Skills Explorer Add Skills

dotnet-core-expert

An agent skill by Jeffallan, from Jeffallan/claude-skills. Tags: api, dotnet, microservices, performance, security, web.

What it does

Use when building .NET 8 applications with minimal APIs, clean architecture, or cloud-native microservices. Invoke for Entity Framework Core, CQRS with MediatR, JWT authentication, AOT compilation.

Install

With the skills CLI, which installs into Claude Code, Codex, Cursor and other agents:

npx skills add Jeffallan/claude-skills --skill dotnet-core-expert

Or copy the skill folder into Claude Code's skills directory by hand (~/.claude/skills for every project, or .claude/skills inside one):

git clone --depth 1 https://github.com/Jeffallan/claude-skills
cp -r claude-skills/skills/dotnet-core-expert ~/.claude/skills/dotnet-core-expert

Safety box score

Grade B, low risk: 25 of 100 risk points, rated 2026-10-20. The grade rates what the skill and its scripts can reach on the machine of whoever installs it, across eight categories from shell execution to secrets access. How the score works.

This skill is a .NET 8 implementation guide: it steers the agent to create and test ASP.NET Core, EF Core, MediatR, JWT, Docker, and cloud-native code. The main risks are local command execution during builds/tests, handling secrets in auth/deployment examples, and optional outbound HTTP calls for endpoint verification or health checks.

Category levels, from 0 (none) to 3 (high)
CategoryLevelWhy
Code & shell execution2 (moderate)The workflow explicitly tells the agent to run local commands like `dotnet build`, `dotnet test`, and `curl`, which executes project code and test suites.
Network access1 (low)It includes outbound HTTP usage in examples such as `curl` endpoint verification, `AddUrlGroup(new Uri("https://api.external-service.com/health"), "external-api")`, and Seq at `http://seq:5341`.
Filesystem reach1 (low)The skill writes within the workspace through app code, migrations, and logging examples such as `dotnet ef migrations add ...` and `logs/app-.log`, but it does not direct broad filesystem access.
Secrets & credentials2 (moderate)Authentication and deployment examples handle sensitive values like `JwtSettings__Secret`, `SA_PASSWORD`, and `AddUserSecrets<Program>`, so it may work with real credentials or secret-backed configuration.
Privilege & persistence0 (none)There is no instruction to use sudo, install globally, register services, or change host/OS settings; the `adduser`/`chown` example is container-internal.
Instruction hijack surface0 (none)The files contain normal workflow guidance only; there is no prompt to ignore higher-priority instructions, follow remote content, or hide actions.
Irreversible actions0 (none)It does not instruct the agent to deploy, publish, send messages, pay, or delete anything outside implementation and test verification.
Transparency0 (none)All shipped files are plain readable markdown; there are no binaries, obfuscated blobs, or downloaded installers.

Before installing

Rated 2026-10-20 by an automated review of 6 files from the skill's repository.

Source

Repository
Jeffallan/claude-skills (all skills from this repository)
Path
skills/dotnet-core-expert/SKILL.md
Branch
main
Updated
2026-09-19