skill-review-component

[Skill] Review an Azure Linux component definition for hygiene and best practices. Use when reviewing comp.toml files, checking overlay quality, validating file organization, or auditing component definitions. Triggers: review component, check hygiene, audit component, validate comp.toml, component review. NOTE: This skill is a work-in-progress — the checklist below covers basics but the full review workflow is still being refined.

Quality

82%

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

Quality

Content

65%Weight 40%Scale 1-3

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 well-structured, actionable review checklist with concrete commands and specific field-level guidance. Its main weaknesses are verbosity in the Scope and overlay sections, the absence of explicit validation checkpoints, and a lack of progressive-disclosure file structure.

Suggestions

Tighten the 'Scope of Changes' paragraph and the long overlay bullets — replace hedging prose with concise rules to lift conciseness.

Add an explicit validation/cross-check step (e.g., 're-run azldev comp query and confirm each flagged issue reproduces before reporting') to give the review workflow a feedback loop.

Move the detailed overlay-type and build-configuration guidance into a referenced file (e.g., references/overlays.md) so SKILL.md stays a lean overview, improving progressive disclosure.

Dimension	Reasoning	Score
Conciseness	The checklist is mostly tight and concrete, but the 'Scope of Changes' paragraph and several overlay bullets ramble with hedging ('This is a balance... However, if the fix would be fairly small...') that could be trimmed.	2 / 3
Actionability	Provides concrete executable commands ('azldev comp list -p <name> -q -O json') and specific decision rules tied to real field names ('build.without', 'spec-search-replace', 'release.calculation').	3 / 3
Workflow Clarity	Steps are numbered 1–7 with a defined severity-grouped output format, but there are no explicit validation checkpoints or feedback loops within the review, and the checklist reads as parallel checks rather than a gated sequence.	2 / 3
Progressive Disclosure	Sections are well organized and the single external link (Release Configuration) is one level deep and clearly signaled, but the skill is a monolithic ~70-line file with all detail inline and no bundle files to offload it.	2 / 3
	Total	9 / 12 Passed

Description

100%Weight 40%Scale 1-3

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 strong: it names concrete actions, provides explicit 'Use when' guidance plus a dedicated triggers list, and occupies a distinct niche. Minor clutter (the '[Skill]' prefix and the work-in-progress NOTE) adds tokens without harming the substance.

Dimension	Reasoning	Score
Specificity	Lists multiple concrete actions — 'Review an Azure Linux component definition for hygiene and best practices' plus 'reviewing comp.toml files, checking overlay quality, validating file organization, or auditing component definitions.'	3 / 3
Completeness	Explicitly states both what it does (review component definitions for hygiene/best practices) and when to use it ('Use when reviewing comp.toml files...') with an explicit Triggers clause, so it is not capped at 2.	3 / 3
Trigger Term Quality	Includes a dedicated 'Triggers:' list of natural phrases a user would say — 'review component, check hygiene, audit component, validate comp.toml, component review.'	3 / 3
Distinctiveness Conflict Risk	Targets a clear niche (Azure Linux comp.toml component definitions) with distinct, domain-specific triggers unlikely to collide with general-purpose skills.	3 / 3
	Total	12 / 12 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
relative_links	Relative link issues: 1 suspicious	Warning

	Total	15 / 16 Passed

Repository: microsoft/azurelinux
Path: .github/skills/skill-review-component/SKILL.md
Commit: 9e308ff

Reviewed: 6 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.