code-review · codewithmukesh — Claude Code skill: Roslyn MCP review for .NET
Multi-dimensional .NET code review: Roslyn MCP catches antipatterns and diagnostics, manual review covers the risky paths first.
npx skills add codewithmukesh/dotnet-claude-kit --skill code-review -a claude-codeWhat code-review does
The skill reviews .NET changes across five dimensions: correctness, security, performance, architecture compliance and test coverage. It starts by scoring blast radius — how far a change ripples. A one-line middleware edit outranks a 300-line rename, so review depth follows the radius, not the diff size.
Before reading any file it runs Roslyn MCP tools: detect_antipatterns flags async void, DateTime.Now, new HttpClient() and broad catch blocks, while get_diagnostics surfaces new warnings and nullability issues. Then find_references and get_dependency_graph show how many consumers a modified API has and where the effects spread. Boundary rules are checked with get_project_graph and detect_circular_dependencies.
Manual review follows a fixed order: data access, security, concurrency, integration, correctness, tests. Style and naming come last, because formatters and analyzers already own them. Every finding lands in Critical, Warnings or Suggestions and states the file and line, why it matters, and how to fix it. The analysis steps need a configured Roslyn MCP server — without it they simply won't run.
What it helps with
- catch N+1 queries and a missing
CancellationTokenbefore merge - confirm every endpoint has
[Authorize]or[AllowAnonymous] - estimate how many consumers a public API change breaks
- spot layer violations and circular dependencies
- decide where review effort goes on a large diff
Example prompts for the agent
- /code-review the changes in this PR
- review the Orders module, focus on data access and security
- what should I review in this branch before merging?
How to install code-review
1Skills CLI (Vercel)
npx skills add codewithmukesh/dotnet-claude-kit --skill code-review -a claude-code2Manually: put the files in place
~/.claude/skills/code-review/SKILL.mdCopy the whole skill folder; for one project use .claude/skills/code-review/
1Skills CLI (Vercel)
npx skills add codewithmukesh/dotnet-claude-kit --skill code-review -a codex2Manually: put the files in place
.agents/skills/code-review/SKILL.mdFor all projects use ~/.agents/skills/
1Skills CLI (Vercel)
npx skills add codewithmukesh/dotnet-claude-kit --skill code-review -a cursor2Manually: put the files in place
.cursor/skills/code-review/SKILL.mdCursor also reads .agents/skills/ and .claude/skills/
1GitHub CLI
gh skill install codewithmukesh/dotnet-claude-kit code-review2Manually: put the files in place
.github/skills/code-review/SKILL.md1Skills CLI (Vercel)
npx skills add codewithmukesh/dotnet-claude-kit --skill code-review -a gemini-cli2Platform CLI
gemini skills install https://github.com/codewithmukesh/dotnet-claude-kit --path skills/code-reviewManually: put the files in place
.devin/skills/code-review/SKILL.mdThe legacy .windsurf/skills/ path still works
Skills CLI (Vercel)
npx skills add codewithmukesh/dotnet-claude-kit --skill code-review -a opencodeClaude.ai
Zip the folder and upload it in Settings → Capabilities → Skills
Step by step, with commands for each platform: How to install skills in Claude Code: five ways
Questions about code-review
How do I install code-review in Claude?
Run npx skills add codewithmukesh/dotnet-claude-kit --skill code-review -a claude-code. The skill lands at ~/.claude/skills/code-review/SKILL.md.
What does code-review do?
It pairs Roslyn MCP analysis with a manual pass ordered by risk, then returns findings sorted into Critical, Warnings and Suggestions. Style and formatting are left out on purpose.
How is code-review different from a normal editor review?
It prioritises by blast radius — data access, security, concurrency and integration boundaries first, naming and formatting last. The analysis steps require a configured Roslyn MCP server.
