claude

pr-review-loop

Autonomous PR review automation with multi-bot support (Gemini, Cursor, Claude)

13 on GitHubby Devon Jonesv1.17.3MITupdated 3 days agoproductivity
/

Plugin pr-review-loop from marketplace devon-claude-skills in devonjones/devon-claude-skills. Commands read from the repo's manifest — 2 days ago.

What it installs

Skills (1)

  • pr-review-loop

    Manage the PR review feedback loop: monitor CI checks, fetch review comments, and iterate on fixes. Use when: (1) pushing changes to a PR and waiting for CI/reviews, (2) user says "new reviews available", (3) iterating on PR feedback from Gemini, Cursor, Claude, or other reviewers, (4) monitoring PR

Subagents (6)

  • code-reviewer

    Reviewer that audits PR diffs for CLAUDE.md compliance and significant bugs. Quotes the exact CLAUDE.md rule when flagging violations; uses confidence ≥80 threshold and the touch-it-you-own-it scope rule.

  • code-simplifier

    Reviewer that flags genuinely confusing complexity, redundant abstractions, dense one-liners that hurt readability, and nested-ternary anti-patterns. Use when reviewing PRs where simplification would meaningfully improve clarity without altering behavior.

  • comment-analyzer

    Reviewer that audits code comments for factual accuracy, comment rot, and long-term maintenance value. Use when reviewing PRs that add or modify comments, docstrings, or inline documentation.

  • pr-test-analyzer

    Reviewer that audits test coverage for behavioral completeness — focuses on critical gaps, untested branches, and brittle tests that overfit implementation. Use when reviewing PRs that add or modify business logic, validation, parsing, error handling, or any code path that warrants test coverage.

  • silent-failure-hunter

    Reviewer that hunts silent failures, inadequate error handling, and inappropriate fallback behavior in PR diffs. Use when reviewing code that adds or modifies try-catch blocks, error handlers, fallback logic, optional chaining, or any path where errors could be suppressed without surfacing.

  • type-design-analyzer

    Reviewer that evaluates type design quality (encapsulation, invariant expression, usefulness, enforcement) on four 1-10 axes. Use when reviewing PRs that introduce new types, modify existing type definitions, or change validation at construction or mutation boundaries.

View source on GitHub

More from devonjones/devon-claude-skills

All 10 plugins →

dream

claude

Mine Claude Code session logs and PR review history into durable project improvements (memories, CLAUDE.md, docs, reviewer-roster tuning) — async 'AI dreaming'.

2 skills

13

Turn a web article into a faithful-capture literature note in an Obsidian vault (fetch + structured extraction; the article sibling of youtube-synthesizer)

1 skill

13

Assess a Claude skill against Anthropic's skill authoring best practices: measured limits, judged criteria, description trigger test, evaluations, and a verdict.

1 skill

13

handoff

claude

Compact the current conversation into a handoff document for another agent (new session, teammate, different agent) to pick up the work without ramping from zero.

1 skill

13

Image generation, editing, and composition using Google's Gemini 3 Pro Image model

1 skill

13

rodney

claude

Drive Chrome from the shell with the rodney CLI: pages, clicks, waits, JS, asserts, screenshots.

1 skill

13

Similar plugins

caveman

claude

Talk like caveman. Cut filler. Keep technical details explicit.

22 skills · 1 command · 3 agents · hooks

JuliusBrussee/caveman 119,462

claude-mem

claudecodex

Persistent memory for Claude Code: the next session starts where the last one left off.

29 skills · 1 MCP server · hooks

thedotmack/claude-mem 116,618

Taste Skill

claudecodex

tasteskill 2.5.1: professional company websites at the figma.com and x.ai level, with one section per screen, real photographs, real product UI, effects kept for tech and gaming pages, and a real-browser checker and finish gate.

1 skill

Leonxlnx/taste-skill 114,391

career-ops

claudecodex

Open-source AI job search that runs locally in your AI coding CLI: scan job portals, evaluate listings into a structured A-H report with a 1-5 score, tailor your CV, track applications

5 skills · hooks

career-ops-hq/career-ops 82,253

mem0

claudecodex

Cross-session memory and token savings for coding agents.

6 skills · 1 agent · 1 MCP server · hooks

mem0ai/mem0 68,893

pake

claudecodex

Package any website or local web build into a lightweight desktop app with Pake CLI.

1 skill

tw93/Pake 63,463

Maintain pr-review-loop?

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 plugins10 plugins