model-building

Implementation details for EF Core model building. Use when changing ConventionSet, ModelBuilder, IConvention implementations, ModelRuntimeInitializer, RuntimeModel, or related classes.

Quality

85%

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

82%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, highly specific internals reference that assumes competence and points to exact code locations and procedures. Its main gaps are the absence of executable code examples and validation checkpoints interleaved into the multi-step workflows rather than collected at the end.

Suggestions

Add a short copy-paste code snippet for the most common task (e.g., overriding ConfigureConventions or adding a CoreAnnotationNames entry) to lift actionability from guidance to executable.

Interleave validation checkpoints inside the 'Adding a New Annotation' procedure (e.g., 'after step 2, confirm the annotation is absent on RuntimeModel') rather than only collecting them in the terminal Validation section.

Consider splitting the testing-location table and/or the detailed annotation procedure into a referenced file (e.g., TESTING.md) so the overview stays a concise entry point with one-level-deep references.

Dimension	Reasoning	Score
Conciseness	The body is dense and information-rich, assuming EF Core/C# competence and delivering only specifics (file paths, class and method names) with no padding or explanation of basic concepts; nearly every token earns its place.	5 / 5
Actionability	Concrete, actionable guidance via exact file paths, method names, and a numbered procedure for adding annotations, but it is navigation/guidance for an existing codebase rather than copy-paste code examples, so it stops short of the 5-anchor's 'copy-paste ready code'.	4 / 5
Workflow Clarity	Multi-step processes (annotation procedure, model lifecycle) are clearly sequenced and a dedicated Validation section plus a snapshot round-trip test step provide checkpoints, but validation is a terminal checklist rather than interleaved feedback loops within the procedures.	4 / 5
Progressive Disclosure	Well-organized with clear section headers, tables, and trees, and there are no bundle files to reference; however it is a single dense multi-topic file with no one-level-deep references or content split across files, keeping it below a 5.	4 / 5
	Total	17 / 20 Passed

Description

87%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, well-targeted description that explicitly covers both what the skill addresses and when to use it, anchored by concrete EF Core class names. The only weakness is a single generic action verb rather than a varied set of concrete actions.

Dimension	Reasoning	Score
Specificity	Names the EF Core model-building domain and enumerates many concrete targets (ConventionSet, ModelBuilder, IConvention, ModelRuntimeInitializer, RuntimeModel), but the action verb is singular/generic ('changing') rather than multiple distinct concrete actions, placing it just below a 5.	4 / 5
Completeness	It clearly states what ('Implementation details for EF Core model building') and an explicit 'Use when changing ...' clause with concrete trigger conditions, satisfying the 5-anchor for both what and when with concrete trigger phrases.	5 / 5
Trigger Term Quality	The class names (ConventionSet, ModelBuilder, ModelRuntimeInitializer, RuntimeModel) are exactly the natural terms an EF Core internals contributor would say, giving strong keyword coverage, though some natural phrasings like 'conventions' or 'compiled model' as standalone triggers are missing.	4 / 5
Distinctiveness Conflict Risk	A narrow niche (EF Core model-building internals) anchored by class names unique to that subsystem gives it distinct triggers with minimal conflict risk against other skills.	5 / 5
	Total	18 / 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: dotnet/efcore
Path: .agents/skills/model-building/SKILL.md
Commit: 92b26f9

Reviewed: about 1 hour 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.