Code review

jazz-max/ruflo-hub

Skill Claude Code

Comprehensive GitHub code review with AI-powered swarm coordination.

baleen37/bstack

Plugin Claude Code

Bundles 26 skills · 896 tokens together

Matt Pocock's agent skills for real engineering: grilling, spec/ticket flows, TDD, code review, domain modelling and more. Plug-and-play, not vibe coding.

tufantunc/review-pro

Plugin Cursor

Bundles 1 plugin

Tiered AI code-review: triage -> relevant specialist reviewers -> synthesis. Reviews AI-written code using AI agents.

V-Songbird/foundry

Skill Claude CodeCodex

Coordinate a Foundry plugin's Claude and Codex README editions, preserving common product content and verifying platform-specific installation, availability and benchmark evidence. Use for paired README edits, benchmark updates or a README parity review before release.

aabhisrv/Spiderbrain.ai-Coremind

MCP server Claude CodeCodexCursor +2

Deterministic context layer for your codebase: change impact, blast radius, answers with receipts. Runs locally from the spiderbrain npm package. Needs 3 environment variables to run.

justinstimatze/gemot

Skill Claude CodeCodex

Review code with multiple specialist subagents, then use gemot to find where they disagree and why. Requires gemot MCP server configured.

md-log/md-log-mcp

MCP server Claude CodeCodexCursor +2

Model Context Protocol server (stdio + remote Streamable HTTP) that lets agents save .md files (with images) straight into md-log. A thin authenticated HTTP client over the hosted md-log service. Runs locally from the md-log-mcp npm package. Needs 2 environment variables to run.

DownAtTheBottomOfTheMoleHole/megalinter-mcp

MCP server Claude CodeCodexCursor +2

MCP server "megalinter" as configured in DownAtTheBottomOfTheMoleHole/megalinter-mcp. Runs ./dist/index.js with node.

javiermrcom/awesome-claude-code

Plugin Claude Code

Bundles 4 commands, 1 agent · 90 tokens together

Safe, intelligent Git workflow for AI-assisted coding with enterprise-grade safety guardrails.

salrad22/code-sentinel

MCP server Claude CodeCodexCursor +2

Code quality analysis MCP server - detects security issues, deceptive patterns, and placeholders. Runs locally from the code-sentinel-mcp npm package.

jigyasudham/veto

MCP server Claude CodeCodexCursor +2

93 agentic MCP tools + 49 specialist agents for every major AI CLI. Self-learning, no API keys. Runs locally from the @jigyasudham/veto npm package.

jghiringhelli/forgecraft-mcp

MCP server Claude CodeCodexCursor +2

CLI + MCP sentinel for engineering standards — SOLID, testing, architecture, CI/CD — auto-tailored to your stack. Minimal MCP footprint (200 tokens) via CLI-first design. Runs locally from the forgecraft-mcp npm package.

morluto/gitcontribute

MCP server Claude CodeCodexCursor +2

Local-first GitHub contribution research workbench. Runs locally from the gitcontribute npm package.

nikolay-e/diffctx

Plugin Claude Code

Bundles 2 commands, 1 MCP server · 28 tokens together

Selects the minimum code an LLM needs to review a git diff.

NYTC69/review-loop

Plugin Claude Code

Bundles 7 skills, 12 agents · 1,017 tokens together

AI-driven code review with independent adversarial review, automated quality polish, and multi-language static analysis. 12 agents, 5 skills, full Plan-Execute-Review-Polish pipeline.

madisonrickert/claude-skills

Plugin Claude Code

Bundles 1 skill · 317 tokens together

Comprehensive, rubric-driven, whole-repository code audit that ends in a prioritized improvement plan with an executive health grade.

ivuorinen/skills

Plugin Claude Code

Bundles 7 skills, 50 commands, 2 agents, 3 hooks, 1 MCP server · 650 tokens together

Nitpicker — hostile audit toolkit: /nitpicker dispatches specialist audit commands (adversarial review, security, tests, docs, types, architecture, perf, reliability, caching, concurrency, error handling, leaks, deps, licensing, CI, commits, migrations, observability, API contracts, a11y, i18n, privacy, confi.

trilwu/gauntlet-loop-skills

Plugin Claude Code

Bundles 2 skills · 423 tokens together

Skills packaging the Gauntlet Loop — build → blind-critic → revise → repeat against a hard bar — for coding, writing, design, data, research, prompt evaluation, detection engineering, and authorized security testing.

justnau1020/claude-os

Skill Claude Code

Orchestrate a full-project consistency audit using a parallel agent team. Spawns lane-specific auditors to cross-reference docs vs code vs tests vs infra, deduplicates findings, and writes a severity-scored audit report.

int2t05/engineering-skills

Plugin Claude Code

Bundles 47 skills, 1 hook · 3,422 tokens together

Unified engineering skills pack for Claude Code — 47 skills organized by the software development lifecycle (product → research → design → develop → tune → test → verify → ship → operate), with shared engineering principles injected at session start, plus product and design principle references linked by domain skills.

hedimanai-pro/guardsman

Plugin Claude Code

Bundles 1 skill · 221 tokens together

Right-sized code, verified before it ships. Risk-tiered engineering judgment for AI coding agents: convention detection, blast-radius tiers, mandatory verification, and a scannable logbook for deliberate shortcuts.

qiao/rust-api-guidelines-skill

Skill Claude CodeCodex

Enforces the official Rust API Guidelines (https://rust-lang.github.io/api-guidelines/) when writing, reviewing, or refactoring Rust library code. Use this skill whenever you are writing new Rust structs, enums, traits, functions, or modules that form a public API — including when designing error types, implementing…

nmoinvaz/speedy-gonzales

Command Claude Code

Walk through changed code comments and pick a writing variation for each.

skillsdirectory/awesome-ai-skills

Skill Claude CodeCodex

Write maintainable, SOLID code with proper design patterns, refactoring techniques, and clean architecture principles. Use when starting new projects, refactoring legacy code, or reviewing architectural decisions.