Name: webiny-infra-catalog
Rating: 46.400000000000006 (1 reviews)
Author: webiny

Blog Docs Log in Get started

webiny-infra-catalog

Infrastructure — 35 abstractions. Infrastructure extensions.

Quality

48%

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/user-skills/generated/infra/SKILL.md

Quality

Content

78%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.

The body is a lean, well-structured catalog with copy-paste-ready import statements and source paths for each of 35 abstractions, plus a tight 3-step usage sequence. Its main weaknesses are the absence of any usage examples and the inlining of a large catalog that would benefit from being split into a separate reference file.

Suggestions

Add a brief usage example for at least one representative abstraction (e.g. a hook like AdminBeforeDeploy) so the 'how to actually use it' is not fully deferred to the source file.

Move the 35-entry catalog into a references file (e.g. references/abstractions.md) and keep SKILL.md as an overview with a clearly signaled link, improving progressive disclosure and token cost when only the overview is needed.

Note the duplicated exports (e.g. AdminStackOutputService and ApiStackOutputService each appear twice with different import paths) and clarify which path is canonical, or de-duplicate to avoid ambiguity.

Dimension	Reasoning	Score
Conciseness	The body is exceptionally lean: each abstraction is three lines (Name/Import/Source) with no prose padding and no explanation of concepts Claude already knows, so every token earns its place.	5 / 5
Actionability	Each entry provides a copy-paste-ready import line and a source path, which is concrete and executable; the gap is that step 2 defers the actual interface/usage to the source file rather than showing any usage example inline.	4 / 5
Workflow Clarity	The 'How to Use' section gives a clear ordered sequence (find → read source → import), and as a non-destructive lookup task it needs no validation checkpoint; it stops short of 5 only because the 'read source' step is a hand-off rather than self-contained guidance.	4 / 5
Progressive Disclosure	There is clear section structure (How to Use, per-entry headers), but all 35 abstractions are inlined as a monolithic flat list with no bundle files, where a catalog of this size would be better placed in a references file with SKILL.md as an overview.	3 / 5
	Total	16 / 20 Passed

Description

17%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.

The description is a terse category label rather than a capability statement: it names the domain and an abstraction count but lists no concrete actions and provides no trigger guidance. It reads as a placeholder, not a description that would help Claude decide when to invoke the skill.

Suggestions

Replace the noun-phrase description with concrete verbs, e.g. 'Catalogs and imports Webiny infrastructure abstractions (hooks, Pulumi components, stack-output services) for use in project setup and deployment.'

Add an explicit 'Use when...' clause with natural trigger terms, e.g. 'Use when extending or customizing Webiny's admin, API, or core infrastructure during build, deploy, or watch flows.'

Include natural keywords and synonyms a user would actually say — 'Webiny infra', 'Pulumi hooks', 'custom domains', 'stack output' — rather than only the generic term 'Infrastructure'.

Dimension	Reasoning	Score
Specificity	It names the domain ("Infrastructure") and a count ("35 abstractions"), but states no concrete actions at all — only noun phrases describing what exists, not what the skill does.	2 / 5
Completeness	It offers only a vague category label as the 'what' ("Infrastructure — 35 abstractions. Infrastructure extensions.") and entirely omits any 'Use when...' trigger guidance, which caps completeness per the rubric.	2 / 5
Trigger Term Quality	The only terms are technical jargon ("Infrastructure", "abstractions", "extensions"); a user would not naturally say these phrases when they need this skill.	1 / 5
Distinctiveness Conflict Risk	"Infrastructure" and "Infrastructure extensions" are very broad and would overlap with many possible skills; the description text alone does not carve out a distinct niche.	2 / 5
	Total	7 / 20 Passed

Validation

100%

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 — 16 / 16 Passed

Validation for skill structure

No warnings or errors.

Repository: webiny/webiny-js
Path: skills/user-skills/generated/infra/SKILL.md
Commit: d98a4e8

Reviewed: 4 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.