Agent skill

Vasp Dos

Density of states (DOS) workflow in VASP. An agent skill from Hello-QM/catgo-LRG.

AGPL-3.0Auto-check passed

Install Vasp Dos

skills CLI

$ npx skills add Hello-QM/catgo-LRG --skill vasp-dos -a claude-code

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

GitHub CLI

$ gh skill install Hello-QM/catgo-LRG vasp-dos --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/vasp-dos .claude/skills/vasp-dos && 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 "vasp-dos" agent skill from https://github.com/Hello-QM/catgo-LRG/tree/main/.claude/skills/vasp-dos into .claude/skills/vasp-dos/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "vasp-dos", 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/.claude/skills/vasp-dos

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 vasp-dos -a codex

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

GitHub CLI

$ gh skill install Hello-QM/catgo-LRG vasp-dos --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/.claude/skills/vasp-dos .agents/skills/vasp-dos && 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 "vasp-dos" agent skill from https://github.com/Hello-QM/catgo-LRG/tree/main/.claude/skills/vasp-dos into .agents/skills/vasp-dos/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "vasp-dos", 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 vasp-dos -a cursor

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

GitHub CLI

$ gh skill install Hello-QM/catgo-LRG vasp-dos --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/.claude/skills/vasp-dos .cursor/skills/vasp-dos && 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 "vasp-dos" agent skill from https://github.com/Hello-QM/catgo-LRG/tree/main/.claude/skills/vasp-dos into .cursor/skills/vasp-dos/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "vasp-dos", 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 .claude/skills/vasp-dos

--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 vasp-dos -a gemini-cli

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

GitHub CLI

$ gh skill install Hello-QM/catgo-LRG vasp-dos --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/.claude/skills/vasp-dos .gemini/skills/vasp-dos && 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 "vasp-dos" agent skill from https://github.com/Hello-QM/catgo-LRG/tree/main/.claude/skills/vasp-dos into .gemini/skills/vasp-dos/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "vasp-dos", 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 vasp-dos

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 vasp-dos -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/.claude/skills/vasp-dos .github/skills/vasp-dos && 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 "vasp-dos" agent skill from https://github.com/Hello-QM/catgo-LRG/tree/main/.claude/skills/vasp-dos into .github/skills/vasp-dos/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "vasp-dos", 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 vasp-dos -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 vasp-dos --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/.claude/skills/vasp-dos .opencode/skills/vasp-dos && 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 "vasp-dos" agent skill from https://github.com/Hello-QM/catgo-LRG/tree/main/.claude/skills/vasp-dos into .opencode/skills/vasp-dos/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "vasp-dos", 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: vasp-dos
GitHub stars: 205
Token cost: ~1.4k tokens
SKILL.md length: 370 words
Files: 1
Skills in repo: 75
Repo updated: Sep 22, 2026
First seen: Oct 7, 2026
Licence: AGPL-3.0

At a glance

Density of states (DOS) workflow in VASP. An agent skill from Hello-QM/catgo-LRG.

Works in 3 steps: geo_opt — relax the structure to… → single_point — SCF with ISMEAR=-5… → dos_analysis — extract d-band center,…
SKILL.md covers Why Three Steps?, Full DOS Workflow, MCP Workflow and Key DOS Parameters, plus 7 more sections
Instructions only: no scripts, shell commands, URLs or credentials in SKILL.md

What it does

Vasp Dos is an agent skill from Hello-QM/catgo-LRG. Density of states (DOS) workflow in VASP. Three-step process for accurate total and projected DOS, d-band center analysis.

Its SKILL.md is about 1.4k 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.

Example prompts

“/vasp-dos”

Requirements

Python 3

Workflow steps

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

geo_opt — relax the structure to equilibrium
single_point — SCF with ISMEAR=-5 (tetrahedron method) and high NEDOS for accurate DOS
dos_analysis — extract d-band center, orbital projections, and plot data

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 python).
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

Vasp Dos loads about 1.4k tokens when it runs. Until then it costs about 33 tokens; SKILL.md has 370 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it: ~33
When it runs · the whole SKILL.md, loaded when a task matches: ~1.4k

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). 370 words, ~1,428 tokens.

Download SKILL.mdSave it as .claude/skills/vasp-dos/SKILL.md (or your agent's skills folder).

name: vasp-dos
description: Density of states (DOS) workflow in VASP. Three-step process for accurate total and projected DOS, d-band center analysis.

VASP Density of States (DOS) Calculation

Compute total and projected density of states. Requires a three-step workflow: geometry optimization, self-consistent single point, and DOS analysis.

Why Three Steps?

geo_opt — relax the structure to equilibrium
single_point — SCF with ISMEAR=-5 (tetrahedron method) and high NEDOS for accurate DOS
dos_analysis — extract d-band center, orbital projections, and plot data

The tetrahedron method (ISMEAR=-5) gives the most accurate DOS but is incompatible with geometry optimization (forces are not well-defined). That is why a separate single point is needed.

