Agent skill

Combinatorial Substitution

by Hello-QM in Hello-QM/catgo-LRG

A skill your agent uses when the user asks for systematic element substitution, combinatorial materials screening, high-throughput composition search, or multi-site replacement across different…

AGPL-3.0Auto-check passed

Install Combinatorial Substitution

skills CLI
$ npx skills add Hello-QM/catgo-LRG --skill combinatorial-substitution -a claude-code

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

GitHub CLI
$ gh skill install Hello-QM/catgo-LRG combinatorial-substitution --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/.claude/skills/structure-substitution .claude/skills/combinatorial-substitution && 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
combinatorial-substitution
GitHub stars
205
Token cost
~1.3k tokens
SKILL.md length
497 words
Files
1
Skills in repo
75
Repo updated
First seen
Licence
AGPL-3.0

At a glance

A skill your agent uses when the user asks for systematic element substitution, combinatorial materials screening, high-throughput composition search, or multi-site replacement across different…

  • Works in 4 steps: Fetch a reference perovskite → Identify site indices → Generate all A/B combinations → …
  • The user asks for systematic element substitution
  • SKILL.md covers Overview, MCP Tool: catgo_substitution, Combinatorics and Complete Workflow: Perovskite…, plus 2 more sections
  • Instructions only: no scripts, shell commands, URLs or credentials in SKILL.md

What it does

Combinatorial Substitution is an agent skill from Hello-QM/catgo-LRG. Use when the user asks for systematic element substitution, combinatorial materials screening, high-throughput composition search, or multi-site replacement across different element groups.

Its SKILL.md is about 1.3k tokens, which your agent loads only when the skill is triggered. It is a single SKILL.md file with no bundled scripts.

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 for systematic element substitution
  • Combinatorial materials screening
  • High-throughput composition search
  • Multi-site replacement across different element groups

Example prompts

  • “/combinatorial-substitution”

Workflow steps

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

  1. Fetch a reference perovskite
  2. Identify site indices
  3. Generate all A/B combinations
  4. Screen with MLP, then refine with DFT

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

Combinatorial Substitution loads about 1.3k tokens when it runs. Until then it costs about 54 tokens; SKILL.md has 497 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it
~54
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). 497 words, ~1,348 tokens.

Download SKILL.mdSave it as .claude/skills/combinatorial-substitution/SKILL.md (or your agent's skills folder).
name
combinatorial-substitution
description
Use when the user asks for systematic element substitution, combinatorial materials screening, high-throughput composition search, or multi-site replacement across different element groups.

Combinatorial Substitution

Overview

Combinatorial substitution systematically replaces elements at specified sites across multiple groups, generating all combinations for materials discovery. Unlike simple doping (which replaces one element with another), this tool creates the full Cartesian product of substitutions across groups.

Common applications:

  • High-entropy alloy screening: test multiple elements at different sublattices
  • Perovskite composition search: vary A-site and B-site cations independently
  • Catalyst optimization: systematic dopant combinations
  • Battery cathode design: screen transition metals at different Wyckoff sites

MCP Tool: catgo_substitution

json
{"tool": "catgo_substitution", "arguments": {
  "structure": "<current structure dict>",
  "groups": [
    {
      "target_indices": [0, 4, 8],
      "replacement_elements": ["Ti", "Zr", "Hf"]
    },
    {
      "target_indices": [1, 5, 9],
      "replacement_elements": ["Mn", "Fe", "Co"]
    }
  ],
  "max_structures": 500
}}
ParameterDescriptionDefault
structureInput structure dict(required)
groupsArray of substitution groups(required)
groups[].target_indicesSite indices to substitute in this group(required)
groups[].replacement_elementsElements to try at these sites(required)
max_structuresSafety cap on total combinations500

Total structures = product of replacement options per group. For the example above: 3 (group 1) x 3 (group 2) = 9 structures.

Router: /build/substitution (POST)

Combinatorics

The tool generates the Cartesian product across groups. Within each group, all target sites receive the same element for a given combination.

GroupsElements per GroupTotal Structures
1 group, 5 elements55
2 groups, 3 each3 x 39
2 groups, 5 each5 x 525
3 groups, 4 each4 x 4 x 464
3 groups, 6 each6 x 6 x 6216

The max_structures cap (default 500) prevents accidental generation of extremely large sets.

Complete Workflow: Perovskite ABO3 Screening

Step 1: Fetch a reference perovskite
json
{"tool": "catgo_fetch", "arguments": {
  "action": "crystal", "formula": "SrTiO3", "source": "mp"
}}
Step 2: Identify site indices
json
{"tool": "catgo_view", "arguments": {"action": "get_state"}}

Identify A-site (Sr) and B-site (Ti) atom indices from the structure.

