Agent skill

Uma Surface Md

Run and diagnose governed ASE plus fairchem UMA molecular dynamics on standardized adsorbed slabs, including NVT/NVE surface trajectories, pre-relaxation, periodic-boundary and collision checks…

Custom licenceAuto-check passedTesting & QA

Install Uma Surface Md

skills CLI

$ npx skills add Tai609/NebulaMat --skill uma-surface-md -a claude-code

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

GitHub CLI

$ gh skill install Tai609/NebulaMat uma-surface-md --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/Tai609/NebulaMat.git skills-src && mkdir -p .claude/skills && cp -r skills-src/runtime/skills-bundle/uma-surface-md .claude/skills/uma-surface-md && 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 "uma-surface-md" agent skill from https://github.com/Tai609/NebulaMat/tree/main/runtime/skills-bundle/uma-surface-md into .claude/skills/uma-surface-md/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "uma-surface-md", 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/Tai609/NebulaMat/tree/main/runtime/skills-bundle/uma-surface-md

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 Tai609/NebulaMat --skill uma-surface-md -a codex

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

GitHub CLI

$ gh skill install Tai609/NebulaMat uma-surface-md --agent codex

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

Manual copy

$ git clone --depth 1 https://github.com/Tai609/NebulaMat.git skills-src && mkdir -p .agents/skills && cp -r skills-src/runtime/skills-bundle/uma-surface-md .agents/skills/uma-surface-md && 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 "uma-surface-md" agent skill from https://github.com/Tai609/NebulaMat/tree/main/runtime/skills-bundle/uma-surface-md into .agents/skills/uma-surface-md/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "uma-surface-md", 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 Tai609/NebulaMat --skill uma-surface-md -a cursor

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

GitHub CLI

$ gh skill install Tai609/NebulaMat uma-surface-md --agent cursor

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

Manual copy

$ git clone --depth 1 https://github.com/Tai609/NebulaMat.git skills-src && mkdir -p .cursor/skills && cp -r skills-src/runtime/skills-bundle/uma-surface-md .cursor/skills/uma-surface-md && 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 "uma-surface-md" agent skill from https://github.com/Tai609/NebulaMat/tree/main/runtime/skills-bundle/uma-surface-md into .cursor/skills/uma-surface-md/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "uma-surface-md", 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/Tai609/NebulaMat.git --path runtime/skills-bundle/uma-surface-md

--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 Tai609/NebulaMat --skill uma-surface-md -a gemini-cli

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

GitHub CLI

$ gh skill install Tai609/NebulaMat uma-surface-md --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/Tai609/NebulaMat.git skills-src && mkdir -p .gemini/skills && cp -r skills-src/runtime/skills-bundle/uma-surface-md .gemini/skills/uma-surface-md && 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 "uma-surface-md" agent skill from https://github.com/Tai609/NebulaMat/tree/main/runtime/skills-bundle/uma-surface-md into .gemini/skills/uma-surface-md/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "uma-surface-md", 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 Tai609/NebulaMat uma-surface-md

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 Tai609/NebulaMat --skill uma-surface-md -a github-copilot

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

Manual copy

$ git clone --depth 1 https://github.com/Tai609/NebulaMat.git skills-src && mkdir -p .github/skills && cp -r skills-src/runtime/skills-bundle/uma-surface-md .github/skills/uma-surface-md && 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 "uma-surface-md" agent skill from https://github.com/Tai609/NebulaMat/tree/main/runtime/skills-bundle/uma-surface-md into .github/skills/uma-surface-md/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "uma-surface-md", 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 Tai609/NebulaMat --skill uma-surface-md -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 Tai609/NebulaMat uma-surface-md --agent opencode

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

Manual copy

$ git clone --depth 1 https://github.com/Tai609/NebulaMat.git skills-src && mkdir -p .opencode/skills && cp -r skills-src/runtime/skills-bundle/uma-surface-md .opencode/skills/uma-surface-md && 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 "uma-surface-md" agent skill from https://github.com/Tai609/NebulaMat/tree/main/runtime/skills-bundle/uma-surface-md into .opencode/skills/uma-surface-md/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "uma-surface-md", 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: uma-surface-md
GitHub stars: 100
Token cost: ~1.6k tokens
SKILL.md length: 685 words
Files: 3 (incl. references)
Skills in repo: 15
Repo updated: Sep 6, 2026
First seen: Oct 7, 2026
Licence: Custom licence

