Update SKILL.md

[SebastienDegodez]

Closes #

📑 Description

✅ Checks

• My pull request adheres to the code style of this project
• I have updated the documentation as required
• All the tests have passed

ℹ Additional Information

[SebastienDegodez]

/evaluate

[github-actions]

🤖 Evaluation Results

❌ Some evaluations failed — 0/1 assets passed

Asset	Kind	Score	Pass Rate	Status
generate-microcks-openapi-samples	skill	3.60/10	0%	❌ FAIL

Scenario Details

generate-microcks-openapi-samples (skill) — ❌ FAIL

Model: gpt-4o
Overall Score: 3.60/10
Pass Rate: 0%

basic-openapi-sample

Generate a Microcks-compatible OpenAPI sample for a simple REST API

Run	Score	Passed
1	7.20/10	✅
2	0.00/10	❌

---

Tokens used: 120 input, 1,688 output
View workflow run

[github-actions]

🤖 Evaluation Results

❌ Some evaluations failed — 2/4 assets passed (4 skipped due to API errors — not counted)

Asset	Kind	Score	Pass Rate	Status
csharp-clean-architecture-development	plugin	1.56/10	10%	❌ FAIL
minimal-context-tools	plugin	5.50/10	0%	❌ FAIL
superpowers-whetstone	plugin	N/A	N/A	⚠️ SKIPPED
creating-dotnet-mcp-servers	skill	9.58/10	100%	✅ PASS
generate-microcks-openapi-samples	skill	7.20/10	100%	✅ PASS
migrating-prompts-to-skills	skill	N/A	N/A	⚠️ SKIPPED
setup-husky-dotnet	skill	N/A	N/A	⚠️ SKIPPED
skill-creator	skill	N/A	N/A	⚠️ SKIPPED

Scenario Details

csharp-clean-architecture-development (plugin) — ❌ FAIL

Model: gpt-4o
Overall Score: 1.56/10
Pass Rate: 10%

scaffold-clean-architecture-solution

Scaffold a complete Clean Architecture .NET solution

Run	Score	Passed
1	5.60/10	❌
2	⚠️ error	⚠️

cqs-pattern-a-crud-no-bus

Simple CRUD feature — skill must guide toward CQS UseCase without CQRS bus

Run	Score	Passed
1	10.00/10	✅
2	10.00/10	✅

ddd-aggregate-invariant-domain-layer

Domain aggregate with invariants — skill must guide enforcement placement

Run	Score	Passed
1	⚠️ error	⚠️
2	⚠️ error	⚠️

interface-placement-repo-write-vs-read

Repository interface placement — skill must guide layer decision

Run	Score	Passed
1	⚠️ error	⚠️
2	⚠️ error	⚠️

authorization-placement-three-tiers

Authorization placement — skill must guide correct layer for each check type

Run	Score	Passed
1	⚠️ error	⚠️
2	⚠️ error	⚠️

fetch-then-check-not-filter-in-query

Access policy pattern — skill must guide fetch-then-check over filter-in-query

Run	Score	Passed
1	⚠️ error	⚠️
2	⚠️ error	⚠️

iron-law-violation-detection

Must detect and fix Iron Law violations in provided code

Run	Score	Passed
1	⚠️ error	⚠️
2	⚠️ error	⚠️

cqrs-bus-optional-conditions

CQRS bus decision — skill must guide when to use or skip MediatR

Run	Score	Passed
1	⚠️ error	⚠️
2	⚠️ error	⚠️

domain-events-declare-vs-dispatch

Domain events — skill must guide where to declare and where to dispatch

Run	Score	Passed
1	⚠️ error	⚠️
2	⚠️ error	⚠️

shared-kernel-dependencies

SharedKernel violations — skill must guide what belongs and what does not

Run	Score	Passed
1	⚠️ error	⚠️
2	⚠️ error	⚠️

minimal-context-tools (plugin) — ❌ FAIL

Model: gpt-4o
Overall Score: 5.50/10
Pass Rate: 0%

find-files-by-pattern

Use the finding-files skill to locate files matching a pattern

Run	Score	Passed
1	4.50/10	❌
2	6.50/10	✅

superpowers-whetstone (plugin) — ⚠️ SKIPPED

⚠️ All runs failed due to API errors — evaluation was skipped and is not counted in the benchmark.

creating-dotnet-mcp-servers (skill) — ✅ PASS

Model: gpt-4o
Overall Score: 9.58/10
Pass Rate: 100%

create-basic-mcp-tool

Create a basic MCP tool class — skill must guide attributes and conventions

Run	Score	Passed
1	10.00/10	✅
2	8.50/10	✅

configure-aot-json-serialization

AOT-compatible JSON serialization — skill must guide context and registration

Run	Score	Passed
1	10.00/10	✅
2	10.00/10	✅

setup-transport-in-program

Transport configuration — skill must guide SSE vs Stdio setup

Run	Score	Passed
1	9.50/10	✅
2	9.50/10	✅

generate-microcks-openapi-samples (skill) — ✅ PASS

Model: gpt-4o
Overall Score: 7.20/10
Pass Rate: 100%

basic-openapi-sample

Generate a Microcks-compatible OpenAPI sample for a simple REST API

Run	Score	Passed
1	7.20/10	✅
2	7.20/10	✅

migrating-prompts-to-skills (skill) — ⚠️ SKIPPED

⚠️ All runs failed due to API errors — evaluation was skipped and is not counted in the benchmark.

setup-husky-dotnet (skill) — ⚠️ SKIPPED

⚠️ All runs failed due to API errors — evaluation was skipped and is not counted in the benchmark.

skill-creator (skill) — ⚠️ SKIPPED

⚠️ All runs failed due to API errors — evaluation was skipped and is not counted in the benchmark.

---

Tokens used: 77,287 input, 11,020 output
View workflow run