Full DOS Workflow

python

from catgo.workflow import Workflow
from catgo.workflow.builtins import geo_opt, single_point, dos_analysis

wf = Workflow("RuO2 DOS")
struct = wf.add_task("structure_input", structure=structure_json)

# Step 1: Optimize geometry
opt = wf.add_task(geo_opt, structure=struct.output.structure,
                  ISIF=2, system_name="relax")

# Step 2: Single point with DOS settings
sp = wf.add_task(single_point, structure=opt.output.structure,
                 ISMEAR=-5,       # Tetrahedron method with Blochl corrections
                 NEDOS=3001,      # Dense energy grid (default is 301)
                 LORBIT=11,       # Projected DOS per atom and orbital
                 LCHARG=True,     # Write charge density
                 EDIFF=1e-6,      # Tight convergence
                 system_name="DOS")

# Step 3: Analyze DOS
dos = wf.add_task(dos_analysis, data=sp.output.energy,
                  d_band=True, system_name="DOS_analysis")

wf.submit()

MCP Workflow

# Create workflow
catgo_workflow_engine(action="create", params={"name": "DOS calculation"})

# Step 1: Input structure
catgo_workflow_engine(action="add_task", params={
  "workflow_id": "wf_xxx",
  "task_type": "structure_input",
  "structure": "<json>"
})

# Step 2: Geometry optimization
catgo_workflow_engine(action="add_task", params={
  "workflow_id": "wf_xxx",
  "task_type": "geo_opt",
  "software": "vasp",
  "structure": "{{t_001.output.structure}}",
  "system_name": "relax"
})

# Step 3: Single point for DOS
catgo_workflow_engine(action="add_task", params={
  "workflow_id": "wf_xxx",
  "task_type": "single_point",
  "software": "vasp",
  "structure": "{{t_002.output.structure}}",
  "ISMEAR": -5,
  "NEDOS": 3001,
  "LORBIT": 11,
  "LCHARG": true,
  "EDIFF": 1e-6,
  "system_name": "DOS"
})

# Step 4: DOS analysis
catgo_workflow_engine(action="add_task", params={
  "workflow_id": "wf_xxx",
  "task_type": "dos_analysis",
  "data": "{{t_003.output.energy}}",
  "d_band": true,
  "system_name": "DOS_analysis"
})

catgo_workflow_engine(action="submit", params={"workflow_id": "wf_xxx"})

Key DOS Parameters

Parameter	Value	Purpose
ISMEAR	-5	Tetrahedron method — accurate DOS integration
NEDOS	3001	Energy grid points (more = smoother DOS)
LORBIT	11	Write atom-projected and orbital-projected DOS
EMIN/EMAX	auto	Energy range (auto-detected from eigenvalues)
LCHARG	True	Write CHGCAR for post-processing

ISMEAR=-5 Requirements

Requires at least 3 k-points in each periodic direction
Do NOT use for Gamma-only calculations (use ISMEAR=0 instead)
Do NOT use during geometry optimization (forces are inaccurate)
For metals with few k-points, use ISMEAR=1, SIGMA=0.2 and accept slightly noisier DOS

d-Band Center Analysis

The dos_analysis task computes the d-band center for transition metals:

d_band_center = integral(rho_d(E) * E dE) / integral(rho_d(E) dE)

This is valuable for catalysis studies (Norskov d-band model). The analysis automatically identifies transition metal atoms and extracts their d-orbital projected DOS.

Spin-Polarized DOS

For magnetic systems, set ISPIN=2 to get spin-up and spin-down DOS separately:

python

sp = wf.add_task(single_point, structure=opt.output.structure,
                 ISMEAR=-5, NEDOS=3001, LORBIT=11,
                 ISPIN=2,
                 MAGMOM="4*5.0 8*0.6",  # Initial moments
                 system_name="DOS_spin")

Show full SKILL.md (147 more words)Show less

Partial DOS (PDOS) for Specific Atoms

LORBIT=11 writes per-atom projections. The dos_analysis task can extract DOS for specific atoms or orbitals. Common use cases:

Surface vs bulk atoms: compare DOS of surface layer vs interior
Adsorbate bonding: compare adsorbate p-states with metal d-states
Alloying effects: compare d-band of alloy components

Skip Optimization (Pre-Optimized Structure)

If the structure is already optimized, skip step 1:

python

wf = Workflow("DOS only")
struct = wf.add_task("structure_input", structure=optimized_json)
sp = wf.add_task(single_point, structure=struct.output.structure,
                 ISMEAR=-5, NEDOS=3001, LORBIT=11,
                 system_name="DOS")
wf.submit()

Troubleshooting

Problem	Fix
Noisy/spiky DOS	Increase NEDOS (try 5001), use ISMEAR=-5
ISMEAR=-5 error	Need >= 3 k-points per direction. Increase k-mesh
No d-band center	dos_analysis only computes d-band for transition metals
DOS looks wrong	Check that SCF is converged (EDIFF=1e-6), check ISPIN for magnetic systems
Fermi level misplaced	VASP sets E_F automatically; verify with band structure

Output

The single_point task produces raw DOSCAR data. The dos_analysis task produces:

output.dos_data — total and projected DOS as plottable arrays
d-band center, d-band width, and band gap (if applicable)

Files

Just SKILL.md in .claude/skills/vasp-dos of Hello-QM/catgo-LRG.

