By mudramartin
A lightweight curated Claude Code skillset for .NET developers. Combines a customized fork of obra/superpowers (workflow), a trimmed fork of Aaronontheweb/dotnet-skills (patterns + agents), and adapted skills from mattpocock/skills (grill-me, design-an-interface). Tuned for .NET 10 + Aspire + Minimal API + NHibernate or EF Core projects with Vue or Blazor frontends. Key overrides: AskUserQuestion-first brainstorming (with deferred-tool preload), domain-first planning before TDD, and executing-plans preferred over subagent-driven-development.
Based on adoption, maintenance, documentation, and repository signals. Not a security audit or endorsement.
Expert in designing effective .NET performance benchmarks and instrumentation. Specializes in BenchmarkDotNet patterns, custom benchmark design, profiling setup, and choosing the right measurement approach for different scenarios. Knows when BenchmarkDotNet isn't suitable and custom benchmarks are needed.
Expert in .NET concurrency, threading, and race condition analysis. Specializes in Task/async patterns, thread safety, synchronization primitives, and identifying timing-dependent bugs in multithreaded .NET applications. Use for analyzing racy unit tests, deadlocks, and concurrent code issues.
Expert in analyzing .NET application performance data, profiling results, and benchmark comparisons. Specializes in JetBrains profiler analysis, BenchmarkDotNet result interpretation, baseline comparisons, regression detection, and performance bottleneck identification.
You MUST use this before any creative work - creating features, building components, adding functionality, or modifying behavior. Explores user intent, requirements and design before implementation.
Ultra-compressed communication mode (~75% token savings via dropping filler, articles, and pleasantries while keeping technical accuracy). Activates ONLY on EXPLICIT user invocation: "caveman mode", "talk like caveman", "use caveman", or /caveman. Stays active across ALL subsequent responses until user explicitly says "stop caveman" or "normal mode". Do NOT activate on shorthand like "be brief" or "shorter answers" — those are conversational, not mode-switches.
Use before committing to the public surface of a module, library, Minimal API endpoint group, or aggregate root — especially when the first design "feels obvious" or when the type is hard to change later. Generates 3+ radically different designs in parallel, then compares them on simplicity, depth, and ease of correct use.
Use when facing 2+ independent tasks that can be worked on without shared state or sequential dependencies
Use when you have a written implementation plan to execute in a separate session with review checkpoints
Uses power tools
Uses Bash, Write, or Edit tools
A lightweight, curated Claude Code skillset for .NET developers.
Plugin identifier: dotlight-skillset
Combines three upstream MIT skill libraries into one opinionated bundle, with workflow overrides that fix the rough edges of "pure TDD" agent loops.
grill-me, design-an-interface, grill-with-docs) and two from hsmejky/skills (improve-architecture, caveman): brainstorming → writing-plans → executing-plans → TDD → code review → finishing-branch, plus worktrees, systematic-debugging, parallel agents, skill authoring, doc-aware grilling (grill-with-docs), Ousterhout-style architecture review (improve-architecture), and explicit-trigger ultra-terse mode (caveman).rider-mcp-first — when JetBrains Rider MCP is attached, force semantic operations over filesystem Grep/Read for 50–90 % token savings on .NET exploration.dotnet-performance-analyst, dotnet-benchmark-designer, dotnet-concurrency-specialist. Use the Agent tool with subagent_type matching the agent name.Superpowers drives the process, dotnet-skills supply the patterns, agents do focused diagnostic work.
Out-of-the-box Superpowers has two habits that hurt .NET projects:
AskUserQuestion as clickable choice cards.Fixed in modified SKILL.md files:
brainstorming — prefers AskUserQuestion over text multi-choice, caps questions at 5-8, enforces Domain Model as the first design section.writing-plans — requires a ## Domain Model section derived from the design. If missing, loops back to brainstorming. Default exec sub-skill is executing-plans, not subagent-driven-development.test-driven-development — domain model must exist in the plan before first RED-GREEN-REFACTOR. Calls out "test-cheating" (satisfying tests by violating invariants) as the #1 LLM-TDD failure mode.subagent-driven-development (too slow; prefer executing-plans)akka-* (5), aspire-mailpit-integration, mjml-email-templates, verify-email-snapshots, marketplace-publishing, skills-index-snippetsakka-net-specialist, docfx-specialist, roslyn-incremental-generator-specialistFor Akka.NET, Mailpit, or DocFX work, install the upstream dotnet-skills plugin alongside — they cooperate fine.
DotLightSkillset focuses on the .NET workflow surface. For adjacent specialties, pair it with:
voltagent-data-ai — specialist agents for data-heavy .NET work: postgres-pro, database-optimizer, data-engineer, ml-engineer, data-scientist. Particularly useful with TimescaleDB / EF Core / NHibernate projects that grow ML-adjacent.playwright@claude-plugins-official — general Playwright MCP integration for non-Blazor SPA stacks (Vue/Vite, React, etc.). Dotlight only ships the Blazor-specific Playwright skill.These work in parallel — no conflicts.
.NET developers using .NET 10, Aspire (or pure host builders), Minimal API, NHibernate or EF Core, Postgres / TimescaleDB, and Vue/Vite or Blazor frontends, who want the auto-review / brainstorming / planning flow from Superpowers without having the agent design the domain for them via TDD. If you also need Akka.NET, install the upstream dotnet-skills plugin alongside — DotLightSkillset is opinionated about which extensions live in scope.
/plugin marketplace add MudraMartin/dotlight-skillset
/plugin install dotlight-skillset@dotlight-marketplace
Update:
/plugin marketplace update
git clone https://github.com/MudraMartin/dotlight-skillset.git ~/dotlight-skillset
Then in Claude Code:
Own this plugin?
Verify ownership to unlock analytics, metadata editing, and a verified badge. GitHub access is read-only (username + org membership).
Sign in to claimOwn this plugin?
Verify ownership to unlock analytics, metadata editing, and a verified badge. GitHub access is read-only (username + org membership).
Sign in to claimnpx claudepluginhub mudramartin/dotlight-skillset --plugin dotlight-skillsetHarness-native ECC operator layer - 67 agents, 271 skills, 92 legacy command shims, reusable hooks, rules, selective install profiles, and production-ready workflows for Claude Code, Codex, OpenCode, Cursor, and related agent harnesses
Comprehensive skill pack with 66 specialized skills for full-stack developers: 12 language experts (Python, TypeScript, Go, Rust, C++, Swift, Kotlin, C#, PHP, Java, SQL, JavaScript), 10 backend frameworks, 6 frontend/mobile, plus infrastructure, DevOps, security, and testing. Features progressive disclosure architecture for 50% faster loading.
Feature development with code-architect/explorer/reviewer agents, CLAUDE.md audit and session learnings, and Agent Skills creation with eval benchmarking from Anthropic.
Access thousands of AI prompts and skills directly in your AI coding assistant. Search prompts, discover skills, save your own, and improve prompts with AI.
Reliable automation, in-depth debugging, and performance analysis in Chrome using Chrome DevTools and Puppeteer
Comprehensive feature development workflow with specialized agents for codebase exploration, architecture design, and quality review