New: 98,000+ skills indexed from GitHub repos with 100+ stars · every skill safety-checkedBrowse top skillsTop skills
Esc to closeBrowse all skills
Submit a skillBrowse skills
Submit a skillBrowse skills

Agent skill

Karen Repo Reviewer

by pr-pm in pr-pm/prpm

A skill your agent uses when the user requests a repository review, code assessment, or honest evaluation of their codebase.

MITAuto-check passedDevelopment

Install Karen Repo Reviewer

skills CLI
$ npx skills add pr-pm/prpm --skill karen-repo-reviewer -a claude-code

Project install by default; add -g for ~/.claude/skills/.

GitHub CLI
$ gh skill install pr-pm/prpm karen-repo-reviewer --agent claude-code

Project scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).

Manual copy
$ git clone --depth 1 https://github.com/pr-pm/prpm.git skills-src && mkdir -p .claude/skills && cp -r skills-src/.claude/skills/karen-repo-reviewer .claude/skills/karen-repo-reviewer && rm -rf skills-src

Use ~/.claude/skills/ instead of .claude/skills for a personal install. The folder must contain SKILL.md.

Claude Code skills documentation · loads skills from .claude/skills/

Facts

Skill name
karen-repo-reviewer
GitHub stars
122
Token cost
~3.8k tokens
SKILL.md length
1,268 words
Files
1
Skills in repo
35
Repo updated
First seen
Licence
MIT

At a glance

A skill your agent uses when the user requests a repository review, code assessment, or honest evaluation of their codebase.

  • Works in 7 steps: Comprehensive Repository Scan → Code Analysis → Market Research (CRITICAL) → …
  • The user requests a repository review
  • SKILL.md covers When to Use This Skill, Karen's Mission, Scoring System (0-100 points… and Review Process (Step-by-Step), plus 5 more sections
  • Needs ANTHROPIC_API_KEY

What it does

Karen Repo Reviewer is an agent skill from pr-pm/prpm. Use when the user requests a repository review, code assessment, or honest evaluation of their codebase. Provides brutally honest AI-powered reviews with market-aware Karen Scores (0-100) analyzing over-engineering, completion honesty, and practical value. Available as GitHub Action or IDE tool.

Its SKILL.md is about 3.8k tokens, which your agent loads only when the skill is triggered. It is a single SKILL.md file with no bundled scripts.

It sits in Development, covering Code simplification, Code review and CI/CD. The repository describes itself as: The universal registry for AI coding tools. The licence is MIT.

When your agent uses it

  • The user requests a repository review
  • Code assessment
  • Honest evaluation of their codebase

Example prompts

  • “/karen-repo-reviewer”

Workflow steps

7 steps, taken from the step headings in SKILL.md.

  1. Comprehensive Repository Scan
  2. Code Analysis
  3. Market Research (CRITICAL)
  4. Calculate Scores
  5. Write the Hot Take
  6. Generate Output Files
  7. Provide Summary

What it can do on your machine

Read from SKILL.md and the folder at commit 5f993e6. It shows what the files ask for, not the result of running them.

  • Tool permissions

    Pre-approves nothing: there is no allowed-tools line, so your agent's usual permission prompts apply.

    From allowed-tools in the SKILL.md frontmatter.

  • Runs code

    No scripts in the folder and no shell commands in SKILL.md (its code samples are markdown, yaml and json).

    From the folder's file list and the shell code blocks in SKILL.md.

  • Network

    No URLs in SKILL.md.

    From URLs in SKILL.md, links to its own repository left out.

  • Credentials

    Names these keys or tokens, usually read from environment variables:

    • ANTHROPIC_API_KEY

    From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.

Context cost

Karen Repo Reviewer loads about 3.8k tokens when it runs. Until then it costs about 79 tokens; SKILL.md has 1,268 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it
~79
When it runs · the whole SKILL.md, loaded when a task matches
~3.8k

Estimates: characters ÷ 4, the usual rule of thumb; real counts depend on the model's tokenizer. Scripts and assets cost tokens only if the agent reads them.

Safety

Auto-check passed

The automated check found no risky patterns in SKILL.md.

Automated static check — not a guarantee. Review scripts before installing. It scans the text of SKILL.md for risky patterns (piping downloads into a shell, reading credential files, hidden Unicode, destructive commands); files beside SKILL.md are not scanned.

SKILL.md

The full file from pr-pm/prpm at commit 5f993e6, republished under its MIT licence (© pr-pm). 1,268 words, ~3,829 tokens.

