computational-heterogeneous-catalysis

Use this skill for end-to-end heterogeneous catalysis workflows, including proposal framing, slab and adsorbate strategy, reaction/energy evaluation, and evidence standards for comparing catalyst candidates.

Quality

63%

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/computational-heterogeneous-catalysis/SKILL.md

Quality

Content

61%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 compact, well-sectioned orchestration skill that stays token-efficient, but its guidance is mostly strategic rather than executable, and it lacks validation checkpoints for the batch compute stages it coordinates. The reference to an unnamed "downstream domain skill" leaves a navigation gap.

Suggestions

Add explicit validation checkpoints for the screening/execute stages (e.g. convergence verification, structure/provenance checks before ranking) to lift workflow clarity.

Name the actual downstream domain skill(s) or provide paths (e.g. "See [slab-construction](../slab-construction/SKILL.md) for the active stage") instead of the anonymous "downstream domain skill" pointer.

Make directives more concrete: give an example naming scheme, a concrete campaign-plan record format, or a worked ranking-metric definition so stages are executable rather than purely strategic.

Dimension	Reasoning	Score
Conciseness	The body is lean — no explanations of concepts Claude already knows, and bullets are short imperative directives — but the Overview/Quick Start pair slightly overlaps ("keep a heterogeneous-catalysis study coherent" vs. the four Quick Start points restate Workflow ideas), so a few lines could be trimmed.	4 / 5
Actionability	As an instruction-only skill the absence of code is acceptable, and there are some concrete specifics ("the project house default is `k*a ~= 35 Å`", "Reuse the same clean-slab and gas references"), but most directives are high-level decisions to make ("Capture catalyst family", "Lock the ranking metric") without the specific steps, formats, or examples needed to execute them.	3 / 5
Workflow Clarity	A clear four-stage sequence exists (Define scope → Build a staged study plan → Enforce consistency → Report) with an evidence-threshold decision point, but the screening/execute stages are batch DFT operations with no explicit validation or verification checkpoints (e.g. convergence checks, structure verification), which caps workflow clarity at 3 per the judging guidelines.	3 / 5
Progressive Disclosure	The body is short (~46 lines) and well-organized into clearly labeled sections, which suits a self-contained skill, but the single external pointer — "Load the downstream domain skill for the active stage" — names no actual file or skill, leaving navigation to that material unresolved.	4 / 5
	Total	14 / 20 Passed

Description

66%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 domain-specific description with concrete capability areas and good natural terminology, but it lacks an explicit "Use when..." trigger clause, which caps its completeness and leaves the activation conditions implied rather than stated.

Suggestions

Add an explicit trigger clause, e.g. "Use when setting up or comparing DFT studies of catalysts, building slab/adsorbate models, or ranking catalyst candidates by adsorption or reaction energies."

Include natural synonyms users would say, such as "catalyst screening", "DFT", and "adsorption energy", to improve trigger-term coverage.

State the operating scope in third-person capability form (e.g. "Defines campaign plans, enforces k-point and reference consistency, and produces ranking reports") to sharpen the what.

Dimension	Reasoning	Score
Specificity	The description lists several concrete domain actions — "proposal framing, slab and adsorbate strategy, reaction/energy evaluation, and evidence standards for comparing catalyst candidates" — but the actions are stated as noun phrases rather than fully enumerated operations, leaving minor gaps in coverage versus the comprehensive anchor.	4 / 5
Completeness	The "what" is clear ("end-to-end heterogeneous catalysis workflows, including proposal framing, slab and adsorbate strategy, reaction/energy evaluation, and evidence standards"), but there is no explicit "Use when..." clause or equivalent trigger guidance — the "when" is only weakly implied by "Use this skill for...", which per the judging guidelines caps completeness at 3.	3 / 5
Trigger Term Quality	Natural domain terms are present ("heterogeneous catalysis", "slab", "adsorbate", "catalyst candidates") that a practitioner would actually say, but common variations and synonyms users might use — e.g. "DFT", "catalyst screening", "adsorption energy", "computational catalysis" — are missing, so coverage is good rather than comprehensive.	4 / 5
Distinctiveness Conflict Risk	The niche is distinct — "heterogeneous catalysis", "slab and adsorbate strategy" are unlikely to fire unrelated skills — but the broad "end-to-end workflows" framing and the existence of related downstream domain skills (referenced in the body) create minor overlap risk with closely related catalysis skills.	4 / 5
	Total	15 / 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/computational-heterogeneous-catalysis/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.