Source text
SKILL.md · MIT
--- name: code-review description: > MCP-powered multi-dimensional code review for .NET projects. Uses Roslyn analysis tools for antipatterns, diagnostics, references, and dependency graphs combined with structured manual review. Prioritizes effort with blast-radius scoring — data access, security, concurrency, and integration boundaries before style — and produces severity-categorized findings with actionable fixes. Use when: "review", "code review", "PR review", "review this", "review my code", "check code quality", "review changes", "what should I review", "review priorities", "blast radius", "critical path". --- # /code-review — MCP-Powered Code Review ## What Performs a multi-dimensional code review combining Roslyn MCP analysis with structured manual review. Effort follows the 80/20 rule: the 20% of code that causes 80% of incidents (data access, security, concurrency, integration boundaries) gets thorough review; style and formatting are left to tooling. Review dimensions: **Correctness** (logic, edge cases, null handling, async pitfalls), **Security** (auth gaps, injection, secrets, CORS), **Performance** (N+1, allocations, missing cancellation), **Architecture compliance** (layer violations, boundary breaches), **Test coverage** (behavior tests for changed types). ## When - "Review this", "code review", "PR review", before merging a pull request - After a major refactor to verify no regressions or design drift - "What should I review?" — deciding where review effort goes on a large change - Onboarding to unfamiliar code and wanting a quality assessment ## How ### Step 1: Scope and Score Blast Radius Identify changed files (`git diff main...HEAD`, specified files, or module). Score each change to set review depth — blast radius determines depth, not line count. A one-line middleware change outranks a 300-line rename. | Blast Radius | Examples | Depth | |---|---|---| | Critical | Middleware, auth, DB migrations, shared kernel, CI/CD | Thorough — every code path | | High | Public API changes, message consumers, EF configuration, new module | Focused — consumers + behavior | | Medium | New feature following existing patterns, bug fix, new endpoint | Standard — checklist pass | | Low | Docs, formatting, renames, logging statements | Glance — build + tests pass | ### Step 2: MCP Analysis (before reading any file) ``` detect_antipatterns(projectFilter: "affected-project") → async void, DateTime.Now, new HttpClient(), broad catch get_diagnostics(scope: "project", path: "affected-project") → new warnings, nullability issues ``` Distinguish newly introduced findings from pre-existing ones — focus on new. ### Step 3: Blast Radius Verification For each modified public API: ``` find_references(symbolName: "ModifiedType") → count consumers; high count = high risk get_dependency_graph(symbolName: "ModifiedMethod", depth: 2) → ripple effects ``` Check whether callers handle changed return types and new error cases. ### Step 4: Architecture Compliance Verify dependency direction (Domain → nothing; Infrastructure → Application → Domain) via `get_project_graph` and `detect_circular_dependencies`. Per architecture: VSA features don't cross-reference; Clean Architecture domain has zero project references; Modular Monolith modules communicate only via integration events — `find_references` on a module's DbContext should resolve only inside that module. ### Step 5: Manual Review — Priority Order Review what tools can't catch, highest-risk areas first: | Priority | Area | Check | |---|---|---| | 1 | Data access | N+1 (missing `Include`/projection), raw SQL with user input, missing `CancellationToken` | | 2 | Security | Every endpoint has explicit `[Authorize]`/`[AllowAnonymous]`, input validated, no secrets in code, no PII in logs | | 3 | Concurrency | Token propagated end-to-end, no `.Result`/`.Wait()`, thread-safe shared state | | 4 | Integration | Retry/timeout on external calls, consumer idempotency, no swallowed exceptions | | 5 | Correctness | Business logic, edge cases (empty/null/concurrent), entities mapped to DTOs at the boundary | | 6 | Tests | Behavior tested (not implementation); happy path + main error case covered | | — | Style/naming | Mention only after the above; formatters and analyzers own this | ### Step 6: Produce the Review Every finding states what's wrong, why it matters, and how to fix it. Never bury a security bug under naming nits. ```markdown ## Code Review: [Scope] ### Summary [1-3 sentences: scope, risk level, recommendation] ### Critical (must fix before merge) - **[Title]** — [file:line] [What's wrong. Why it matters. How to fix.] ### Warnings (should fix, creates tech debt) - **[Title]** — [file:line] [...] ### Suggestions (nice to have) - **[Title]** — [file:line] [...] ### Architecture Compliance [PASS/WARN with boundary-violation notes] ### Test Coverage [Which changed types have tests; specific scenarios to add] ### What's Good - [Always include — reinforce good patterns] ``` **Quick review** (1-2 files, low blast radius): run `detect_antipatterns` + `get_diagnostics`, read for correctness, output Summary + Issues + What's Good. ## Example ``` User: /code-review the changes in this PR Claude: 7 changed files across 3 projects. CreateOrder touches data access and a public endpoint — High blast radius. Running MCP analysis... ## Code Review: Order Processing Feature ### Summary Adds CreateOrder/GetOrder endpoints with EF Core persistence. Well-structured VSA feature. Two issues need attention before merge. ### Critical (must fix before merge) - **Missing CancellationToken propagation** — CreateOrder.cs:38 SaveChangesAsync() called without the token. Client disconnects keep burning server resources. Pass `ct` from the handler parameter. ### Warnings (should fix, creates tech debt) - **N+1 query in GetOrder** — GetOrder.cs:25 Order loaded without `.Include(o => o.Items)`; one lazy load per item during serialization. Eager-load or use a projection. ### Suggestions (nice to have) - **Seal the handler** — CreateOrderHandler.cs:10 Not designed for inheritance; `sealed` enables devirtualization. ### Architecture Compliance PASS — all changes within Features/Orders/, no layer violations. ### Test Coverage Happy path covered. Add tests for validation failure and not-found. ### What's Good - Clean command/query separation; FluentValidation covers edge cases - Response DTOs are records, no entity leaks ``` ## Related - `/de-sloppify` — Cleanup pass for the style/formatting issues review skips - `/verify` — Automated verification pipeline (complements manual review) - `/health-check` — Broader project health assessment beyond a single PR
© codewithmukesh · MIT · codewithmukesh/dotnet-claude-kit
Similar skills
Everything for Code review and refactoring →code-review by other authors comes first.