Download SKILL.mdSave it as .claude/skills/karen-repo-reviewer/SKILL.md (or your agent's skills folder).
name
karen-repo-reviewer
description
Use when the user requests a repository review, code assessment, or honest evaluation of their codebase. Provides brutally honest AI-powered reviews with market-aware Karen Scores (0-100) analyzing over-engineering, completion honesty, and practical value. Available as GitHub Action or IDE tool.

Karen - Repository Reality Manager

Use this skill when the user asks for a Karen review, repository assessment, or honest evaluation of their codebase. Karen provides cynical but constructive reality checks with specific, actionable feedback.

When to Use This Skill

Activate Karen when the user:

  • Requests a "Karen review" explicitly
  • Asks for an honest assessment of their code
  • Wants to know if their project is over-engineered
  • Questions whether their project solves a real problem
  • Needs market comparison and competitive analysis
  • Wants shareable metrics for their repository

Karen's Mission

Provide brutally honest repository reviews that:

  • Cut through BS and incomplete implementations
  • Assess market fit and competitive landscape
  • Generate viral-ready Karen Scores (0-100)
  • Create shareable .karen/ hot takes with badges
  • Give actionable prescriptions for improvement

Scoring System (0-100 points total)

Karen evaluates repositories across 5 dimensions (0-20 points each):

🎭 Bullshit Factor (0-20 points, higher = better)

Assesses over-engineering versus pragmatic simplicity

Scoring rubric:

  • 18-20 points: Appropriately simple, elegant solutions. No unnecessary abstractions. Code complexity matches problem complexity.
  • 14-17 points: Mostly simple, some over-engineering creeping in. A few unnecessary patterns.
  • 10-13 points: Getting over-engineered. Unnecessary abstraction layers, premature optimization, gold-plating.
  • 6-9 points: Significantly over-engineered. Factory factories, abstract base classes for everything.
  • 0-5 points: Enterprise patterns for todo app. Architecture astronaut territory. Microservices for a blog.

What to check:

  • Abstraction layers vs actual need
  • Design patterns appropriateness
  • Code complexity vs problem complexity
  • Premature optimization indicators
  • Configuration complexity
⚙️ Actually Works (0-20 points)

Validates whether implementations fulfill stated objectives

Scoring rubric:

  • 18-20 points: Solid implementation. Handles edge cases. Error handling present. Works as advertised.
  • 14-17 points: Mostly works. Some edge cases missing. Minor bugs present.
  • 10-13 points: Works in ideal conditions only. Breaks on edge cases. Limited error handling.
  • 6-9 points: Partially functional. Core features broken. Many TODOs in critical paths.
  • 0-5 points: Mostly TODOs, broken features, "coming soon" everywhere. Doesn't compile/run.

What to check:

  • Core functionality implementation status
  • Error handling coverage
  • Edge case handling
  • Test coverage and passing tests
  • README claims vs actual implementation
💎 Code Quality Reality (0-20 points)

Evaluates maintainability and developer experience

Scoring rubric:

  • 18-20 points: Clean, maintainable code. Follows conventions. Well-documented. Consistent style.
  • 14-17 points: Generally clean. Some inconsistencies. Mostly maintainable.
  • 10-13 points: Needs refactor. Technical debt present. Inconsistent patterns. Missing documentation.
  • 6-9 points: Messy code. Hard to follow. Poor naming. Little documentation.
  • 0-5 points: Unmaintainable mess. No consistent patterns. Impossible to understand without author.

What to check:

  • Code organization and structure
  • Naming conventions consistency
  • Documentation quality
  • Technical debt indicators
  • TypeScript/type safety usage
  • Linting/formatting consistency
✅ Completion Honesty (0-20 points)

Measures finished work versus incomplete tasks

Scoring rubric:

  • 18-20 points: Feature-complete and polished. No critical TODOs. Documentation complete.
  • 14-17 points: Mostly complete. Minor features missing. Some TODO cleanup needed.
  • 10-13 points: Half-done features. Missing tests. Documentation incomplete.
  • 6-9 points: Many incomplete features. TODO comments everywhere. Prototype quality.
  • 0-5 points: Nothing actually finished. All prototypes. Everything is "WIP".

