agentsclimarketplace

Relax

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

Prepare DFTB+ geometry-relaxation task inputs from a user-provided structure and optimization settings. Use when the user needs ion-only or cell-coupled structural optimization.From its SKILL.md

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

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

1.4 KB, 205 tokens by cl100k_base, as published. Nobody here has run it

DFTB+ Relax (Subskill)

Scope

This skill prepares relaxation tasks only.

It should generate:

  • geometry input
  • relaxation-capable dftb_in.hsd
  • explicit optimizer/convergence controls

It should not submit or execute jobs.

Relax intent is mandatory

Before preparing inputs, classify intent:

  • ion-only relaxation
  • cell+ion relaxation
  • constrained relaxation (e.g., slab constraints)

If intent is ambiguous, ask for clarification.

Must provide

  • structure input
  • SK parameter set choice
  • optimizer settings and convergence target
  • SCC and k-point policies

Usually should be explicit

  • stress/cell update policy
  • fixed-atom/layer constraints
  • charge/spin initialization when relevant

Expected output

  1. relaxation-task input/script layout
  2. explicit relaxation-policy rationale
  3. settings summary and assumptions
  4. unresolved choices for confirmation
  5. 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.