Skills DirectorySkills Directory
SkillsLearnSecurityCategoriesDocsBlogPro
Sign InSubmit Skill
Skills Directory

Security-tested agent skills for Claude, coding agents, and AI workflows.

Directory

  • Browse Skills
  • All Skills A–Z
  • Claude Skills
  • Claude Code Skills
  • Agent Skills
  • Categories
  • Authors
  • Submit a Skill

Learn

  • Learn Hub
  • Install Claude Skills
  • Write SKILL.md
  • Skills vs MCP
  • Directories Compared

Security

  • Security
  • Methodology
  • Secure Claude Skills
  • Security Badges
  • Chrome Extension
  • Skill Manager

Company

  • About
  • Community
  • Blog
  • API Docs
  • Advertise

2026 Skills Directory. All rights reserved.

ProTermsPrivacyRefunds
Back to skills

Review Local

ASecurity

Orchestrated code review of git diff using parallel agents. Standard mode (diff-scoped) or full mode (adds Roslyn semantic analysis). Produces severity-grouped plan.

2 stars
0 votes
0 copies
0 views
Added 10/6/2026
code-qualitygorefactoringcode-reviewgitsecurityperformance

Works with

mcp

Security Analysis

A100/100

Pro scans all 8 files and shows the line behind each finding

Scanned 10/6/2026

$npx -y skills add e128/dotnet-reference --skill review-local --agent claude-code

Installs into .claude/skills of the current project.

Are you the author of Review Local?

Add the live security badge to your README — it updates automatically with every re-scan.

Security grade badge for Review Local
[![Security: A — Skills Directory](https://www.skillsdirectory.com/api/skills/e128-review-local/badge)](https://www.skillsdirectory.com/skills/e128-review-local)

More formats (shields.io, HTML) on the badges page. Keep it an A: scan every change in CI with Pro.

Download with Pro
Files
SKILL.md
---
name: review-local
description: >
  Orchestrated code review of git diff using parallel agents. Standard mode (diff-scoped)
  or full mode (adds Roslyn semantic analysis). Produces severity-grouped plan.
when_to_use: "dispatched by review router"
argument-hint: "[--full] [days N | commits N] [--perf] [--test-quality] [dry run] [critical only]"
user-invocable: true
---

# Review: Local Mode

Comprehensive code review using orchestrated agents. Discovers changed .NET files from git history, dynamically identifies code review agents, runs them in parallel, and produces a consolidated report grouped by severity.

**Standard mode (default):** Day-to-day review, fast turnaround, diff-scoped agent review only.
**Full mode (`--full`):** Pre-ship review, maximum coverage, adds solution-wide Roslyn semantic analysis (antipatterns + circular dependencies).

## Usage

```
code review days 1            # Standard
review --full last 3 days     # Full 3-vector
dry run                       # Preview only
critical only                 # Filter to CRITICAL
--perf                        # Spawn a performance-focused review agent
--test-quality                # Load enriched test rubric
```

## Scope Parameters

| Pattern in user message          | Scope                                           |
|----------------------------------|-------------------------------------------------|
| `days N` / `last N days`         | `scripts/diff.sh --days N --files`              |
| `commits N` / `last N commits`   | `scripts/diff.sh --commits N --files`           |
| `dry run` / `preview`            | Discovery only, no agents                       |
| `critical only` / `high+`        | Filter report by min severity                   |
| `--perf`                         | Spawn a performance-focused review agent on diff scope |
| `--test-quality`                 | Inject enriched Test Quality Rubric              |

If no scope is provided, ask for one.

## --perf and --test-quality Flags

**--perf:** Spawn a performance-focused review agent on diff scope in addition to normal review agents, using the anti-pattern catalog in [references/perf-patterns.md](references/perf-patterns.md). Findings merged into report.

**--test-quality:** Load enriched Test Quality Rubric from [references/review-rubrics.md](references/review-rubrics.md) and inject into agent prompts for `tests/**/*.cs` files.

## How It Works

### Phase 1: Discovery

Run in parallel: no ordering dependency:
- Parse arguments from user input
- Gather change context: `scripts/diff.sh --json`, with `--days N` or `--commits N` when the scope names one
- Discover agents dynamically: read `.claude/agents/`. Filter to code-review-relevant agents (include: code, review, check, fix, validate, compliance, security, quality, refactor, build, test, warning, diagnostic, concurrency, performance, exclude: pipeline, sanitizer, lode, corpus, mhtml, markdown, web, fetch, download)

From diff: filter to .NET files. Classify each changed file with `scripts/internal/mechanical-diff.sh --json`, files marked `MECHANICAL` (every changed token is a pure namespace-prefix substitution) are excluded from deep review. Generate unified diff. Pick per-agent-slice diff delivery with `scripts/internal/cr-diff-deliver.sh <difffile>`, it emits `inline` / `write <path>` / `split <paths…>` by the 30KB/40KB thresholds (writing to `.claude/tmp/cr-<name>.diff` or splitting at file boundaries). Clean up `.claude/tmp/cr-*.diff` after completion.

### Phase 2: Execution

**Vector 1: Code-Review Agents (always runs)**
Spawn agents in parallel: pass each the unified diff and severity rules. Include: "Review only the diff provided. Flag pre-existing concerns as 'adjacent concern' without investigating." Handle timeouts/errors gracefully.

**Vector 2: Roslyn Navigator (--full only)**
Run MCP calls in main context (session-only):
1. `mcp__cwm-roslyn-navigator__detect_antipatterns` with the solution file
2. `mcp__cwm-roslyn-navigator__detect_circular_dependencies` with the solution file

Severity mapping: Circular (cross-project) → HIGH, Circular (namespace) → MEDIUM, Antipatterns → MEDIUM, Generated code → SKIP, Informational → LOW.

Graceful degradation: if MCP unavailable, note "Roslyn navigator: MCP server not running, skipped".

### Phase 3: Plan Generation

See [references/implementation.md](references/implementation.md) for full orchestration details: dedup algorithm, severity grouping, plan file format (plan.md/tasks.md/context.md), report template, and analyzer-candidate mining integration.

### Phase 4: Exit

1. Offer to execute the plan if CRITICAL or HIGH issues
2. Spawn the `analyzer-review-miner` agent in background to mine findings for new analyzer candidates
3. Return exit code: 0 (clean/LOW), 1 (MEDIUM/HIGH), 2 (CRITICAL)

## Severity Classification

| Severity     | Description              | Examples                                          |
|--------------|--------------------------|---------------------------------------------------|
| **CRITICAL** | Blocks shipping          | Build failures, security vulns, race conditions   |
| **HIGH**     | Must fix before merge    | Analyzer errors, concurrency, perf regressions    |
| **MEDIUM**   | Should fix               | Code smells, refactoring, missing XML docs        |
| **LOW**      | Nice to have             | Style preferences, minor optimizations            |

## Review Rubrics

Seven rubric checklists in [references/review-rubrics.md](references/review-rubrics.md). Inject relevant sections into agent prompts based on diff content. Eighth rubric for multi-file consistency in [references/cross-file-consistency.md](references/cross-file-consistency.md).

## References

- [references/compliance-and-format.md](references/compliance-and-format.md)
- [references/review-rubrics.md](references/review-rubrics.md)
- [references/cross-file-consistency.md](references/cross-file-consistency.md)
- [references/error-handling.md](references/error-handling.md)
- [references/implementation.md](references/implementation.md)
- [references/clanker-patterns.md](references/clanker-patterns.md)
- [references/perf-patterns.md](references/perf-patterns.md)

Attribution

e128e128
View sourceSee grades on GitHubMore from e128 →
SSkills DirectorySkills Directory

Ship a skill? Prove it's safe.

Free 120-pattern security scan, letter grade, and an embeddable README badge.

Submit a skill

Is this your skill, or is something wrong with this listing? Request removal or report an issue. Author removals are honored within 72 hours.

Comments (0)

No comments yet. Be the first to comment!

SSkills DirectorySkills Directory

Ship a skill? Prove it's safe.

Free 120-pattern security scan, letter grade, and an embeddable README badge.

Submit a skill

Related Skills

Caveman Review

Ultra-compressed code review comments. Cuts noise from PR feedback while preserving the actionable signal. Each comment is one line: location, problem, fix. Use when user says "review this PR", "code review", "review the diff", "/review", or invokes /caveman-review. Auto-triggers when reviewing pull requests.

1100021 votes

Caveman Commit

Ultra-compressed commit message generator. Cuts noise from commit messages while preserving intent and reasoning. Conventional Commits format. Subject ≤50 chars, body only when "why" isn't obvious. Use when user says "write a commit", "commit message", "generate commit", "/commit", or invokes /caveman-commit. Auto-triggers when staging changes.

1100021 votes

Springboot Verification

Verification loop for Spring Boot projects: build, static analysis, tests with coverage, security scans, and diff review before release or PR.

2456590 votes

Verification Loop

一个全面的 Claude Code 会话验证系统。

2456590 votes

Django Verification

Verification loop for Django projects: migrations, linting, tests with coverage, security scans, and deployment readiness checks before release or PR.

2456590 votes
View all in code-quality →