Skip to content

$aisearch
$cd/explore
$cd/occupations
$ls/categories
$watchtrending
$bookcoaching
$mandocs

Frontend Backend ML / AI Data Science Prompt Engineer DevOps iOS Android Designer SQL SEO Marketing Finance Game Dev Image Gen Productivity

Prompt Engineer

> Need hands-on help? Book a 1-on-1 coaching session

$100/hr · pay-per-session →

The marketplace for AI skills. Discover, share, and install skills for Claude and beyond — made by creators, curated for builders.

Explore

All skills
Categories
Search
Featured

Build

Submit a skill
Create a skill
API
Blog

Company

About
Contact
FAQ
Changelog

Legal

Privacy
Terms
Cookies
Disclaimer
DMCA
Acceptable Use
Security
Accessibility

Popular searches

Claude Code skills
SKILL.md examples
RAG skills
AI agent skills
Prompt engineering
MCP server skills
Claude Sonnet skills
Claude vs ChatGPT
Cursor AI skills
Frontend Claude skills
Backend Claude skills
SQL Claude skills
DevOps AI skills
SEO content AI
iOS development AI
Android AI skills
Testing & QA skills
Data science skills
Image generation
Video editing AI

Browse by role

$ Frontend engineer
$ Backend engineer
$ Mobile / iOS / Android
$ Data engineer
$ DevOps / SRE
$ Designer
$ Product manager
$ Marketer / SEO
$ Prompt engineer

Browse by tool

$ Claude Code
$ Cursor
$ Windsurf
$ VS Code
$ Zed
$ Warp
$ Raycast
$ GitHub Copilot

© 2026 ClaudeSkill. All rights reserved.

Not affiliated with Anthropic. Claude is a trademark of Anthropic, PBC.

$pwd:

~
explore
Prompt Engineer
evals-runner

// Build, run, and report on LLM evals. Pairwise comparisons, judges, regression detection.

Evals RunnerVerified Creator

git log --oneline --stat

HEAD

Stars: 2.9k
Forks: 98
Updated: Apr 27, 2026

repo --stat

stars
2.9k
forks
98
last update
Apr 27, 2026
license
MITv2.0.5

quickstart.sh

3 steps

1
Install
// Drops SKILL.md into ~/.claude/skills/
```
$ claude skills add evals-runner
```

2

Invoke

// Run from any project directory

$ claude --skill evals-runner "help me ship this"

3
Iterate
// Re-run with edits — Claude keeps the skill loaded
```
$ claude --skill evals-runner "now refactor it"
```

evals-runner/

references

references/
SKILL.mdopen
README.mdopen

SKILL.md

readonly

name:: Evals Runner
slug:: evals-runner
version:: v2.0.5
license:: MIT
author:: @evalforge
repository:: github.com/evalforge/evals-runner
categories:: Prompt Engineer QA / Testing
tags:: #evals#llm#benchmarks#judges#regression
description:: Build, run, and report on LLM evals. Pairwise comparisons, judges, regression detection.

features.md

3 capabilities

// What you can do with it

Automates the tedious parts of the workflow.
Gives Claude the right context, tools, and guardrails.
Produces consistent, reviewable output every time.

README.md

evals-runner/README.md

5 sections

Loading README…

@evalforge/index.json

more by author

authored by

Prompt Eval Kit
Design, run, and score prompt evaluations with variance-aware benchmarks and regression tracking.
2.2k

$ cat reviews/

Reviews

// No reviews yet. Be the first.

Loading review form…

$ ls related/

explore all →

web-accessibility-audit.md

@deque-axe

Web Accessibility Auditor · v4.9.1

Audit and fix WCAG 2.2 AA issues: ARIA, colour contrast, keyboard nav, and screen reader support.

5.8k 8.4k MPL-2.0

Frontend#accessibility#wcag#aria

2026-04-18cd ./web-accessibility-audit →

browser-use-automation.md

@browser-use

Browser Use Automation · v0.9.4

Drive a real browser to fill forms, scrape data, or test flows. Vision + DOM hybrid.

QA / Testing#browser-use#automation#scraping

2026-05-06cd ./browser-use-automation →

code-review-master.md

@reviewlab

Code Review Master · v3.1.0

PR review in Claude. Style, security, perf, tests — with file-by-file inline comments.

QA / Testing#code-review#pr#linting

2026-05-03cd ./code-review-master →

package.json

"author":

@evalforge

"repository":

evalforge/evals-runner

install --global

v1

$npx skills add evals-runner

# Paste into your shell, or drop into skills.sh to track installs per project.

download --local

[HINT] Paste the command into your terminal, or drop the unzipped files into ~/.claude/skills/.

on this page

Evals Runner
What it does
Install
How it works
Tips

need_help.md

Stuck?

Book a live 1-on-1 session — we can pair on this skill, or anything AI-related, in your own codebase.

Book a session — $100/hr