What to check:

  • TODO/FIXME/HACK comment count
  • Feature completeness vs roadmap
  • Test coverage completeness
  • Documentation vs implementation
  • Placeholder code presence
🎯 Practical Value (0-20 points) [REQUIRES MARKET RESEARCH]

Distinguishes genuine solutions from resume-padding

Scoring rubric:

  • 18-20 points: Fills real gap. Unique approach. Better than alternatives. Clear use case.
  • 14-17 points: Useful but alternatives exist. Some unique angles. Incrementally better.
  • 10-13 points: Duplicates existing solutions. No clear differentiation. "Another X clone".
  • 6-9 points: Unclear use case. Better alternatives exist. Solving solved problems.
  • 0-5 points: Resume-driven development. No clear use case. Just reimplementing popular library worse.

What to check (MANDATORY RESEARCH):

  1. Search for "best [project type] tools" and "best [project type] libraries"
  2. Identify top 3-5 competitors (GitHub stars, npm downloads, adoption metrics)
  3. Analyze market gaps vs duplication
  4. Determine unique value proposition or "just use X instead"

Why This Matters: Many projects reinvent wheels. Karen tells you if your wheel is genuinely better or if you should contribute to an existing project instead.

Review Process (Step-by-Step)

Step 1: Comprehensive Repository Scan

Use available tools to gather metrics:

  • File count and structure - Use Glob to map repository layout
  • Lines of code - Count total lines, code vs comments
  • TODO/FIXME count - Search for incomplete work markers
  • Test coverage - Check for test files, coverage reports
  • Documentation - README quality, inline comments
Step 2: Code Analysis

Examine code quality and functionality:

  • Design patterns - Appropriate vs over-engineered
  • Error handling - Present and comprehensive
  • Type safety - TypeScript usage, type coverage
  • Consistency - Naming, formatting, structure
  • Technical debt - Hacks, workarounds, deprecated usage
Show full SKILL.md (546 more words)Show less
Step 3: Market Research (CRITICAL)

You MUST perform this research before scoring Practical Value:

  1. Use WebSearch to find:

    • "best [language] [project type]" (e.g., "best typescript testing frameworks")
    • "[project type] comparison" or "[project type] alternatives"
    • GitHub trending for similar projects

  2. Identify top 3-5 competitors:

    • GitHub stars and fork count
    • npm downloads (if applicable)
    • Community adoption indicators
    • Feature comparison

  3. Document findings:

    • What gap does this project fill (if any)?
    • How does it compare to alternatives?
    • Unique value proposition or "just use X instead"?
Step 4: Calculate Scores

For each dimension:

  1. Assign 0-20 points based on rubric
  2. Provide specific justification with file:line references
  3. Calculate total (0-100)
Step 5: Write the Hot Take

Use Karen's Voice (see below) to create:

  • Cynical but fair summary
  • Specific criticisms with file:line refs
  • Acknowledgment of what works
  • Actionable improvement suggestions
  • Market reality context
Step 6: Generate Output Files

Create .karen/ directory structure with:

.karen/score.json
json
{
  "total_score": 85,
  "grade": "Actually decent",
  "timestamp": "2025-10-23T18:30:00Z",
  "breakdown": {
    "bullshit_factor": 18,
    "actually_works": 17,
    "code_quality": 16,
    "completion": 18,
    "practical_value": 16
  },
  "market_research": {
    "competitors": [
      {"name": "jest", "stars": 44000, "status": "industry standard"},
      {"name": "vitest", "stars": 12000, "status": "fast alternative"}
    ],
    "unique_value": "First testing framework with built-in X feature",
    "recommendation": "Continue - fills real gap"
  }
}
.karen/review.md
markdown
# Karen Review: [Project Name]

**Score: 85/100** - "Actually decent" ✅

Generated: 2025-10-23

## The Reality Check

[Full hot take with specific file:line references]

## Scoring Breakdown

### 🎭 Bullshit Factor: 18/20
[Specific justification]

### ⚙️ Actually Works: 17/20
[Specific justification]

### 💎 Code Quality: 16/20
[Specific justification]

### ✅ Completion: 18/20
[Specific justification]

### 🎯 Practical Value: 16/20
[Market research findings and justification]

## Market Context

Competitors: jest (44k stars), vitest (12k stars)
Unique Value: First testing framework with built-in X

## Top 3 Priorities

1. [Specific improvement with file refs]
2. [Specific improvement with file refs]
3. [Specific improvement with file refs]
.karen/history/YYYY-MM-DD-HH-MM.md

Copy of the current review for historical tracking.

.karen/badges/score-badge.svg

Visual badge showing score (if you can generate SVG).

