Agent skill

Dft

Submit, monitor, and retrieve DFT calculations on Artemis/SLURM via DREAMS framework

Apache-2.0Auto-check passed

Install Dft

skills CLI

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

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

GitHub CLI

$ gh skill install lamm-mit/scienceclaw dft --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/dft .claude/skills/dft && 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/

Paste into Claude Code

Install the "dft" agent skill from https://github.com/lamm-mit/scienceclaw/tree/main/skills/dft into .claude/skills/dft/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "dft", 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

$skill-installer install https://github.com/lamm-mit/scienceclaw/tree/main/skills/dft

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 lamm-mit/scienceclaw --skill dft -a codex

Project install goes to .agents/skills/; add -g for ~/.codex/skills/.

GitHub CLI

$ gh skill install lamm-mit/scienceclaw dft --agent codex

Project scope by default (.agents/skills/); add --scope user for a personal install.

Manual copy

$ git clone --depth 1 https://github.com/lamm-mit/scienceclaw.git skills-src && mkdir -p .agents/skills && cp -r skills-src/skills/dft .agents/skills/dft && rm -rf skills-src

Use ~/.agents/skills/ instead of .agents/skills for a personal install.

Codex skills documentation · loads skills from .agents/skills/

Paste into Codex

Install the "dft" agent skill from https://github.com/lamm-mit/scienceclaw/tree/main/skills/dft into .agents/skills/dft/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "dft", 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 lamm-mit/scienceclaw --skill dft -a cursor

Project install goes to .agents/skills/; add -g for ~/.cursor/skills/.

GitHub CLI

$ gh skill install lamm-mit/scienceclaw dft --agent cursor

Project scope by default (.agents/skills/); add --scope user for a personal install.

Manual copy

$ git clone --depth 1 https://github.com/lamm-mit/scienceclaw.git skills-src && mkdir -p .cursor/skills && cp -r skills-src/skills/dft .cursor/skills/dft && rm -rf skills-src

Use ~/.cursor/skills/ instead of .cursor/skills for a personal install.

Cursor skills documentation · loads skills from .cursor/skills/, .agents/skills/, .claude/skills/, .codex/skills/

Paste into Cursor

Install the "dft" agent skill from https://github.com/lamm-mit/scienceclaw/tree/main/skills/dft into .cursor/skills/dft/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "dft", 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

$ gemini skills install https://github.com/lamm-mit/scienceclaw.git --path skills/dft

--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 lamm-mit/scienceclaw --skill dft -a gemini-cli

Project install goes to .agents/skills/; add -g for ~/.gemini/skills/.

GitHub CLI

$ gh skill install lamm-mit/scienceclaw dft --agent gemini-cli

Project scope by default (.agents/skills/); add --scope user for a personal install.

Manual copy

$ git clone --depth 1 https://github.com/lamm-mit/scienceclaw.git skills-src && mkdir -p .gemini/skills && cp -r skills-src/skills/dft .gemini/skills/dft && rm -rf skills-src

Use ~/.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/

Paste into Gemini CLI

Install the "dft" agent skill from https://github.com/lamm-mit/scienceclaw/tree/main/skills/dft into .gemini/skills/dft/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "dft", 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.

GitHub CLI

$ gh skill install lamm-mit/scienceclaw dft

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 lamm-mit/scienceclaw --skill dft -a github-copilot

Project install goes to .agents/skills/; add -g for ~/.copilot/skills/.

Manual copy

$ git clone --depth 1 https://github.com/lamm-mit/scienceclaw.git skills-src && mkdir -p .github/skills && cp -r skills-src/skills/dft .github/skills/dft && rm -rf skills-src

Use ~/.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/

Paste into GitHub Copilot

Install the "dft" agent skill from https://github.com/lamm-mit/scienceclaw/tree/main/skills/dft into .github/skills/dft/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "dft", 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 lamm-mit/scienceclaw --skill dft -a opencode

OpenCode documents no install command of its own. Project install goes to .agents/skills/; add -g for ~/.config/opencode/skills/.

GitHub CLI

$ gh skill install lamm-mit/scienceclaw dft --agent opencode

Project scope by default (.agents/skills/); add --scope user for a personal install.

Manual copy

$ git clone --depth 1 https://github.com/lamm-mit/scienceclaw.git skills-src && mkdir -p .opencode/skills && cp -r skills-src/skills/dft .opencode/skills/dft && rm -rf skills-src

Use ~/.config/opencode/skills/ instead of .opencode/skills for a personal install.