At a glance

Run and diagnose governed ASE plus fairchem UMA molecular dynamics on standardized adsorbed slabs, including NVT/NVE surface trajectories, pre-relaxation, periodic-boundary and collision checks…

Works in 9 steps: Require a governed input. Accept only… → Validate slab periodicity and geometry.… → Reject construction bugs before model… → …
A user asks for UMA/fairchem surface MD
SKILL.md covers Workflow, Protocol and Failure Reference and Tool Contract
Instructions only: no scripts, shell commands, URLs or credentials in SKILL.md

What it does

Uma Surface Md is an agent skill from Tai609/NebulaMat. Run and diagnose governed ASE plus fairchem UMA molecular dynamics on standardized adsorbed slabs, including NVT/NVE surface trajectories, pre-relaxation, periodic-boundary and collision checks, CUDA/backend triage, and auditable quality gates. Use when a user asks for UMA/fairchem surface MD, adsorbate dynamics, slab thermal screening, trajectory generation, or explains a UMA MD divergence, NaN/Inf, temperature explosion, or CUDA illegal-instruction failure.

Its SKILL.md is about 1.6k tokens, which your agent loads only when the skill is triggered. The skill folder holds 4 other files, including reference files (for example `agents/openai.yaml` and `references/failure-diagnostics.md`).

It sits in Testing & QA, covering Quality gates and Physical and earth sciences. It works with CUDA. The repository describes itself as: NebulaMat scientific materials research workbench.

When your agent uses it

A user asks for UMA/fairchem surface MD
Adsorbate dynamics
Slab thermal screening
Trajectory generation

Example prompts

“/uma-surface-md”

Workflow steps

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

Require a governed input. Accept only the adsorbed.extxyz artifact produced by standardize_uma_adsorption_structure_set, with a passing…
Validate slab periodicity and geometry. A surface slab must use pbc=(True, True, False); never replicate the vacuum direction and never…
Reject construction bugs before model loading. For OH/H2O, verify covalent bond lengths and angles, periodic-image separation, finite…
Use the governed runner. Prefer run_uma_surface_md or materials-uma-md. Its default protocol is model uma-s-1p2p1, task oc25, device cuda…
Use conservative dynamics for H/O systems. For a manual ASE run or a diagnostic rerun, start at 0.1-0.25 fs, then increase only after a…
Pre-relax before MD. Freeze the bottom slab layers, attach the UMA calculator, run LBFGS with fmax=0.05 eV/A for at most 200 steps, and…
Guard every trajectory. Record finite energy, kinetic energy, temperature, forces, coordinates, velocities, and minimum distances. Abort…
Isolate CUDA failures. Run each adsorbate in a fresh process. For diagnosis, set CUDA_LAUNCH_BLOCKING=1, run one forward with…
Audit and interpret. Require status=completed, all replicas complete, finite-value and collision gates passed, and a recorded…

What it can do on your machine

Read from SKILL.md and the folder at commit c906ed5. 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

Uma Surface Md loads about 1.6k tokens when it runs, and up to ~2.5k if it reads all its reference files. Until then it costs about 120 tokens; SKILL.md has 685 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it: ~120
When it runs · the whole SKILL.md, loaded when a task matches: ~1.6k
With references · SKILL.md plus every file in references/, read only if the agent opens them: ~2.5k

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

Its licence (Custom licence) doesn't allow us to republish the file, so here is its outline and opening line. It has 685 words (~1,557 tokens).

“Treat UMA surface MD as an initial ML-potential dynamics screen, not DFT-AIMD, free-energy sampling, or proof of thermal stability. Preserve standardized input lineage and stop on failed quality gates; never turn a trajectory into a mechanistic, activity, or experimental claim…”

— opening of SKILL.md by Tai609, Custom licence

name: uma-surface-md

Read the full SKILL.md on GitHub

Files

SKILL.md and 2 other files (references) in runtime/skills-bundle/uma-surface-md of Tai609/NebulaMat.

