Agent-Skills-4-Vibe-Coding-CLI, 508 stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains Dreams?

lamm-mit (a GitHub user) maintains it in lamm-mit/scienceclaw, which has 244 GitHub stars. The repository holds 86 skills in this directory. The repository was last updated on August 21, 2026.

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