OpenCode skills documentation · loads skills from .opencode/skills/, .claude/skills/, .agents/skills/

Paste into OpenCode

Install the "dft" agent skill from https://github.com/lamm-mit/scienceclaw/tree/main/skills/dft into .opencode/skills/dft/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "dft", 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: dft
GitHub stars: 244
Token cost: ~596 tokens
SKILL.md length: 163 words
Files: 6 (incl. scripts, references)
Skills in repo: 85
Repo updated: Aug 21, 2026
First seen: Oct 7, 2026
Licence: Apache-2.0

At a glance

Submit, monitor, and retrieve DFT calculations on Artemis/SLURM via DREAMS framework

SKILL.md covers Status: IN DEVELOPMENT, Prerequisites, Scripts and Parameters, plus 3 more sections
Runs Python scripts from its folder; calls python3

What it does

Dft is an agent skill from lamm-mit/scienceclaw. Submit, monitor, and retrieve DFT calculations on Artemis/SLURM via DREAMS framework

Its SKILL.md is about 600 tokens, which your agent loads only when the skill is triggered. The skill folder holds 7 other files, including scripts and reference files (for example `references/dreams_integration.md`, `scripts/dft_retrieve.py` and `scripts/dft_status.py`).

The licence is Apache-2.0.

Example prompts

“/dft”

Requirements

Python 3

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 3 files in scripts/ (Python), which the agent can run.
Shell commands in SKILL.md call:
- python3
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
- arxiv.org
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

Dft loads about 596 tokens when it runs, and up to ~909 if it reads all its reference files. Until then it costs about 22 tokens; SKILL.md has 163 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it: ~22
When it runs · the whole SKILL.md, loaded when a task matches: ~596
With references · SKILL.md plus every file in references/, read only if the agent opens them: ~909

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). 163 words, ~596 tokens.

Download SKILL.mdSave it as .claude/skills/dft/SKILL.md (or your agent's skills folder). This skill also uses 5 other files; get the full folder from GitHub.

name: dft
description: Submit, monitor, and retrieve DFT calculations on Artemis/SLURM via DREAMS framework

DFT Skill

Submit and monitor density functional theory (DFT) calculations on the Artemis HPC cluster via the SLURM scheduler. Uses the DREAMS framework for structured DFT workflows (paper).

Status: IN DEVELOPMENT

Prerequisites

Access to Artemis HPC cluster (SLURM scheduler)
Quantum Espresso installed on the cluster
DREAMS framework configured (see references/dreams_integration.md)
SSH key or credentials for job submission from a login node

Scripts

`dft_submit.py` — Submit a relaxation/SCF job

bash

python3 {baseDir}/scripts/dft_submit.py \
  --structure path/to/structure.cif \
  --calc-type relax \
  --format json

`dft_status.py` — Poll job status

bash

python3 {baseDir}/scripts/dft_status.py \
  --job-id 12345 \
  --format json

`dft_retrieve.py` — Retrieve and parse completed results

bash

python3 {baseDir}/scripts/dft_retrieve.py \
  --job-id 12345 \
  --format json

Parameters

Parameter	Script	Description
`--structure`	submit	Path to CIF or POSCAR file
`--calc-type`	submit	`relax` \| `scf` \| `vc-relax` \| `bands`
`--job-id`	status, retrieve	SLURM job ID
`--mp-id`	submit	Materials Project ID (fetches structure automatically)
`--format`	all	`summary` \| `json`
`--dry-run`	submit	Print SLURM script without submitting
`--queue`	submit	SLURM partition: `venkvis-cpu` (default), `venkvis-largemem`, `venkvis-a100`, `venkvis-h100`, `debug`

Output (JSON)

Submit

json

{"job_id": "12345", "calc_type": "relax", "structure": "LaH10", "status": "PENDING", "submit_time": "..."}

Status

json

{"job_id": "12345", "status": "RUNNING", "elapsed": "00:45:12", "node": "artemis-gpu-01"}

Retrieve

json

{"job_id": "12345", "status": "COMPLETED", "total_energy_eV": -142.38, "forces_converged": true, "relaxed_structure_cif": "...", "band_gap_eV": 0.0}

Scheduler: SLURM (sbatch), NOT PBS

Safety

Never submit jobs from inside a compute node
Never auto-generate input files without user confirmation
Always validate structure file exists before submission

Files

SKILL.md and 5 other files (scripts, references) in skills/dft of lamm-mit/scienceclaw.

SKILL.md
references/dreams_integration.md
requirements.txt
scripts/dft_retrieve.py
scripts/dft_status.py
scripts/dft_submit.py

Open the folder on GitHubat commit ab9aba1

Compare with similar skills

Dft 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.

