Agent skill

Mace Ni Benchmark

AGPL-3.0Auto-check passedData & Analytics

Install Mace Ni Benchmark

skills CLI

$ npx skills add Hello-QM/catgo-LRG --skill mace-ni-benchmark -a claude-code

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

GitHub CLI

$ gh skill install Hello-QM/catgo-LRG mace-ni-benchmark --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/Hello-QM/catgo-LRG.git skills-src && mkdir -p .claude/skills && cp -r skills-src/server/catgo/workflow/skills/analysis/mace_ni_benchmark .claude/skills/mace-ni-benchmark && 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 "mace-ni-benchmark" agent skill from https://github.com/Hello-QM/catgo-LRG/tree/main/server/catgo/workflow/skills/analysis/mace_ni_benchmark into .claude/skills/mace-ni-benchmark/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "mace-ni-benchmark", 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/Hello-QM/catgo-LRG/tree/main/server/catgo/workflow/skills/analysis/mace_ni_benchmark

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 Hello-QM/catgo-LRG --skill mace-ni-benchmark -a codex

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

GitHub CLI

$ gh skill install Hello-QM/catgo-LRG mace-ni-benchmark --agent codex

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

Manual copy

$ git clone --depth 1 https://github.com/Hello-QM/catgo-LRG.git skills-src && mkdir -p .agents/skills && cp -r skills-src/server/catgo/workflow/skills/analysis/mace_ni_benchmark .agents/skills/mace-ni-benchmark && 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 "mace-ni-benchmark" agent skill from https://github.com/Hello-QM/catgo-LRG/tree/main/server/catgo/workflow/skills/analysis/mace_ni_benchmark into .agents/skills/mace-ni-benchmark/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "mace-ni-benchmark", 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 Hello-QM/catgo-LRG --skill mace-ni-benchmark -a cursor

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

GitHub CLI

$ gh skill install Hello-QM/catgo-LRG mace-ni-benchmark --agent cursor

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

Manual copy

$ git clone --depth 1 https://github.com/Hello-QM/catgo-LRG.git skills-src && mkdir -p .cursor/skills && cp -r skills-src/server/catgo/workflow/skills/analysis/mace_ni_benchmark .cursor/skills/mace-ni-benchmark && 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 "mace-ni-benchmark" agent skill from https://github.com/Hello-QM/catgo-LRG/tree/main/server/catgo/workflow/skills/analysis/mace_ni_benchmark into .cursor/skills/mace-ni-benchmark/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "mace-ni-benchmark", 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/Hello-QM/catgo-LRG.git --path server/catgo/workflow/skills/analysis/mace_ni_benchmark

--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 Hello-QM/catgo-LRG --skill mace-ni-benchmark -a gemini-cli

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

GitHub CLI

$ gh skill install Hello-QM/catgo-LRG mace-ni-benchmark --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/Hello-QM/catgo-LRG.git skills-src && mkdir -p .gemini/skills && cp -r skills-src/server/catgo/workflow/skills/analysis/mace_ni_benchmark .gemini/skills/mace-ni-benchmark && 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 "mace-ni-benchmark" agent skill from https://github.com/Hello-QM/catgo-LRG/tree/main/server/catgo/workflow/skills/analysis/mace_ni_benchmark into .gemini/skills/mace-ni-benchmark/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "mace-ni-benchmark", 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 Hello-QM/catgo-LRG mace-ni-benchmark

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 Hello-QM/catgo-LRG --skill mace-ni-benchmark -a github-copilot

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

Manual copy

$ git clone --depth 1 https://github.com/Hello-QM/catgo-LRG.git skills-src && mkdir -p .github/skills && cp -r skills-src/server/catgo/workflow/skills/analysis/mace_ni_benchmark .github/skills/mace-ni-benchmark && 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 "mace-ni-benchmark" agent skill from https://github.com/Hello-QM/catgo-LRG/tree/main/server/catgo/workflow/skills/analysis/mace_ni_benchmark into .github/skills/mace-ni-benchmark/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "mace-ni-benchmark", 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 Hello-QM/catgo-LRG --skill mace-ni-benchmark -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 Hello-QM/catgo-LRG mace-ni-benchmark --agent opencode