Open the folder on GitHubat commit fd6291b

Compare with similar skills

Vasp Dos 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.

Vasp Dos compared with similar skills
Skill	Stars	Used in	Tokens	Auto-check	Licence	Repo updated
Vasp Dos this skillHello-QM/catgo-LRG	205	—	~1.4k	Automated safety check: Pass	AGPL-3.0	17 days ago
Robius State Managementsickn33/agentic-awesome-skills	47k	2 repos	~3.3k	Automated safety check: Pass	MIT	today
State Managementcompozy/compozy	2.8k	—	~2.5k	Automated safety check: Pass	MIT	yesterday
You Might Not Need Statesimstudioai/sim	30k	—	~672	Automated safety check: Pass	Apache-2.0	yesterday
Dos Verify Done Claimssickn33/agentic-awesome-skills	47k	1 repos	~2.1k	Automated safety check: Pass	MIT	today
Sync State Invariantsopenchamber/openchamber	11k	—	~2.7k	Automated safety check: Pass	MIT	yesterday

Similar skills

Robius State Management
sickn33/agentic-awesome-skills
CRITICAL: Use for Robius state management patterns. An agent skill from sickn33/agentic-awesome-skills.
47k GitHub starsUsed in 2 repos~3.3k tokens
Frontend & DesignAuto-check passed
State Management
compozy/compozy
Model, review, and refactor application state so source state stays minimal, derived state is computed instead of synchronized, impossible states are not representable, and each piece of state lives…
2.8k GitHub stars~2.5k tokensUpdated yesterday
Frontend & DesignAuto-check passed
You Might Not Need State
simstudioai/sim
Analyze and fix unnecessary useState, derived state, and server-state-in-local-state anti-patterns
30k GitHub stars~672 tokensUpdated yesterday
Frontend & DesignAuto-check passed
Dos Verify Done Claims
sickn33/agentic-awesome-skills
Before accepting an agent's 'done / shipped / fixed' claim, verify it against ground truth (git ancestry + the commit's own diff) using the DOS kernel's dos verify and dos commit-audit — never the…
47k GitHub starsUsed in 1 repo~2.1k tokens
Media & CreativeAuto-check passed
Sync State Invariants
openchamber/openchamber
A skill your agent uses when changing session synchronization, bootstrap or reconnect state, event reducers, polling, optimistic updates, message queues, live activity, ordering/reconciliation…
11k GitHub stars~2.7k tokensUpdated yesterday
Business, Finance & HRAuto-check passed
Project State Governor
sickn33/agentic-awesome-skills
Govern evidence-backed canonical project state across sessions, branches, reviews, and research cycles without inventing product intent.
47k GitHub starsUsed in 1 repo~4.6k tokens
Auto-check passed

Questions about Vasp Dos

What does Vasp Dos do?

Density of states (DOS) workflow in VASP. An agent skill from Hello-QM/catgo-LRG. Vasp Dos is an agent skill from Hello-QM/catgo-LRG. Density of states (DOS) workflow in VASP.

How do I install Vasp Dos in Claude Code?

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

How do I install Vasp Dos in Codex?

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

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

What does Vasp Dos need to run?

SKILL.md names no scripts, command-line tools or credentials: Vasp Dos is instructions for the agent only. Our summary lists: Python 3.

Does Vasp Dos 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 Vasp Dos 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 Vasp Dos use?

Vasp Dos 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 Vasp Dos use?

About 1.4k tokens (SKILL.md is roughly 5.7k 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 Vasp Dos?

Skills that share tags, products or a category with Vasp Dos: Robius State Management (sickn33/agentic-awesome-skills, 47k stars), State Management (compozy/compozy, 2.8k stars), You Might Not Need State (simstudioai/sim, 30k stars) and Dos Verify Done Claims (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 Vasp Dos?

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 Vasp Dos

Facts

At a glance

What it does

Example prompts

Requirements

Workflow steps

What it can do on your machine

Tool permissions

Runs code

Network

Credentials

Context cost

Safety

SKILL.md

VASP Density of States (DOS) Calculation

Why Three Steps?

Full DOS Workflow

MCP Workflow

Key DOS Parameters

ISMEAR=-5 Requirements

d-Band Center Analysis

Spin-Polarized DOS

Partial DOS (PDOS) for Specific Atoms

Skip Optimization (Pre-Optimized Structure)

Troubleshooting

Output

Files

Compare with similar skills

Similar skills

More from Hello-QM/catgo-LRG

Questions about Vasp Dos