vasp-input-preparation

Use this skill for preparing VASP relaxation and single-point input sets, choosing calc_type and key defaults correctly, handling INCAR override edge cases, and producing execution-ready folder layouts before dispatch.

Quality

78%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

Passed

No findings from the security scan

Fix and improve this skill with Tessl

tessl review fix ./skills/vasp-input-preparation/SKILL.md

Quality

Content

72%Weight 40%Scale 1-5

Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.

A lean, well-structured, and genuinely actionable instruction-only skill body with no padding and appropriate single-file organization. Its one real gap is the absence of any validation/verification step for a batch-preparation workflow, which both caps workflow clarity and leaves the operator without a pre-dispatch sanity check.

Suggestions

Add an explicit validation step to the workflow, e.g. after preparation verify the output tree contains one directory per structure and that generated INCARs reflect any user_incar_settings overrides, reporting discrepancies before dispatch.

Include one concrete example tool invocation with key parameters (e.g. a vasp_relax_prepare call with calc_type="slab", output_root, and a targeted user_incar_settings override) so the guidance is copy-paste ready.

Consolidate the duplicated k_product house-default guidance (stated in both section 3 and Method-critical defaults) into a single place to trim tokens and avoid the two statements drifting apart.

Dimension	Reasoning	Score
Conciseness	The body is lean bullet-style project policy with no explanation of concepts Claude already knows, but has minor trimmable duplication: the k_product house default is stated twice ("Project house default for `k_product` is `35`" in section 3 and "use `k*a ~= 35 Å` as the initial project default" in Method-critical defaults) and Quick Start overlaps the Workflow steps, fitting the score-4 anchor rather than 3 which would require unnecessary explanation.	4 / 5
Actionability	Guidance is concrete throughout — named tools, calc_type values (bulk/slab/gas), exact settings (NSW=0, IBRION=-1, ISIF=2/3, k_product 35/50), element-map requirements, and exact output layout (output_root/<stem>/) — but there is no example tool invocation showing parameters, so it is not copy-paste ready, matching score 4 rather than 5.	4 / 5
Workflow Clarity	Five clearly sequenced steps cover tool choice, regime, defaults, overrides, and output layout, but the workflow involves batch operations (directory input "preserves relative layout and appends <stem>/ per structure"; output contract includes "processed structure count") with no validation or verification checkpoint before dispatch, so the rubric's batch-operation cap applies and workflow clarity cannot exceed 3.	3 / 5
Progressive Disclosure	There are no bundle files and none are needed: the body is roughly 45 non-blank lines of single-purpose policy, cleanly sectioned (Overview, Quick Start, Suggested tools, Workflow, Method-critical defaults, Output Contract, References) with easy navigation, which meets the rubric's simple-skill exception for scoring 5 on well-organized sections without external references.	5 / 5
	Total	16 / 20 Passed

Description

83%Weight 40%Scale 1-5

Based on the skill's description, can an agent find and select it at the right time? Clear, specific descriptions lead to better discovery.

A strong, specific description that clearly states what the skill does with concrete domain actions and low conflict risk. Its main weakness is trigger phrasing: the "when" is a purpose clause rather than an explicit user-side trigger, and some natural synonyms users would actually say are absent.

Dimension	Reasoning	Score
Specificity	The description lists multiple concrete actions — "preparing VASP relaxation and single-point input sets", "choosing calc_type and key defaults", "handling INCAR override edge cases", "producing execution-ready folder layouts" — comprehensively covering the skill's scope, matching the score-5 anchor rather than 4 where coverage would have minor gaps.	5 / 5
Completeness	The "what" is explicit and concrete, and equivalent trigger guidance exists via "Use this skill for ... before dispatch" (so it is not capped at 3), but the "when" is a purpose clause rather than an explicit concrete trigger phrase like "Use when the user asks to set up VASP runs", matching the score-4 anchor.	4 / 5
Trigger Term Quality	Good natural keyword coverage ("VASP", "relaxation", "single-point", "INCAR", "input sets") but missing common variations a user might say such as "DFT", "geometry optimization", "slab/surface calculations", or file-level triggers like POSCAR/INCAR files, so it fits the score-4 anchor rather than the comprehensive score-5 anchor.	4 / 5
Distinctiveness Conflict Risk	The niche is highly distinct (VASP relaxation vs single-point preparation, INCAR overrides, calc_type regimes) with minimal overlap risk against any plausible sibling skill, matching the score-5 anchor for a clear niche with distinct triggers.	5 / 5
	Total	18 / 20 Passed

Validation

93%

Warnings & errors only

Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.

Validation — 15 / 16 Passed

Validation for skill structure

Criteria	Description	Result
metadata_version	'metadata.version' is missing	Warning

	Total	15 / 16 Passed

Repository: fernandezbaptiste/CatMaster
Path: skills/vasp-input-preparation/SKILL.md
Commit: c87fc76

Reviewed: 2 days ago

Table of Contents

Discovery Implementation Validation

Is this your skill?

If you maintain this skill, you can claim it as your own. Once claimed, you can manage eval scenarios, bundle related skills, attach documentation or rules, and ensure cross-agent compatibility.