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

Manual copy

$ git clone --depth 1 https://github.com/Hello-QM/catgo-LRG.git skills-src && mkdir -p .opencode/skills && cp -r skills-src/server/catgo/workflow/skills/analysis/mace_ni_benchmark .opencode/skills/mace-ni-benchmark && 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 "mace-ni-benchmark" agent skill from https://github.com/Hello-QM/catgo-LRG/tree/main/server/catgo/workflow/skills/analysis/mace_ni_benchmark into .opencode/skills/mace-ni-benchmark/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "mace-ni-benchmark", 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: mace-ni-benchmark
GitHub stars: 205
Token cost: ~1.3k tokens
SKILL.md length: 605 words
Files: 2
Skills in repo: 75
Repo updated: Sep 22, 2026
First seen: Oct 7, 2026
Licence: AGPL-3.0

At a glance

Works in 4 steps: Ni bulk (FCC) — fcc Ni, a ≈ 3.524 Å… → H₂ molecule — two H atoms ~0.74 Å apart… → CO* on Ni(111) — NEB reactant (CO… → …
The user asks to reproduce the Kreitz 2021 Ni surface benchmark
SKILL.md covers When to invoke, The six target quantities, How to invoke and Expected deviations (MACE-MP-0…, plus 3 more sections
Instructions only: no scripts, shell commands, URLs or credentials in SKILL.md

What it does

Mace Ni Benchmark is an agent skill from Hello-QM/catgo-LRG. Use when the user asks to reproduce the Kreitz 2021 Ni surface benchmark, run the MACE Ni benchmark, or compare a machine-learning potential (MACE, CHGNet, M3GNet) against DFT-D3 surface-science references. Invokes the "UMA Catalysis Tutorial" preset (template key umacatalysisscreening).

Its SKILL.md is about 1.3k tokens, which your agent loads only when the skill is triggered. The skill folder holds 1 other file (for example `README.md`).

It sits in Data & Analytics, covering Machine learning. The repository describes itself as: AI-driven workbench for computational materials science — interactive 3D structure viewer, natural-language CatBot assistant, visual DAG workflow engine, HPC job submission… The licence is AGPL-3.0.

When your agent uses it

The user asks to reproduce the Kreitz 2021 Ni surface benchmark
Run the MACE Ni benchmark
Compare a machine-learning potential (MACE
M3GNet) against DFT-D3 surface-science references

Example prompts

“UMA Catalysis Tutorial”
“/mace-ni-benchmark”

Workflow steps

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

Ni bulk (FCC) — fcc Ni, a ≈ 3.524 Å (Materials Project mp-23)
H₂ molecule — two H atoms ~0.74 Å apart in a 20 Å box
CO* on Ni(111) — NEB reactant (CO adsorbed on a 3×3 Ni(111) slab)
C* + O* on Ni(111) — NEB product (C and O separately adsorbed)

What it can do on your machine

Read from SKILL.md and the folder at commit fd6291b. 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 (its code samples are json).
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

Mace Ni Benchmark loads about 1.3k tokens when it runs. Until then it costs about 78 tokens; SKILL.md has 605 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it: ~78
When it runs · the whole SKILL.md, loaded when a task matches: ~1.3k

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 Hello-QM/catgo-LRG at commit fd6291b, republished under its AGPL-3.0 licence (© Hello-QM). 605 words, ~1,271 tokens.

Download SKILL.mdSave it as .claude/skills/mace-ni-benchmark/SKILL.md (or your agent's skills folder). This skill also uses 1 other file; get the full folder from GitHub.

name: mace-ni-benchmark
description: Use when the user asks to reproduce the Kreitz 2021 Ni surface benchmark, run the MACE Ni benchmark, or compare a machine-learning potential (MACE, CHGNet, M3GNet) against DFT-D3 surface-science references. Invokes the "UMA Catalysis Tutorial" preset (template key `uma_catalysis_screening`).

