PluginBench
Skill
Review
Audit score 70

code-review

codewithmukesh/dotnet-claude-kit

MCP-powered multi-dimensional code review for .NET projects with blast-radius prioritization

What is code-review?

Performs structured code review combining Roslyn analysis with manual inspection, prioritizing high-risk areas (data access, security, concurrency, integration) before style. Use when reviewing pull requests, refactors, or assessing code quality in .NET projects.

  • Scores blast radius of changes to determine review depth and effort allocation
  • Detects antipatterns and diagnostics via Roslyn MCP analysis before manual review
  • Analyzes reference counts and dependency graphs to identify ripple effects
  • Verifies architecture compliance and layer boundaries
  • Prioritizes findings by severity: Critical (must fix), Warnings (tech debt), Suggestions (nice-to-have)
  • Produces actionable findings with what's wrong, why it matters, and how to fix it

How to install code-review

npx skills add https://github.com/codewithmukesh/dotnet-claude-kit --skill code-review
Prerequisites
  • Access to a .NET project with git history
  • Roslyn MCP tools available in the environment
Claude Code
Cursor
Windsurf
Cline

How to use code-review

  1. 1.Identify changed files using git diff or specify files/modules to review
  2. 2.Run MCP analysis (detect_antipatterns, get_diagnostics) on affected projects
  3. 3.Score blast radius of each change (Critical/High/Medium/Low) to set review depth
  4. 4.Verify architecture compliance using get_project_graph and detect_circular_dependencies
  5. 5.Manually review highest-risk areas in priority order: data access, security, concurrency, integration, correctness, tests
  6. 6.Produce findings report with severity categories, actionable fixes, and what's good about the code

Use cases

Good for
  • Review pull requests before merging to catch correctness, security, and performance issues
  • Assess blast radius of major refactors to verify no regressions or design drift
  • Decide where to focus review effort on large changes across multiple files
  • Onboard to unfamiliar codebases with a quality assessment and risk analysis
  • Verify architecture compliance after changes to shared kernel or public APIs
Who it's for
  • Backend engineers reviewing .NET code changes
  • Tech leads assessing pull request risk before approval
  • Developers onboarding to unfamiliar .NET projects
  • Teams practicing code review with structured prioritization

code-review FAQ

How does blast radius scoring work?

Changes are scored by risk impact, not line count. Middleware, auth, DB migrations, and shared kernel changes get thorough review (Critical). Public API changes and new modules get focused review (High). Bug fixes and new features following patterns get standard review (Medium). Docs and renames get a glance (Low).

What's the difference between Critical, Warnings, and Suggestions?

Critical findings must be fixed before merge (security, correctness, concurrency bugs). Warnings should be fixed to avoid tech debt (N+1 queries, missing tokens). Suggestions are nice-to-have improvements (sealing classes, naming).

How does this handle large pull requests?

Blast radius scoring focuses effort on the 20% of code causing 80% of incidents. Tools identify antipatterns and diagnostics automatically; manual review targets only high-risk areas, not every line.

Does this replace automated linters and formatters?

No. This skill focuses on logic, security, performance, and architecture—areas tools can't catch. Style and formatting are left to linters and formatters.

What MCP tools does this use?

detect_antipatterns (async void, DateTime.Now, broad catch), get_diagnostics (warnings, nullability), find_references (consumer count), get_dependency_graph (ripple effects), get_project_graph (architecture), and detect_circular_dependencies.

Full instructions (SKILL.md)

Source of truth, from codewithmukesh/dotnet-claude-kit.


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 RadiusExamplesDepth
CriticalMiddleware, auth, DB migrations, shared kernel, CI/CDThorough — every code path
HighPublic API changes, message consumers, EF configuration, new moduleFocused — consumers + behavior
MediumNew feature following existing patterns, bug fix, new endpointStandard — checklist pass
LowDocs, formatting, renames, logging statementsGlance — 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:

PriorityAreaCheck
1Data accessN+1 (missing Include/projection), raw SQL with user input, missing CancellationToken
2SecurityEvery endpoint has explicit [Authorize]/[AllowAnonymous], input validated, no secrets in code, no PII in logs
3ConcurrencyToken propagated end-to-end, no .Result/.Wait(), thread-safe shared state
4IntegrationRetry/timeout on external calls, consumer idempotency, no swallowed exceptions
5CorrectnessBusiness logic, edge cases (empty/null/concurrent), entities mapped to DTOs at the boundary
6TestsBehavior tested (not implementation); happy path + main error case covered
—Style/namingMention 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.

## 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