Step 3: Generate all A/B combinations
json
{"tool": "catgo_substitution", "arguments": {
  "groups": [
    {
      "target_indices": [0],
      "replacement_elements": ["Sr", "Ba", "Ca", "La"]
    },
    {
      "target_indices": [1],
      "replacement_elements": ["Ti", "Zr", "Hf", "Mn", "Fe"]
    }
  ]
}}

This generates 4 x 5 = 20 perovskite compositions: SrTiO3, SrZrO3, BaTiO3, LaFeO3, etc.

Step 4: Screen with MLP, then refine with DFT

For 20 structures, use a two-stage workflow:

json
{"tool": "catgo_workflow_engine", "arguments": {
  "action": "create", "params": {"name": "Perovskite ABO3 screening"}
}}

First relax all candidates with an ML potential:

json
{"tool": "catgo_workflow_engine", "arguments": {
  "action": "add_task", "params": {
    "workflow_id": "<wf_id>",
    "task_type": "geo_opt",
    "params": {"software": "mlp", "mlp_model": "mace",
               "system_name": "perovskite-screen-mlp"}
  }
}}

Then run DFT on the most promising candidates.

Show full SKILL.md (196 more words)Show less

Difference from Doping (catgo_structure action: doping)

FeatureDopingCombinatorial Substitution
PurposeReplace one element with anotherScreen multiple compositions
Output1 structure (or enumerated configs)N structures (Cartesian product)
GroupsSingle host/dopant pairMultiple independent groups
MCP toolcatgo_structure(action: doping)catgo_substitution
Use caseTargeted modificationSystematic screening

Use doping when you want to modify a single structure. Use substitution when you want to generate a library of compositions.

Common Pitfalls

  1. Always check site indices with catgo_view before substituting. Atom indices depend on the specific structure and may change after supercell expansion or slab generation.
  2. The Cartesian product can grow rapidly. 4 groups x 6 elements each = 1296 structures. Use max_structures to cap output.
  3. All sites within a group receive the same element in each combination. If you need different elements at different sites within the same group, split them into separate groups.
  4. Generated structures are unrelaxed. The substituted atoms keep the original positions. Always run geometry optimization before comparing energies.
  5. For transition metal substitutions in oxides, enable spin polarization (ISPIN=2) and consider DFT+U corrections.
  6. Charge neutrality is not enforced. Substituting Ca2+ for La3+ requires compensating defects or a charged cell.

© Hello-QM, AGPL-3.0. 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 .claude/skills/structure-substitution of Hello-QM/catgo-LRG.

Open the folder on GitHubat commit fd6291b

Compare with similar skills

Combinatorial Substitution 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.

Combinatorial Substitution compared with similar skills
SkillStarsUsed inTokensAuto-checkLicenceRepo updated
Combinatorial Substitution this skillHello-QM/catgo-LRG205—~1.3kAutomated safety check: PassAGPL-3.0
Decorative Elementsthedaviddias/Front-End-Checklist74k—~672Automated safety check: PassMIT
Scaffold Elementremotion-dev/remotion63k—~202Automated safety check: PassCustom licence
Investor Materialsaffaan-m/ECC276k3 repos~268Automated safety check: PassMIT
Material Designsickn33/agentic-awesome-skills47k1 repos~2.6kAutomated safety check: PassMIT
Materialbergside/awesome-design-skills3.1k1 repos~919Automated safety check: PassMIT

Similar skills

  • Decorative Elements

    thedaviddias/Front-End-Checklist

    A skill your agent uses when reviewing rendered HTML, interactive components, or design-system patterns related to Hide decorative elements from assistive technology.

    74k GitHub stars~672 tokensUpdated 3 days ago
    Frontend & DesignAuto-check passed
  • Scaffold Element

    remotion-dev/remotion

    Official

    Scaffold a new Remotion Element for development in the docs Remotion Studio.

    63k GitHub stars~202 tokensUpdated today
    Media & CreativeAuto-check passed
  • Investor Materials

    affaan-m/ECC

    创建和更新宣传文稿、一页简介、投资者备忘录、加速器申请、财务模型和融资材料。当用户需要面向投资者的文件、预测、资金用途表、里程碑计划或必须在多个融资资产中保持内部一致性的材料时使用。

    276k GitHub starsUsed in 3 repos~268 tokens
    Auto-check passed
  • Material Design

    sickn33/agentic-awesome-skills

    Web and App implementation guide for Material Design. An agent skill from sickn33/agentic-awesome-skills.