MACE Ni Benchmark — Kreitz 2021 Reproduction

Reproduces six Ni surface DFT-D3 target quantities end-to-end with MACE-MP-0, on a single Ni bulk source, in one workflow.

When to invoke

Trigger phrases (any of):

"reproduce Kreitz 2021 Ni benchmark"
"run the MACE Ni benchmark"
"benchmark MACE against DFT-D3 for Ni"
"validate MLP on Ni surfaces"

Also invoke when the user asks to compute multiple of the six quantities below for Ni at once — one preset is cheaper than six separate workflows.

The six target quantities

#	Quantity	Source node	Result key
1	γ(111), γ(100), γ(110), γ(211)	`surface_energy`	`per_facet[hkl].gamma_J_per_m2`
2	Wulff facet area fractions	`wulff_construction`	`area_fractions[hkl]`
3	H adsorption energy on Ni(111) FCC hollow (ZPE-corrected)	`adsorption_energy`	`E_ads_ZPE_eV`
4	Coverage slope ∂E_ads/∂θ (1,2,4,8,16 H on 4×4 Ni(111))	`coverage_analysis`	`fit.slope`
5	CO* ↔ C* + O* NEB barrier	`ts_search` (`mlp_neb`)	`activation_barrier_kcal_mol`
6	TS imaginary-mode frequency	`freq` (`mlp_vibrations`)	`dominant_imag_freq_cm` (with `is_valid_ts` flag)

All six are viewable side-by-side in the project dashboard's "Benchmark" tab once any workflow derived from uma_catalysis_screening (or with a matching name) is present in the project.

How to invoke

Option A — UI (recommended)

In the Workflow Editor, click New from preset → Surface Catalysis → UMA Catalysis Tutorial. A 26-node DAG loads. The template is defined in src/lib/workflow/graph-model.ts::uma_catalysis_screening.

After it loads, the user must load structures into 4 input nodes:

Ni bulk (FCC) — fcc Ni, a ≈ 3.524 Å (Materials Project mp-23)
H₂ molecule — two H atoms ~0.74 Å apart in a 20 Å box
CO* on Ni(111) — NEB reactant (CO adsorbed on a 3×3 Ni(111) slab)
C* + O* on Ni(111) — NEB product (C and O separately adsorbed)

Option B — Manual DAG build (not recommended)

Rebuilding the 26-node DAG by hand costs ~2x the effort and always drifts from the defaults tested against MACE-MP-0 medium. Only do this if the user needs a custom variant (e.g. different slab supercell, or a non-cubic/non-Ni system).

Show full SKILL.md (297 more words)Show less

Expected deviations (MACE-MP-0 vs RPBE-D3)

Quantity	Typical \|CatGo − Kreitz\|	Notes
γ(hkl)	~0.1 J/m²	γ(111) tends to be ~0.05 J/m² higher
Wulff fractions	< 0.05	Dominant (111) facet rank is preserved
E_ads(H, ZPE)	~0.1 eV	MACE-MP-0 slightly overbinds H
Coverage slope	~0.03 eV/ML	Sign (repulsive) should match
NEB barrier	~0.2 eV	Largest single deviation
ν_imag	~50 cm⁻¹	Sign must be negative (imaginary)

If deviations are much larger than these ranges, check:

Did the bulk opt converge? (fmax < 0.05 eV/Å with relax_cell: true)
Did NEB converge to the expected CI image? (neb_converged: true)
Is is_valid_ts: true on the freq step at the TS? (Exactly one imaginary mode above the 20 cm⁻¹ trivial-mode filter.)

Defaults worth preserving

software: mlp, model: MACE, device: auto → uses MACE-MP-0 medium via the default mace_mp("medium", default_dtype="float64") path. Checkpoint auto-downloads to ~/.cache/mace/ on first run (~200 MB, ~2 min).
Vibrations freeze the Ni slab and vibrate the adsorbate only (freeze_mode: layers, freeze_layers: 2, freeze_invert: false) → ~20× cheaper freqs without losing ZPE accuracy. Note: freeze_invert inverts the set of atoms ASE displaces, so false here means the frozen set (bottom 2 Ni layers) is actually frozen and everything else vibrates — the standard catalysis setup. true would vibrate only the bottom 2 Ni layers (wrong for ZPE).
NEB: 8 images, climb: true, FIRE optimizer, fmax: 0.05 eV/Å.
Coverage sweep: 1,2,4,8,16 H on 4×4 hollow-site filling.

Reproducibility

Every MLP-dispatched step writes metadata.json (captured via the C1 footer in server/workflow/engines/mlp.py) into result_json.metadata:

json

{
  "mace_torch_version": "0.3.15",
  "torch_version": "2.10.0",
  "mace_model": "mace-mp-0-medium",
  "model_sha256": null,
  "device": "cuda:0" | "cpu",
  "gpu_name": "...",
  "wall_time_s": 12.3,
  "host": "...",
  "timestamp": "..."
}

The Benchmark tab surfaces the latest MLP step's metadata panel. Users export CSV from the same tab to share the full 6-row table with the metadata footer included as RFC-4180-escaped comment lines.

structure/slab/ — slab generation internals
adsorption/ — the general E_ads formula this preset specializes
oer/, her/ — if the user wants surface reactivity trends on top of γ(hkl)

Files

SKILL.md and 1 other file in server/catgo/workflow/skills/analysis/mace_ni_benchmark of Hello-QM/catgo-LRG.

SKILL.md
README.md

Open the folder on GitHubat commit fd6291b

Compare with similar skills

Mace Ni Benchmark 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.

Mace Ni Benchmark compared with similar skills
Skill	Stars	Used in	Tokens	Auto-check	Licence	Repo updated
Mace Ni Benchmark this skillHello-QM/catgo-LRG	205	—	~1.3k	Automated safety check: Pass	AGPL-3.0	18 days ago
Scikit LearnzLanqing/codex-claude-academic-skills	4.7k	16 repos	~3.9k	Automated safety check: Pass	BSD-3-Clause	4 mo ago
Agentic Kaggle WorkflowFrankS-IntelLab/agentic-kaggle-skill	188	—	~4k	Automated safety check: Pass	MIT	3 mo ago
Senior Data ScientistRaidriar7170/hermes-skilleval	125	5 repos	~1.4k	Automated safety check: Pass	MIT	14 days ago
Geomlitalo-goncalves/geoML	109	—	~4.9k	Automated safety check: Pass	GPL-3.0	today
QuantMind Training Config Generatorqusong0627/QuantMind	1.7k	—	~1.5k	Automated safety check: Pass	AGPL-3.0	today

Similar skills

Scikit Learn
zLanqing/codex-claude-academic-skills
Machine learning in Python with scikit-learn. An agent skill from zLanqing/codex-claude-academic-skills.
4.7k GitHub starsUsed in 16 repos~3.9k tokens
Data & AnalyticsAuto-check passed
Agentic Kaggle Workflow
FrankS-IntelLab/agentic-kaggle-skill
Takes a Kaggle competition from rules and validation design through baselines, ensembling and notebook architecture to a scored submission.
188 GitHub stars~4k tokensUpdated 3 mo ago
Data & AnalyticsAuto-check passed
Senior Data Scientist
Raidriar7170/hermes-skilleval
World-class data science skill for statistical modeling, experimentation, causal inference, and advanced analytics.
125 GitHub starsUsed in 5 repos~1.4k tokens
Data & AnalyticsAuto-check passed
Geoml
italo-goncalves/geoML
Working knowledge of the geoML Python package (github.com/italo-goncalves/geoML): variational Gaussian processes for spatial data, implicit geological modelling, block models, drillhole data…
109 GitHub stars~4.9k tokensUpdated today
Data & AnalyticsAuto-check passed
QuantMind Training Config Generator
qusong0627/QuantMind
Turns a plain-language model training request into a validated QuantMind training config file that can be imported from the Model Training page.
1.7k GitHub stars~1.5k tokensUpdated today
Data & AnalyticsAuto-check passed
Retention Analysis
liangdabiao/claude-data-analysis-ultra-main
Analyze user retention and churn using survival analysis, cohort analysis, and machine learning.
290 GitHub stars~1.3k tokensUpdated 5 mo ago
Data & AnalyticsAuto-check: notes

Questions about Mace Ni Benchmark

What does Mace Ni Benchmark do?

A skill your agent uses when the user asks to reproduce the Kreitz 2021 Ni surface benchmark, run the MACE Ni benchmark, or compare a machine-learning potential (MACE, CHGNet, M3GNet) against DFT-D3…. Mace Ni Benchmark is an agent skill from Hello-QM/catgo-LRG. Use when the user asks to reproduce the Kreitz 2021 Ni surface benchmark, run the MACE Ni benchmark, or compare a machine-learning potential (MACE, CHGNet, M3GNet) against DFT-D3 surface-science references.

When should I use Mace Ni Benchmark?

Mace Ni Benchmark fits situations like: the user asks to reproduce the Kreitz 2021 Ni surface benchmark; run the MACE Ni benchmark; compare a machine-learning potential (MACE; M3GNet) against DFT-D3 surface-science references.

How do I install Mace Ni Benchmark in Claude Code?

Run `npx skills add Hello-QM/catgo-LRG --skill mace-ni-benchmark -a claude-code`. Or copy the skill folder (server/catgo/workflow/skills/analysis/mace_ni_benchmark in Hello-QM/catgo-LRG) into .claude/skills/mace-ni-benchmark in your project. Claude Code loads it when a task matches its description.

How do I install Mace Ni Benchmark in Codex?

Run `npx skills add Hello-QM/catgo-LRG --skill mace-ni-benchmark -a codex`. Or copy the skill folder (server/catgo/workflow/skills/analysis/mace_ni_benchmark in Hello-QM/catgo-LRG) into .agents/skills/mace-ni-benchmark in your project. Codex loads it when a task matches its description.

Can I use Mace Ni Benchmark 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 Hello-QM/catgo-LRG --skill mace-ni-benchmark -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/mace-ni-benchmark, .gemini/skills/mace-ni-benchmark, .github/skills/mace-ni-benchmark and .opencode/skills/mace-ni-benchmark in your project.

What does Mace Ni Benchmark need to run?

SKILL.md names no scripts, command-line tools or credentials: Mace Ni Benchmark is instructions for the agent only.

Does Mace Ni Benchmark 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 Mace Ni Benchmark 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 Mace Ni Benchmark use?

Mace Ni Benchmark is published under the AGPL-3.0 licence (the repository's licence). It allows redistribution, so the full SKILL.md is shown on this page.

How many tokens does Mace Ni Benchmark use?

About 1.3k tokens (SKILL.md is roughly 5.1k 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 Mace Ni Benchmark?

Skills that share tags, products or a category with Mace Ni Benchmark: Scikit Learn (zLanqing/codex-claude-academic-skills, 4.7k stars), Agentic Kaggle Workflow (FrankS-IntelLab/agentic-kaggle-skill, 188 stars), Senior Data Scientist (Raidriar7170/hermes-skilleval, 125 stars) and Geoml (italo-goncalves/geoML, 109 stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains Mace Ni Benchmark?

Hello-QM (a GitHub user) maintains it in Hello-QM/catgo-LRG, which has 205 GitHub stars. The repository holds 75 skills in this directory. The repository was last updated on September 22, 2026.

Source: Hello-QM/catgo-LRG on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.

Install Mace Ni Benchmark

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

MACE Ni Benchmark — Kreitz 2021 Reproduction

When to invoke

The six target quantities

How to invoke

Option A — UI (recommended)

Option B — Manual DAG build (not recommended)

Expected deviations (MACE-MP-0 vs RPBE-D3)

Defaults worth preserving

Reproducibility

Related skills

Files

Compare with similar skills

Similar skills

More from Hello-QM/catgo-LRG

Related

Questions about Mace Ni Benchmark