AGENT SKILL

csharp-expert

Writes and reviews production C# on the current stable .NET release (C# 14, .NET 10). Use when the user says c#-expert, C#, csharp, .NET, csproj, dotnet, or asks to implement, fix, or review .cs code. Do NOT use for F#, Visual Basic, non-.NET languages, or work that is not C#/.NET source.

License 许可
CC-BY-4.0
最近更新
2026-11-14
Stars
★ 1
Forks
0

01 前言 Front Matter

name
csharp-expert
license
CC-BY-4.0
metadata
{ "author": "AEOS", "version": "1.0.0", "owner_agent": "codenavi-agent" }
description
Writes and reviews production C# on the current stable .NET release (C# 14, .NET 10). Use when the user says c#-expert, C#, csharp, .NET, csproj, dotnet, or asks to implement, fix, or review .cs code. Do NOT use for F#, Visual Basic, non-.NET languages, or work that is not C#/.NET source.

02 资源文件 7

03 SKILL.md 正文

C# Expert

Governance: CodENavi Full Workspace v2. Skill of codenavi-agent; inherit AGENTS.md. Lifecycle: BRIEFING → RECON → PLAN → EXECUTE → VERIFY → DEBRIEF. Source roles/workers are internal lenses. Never create agent identities or bypass runtime secret/permission gates.

Governance: CodENavi Full Workspace v2. A skill of codenavi-agent. It creates no other agent identity.

Write and review C# source on the current stable .NET release. Module map: references/INDEX.md.

Mission

New C# uses C# 14 on net10.0. An existing project keeps the TargetFramework and LangVersion it already declares. Do not retarget because a newer SDK exists. Version pin and refresh rule: references/current-release.md.

Workflow

  1. Read every TargetFramework and LangVersion in the SDK-style .csproj files this change touches. Map and idiom rules: references/project-and-idioms.md.
  2. For a new project, set TargetFramework to net10.0 and leave LangVersion unset so the default is C# 14. For an existing project, write only syntax that its TFM and LangVersion accept.
  3. Apply C# 14 features only when step 2 allows them. Feature rules: references/csharp-14.md.
  4. Keep the change inside C# source, the .csproj that compiles it, and the C# test project that covers it.
  5. Verify with the commands in references/verify.md. A compile failure blocks any claim that the code is done.

Rules

  1. Enable nullable on a new file when the project sets <Nullable>enable</Nullable>, and on every file of a project this skill creates.
  2. Do not set LangVersion to preview. Do not use C# 15 or net11.0 unless the repository already declares that target.
  3. Prefer the BCL or a package the project already references. Add a package only when the user asked for that dependency.
  4. Match the project's namespace style, file layout, and analyzer settings.

Example

User says: "adicione um contador com get customizado neste tipo." Result: a field-backed property when the project is C# 14.

public int Count
{
    get => field;
    set => field = value < 0 ? 0 : value;
}

On net8.0 the same request uses an explicit backing field. The TFM stays net8.0.

Stop

Stop when the change is not C#/.NET source, the .csproj TFM cannot be read, or dotnet is absent and the syntax must be compiled to confirm. Say which input is missing.

Output

Report the detected TFM, the language version used, the files changed, and the dotnet build or dotnet test result from references/verify.md.

Provenance and source freshness: provenance.

04 同仓库更多 Skills

paulosantanna
paulosantanna/ai-assistent-universal-coder

workspace-brain

Operate the CodENavi workspace brain MCP and CLI — cloud DeepSeek RAG, disk corpus at WORKSPACE_BRAIN_ROOT, Jev URL curation, and event logging for Cursor/Codex/OpenCode/Claude. Use when ingesting repo knowledge, asking the brain, mapping web seeds, or recording AI-driven file changes. Do NOT use for local Ollama RAG or storing API keys in git.

★ 1
paulosantanna
paulosantanna/ai-assistent-universal-coder

workbench-profile-resolver

Provide enterprise-grade capability for `workbench-profile-resolver` inside AEOS v1.1. Use when the user requests workbench profile resolver or invokes workbench-profile-resolver. Do NOT use for unrelated tools or unapproved remote writes.

★ 1
paulosantanna
paulosantanna/ai-assistent-universal-coder

wordpress-expert

Staff-level WordPress engineering super-skill for one-shot site mapping, clean-code AI-assisted project creation/modification, the complete installed plugin universe, governed remote wp-admin operations, themes/blocks/layout, third-party integrations and production-safe changes. Use when the user requests wordpress expert or invokes wordpress-expert. Do NOT use for unrelated languages, domains or production deployment.

★ 1
paulosantanna
paulosantanna/ai-assistent-universal-coder

whatsapp-simulator

Generate synthetic WhatsApp-style conversation fixtures for testing conversational systems, support flows and automation. Use when the user requests whatsapp simulator or invokes whatsapp-simulator. Do NOT use for unrelated tools or unapproved remote writes.

★ 1
paulosantanna
paulosantanna/ai-assistent-universal-coder

web-quality-audit

Assimilated TLC/web-quality multi-area audit. Review performance, accessibility, SEO and best practices in one pass. Triggers: audit my site, review web quality, check page quality, optimize my website across areas. Do not use for a single-area job (core-web-vitals, ai-seo, best-practices, perf-lighthouse).

★ 1
paulosantanna
paulosantanna/ai-assistent-universal-coder

voiceai

Provide an evidence-backed voice interface for AEOS. Activating this skill is treated as explicit current-session consent for `voiceai` to record user audio or transcribe audio from user-authorized audio/video media within the declared scope. The skill can: Use when the user requests voiceai or invokes voiceai. Do NOT use for unrelated tools or unapproved remote writes.

★ 1