    47k GitHub starsUsed in 1 repo~2.6k tokens
    MobileAuto-check passed
  • Material

    bergside/awesome-design-skills

    Google's Material Design with layered surfaces, dynamic theming, built-in motion, and responsive cross-platform patterns.

    3.1k GitHub starsUsed in 1 repo~919 tokens
    Frontend & DesignAuto-check passed
  • Html5 Semantic Elements

    thedaviddias/Front-End-Checklist

    A skill your agent uses when reviewing templates, rendered HTML, or shared components related to Use semantic HTML elements.

    74k GitHub stars~449 tokensUpdated 3 days ago
    Auto-check passed

More from Hello-QM/catgo-LRG

All 75 skills in this repo
  • Campaign Md Orchestration

    Hello-QM/catgo-LRG

    Drive a file-first, agent-in-the-loop computational campaign via a folder + markdown tree (no DB).

    205 GitHub stars~1.6k tokensUpdated 17 days ago
    Auto-check passed
  • Catgo Gibbs Pipeline

    Hello-QM/catgo-LRG

    Compute adsorption/reaction Gibbs free energies, free-energy diagrams, and electrochemical overpotentials (HER/ORR/OER/CO2RR/NRR) with VASP.

    205 GitHub stars~669 tokensUpdated 17 days ago
    Auto-check passed
  • Abinit

    Hello-QM/catgo-LRG

    Generate and manage ABINIT DFT calculations. An agent skill from Hello-QM/catgo-LRG.

    205 GitHub stars~963 tokensUpdated 17 days ago
    Auto-check passed
  • Adsorbate Placement

    Hello-QM/catgo-LRG

    A skill your agent uses when the user asks to place an adsorbate molecule on a surface, find adsorption sites, or set up a surface+adsorbate model for DFT.

    205 GitHub stars~3k tokensUpdated 17 days ago
    Auto-check passed
  • Adsorption Energy

    Hello-QM/catgo-LRG

    A skill your agent uses when the user asks for adsorption energy, binding energy, or wants to compare how strongly a molecule binds to a surface.

    205 GitHub stars~1.4k tokensUpdated 17 days ago
    Auto-check passed
  • Analysis Router

    Hello-QM/catgo-LRG

    A skill your agent uses when the user asks to analyze computational results: Gibbs free energy, OER/HER/CO2RR overpotentials, adsorption energy, convergence tests, DOS/d-band analysis, or Bader…

    205 GitHub stars~869 tokensUpdated 17 days ago
    Auto-check passed

Questions about Combinatorial Substitution

What does Combinatorial Substitution do?

A skill your agent uses when the user asks for systematic element substitution, combinatorial materials screening, high-throughput composition search, or multi-site replacement across different…. Combinatorial Substitution is an agent skill from Hello-QM/catgo-LRG. Use when the user asks for systematic element substitution, combinatorial materials screening, high-throughput composition search, or multi-site replacement across different element groups.

When should I use Combinatorial Substitution?

Combinatorial Substitution fits situations like: the user asks for systematic element substitution; combinatorial materials screening; high-throughput composition search; multi-site replacement across different element groups.

How do I install Combinatorial Substitution in Claude Code?

Run `npx skills add Hello-QM/catgo-LRG --skill combinatorial-substitution -a claude-code`. Or copy the skill folder (.claude/skills/structure-substitution in Hello-QM/catgo-LRG) into .claude/skills/combinatorial-substitution in your project. Claude Code loads it when a task matches its description.

How do I install Combinatorial Substitution in Codex?

Run `npx skills add Hello-QM/catgo-LRG --skill combinatorial-substitution -a codex`. Or copy the skill folder (.claude/skills/structure-substitution in Hello-QM/catgo-LRG) into .agents/skills/combinatorial-substitution in your project. Codex loads it when a task matches its description.

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

What does Combinatorial Substitution need to run?

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

Does Combinatorial Substitution 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 Combinatorial Substitution 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 Combinatorial Substitution use?

Combinatorial Substitution 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 Combinatorial Substitution use?

About 1.3k tokens (SKILL.md is roughly 5.4k 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 Combinatorial Substitution?

Skills that share tags, products or a category with Combinatorial Substitution: Decorative Elements (thedaviddias/Front-End-Checklist, 74k stars), Scaffold Element (remotion-dev/remotion, 63k stars), Investor Materials (affaan-m/ECC, 276k stars) and Material Design (sickn33/agentic-awesome-skills, 47k stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains Combinatorial Substitution?

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.