claude

review-beta

Adversarial multi-aspect review. One entry skill routes any review request — docs, code, agent configuration, CI, front-end, mobile, whole-repo — to the aspect skills that apply, runs each in an isolated fork behind its own tool probe, and synthesizes one de-duplicated, verified report. Requires Claude Code v2.1.218 or later (the aspect skills rely on `background: false`).

3 on GitHubby Nathan Heapsv0.1.0updated todayutility
/

Plugin review-beta from marketplace ai-mktpl in nsheaps/ai-mktpl. Commands read from the repo's manifest — today.

What it installs

Skills (9)

  • agentic-configuration

    Invoked by review-beta:start, which routes every review request and decides which aspects apply — use that entry skill first; this is one of the aspects it delegates to. Reviews whether agent configuration is well built — skills, plugin manifests, hook wiring, agents, commands and the MCP config the

  • best-practices

    Invoked by review-beta:start, which routes every review request and decides which aspects apply — use that entry skill first; this is one of the aspects it delegates to. Reviews whether code follows the idiomatic practice its own ecosystem publishes, running scripts/probe-best-practices.sh — golangc

  • correctness

    Invoked by review-beta:start, which routes every review request and decides which aspects apply — use that entry skill first; this is one of the aspects it delegates to. Reviews a change for correctness defects and returns a structured findings report with a verdict, running scripts/probe-correctnes

  • design

    Invoked by review-beta:start, which routes every review request and decides which aspects apply — use that entry skill first; this is one of the aspects it delegates to. Reviews a change for design-health regressions and returns a structured findings report with a verdict, running scripts/probe-desi

  • docs

    Invoked by review-beta:start, which routes every review request and decides which aspects apply — use that entry skill first; this is one of the aspects it delegates to. Reviews documentation changes and returns a structured findings report with a verdict, running scripts/probe-docs.sh — lychee, mar

  • org-fit

    Invoked by review-beta:start, which routes every review request and decides which aspects apply — use that entry skill first; this is one of the aspects it delegates to. Reviews whether a change fits the organization it lands in, and returns a structured findings report with a verdict, running scrip

  • process

    Invoked by review-beta:start, which routes every review request and decides which aspects apply — use that entry skill first; this is one of the aspects it delegates to. Reviews how a change arrives and rolls out, and returns a structured findings report with a verdict, running scripts/probe-process

  • security

    Invoked by review-beta:start, which routes every review request and decides which aspects apply — use that entry skill first; this is one of the aspects it delegates to. Reviews a change for security defects and returns a structured findings report with a verdict, running scripts/probe-security.sh —

  • start

    Start here for every review request, before reaching for any other review skill. Works out what kind of review was actually asked for — documentation, code, agent configuration, CI, front-end, mobile, or a whole-repo audit — and returns a table of contents naming which aspect skills apply and in wha

View source on GitHub

More from nsheaps/ai-mktpl

All 57 plugins →

scm-utils

claude

Source control management utilities for improving interactions with branches and PRs, both locally and in CI environments

19 skills · 1 command · hooks

3

cloudflare

claude

Skills for managing Cloudflare developer platform components including Workers, R2, D1, AI Gateway, Pages, Tunnels, and more — with Pulumi IaC setup for each.

15 skills

3

claude-builtins

claude

Claude Code's built-in slash-command prompts, taken verbatim from the CLI binary and driven from portable plugin skills: /security-review (a senior-security-engineer review of the current branch vs origin/HEAD), /init (generate a CLAUDE.md), /insights (transcript scan, verbatim facet classification, and a self-contained HTML report), /team-onboarding (co-author an ONBOARDING.md from how you actually use Claude Code), and /usage (a local, approximate analysis of your transcripts — token counts plus the binary's relative weight; the built-in's server-side utilization/cost is not reproducible).

7 skills · 5 commands

3

google-workspace-cli

claude

Install and manage the Google Workspace CLI (gws) with per-service skills for Gmail, Calendar, Drive, Docs, Sheets, Slides, Chat, Tasks, Contacts, and Admin

11 skills · hooks

3

agentic-behavior

claude

Skills for configuring Claude Code, behavior correction, memory tracking, autonomy rules, time-context awareness, and session exit/restart. Combines prompt history tracking, git-backed memory sync, the self-checking Ralph loop pattern, and graceful session exit via SIGINT.

9 skills · hooks

3

sdlc-utils

claude

Software development lifecycle utilities — skills organized by SDLC phase: plan, implement, review, test, deploy, and maintain.

9 skills · 1 command

3

Similar plugins

mattpocock-skills

claude

Matt Pocock's agent skills for real engineering (grilling, spec/ticket flows, TDD, code review, domain modelling and more).

39 skills

mattpocock/skills 323,108

academic-research-skills

claude

5 skills + 35 modes + Material Passport pipeline. Includes v3.6.7 cross-model audit gate and v3.6.8 generator-evaluator contract.

5 skills · 16 commands · 4 agents · hooks

Imbad0202/academic-research-skills 56,698

open-code-review

claude

Perform AI code review on Git diffs — supports workspace changes, branch ranges, and single commits with concurrent per-file analysis, codebase search, and deep context-aware review.

2 commands

alibaba/open-code-review 50,068

agent-teams

claudecodex

Orchestrate multi-agent teams for parallel code review, hypothesis-driven debugging, and coordinated feature development using Claude Code's Agent Teams

6 skills · 7 commands · 4 agents

wshobson/agents 42,461

codex

claude

Use Codex from Claude Code to review code or delegate tasks.

3 skills · 8 commands · 1 agent · hooks

openai/codex-plugin-cc 35,098

lancedb

claudecodex

Write, review, debug, and document LanceDB pipelines in Python and TypeScript that work with both LanceDB Embedded and LanceDB Enterprise.

lancedb/lancedb 11,887

Maintain review-beta?

This page updates itself from your repo. Add the badge to your README, or get it Featured to pin it above the organic results with a followed link to your site.

claude & codex plugins57 plugins