agentsclimarketplace

Electronic

Skill jinzhezenggroup/computational-chemistry-agent-skills/quantum-chemistry/dftbplus/electronic

Prepare DFTB+ electronic-analysis task inputs based on prior ground-state context. Use when the user requests band/DOS-style analyses and needs prerequisite-aware setup.From its SKILL.md

Install
npx -y skills add jinzhezenggroup/computational-chemistry-agent-skills --skill electronic

Assembled from the repository path, not quoted from the project. Check it against their README if it does not work.

What its file declares

Copied from the file, not written here

The file declares its own license as LGPL-3.0-or-later. That is the author’s claim about this one file, and it is not the same thing as the license GitHub reports for the repository, which is listed with the other numbers below.

SKILL.md

1.3 KB, 180 tokens by cl100k_base, as published. Nobody here has run it

DFTB+ Electronic Analysis (Subskill)

Scope

This skill prepares post-ground-state electronic-analysis tasks.

It should:

  • verify prerequisite context
  • prepare analysis-specific input controls
  • report assumptions and unresolved choices

It should not submit or execute jobs.

Prerequisites

Require explicit prior converged context compatible with requested analysis.

If prerequisites are missing, stop and ask for them.

Must provide

  • source context path
  • analysis intent (band, dos, or both)
  • path/mesh policy as applicable
  • resolution/broadening policy

Usually should be explicit

  • k-path convention source
  • projection settings if needed
  • output format expectations

Expected output

  1. analysis-stage input/script updates
  2. prerequisite check summary
  3. settings summary and assumptions
  4. handoff note to dpdisp-submit if execution is requested

What ships with it

Read from the repository

Just SKILL.md. No reference files, no scripts.

Keep looking

Skills are one crate of 325,949. Ordering is by how many stacks a row turns up in, so the top of any crate is what has actually been picked rather than what has the most stars.