Dft compared with similar skills
Skill	Stars	Used in	Tokens	Auto-check	Licence	Repo updated
Dft this skilllamm-mit/scienceclaw	244	—	~596	Automated safety check: Pass	Apache-2.0	1 mo ago
Qdrant Monitoringgithub/awesome-copilot	40k	1 repos	~276	Automated safety check: Pass	MIT	today
Iterative Retrievalaffaan-m/ECC	274k	7 repos	~1.6k	Automated safety check: Pass	MIT	2 days ago
Agent Performance Monitorruvnet/ruflo	74k	2 repos	~4.9k	Automated safety check: Pass	MIT	today
Monitor Streamruvnet/ruflo	74k	—	~188	Automated safety check: Pass	MIT	today
Monitoring ExpertJeffallan/claude-skills	12k	—	~1.6k	Automated safety check: Pass	MIT	4 days ago

Similar skills

Qdrant Monitoring
github/awesome-copilot
Official
Guides Qdrant monitoring and observability setup. An agent skill from github/awesome-copilot.
40k GitHub starsUsed in 1 repo~276 tokens
DevOps & CloudAuto-check passed
Iterative Retrieval
affaan-m/ECC
Pattern for progressively refining context retrieval to solve the subagent context problem.
274k GitHub starsUsed in 7 repos~1.6k tokens
Agent WorkflowsAuto-check passed
Agent Performance Monitor
ruvnet/ruflo
Agent skill for performance-monitor - invoke with $agent-performance-monitor
74k GitHub starsUsed in 2 repos~4.9k tokens
Auto-check passed
Monitor Stream
ruvnet/ruflo
Stream live swarm events using the Monitor tool for real-time observability
74k GitHub stars~188 tokensUpdated today
DevOps & CloudAuto-check passed
Monitoring Expert
Jeffallan/claude-skills
Sets up application monitoring: structured logs, Prometheus metrics, OpenTelemetry tracing, Grafana dashboards, alert rules and load tests with k6 or Artillery.
12k GitHub stars~1.6k tokensUpdated 4 days ago
DevOps & CloudAuto-check passed
Implementing Security Monitoring With Datadog
mukul975/Anthropic-Cybersecurity-Skills
Implements security monitoring using Datadog Cloud SIEM, Cloud Security Management (CSM), and Workload Protection to detect threats, enforce compliance, and respond to security events across cloud…
34k GitHub stars~3.7k tokensUpdated 1 mo ago
SecurityAuto-check: notes

Questions about Dft

What does Dft do?

Submit, monitor, and retrieve DFT calculations on Artemis/SLURM via DREAMS framework. Dft is an agent skill from lamm-mit/scienceclaw.

How do I install Dft in Claude Code?

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

How do I install Dft in Codex?

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

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

What does Dft need to run?

Going by SKILL.md and its folder, Dft needs Python for the scripts in its folder and the command-line tools its instructions call (python3). Our summary lists: Python 3.

Does Dft access the network?

SKILL.md names 2 domains. As links in the text: github.com and arxiv.org. This is read from the text; nothing was executed.

Is Dft 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 Dft use?

Dft 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 Dft use?

About 596 tokens (SKILL.md is roughly 2.4k 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 313 tokens, read only when the agent opens those files.

What are the alternatives to Dft?

Skills that share tags, products or a category with Dft: Qdrant Monitoring (github/awesome-copilot, 40k stars), Iterative Retrieval (affaan-m/ECC, 274k stars), Agent Performance Monitor (ruvnet/ruflo, 74k stars) and Monitor Stream (ruvnet/ruflo, 74k stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains Dft?

lamm-mit (a GitHub user) maintains it in lamm-mit/scienceclaw, which has 244 GitHub stars. The repository holds 85 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.

Install Dft

Facts

At a glance

What it does

Example prompts

Requirements

What it can do on your machine

Tool permissions

Runs code

Network

Credentials

Context cost

Safety

SKILL.md

DFT Skill

Status: IN DEVELOPMENT

Prerequisites

Scripts

dft_submit.py — Submit a relaxation/SCF job

dft_status.py — Poll job status

dft_retrieve.py — Retrieve and parse completed results

Parameters

Output (JSON)

Submit

Status

Retrieve

Scheduler: SLURM (sbatch), NOT PBS

Safety

Files

Compare with similar skills

Similar skills

More from lamm-mit/scienceclaw

Questions about Dft

`dft_submit.py` — Submit a relaxation/SCF job

`dft_status.py` — Poll job status

`dft_retrieve.py` — Retrieve and parse completed results