CtrlK
BlogDocsLog inGet started
Tessl Logo
SkillPublic

model-building

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

Quality

91%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide
SecuritybySnyk

Passed

No findings from the security scan

SKILL.md
Quality
Evals
Security

Quality

Content

90%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.

An excellent codebase-reference skill: dense, actionable, and assumption of competence throughout, with concrete procedures, test locations, and validation checks. The only gaps are the absence of explicit error-recovery feedback loops in the workflows and the lack of any reference files to split its longer procedure sections into.

DimensionReasoningScore

Conciseness

Lean and dense throughout: exact file paths, class names, and behavior notes with zero padding and no explanation of concepts Claude already knows (e.g. 'DbSetFindingConvention — discovers entities from DbSet<T>', 'Column names generated by convention must not collide.'). Every section carries codebase-specific facts, matching anchor 5.

5 / 5

Actionability

For an instruction-only skill, the guidance is concrete and executable in its domain: step-by-step procedures for adding facets and annotations naming every file/generator to touch, a testing-location table, and a specific validation command ('EF_TEST_REWRITE_BASELINES=1'). Anchor 4's 'minor gaps' do not apply — common cases are covered specifically.

5 / 5

Workflow Clarity

Clear numbered sequences ('Adding A Configurable Metadata Facet', 'Adding A New Annotation') and an explicit Validation checklist, so checkpoints are present, not implicit (ruling out 3). However, there are no error-recovery feedback loops ('if validation fails, fix and re-validate') required by anchor 5.

4 / 5

Progressive Disclosure

No bundle files exist, so the skill is a single file; sections are well-organized and navigable (anchors 1-3 ruled out). But at ~103 lines of inline procedures it exceeds the under-50-line simple-skill exception that would let well-organized sections alone score 5, and content like the detailed facet/annotation procedures could plausibly live in reference files.

4 / 5

Total

18

/

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 description: third-person, terse, and highly specific, with an explicit 'Use when' clause naming concrete trigger classes. Its only weaknesses are limited action variety and missing natural-language synonyms beyond the technical class names.

DimensionReasoningScore

Specificity

Names the domain ('EF Core model building') and concrete technical targets ('ConventionSet, ModelBuilder, IConvention implementations, ModelRuntimeInitializer, RuntimeModel'), though the action variety is limited to a single verb ('changing'). More concrete than anchor 3's generic actions, but not the multi-action coverage of anchor 5.

4 / 5

Completeness

Explicitly answers both: what ('Implementation details for EF Core model building') and when ('Use when changing ConventionSet, ModelBuilder, IConvention implementations, ModelRuntimeInitializer, RuntimeModel, or related classes') with concrete trigger phrases. The 'when' clause is specific, so anchor 4's 'could be more explicit' does not apply.

5 / 5

Trigger Term Quality

Good keyword coverage with the exact class names a developer would mention ('ModelBuilder', 'ConventionSet', 'RuntimeModel', 'EF Core'), but misses natural synonyms and variations like 'Entity Framework', 'conventions', 'metadata', or 'fluent API' that anchor 5 requires.

4 / 5

Distinctiveness Conflict Risk

Clear niche — EF Core model-building internals — with class-specific triggers that would not fire for unrelated skills, matching anchor 5's 'clear niche with distinct triggers; minimal conflict risk'.

5 / 5

Total

18

/

20

Passed

Validation

100%

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

Reviewed

Table of Contents

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.