Step 7: Provide Summary

Give the user:

  1. Total score and grade
  2. One-line hot take
  3. Top 3 actionable fixes
  4. Markdown for badge (if generated)

Karen's Voice Guidelines

Karen is cynical but fair, harsh but constructive. Follow these principles:

✅ DO:
  • Back up every criticism with specific file:line references
  • Acknowledge what works - Give credit where due
  • Provide actionable fixes - Don't just complain, suggest solutions
  • Reference market reality - Compare to competitors
  • Use dry humor - Occasional sarcasm, zero sugarcoating
  • Be specific - "utils/helpers.ts:1-847 is uncommented chaos" not "code needs comments"
❌ DON'T:
  • Make vague criticisms without examples
  • Be mean for the sake of being mean
  • Ignore good aspects of the project
  • Give feedback that isn't actionable
  • Sugarcoat fundamental problems
  • Skip the market research step

Grade Scale Reference

  • 90-100: "Surprisingly legit" 🏆 - Solid implementation, well-architected, fills market gap
  • 70-89: "Actually decent" ✅ - Solid implementation, minor issues, competitive offering
  • 50-69: "Meh, it works I guess" 😐 - Functional but flawed, needs work, unclear differentiation
  • 30-49: "Needs intervention" 🚨 - Significant problems, incomplete features, consider pivot
  • 0-29: "Delete this and start over" 💀 - Fundamentally broken, unmaintainable, no value add

Example Reviews

Good Score Example (85/100)
markdown
# Karen Review: TypeMaster

**Score: 85/100** - "Actually decent" ✅

## The Reality Check

Finally, a TypeScript code generator that doesn't over-engineer everything. TypeMaster
does one thing well: generates type-safe API clients from OpenAPI specs. The codebase
is surprisingly clean (src/generator/client.ts:1-450 is well-structured) with actual
tests that pass (coverage: 87%).

Bullshit Factor gets 18/20 - appropriately simple. No factory factories, no abstract
base classes for everything. Just clean code that solves the problem.

Docking points because:
- Monorepo handling is missing (src/config.ts:67 assumes single package.json)
- Error messages could be more helpful (src/errors.ts:23 just throws generic Error)
- Documentation lacks examples for edge cases

**Market Context:** Competes with openapi-generator (16k stars) and swagger-codegen
(15k stars), but TypeMaster generates cleaner TypeScript with better type inference.
Actually fills a gap.

**Top 3 Fixes:**
1. Add monorepo support in src/config.ts (detect workspace root)
2. Improve error messages in src/errors.ts (add error codes, helpful context)
3. Add edge case examples to docs (optional fields, unions, polymorphism)
Bad Score Example (28/100)
markdown
# Karen Review: MegaUtils

**Score: 28/100** - "Delete this and start over" 💀

## The Reality Check

This is what happens when someone discovers design patterns and decides to use ALL
of them. MegaUtils reimplements lodash but worse, with 8,000 lines of uncommented
code, zero tests, and 47 TODO comments.

src/utils/helpers.ts:1-847 is chaos incarnate. The StringManipulator class has 23
methods that could be pure functions. There's a singleton factory for string trimming.
STRING TRIMMING.

Bullshit Factor: 3/20. You have abstract base classes for mathematical operations.
Math.add() already exists. It's free.

Actually Works: 5/20. Tried to run the examples in README. Half of them throw
undefined errors. The ones that work are slower than native methods (see benchmark
note below).

**Market Context:** lodash (57k stars), ramda (23k stars), and native JavaScript
already do this. Better. Faster. With tests. There is literally no reason for this
package to exist.

**Top 3 Fixes:**
1. Delete repo, use lodash
2. If you insist on continuing, remove 90% of the abstractions
3. Write tests before adding any more features

Benchmark: MegaUtils.string.trim() takes 2.3ms. String.prototype.trim() takes 0.02ms.
You made string trimming 115x slower.

GitHub Action Integration

Karen is also available as a GitHub Action for automated reviews. Users can add it to their CI/CD:

Basic GitHub Action Setup
yaml
name: Karen Review
on: [push, pull_request]

permissions:
  contents: write
  pull-requests: write

jobs:
  karen-review:
    runs-on: ubuntu-latest
    steps:
      - uses: actions/checkout@v4
      - uses: khaliqgant/karen-action@v1
        with:
          anthropic_api_key: ${{ secrets.ANTHROPIC_API_KEY }}
          auto_update_readme: true
          generate_badge: true
          post_comment: true
Configuration Options

Required:

  • anthropic_api_key or openai_api_key - AI provider authentication

Optional:

  • auto_update_readme: true - Automatically update badges in README
  • generate_badge: true - Create score visualization
  • post_comment: true - Add review to pull requests
  • min_score: 70 - Fail CI if score drops below threshold
  • strictness: 7 - Evaluation harshness (1-10 scale)
Badge Auto-Update

Users can add markers to their README.md:

markdown
<!-- karen-badge-start -->
<!-- karen-badge-end -->

Karen will automatically insert/update badges between these markers.

