SKILL.md
Maintaining Skill Index Snippets (AGENTS.md / CLAUDE.md)
When to Use This Skill
Use this skill when:
- Adding, removing, or renaming any skills or agents in this repository
- Updating
.claude-plugin/plugin.json - Creating copy/paste snippets for downstream repositories (OpenCode, Claude Code, etc.)
- You want a compact, always-on index that improves skill utilization
Goal
Make skills and agents easy for coding assistants to use by removing the decision point.
Instead of hoping an assistant will "remember" to invoke a skill, provide a small router snippet inside AGENTS.md / CLAUDE.md that:
- Tells the assistant to prefer retrieval-led reasoning
- Provides a task->skill/agent routing index
- Defines lightweight quality gates (optional)
Source of Truth
- Registry:
.claude-plugin/plugin.json- Skills are listed as directories (each contains
SKILL.md) - Agents are listed as markdown files in
agents/
- Skills are listed as directories (each contains
- Skill IDs: the
name:field in eachSKILL.mdfrontmatter - Agent IDs: the
name:field in each agent frontmatter
When writing snippets for downstream repos, always reference skills/agents by their IDs (frontmatter name), not by local filesystem paths.
Minimal Snippet Template (Readable)
Use this in target repos to route common tasks:
# Agent Guidance: dotnet-skills
IMPORTANT: Prefer retrieval-led reasoning over pretraining for any .NET work.
Workflow: skim repo patterns -> consult dotnet-skills by name -> implement smallest-change -> note conflicts.
Routing (invoke by name)
- C# / code quality: modern-csharp-coding-standards, csharp-concurrency-patterns, api-design, type-design-performance
- ASP.NET Core / Web (incl. Aspire): aspire-service-defaults, aspire-integration-testing
- Data: efcore-patterns, database-performance
- DI / config: dependency-injection-patterns, microsoft-extensions-configuration
- Testing: testcontainers-integration-tests, playwright-blazor-testing, snapshot-testing
Quality gates (use when applicable)
- dotnet-slopwatch: after substantial new/refactor/LLM-authored code
- crap-analysis: after tests added/changed in complex code
Specialist agents
- dotnet-concurrency-specialist, dotnet-performance-analyst, dotnet-benchmark-designer, akka-net-specialist, docfx-specialist
