claude

reviewer-eval

Turn a defect a reviewer missed into a kept eval case, and prove the rule that should catch it: missed under today's rules, caught with the new one, quiet on the fixed commit.

0 on GitHubby Stanislav Krasnoyarovv0.1.0MITupdated yesterdayworkflow
/

Plugin reviewer-eval from marketplace redsteep in redsteep/skills. Commands read from the repo's manifest — today.

What it installs

Skills (1)

  • reviewer-eval

    Turn a defect a reviewer missed into a kept eval case, and prove the instruction that should catch it — the reviewer must miss it under today's rules, catch it with the amended rule, and stay quiet on the fixed commit, each run in its own subagent on throwaway worktrees. Use when the user asks to "c

View source on GitHub

More from redsteep/skills

All 9 plugins →

Gated review of a finished feature branch before the PR: surface vs the spec, E2E, architecture, test strategy, mutation testing, refactor. Blocks `gh pr create` until the review has run.

1 skill · 3 agents · hooks

0

Adversarial review of a proposed design against the code it lands in — seven named tests from DDD and SOLID, read as a slice across every layer. Before implementation on the spec, and again on the branch to catch drift.

1 skill · hooks

0

factory

claude

A software factory on your own box: Trello cards labelled `ready` become one PR per step, at most three in flight. A dispatcher on a timer runs one background Claude worker per step; you approve each spec and review each PR from the Claude app, pinged on Slack. Only the tiniest PRs auto-merge, through a deterministic gate hook.

1 skill · hooks

0

While you read a PR, Claude answers questions and runs things but queues change requests instead of editing. Turns on automatically after `gh pr create`.

1 command · hooks

0

When you correct Claude's implementation, it fixes the code and proposes the one-line instruction change that would have prevented it.

hooks

0

Unattended night run: takes one allowed tech-debt item (GitHub issues by default, any backlog via the profile) to a PR — a draft only while a gate stays open — proposes markings for a few more, and notifies through a project-defined command.

1 command

0

Similar plugins

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

superpowers

claudecodex

Core skills library for Claude Code: TDD, debugging, collaboration patterns, and proven techniques

15 skills · hooks

obra/superpowers 316,836

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

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

Backend API design, GraphQL architecture, workflow orchestration with Temporal, and test-driven backend development

9 skills · 1 command · 8 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

Maintain reviewer-eval?

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 plugins9 plugins