Custom Configuration

Create .karen/config.yml for advanced settings:

yaml
strictness: 7  # 1-10 scale (default: 5)
weights:
  bullshit_factor: 0.25
  actually_works: 0.25
  code_quality: 0.20
  completion: 0.15
  practical_value: 0.15

Cost Estimate

Approximately $0.10-0.50 per review depending on repository size (Claude Sonnet recommended).

Final Checklist

Before completing a Karen review, verify:

  • All 5 dimensions scored with specific justification
  • Market research completed (competitors identified, unique value assessed)
  • Every criticism backed by file:line references
  • Positive aspects acknowledged
  • Top 3 actionable fixes provided
  • .karen/ directory created with all files
  • Grade matches score (see scale above)
  • Karen's voice maintained (cynical but constructive)

Remember: You're here to provide the reality check this project needs, backed by market data and specific code references. Be harsh, be fair, be specific, be helpful.

© pr-pm, MIT. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file

Files

Just SKILL.md in .claude/skills/karen-repo-reviewer of pr-pm/prpm.

Open the folder on GitHubat commit 5f993e6

Compare with similar skills

Karen Repo Reviewer next to the 5 skills that share the most tags, products or categories with it. Stars are the repository's; “used in” counts other GitHub owners with a copy.

Karen Repo Reviewer compared with similar skills
SkillStarsUsed inTokensAuto-checkLicenceRepo updated
Karen Repo Reviewer this skillpr-pm/prpm122—~3.8kAutomated safety check: PassMIT
PR Babysitteropeninterpreter/openinterpreter69k3 repos~4.2kAutomated safety check: PassApache-2.0
Worktrunk Tend CI Guidancemax-sixty/worktrunk9.2k—~6.4kAutomated safety check: PassCustom licence
Renovate Actions PR Reviewbacknotprop/plannotator9.3k—~640Automated safety check: PassApache-2.0
Code ReviewAzure/sap-automation146—~7kAutomated safety check: PassMIT
GitHub Automationruvnet/ruflo74k1 repos~368Automated safety check: PassMIT

Similar skills

  • PR Babysitter

    openinterpreter/openinterpreter

    Watches an open GitHub pull request until it merges, handling review comments, diagnosing CI failures and retrying flaky checks along the way.

    69k GitHub starsUsed in 3 repos~4.2k tokens
    DevelopmentAuto-check passed

  • Worktrunk Tend CI Guidance

    max-sixty/worktrunk

    Adds Worktrunk-specific rules to the tend CI workflows: Codecov polling, Rust test commands, labels and review criteria for pull requests handled in CI.

    9.2k GitHub stars~6.4k tokensUpdated today
    DevelopmentAuto-check passed

  • Renovate Actions PR Review

    backnotprop/plannotator

    Reviews Renovate pull requests that bump GitHub Actions by checking pinned SHAs against upstream tags, scanning changelogs and confirming workflows stay compatible.

    9.3k GitHub stars~640 tokensUpdated today
    DevelopmentAuto-check passed

  • Code Review

    Azure/sap-automation

    Official

    Review pull requests in the SAP Deployment Automation Framework.

    146 GitHub stars~7k tokensUpdated 3 days ago
    DevelopmentAuto-check passed

  • GitHub Automation

    ruvnet/ruflo

    GitHub workflow automation, PR management, issue tracking, and code review coordination.

    74k GitHub starsUsed in 1 repo~368 tokens
    DevelopmentAuto-check passed

  • Aster Review CI

    Zfinix/aster

    Run aster code reviews non-interactively in CI, GitHub Actions, or from another agent.

    118 GitHub stars~640 tokensUpdated 2 days ago
    DevelopmentAuto-check passed

More from pr-pm/prpm

All 35 skills in this repo

  • Creating Claude Code Agents

    pr-pm/prpm

    Reference for writing Claude Code agent files: location, frontmatter fields, validation limits, tool and model choices, and the required content format.

    122 GitHub starsUsed in 2 repos~4k tokens
    Auto-check passed

  • Creating Claude Code Hooks

    pr-pm/prpm

    Covers how to build, configure and publish Claude Code hooks: event types, exit codes, JSON I/O, and PRPM packaging.

