autoreview
01Plugin Claude Code
Hard acceptance gate: review all session changes for production quality before marking work complete.
Provider-agnostic agent skills and plugins for AI coding assistants. By Robert Courson.
Plugin Claude Code
Hard acceptance gate: review all session changes for production quality before marking work complete.
Command
Hard acceptance gate — review all session changes for production quality before marking work done.
Skill Claude CodeCodex
Hard acceptance gate: review all session changes for production quality before marking work complete. Use when the user invokes /review, asks for a session review, production-quality check, final acceptance review, or before considering a task done.
Plugin Claude Code
Offensive hotspot-driven hunt workflow for bugs, pain points, and inefficiencies — 13 analysis lenses, a zero-dependency toolkit (deterministic hotspots, structured findings, fingerprinted dedupe, baseline diffing, SARIF/HTML/markdown reports, CI exit codes), enforceable verification and coverage in CI, a fast…
Command
Fast bughunt variant — fan out Composer 2.5 / Grok hunters via the Cursor CLI (cursor-agent), with the skeptic pass kept on a strong reasoner. Report-only.
Command
Hunt for hidden bugs, pain points, and inefficiencies across a codebase and report ranked, reproducible, baseline-diffed findings (report-only).
Command
Flush out hidden bugs dynamically with property-based / fuzz / differential harnesses.
Command
Triage a suspected bug or a set of findings — severity × confidence, minimal repro, standard report.
Skill Claude CodeCodex
Adversarial, hotspot-driven bug-hunting workflow for bugs, pain points, and inefficiencies across project types (iOS, macOS, web, services, terminal tools). A zero-dependency toolkit ranks hotspots, agents inspect risk areas through 13 analysis lenses, a mandatory skeptic pass refutes false positives, and strict merge…
Skill Claude CodeCodex
Flush out hidden bugs dynamically by generating property-based tests, fuzz targets, or differential oracles, RUNNING them against the project's own test runner, then shrinking failures into regression tests or ready-to-commit harnesses. Use when the user invokes /fuzz, wants to harden a function, or when bughunt needs…
Skill Claude CodeCodex
Triage a suspected bug or a set of findings into a ranked, evidence-backed report: assign severity and confidence, build a minimal reproduction or failing test, and emit the standard finding schema (markdown + JSON). Use when the user invokes /triage, hands you a crash or suspicious behavior to assess, or when bughunt…
Plugin Claude Code
Design, critique, and scaffold native macOS apps — HIG, Liquid Glass, menus, toolbars, sidebars, safe areas, accessibility, SwiftUI/AppKit.
Command
Design, critique, or scaffold a native macOS app (HIG, Liquid Glass, SwiftUI/AppKit).
Skill Claude CodeCodex
Design, critique, or scaffold native macOS applications using current HIG, Liquid Glass, menu/toolbar conventions, safe areas, accessibility, and SwiftUI/AppKit patterns. Use when the user invokes /macos-design or names this skill for macOS app design, UI review, native UI generation, or notch-style / Dynamic Island…
Plugin Claude Code
Design and implement macOS Dynamic Island / notch-style apps — NSPanel, geometry, state machine, module widgets (media, HUD, shelf, agents).
Command
Design or implement a macOS Dynamic Island / notch-style app (NSPanel, modules).
Skill Claude CodeCodex
Design and implement macOS Dynamic Island / notch-style apps: NSPanel, hardware-aligned geometry, state machine, module widgets (agent monitor, media, HUD, shelf, camera). Use for /macos-notch or notch-style macOS UI.
Plugin Claude Code
Smoke-test macOS .app/.pkg in disposable Tart VMs via the macbox CLI or MCP.
Command
Smoke-test a macOS .app/.pkg in a disposable Tart VM — launch, logs, screenshots, crashes.
Skill Claude CodeCodex
Test, launch, debug, smoke-test, or validate a macOS .app or .pkg in a disposable local Tart VM via macbox CLI or MCP. Use when the user mentions macbox, macOS sandbox, VM smoke test, guest automation, or isolated app testing.
Plugin Claude Code
Product-driven greenfield Next.js: intake profiles, typed env, Vitest, tRPC, Neon/Drizzle, optional Clerk, Vercel, intake add-ons (AI SDK, Resend, Stripe, Sentry, PostHog).
Command
Greenfield or extend a Next.js app (Tailwind v4, tRPC, TanStack Query, optional Clerk, Neon/Drizzle, Vercel).
Skill Claude CodeCodex
Greenfield or extend a Next.js app with Tailwind v4, tRPC, TanStack Query, optional Clerk, Neon/Drizzle, Vercel, and intake-selected add-ons (AI SDK, Resend, Stripe, Sentry, PostHog) fully installed and build-green. Use for /scaffold or new project setup.
Plugin Claude Code
Opinionated design director for frontend interfaces. Reviews, fixes, and builds UI with a 38-pattern anti-slop standard — color, typography, layout, copy, interaction, production. One command, zero AI slop.
At most 3 mods per repository are shown here — the rest are on their repository pages: