How do I install the Dft Gpaw skill?

Run npx skillmds@latest add gabrielmoreira/dft-gpaw in your terminal (requires Node.js), paste this page's agent-chat prompt into Claude, Cursor, or any MCP-connected agent, or download the SKILL.md file and copy it into your agent's skills directory.

Is Dft Gpaw safe to use?

This skill has not completed SkillMD's automated safety review yet. Independent scanners report: SkillSpector: PASS, Skill Scanner: PASS. Capability flags: docs only. SkillMD never runs a skill's scripts for you; review the SKILL.md before installing.

Which AI agents work with Dft Gpaw?

This skill is tagged as working with Claude Code, Claude.ai, OpenAI Codex. SKILL.md is an open format, so most agents that read a skills directory can load it too.

Is Dft Gpaw free to use?

Yes. Installing skills from SkillMD is free. This skill is licensed under LGPL-3.

Who published Dft Gpaw?

gabrielmoreira (@gabrielmoreira) published this skill. Their other Agent Skills are listed on their SkillMD profile.

Dft Gpaw by gabrielmoreira — Agent Skill

Name: Dft Gpaw
Rating: 4.2 (5 reviews)
Author: gabrielmoreira

Dft Gpaw

Route GPAW DFT requests to task-specific subskills based on user intent. Use when the user asks for GPAW workflows and you must decide between static SCF, relaxation, DOS, or band-structure task preparation. This orchestration skill dispatches to the correct GPAW subskill and enforces consistent handoff to submission skills.

gabrielmoreira Updated Sep 9, 2026 17 repo stars

File contents

GPAW Task Router

Use this skill as the top-level GPAW orchestration layer.

Purpose

This skill routes requests to one task-specific GPAW subskill path:

dft-gpaw/static
dft-gpaw/relax
dft-gpaw/dos
dft-gpaw/band

Scope

This router skill should:

require a user-provided structure or prerequisite run context
classify request intent into one GPAW task type
collect minimal shared context before dispatch
delegate detailed parameter handling to the selected subskill
enforce consistent output/handoff policy across subskills

This router skill should not:

own full task-specific Python templates for all cases
execute or submit calculations
bypass subskill-specific guardrails

Hard requirement

The user must provide enough starting context:

structure input for static / relax
prerequisite ground-state context for dos / band

If prerequisites are missing, stop and ask for them.

Routing rules

If user requests single-point SCF/energy: route to dft-gpaw/static.
If user requests geometry optimization: route to dft-gpaw/relax.
If user requests DOS workflow: route to dft-gpaw/dos.
If user requests band-structure workflow: route to dft-gpaw/band.
If intent is ambiguous, ask one focused clarification question before routing.

Shared policy for all subskills

do not invent missing physical parameters
do not fabricate restart context/results
expose assumptions explicitly
return handoff-ready task layout
if execution is requested, hand off to dpdisp-submit

Output from router

Provide:

selected subskill path
why it was selected
minimal missing inputs (if any)
explicit next step (invoke selected subskill)

---name: dft-gpawdescription: Route GPAW DFT requests to task-specific subskills based on user intent. Use when the user asks for GPAW workflows and you must decide between static SCF, relaxation, DOS, or band-structure task preparation. This orchestration skill dispatches to the correct GPAW subskill and enforces consistent handoff to submission skills.license: LGPL-3.0-or-later--- # GPAW Task Router Use this skill as the **top-level GPAW orchestration layer**. ## Purpose This skill routes requests to one task-specific GPAW subskill path: - `dft-gpaw/static` - `dft-gpaw/relax` - `dft-gpaw/dos` - `dft-gpaw/band` ## Scope This router skill should: - require a user-provided structure or prerequisite run context - classify request intent into one GPAW task type - collect minimal shared context before dispatch - delegate detailed parameter handling to the selected subskill - enforce consistent output/handoff policy across subskills This router skill should **not**: - own full task-specific Python templates for all cases - execute or submit calculations - bypass subskill-specific guardrails ## Hard requirement The user must provide enough starting context: - structure input for `static` / `relax` - prerequisite ground-state context for `dos` / `band` If prerequisites are missing, stop and ask for them. ## Routing rules 1. If user requests single-point SCF/energy: route to `dft-gpaw/static`. 1. If user requests geometry optimization: route to `dft-gpaw/relax`. 1. If user requests DOS workflow: route to `dft-gpaw/dos`. 1. If user requests band-structure workflow: route to `dft-gpaw/band`. 1. If intent is ambiguous, ask one focused clarification question before routing. ## Shared policy for all subskills - do not invent missing physical parameters - do not fabricate restart context/results - expose assumptions explicitly - return handoff-ready task layout - if execution is requested, hand off to `dpdisp-submit` ## Output from router Provide: 1. selected subskill path 1. why it was selected 1. minimal missing inputs (if any) 1. explicit next step (invoke selected subskill)

Frequently asked questions