infra-setup

Non-user-invocable provider/setup reference for evo backend switching, prerequisite checks, and auth/install guidance.

Quality

77%

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 ./plugins/evo/skills/infra-setup/SKILL.md

Quality

Content

92%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 actionable, well-sequenced with validation checkpoints for a destructive config-mutating task, and cleanly offloads provider detail to a one-level-deep reference file.

Dimension	Reasoning	Score
Conciseness	Lean, no padding, and assumes Claude's knowledge of evo; a few exhaustive provider lists could be trimmed slightly, keeping it just below the score-5 'every token earns its place' bar.	4 / 5
Actionability	Provides copy-paste-ready, executable commands for every install path (uv tool, pip/venv, pipx) and the config/auth steps, with parameter placeholders clearly delimited.	5 / 5
Workflow Clarity	An explicit 8-step flow with prerequisite checks, environment-aware validation ('verify the SDK import only when... same environment'), and 'ask the user before installing' feedback loops for the config-mutating operation.	5 / 5
Progressive Disclosure	SKILL.md is a concise overview that clearly signals a single one-level-deep reference (references/provider-matrix.md, a real file), with provider detail appropriately split out and easy to navigate.	5 / 5
	Total	19 / 20 Passed

Description

62%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 specific and well-scoped to a clear niche, but as a non-user-invocable reference it lacks a 'Use when...' trigger clause and natural user-facing keywords, capping trigger quality and completeness at 3.

Suggestions

Add an explicit 'Use when...' clause stating when this reference should be loaded, even if it is non-user-invocable (e.g., 'Use when switching evo experiment backends or configuring a remote provider').

Include one or two natural user phrasings or synonyms (e.g., 'change where experiments run', 'remote provider setup') to broaden trigger coverage.

Consider listing the provider names directly in the description to improve specificity toward the score-5 anchor.

Dimension	Reasoning	Score
Specificity	Names the evo backend-switching domain plus several concrete actions ('prerequisite checks', 'auth/install guidance', 'provider/setup reference'); comprehensive like the score-5 anchor is not quite reached given the compact, single-clause coverage.	4 / 5
Completeness	Clearly states what the skill does but omits any 'Use when...' trigger guidance, which per the rubric caps completeness at 3.	3 / 5
Trigger Term Quality	Domain-relevant keywords ('evo backend switching', 'prerequisite checks', 'auth/install') are present but lean technical, missing natural user phrasings and synonyms; the skill is explicitly non-user-invocable, so trigger terms are inherently limited.	3 / 5
Distinctiveness Conflict Risk	The 'evo backend switching' niche is highly specific with distinct triggers and minimal overlap risk against other skills.	5 / 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
frontmatter_unknown_keys	Unknown frontmatter key(s) found; consider removing or moving to metadata	Warning

	Total	15 / 16 Passed

Repository: evo-hq/evo
Path: plugins/evo/skills/infra-setup/SKILL.md
Commit: ab5fbd6

Reviewed: 5 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.