SKILL.md
agents/openai.yaml
references/failure-diagnostics.md

Open the folder on GitHubat commit c906ed5

Compare with similar skills

Uma Surface Md 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.

Uma Surface Md compared with similar skills
Skill	Stars	Used in	Tokens	Auto-check	Licence	Repo updated
Uma Surface Md this skillTai609/NebulaMat	100	—	~1.6k	Automated safety check: Pass	Custom licence	1 mo ago
Test Writing WorkflowiOfficeAI/AionUi	33k	1 repos	~1.2k	Automated safety check: Pass	Apache-2.0	1 mo ago
SoloPi AI Controlalipay/SoloPi	6.3k	—	~3.6k	Automated safety check: Pass	Apache-2.0	1 mo ago
Quality Scandiegosouzapw/OmniRoute	74k	—	~748	Automated safety check: Pass	MIT	today
Test GuardamElnagdy/guard-skills	1.3k	2 repos	~2.1k	Automated safety check: Pass	MIT	3 mo ago
Triage Sonarqubenetdata/netdata	81k	—	~2.8k	Automated safety check: Notes	GPL-3.0	today

Similar skills

Test Writing Workflow
iOfficeAI/AionUi
Sets the test-writing workflow for the repository: risk-first scenario lists, behavior-focused Vitest tests, a full run before each commit and a coverage target.
33k GitHub starsUsed in 1 repo~1.2k tokens
Testing & QAAuto-check passed
SoloPi AI Control
alipay/SoloPi
Drives Android devices through SoloPi's typed command line to record, replay and verify app behavior, with device pools and signed on-device decision models.
6.3k GitHub stars~3.6k tokensUpdated 1 mo ago
Testing & QAAuto-check passed
Quality Scan
diegosouzapw/OmniRoute
Runs a scoped, read-only quality scan on a repository candidate and reports exact evidence, failures and frozen debt, without treating a static scan as release acceptance.
74k GitHub stars~748 tokensUpdated today
Testing & QAAuto-check passed
Test Guard
amElnagdy/guard-skills
Reviews newly written or edited tests against nine rules that cut test bloat, such as mock-heavy checks and near-duplicate cases, before they are committed.
1.3k GitHub starsUsed in 2 repos~2.1k tokens
Testing & QAAuto-check passed
Triage Sonarqube
netdata/netdata
Inspect, review, or apply authorized triage decisions to SonarCloud issues and security hotspots; also review the Sonar helpers.
81k GitHub stars~2.8k tokensUpdated today
Testing & QAAuto-check: notes
Cherry Studio Regression Tests
CherryHQ/cherry-studio
Runs Cherry Studio's critical-path regression suite as deterministic Playwright E2E tests through a GitHub workflow on macOS and Windows runners.
52k GitHub stars~1.2k tokensUpdated today
Testing & QAAuto-check passed

More from Tai609/NebulaMat

All 15 skills in this repo

Image OCR
Tai609/NebulaMat
Read and transcribe the text visible inside an image file (PNG/JPG/JPEG/WebP/BMP/GIF) using the built-in Windows Media.Ocr OCR engine, with NO external credential or network required.
100 GitHub stars~1.1k tokensUpdated 1 mo ago
Auto-check passed
Nature Figure
Tai609/NebulaMat
Create, revise, audit, and export submission-grade scientific figures for Nature-family and other high-impact venues in Python (matplotlib/seaborn) or R (ggplot2/patchwork/ComplexHeatmap), including…
100 GitHub stars~1.9k tokensUpdated 1 mo ago
Auto-check passed
Aris Proof Orchestrator
Tai609/NebulaMat
Manage a stateful, run-directory-based proof project with Codex: continuation across runs, run-local source bookkeeping, manual GPT Pro handoff packages when a local attempt stalls, and an optional…
100 GitHub stars~5k tokensUpdated 1 mo ago
Auto-check passed
Electrochemical Adsorption Model Construction
Tai609/NebulaMat
Build provenance-controlled facet-specific electrochemical adsorption model cohorts from MatterGen candidates after MatterSim relaxation, including slab terminations, adsorption sites and…
100 GitHub stars~2.7k tokensUpdated 1 mo ago
Auto-check passed
Mattergen Structure Generation
Tai609/NebulaMat
Generate auditable candidate crystal structures with the project's pinned MatterGen runtime, including request construction, model/conditioning selection, GPU-cost bounds, workspace-safe output…
100 GitHub stars~1.9k tokensUpdated 1 mo ago
Auto-check passed
Mattersim Relaxation Screening
Tai609/NebulaMat
Run governed MatterSim-v1.0.0-5M energy, force, stress, and optional ASE FIRE relaxation for workspace-local standardized structures.
100 GitHub stars~1.6k tokensUpdated 1 mo ago
Auto-check passed