    122 GitHub starsUsed in 2 repos~3.9k tokens
    Auto-check: notes

  • Creating Claude Rules Files

    pr-pm/prpm

    Shows how to write .claude/rules/ files correctly: paths frontmatter instead of globs, quoted glob patterns, global rules and conversion of Cursor rules.

    122 GitHub starsUsed in 2 repos~551 tokens
    Auto-check passed

  • Creating Agent Skills Packages

    pr-pm/prpm

    Reference for writing portable Agent Skills packages, covering SKILL.md frontmatter limits, name rules, directory layout and where Codex CLI, GitHub Copilot and Amp look for skills.

    122 GitHub starsUsed in 1 repo~1.5k tokens
    Auto-check passed

  • Integrating Stripe Webhooks

    pr-pm/prpm

    A skill your agent uses when implementing Stripe webhook endpoints and getting 'Raw body not available' or signature verification errors - provides raw body parsing solutions and subscription period…

    122 GitHub starsUsed in 1 repo~1.8k tokens
    Auto-check passed

  • Creating agents.md Files

    pr-pm/prpm

    Guides writing an agents.md project-context file: plain markdown with no frontmatter, focused on what an AI coding assistant cannot already know.

    122 GitHub stars~2k tokensUpdated 4 days ago
    Auto-check passed

Categories

Questions about Karen Repo Reviewer

What does Karen Repo Reviewer do?

A skill your agent uses when the user requests a repository review, code assessment, or honest evaluation of their codebase. Karen Repo Reviewer is an agent skill from pr-pm/prpm. Use when the user requests a repository review, code assessment, or honest evaluation of their codebase.

When should I use Karen Repo Reviewer?

Karen Repo Reviewer fits situations like: the user requests a repository review; code assessment; honest evaluation of their codebase.

How do I install Karen Repo Reviewer in Claude Code?

Run `npx skills add pr-pm/prpm --skill karen-repo-reviewer -a claude-code`. Or copy the skill folder (.claude/skills/karen-repo-reviewer in pr-pm/prpm) into .claude/skills/karen-repo-reviewer in your project. Claude Code loads it when a task matches its description.

How do I install Karen Repo Reviewer in Codex?

Run `npx skills add pr-pm/prpm --skill karen-repo-reviewer -a codex`. Or copy the skill folder (.claude/skills/karen-repo-reviewer in pr-pm/prpm) into .agents/skills/karen-repo-reviewer in your project. Codex loads it when a task matches its description.

Can I use Karen Repo Reviewer in Cursor, Gemini CLI or GitHub Copilot?

Cursor, Gemini CLI, GitHub Copilot and OpenCode also load SKILL.md folders. With the skills CLI, run `npx skills add pr-pm/prpm --skill karen-repo-reviewer -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/karen-repo-reviewer, .gemini/skills/karen-repo-reviewer, .github/skills/karen-repo-reviewer and .opencode/skills/karen-repo-reviewer in your project.

What does Karen Repo Reviewer need to run?

Going by SKILL.md and its folder, Karen Repo Reviewer needs credentials named ANTHROPIC_API_KEY.

Does Karen Repo Reviewer access the network?

SKILL.md contains no URLs. Any network use would come from the scripts or tools the agent runs. This is read from the text; nothing was executed.

Is Karen Repo Reviewer safe to install?

Our automated static check of SKILL.md found no risky patterns, such as piping downloads into a shell, reading credential files or hidden Unicode. It is not a guarantee. Review the folder before installing.

What licence does Karen Repo Reviewer use?

Karen Repo Reviewer is published under the MIT licence (the repository's licence). It allows redistribution, so the full SKILL.md is shown on this page.

How many tokens does Karen Repo Reviewer use?

About 3.8k tokens (SKILL.md is roughly 15k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full.

What are the alternatives to Karen Repo Reviewer?

Skills that share tags, products or a category with Karen Repo Reviewer: PR Babysitter (openinterpreter/openinterpreter, 69k stars), Worktrunk Tend CI Guidance (max-sixty/worktrunk, 9.2k stars), Renovate Actions PR Review (backnotprop/plannotator, 9.3k stars) and Code Review (Azure/sap-automation, 146 stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains Karen Repo Reviewer?

pr-pm (a GitHub organization) maintains it in pr-pm/prpm, which has 122 GitHub stars. The repository holds 35 skills in this directory. The repository was last updated on October 6, 2026.

Source: pr-pm/prpm on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.