hello-qm/catgo-lrg/analysis

Claude Code and agent skill by hello-qm/catgo-lrg

Trust tier 3
  • community
Source check pending

Checking that the SKILL.md file is still in the repository.

Use 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 charge analysis.

Install

npx vskill@latest install hello-qm/catgo-lrg/analysis

SKILL.md

Analysis Router

This skill routes analysis requests to the correct sub-skill based on what the user is asking for.

Routing Table

User IntentSub-SkillKey Indicators
Gibbs free energy, ZPE, thermal correctionsgibbs/"free energy", "ZPE", "entropy", "thermal"
OER overpotentialoer/"OER", "oxygen evolution", "water splitting anode"
HER overpotentialher/"HER", "hydrogen evolution", "water splitting cathode"
CO2 reductionco2rr/"CO2RR", "CO2 reduction", "carbon dioxide"
Adsorption energyadsorption/"adsorption energy", "binding energy", "E_ads"
ENCUT/KPOINTS convergenceconvergence/"convergence", "ENCUT test", "k-point test"
DOS, d-band center, PDOSdos_analysis/"DOS", "d-band", "PDOS", "density of states"
Bader chargecharge/"Bader", "charge transfer", "charge analysis"
MACE Ni benchmark (Kreitz 2021)mace_ni_benchmark/"Kreitz", "MACE Ni benchmark", "MLP vs DFT-D3 on Ni"

MCP Tool: catgo_analyze

All analysis actions use the catgo_analyze tool with an action parameter.

json
{"tool": "catgo_analyze", "arguments": {"action": "convergence", ...}}
{"tool": "catgo_analyze", "arguments": {"action": "frequencies", ...}}
{"tool": "catgo_analyze", "arguments": {"action": "forces", ...}}

MCP Tool: catgo_workflow_engine

Most analysis workflows are built as DAGs using the workflow tool.

json
{"tool": "catgo_workflow_engine", "arguments": {"action": "create", "name": "Analysis WF"}}
{"tool": "catgo_workflow_engine", "arguments": {"action": "add_task", "workflow_id": "...", "task_type": "gibbs_energy", ...}}

Python API Pattern

All analysis workflows follow the same skeleton:

python
from catgo.workflow import Workflow
wf = Workflow("Analysis name")
# 1. Input structure
inp = wf.add_task("structure_input", structure=structure_json)
# 2. Compute (geo_opt, single_point, freq, etc.)
opt = wf.add_task("geo_opt", structure=inp.output.structure, software="vasp")
frq = wf.add_task("freq", structure=opt.output.structure, software="vasp",
freeze_mode="layers", freeze_layers=4)
# 3. Analyze (gibbs_energy, dos_analysis, charge_analysis, etc.)
gib = wf.add_task("gibbs_energy", energy=opt.output.energy,
frequencies=frq.output.frequencies, phase="adsorbed")
wf.submit()

Decision Guide

  • Single intermediate (H*, OH) --> her/, adsorption/
  • Multiple intermediates in reaction pathway --> oer/, co2rr/
  • Parameter sweep, no reaction --> convergence/
  • Post-processing existing calculation --> dos_analysis/, charge/
  • Converting DFT energy to thermodynamic quantity --> gibbs/

Common Pitfalls

  1. Always run geo_opt before freq -- frequencies on unrelaxed structures are meaningless.
  2. For surface calculations, always use freeze_mode="layers" in freq to avoid

imaginary frequencies from slab bottom atoms.

  1. Gibbs energy needs both energy (from geo_opt) and frequencies (from freq) --

these come from separate tasks connected via output references.

  1. Convergence tests use single_point (not geo_opt) to isolate the parameter effect.

Security

  • Security scanPassed, 90 of 100Pattern checks on the skill's files.
  • Model reviewPassed

Quality evaluation

  • Task evaluationNot runNo evaluation yet. Run one in Skill Studio.

Source

Popularity

Repository stars
172
Repository forks
18
7-day trend score
26

Stars and forks are for the whole GitHub repository, not this skill alone. Not refreshed yet.

Works with

Any agent vskill installs to: 56 targets in all. These 39 have a page on this site.

  • Claude Code
  • Cursor
  • GitHub Copilot
  • Windsurf
  • Codex
  • Gemini CLI
  • Cline
  • Amp
  • Roo Code
  • Goose
  • Continue
  • Kilo Code
  • Junie
  • Trae
  • OpenHands
  • Qwen Code
  • AI Agent
  • Tabnine Chat
  • Sourcegraph Cody
  • Amazon Q
  • Firebase Genkit
  • Sweep
  • Devin
  • Phind
  • Mentat
  • Claude Desktop
  • Aider
  • GPT Pilot
  • Plandex
  • bolt.new
  • v0
  • Replit Agent
  • Anse
  • TypingMind
  • BetterChatGPT
  • LibreChat
  • Warp AI
  • Pieces
  • Fig AI
Embed badge
vskill VERIFIED badge
[![vskill VERIFIED](https://verified-skill.com/api/v1/skills/hello-qm/catgo-lrg/analysis/badge)](https://verified-skill.com/skills/hello-qm/catgo-lrg/analysis)

Something wrong with this skill or its page? Tell us.