Works with

CUDA

Questions about Uma Surface Md

What does Uma Surface Md do?

Run and diagnose governed ASE plus fairchem UMA molecular dynamics on standardized adsorbed slabs, including NVT/NVE surface trajectories, pre-relaxation, periodic-boundary and collision checks…. Uma Surface Md is an agent skill from Tai609/NebulaMat. Run and diagnose governed ASE plus fairchem UMA molecular dynamics on standardized adsorbed slabs, including NVT/NVE surface trajectories, pre-relaxation, periodic-boundary and collision checks, CUDA/backend triage, and auditable quality gates.

When should I use Uma Surface Md?

Uma Surface Md fits situations like: A user asks for UMA/fairchem surface MD; adsorbate dynamics; slab thermal screening; trajectory generation.

How do I install Uma Surface Md in Claude Code?

Run `npx skills add Tai609/NebulaMat --skill uma-surface-md -a claude-code`. Or copy the skill folder (runtime/skills-bundle/uma-surface-md in Tai609/NebulaMat) into .claude/skills/uma-surface-md in your project. Claude Code loads it when a task matches its description.

How do I install Uma Surface Md in Codex?

Run `npx skills add Tai609/NebulaMat --skill uma-surface-md -a codex`. Or copy the skill folder (runtime/skills-bundle/uma-surface-md in Tai609/NebulaMat) into .agents/skills/uma-surface-md in your project. Codex loads it when a task matches its description.

Can I use Uma Surface Md 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 Tai609/NebulaMat --skill uma-surface-md -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/uma-surface-md, .gemini/skills/uma-surface-md, .github/skills/uma-surface-md and .opencode/skills/uma-surface-md in your project.

What does Uma Surface Md need to run?

SKILL.md names no scripts, command-line tools or credentials: Uma Surface Md is instructions for the agent only.

Does Uma Surface Md 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 Uma Surface Md 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 Uma Surface Md use?

Uma Surface Md has a licence file (the repository's licence) that doesn't match a standard licence. Read it on GitHub before reusing the skill.

How many tokens does Uma Surface Md use?

About 1.6k tokens (SKILL.md is roughly 6.2k 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 989 tokens, read only when the agent opens those files.

What are the alternatives to Uma Surface Md?

Skills that share tags, products or a category with Uma Surface Md: Test Writing Workflow (iOfficeAI/AionUi, 33k stars), SoloPi AI Control (alipay/SoloPi, 6.3k stars), Quality Scan (diegosouzapw/OmniRoute, 74k stars) and Test Guard (amElnagdy/guard-skills, 1.3k stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains Uma Surface Md?

Tai609 (a GitHub user) maintains it in Tai609/NebulaMat, which has 100 GitHub stars. The repository holds 15 skills in this directory. The repository was last updated on September 6, 2026.

Source: Tai609/NebulaMat on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.

Install Uma Surface Md

Facts

At a glance

What it does

When your agent uses it

Example prompts

Workflow steps

What it can do on your machine

Tool permissions

Runs code

Network

Credentials

Context cost

Safety

SKILL.md

Files

Compare with similar skills

Similar skills

More from Tai609/NebulaMat

Related

Questions about Uma Surface Md