Skip to content
store
eval

Open source alternatives to eval

24 open source AI Skills apps to use instead, best rated first.

Top picks

  1. G

    github-ops

    Launch

    github-ops is an agent skill from the ECC collection by affaan-m, listed on skills.sh. It manages a GitHub repository with a focus on community health, CI reliability and the experience of contributors. It covers triaging issues by classify

    Open source

  2. O

    opensource-pipeline

    Launch

    opensource-pipeline is an agent skill from the ECC collection by affaan-m, listed on skills.sh. It prepares a private project for safe public release through a three-stage pipeline. The fork stage strips secrets from a copy. The sanitise st

    Open source

  3. A

    andrej-karpathy-skills

    Launch

    andrej-karpathy-skills is a single CLAUDE.md file from the multica-ai project that is meant to improve how Claude Code behaves on coding tasks. It is derived from Andrej Karpathy's public observations about LLM coding pitfalls. The file dis

    Open source

  4. M

    microsoft/markitdown

    Launch

    markitdown-mcp is the MCP server package for MarkItDown, Microsoft's tool for converting many file formats to Markdown for language models. It is a lightweight server that runs over stdio, Streamable HTTP or SSE, and exposes one tool, conve

    Open source

  5. O

    od-contribute

    Launch

    od-contribute is an agent skill in the OpenDesign project that provides a guided, one-click contribution flow to the OpenDesign repository, written so that people without a coding background can send a real pull request. It is locked to the

    Open source

  6. G

    github-deep-research

    Launch

    github-deep-research is an agent skill from the DeerFlow project that researches a single GitHub repository in several rounds and writes a report in Markdown. It is for requests that need more than a README summary, such as a comprehensive

    Open source

More AI Skills apps

See all
7
M

modelcontextprotocol/server-everything

Exercises all features of the MCP protocol

Launch
8
M

modelcontextprotocol/server-filesystem

Direct local file system access

Launch
9
M

modelcontextprotocol/server-memory

Knowledge graph-based persistent memory for maintaining context

Launch
10
N

netdata/netdata#Netdata

Discovery, exploration, reporting and root cause analysis over Netdata metrics

Launch
11
L

Learn Claude Code

by shareAI-lab - A really interesting analysis of how coding agents like Claude

Launch
12
C

career-ops

Job-search skill collection for JD evaluation, ATS resumes, portal scans

Launch
13
S

Sequential Thinking

Dynamic and reflective problem-solving through thought sequences

Launch
14
R

Reactive Resume

A one-of-a-kind resume builder that keeps your privacy in mind

Launch
15
E

elie222/inbox-zero

Inbox Zero features on top of Gmail, such as finding emails

Launch
16
S

simple-issue-description

Turn a rough bug report, feature request, support note

Launch
17
C

Compound Engineering Plugin

by EveryInc - A very pragmatic set of well-designed agents, skills

Launch
18
S

SuperClaude

by SuperClaude-Org

Launch
19
M

MCP Toolbox for Databases

MCP Toolbox for Databases enables your agent to connect to your database

Launch
20
A

awslabs/mcp

Suite of servers for integrating with AWS services and resources

Launch
21
R

Ralph for Claude Code

by Frank Bria - An autonomous AI development framework

Launch
22
M

mobilerun

Automate your mobile devices with natural language commands

Launch
23
O

openstatus

Manage monitors, status pages

Launch
24
C

Claude Squad

by smtg-ai - A terminal app

Launch

About eval

E

eval

Evaluate and rank agent results by metric or LLM judge for an AgentHub session

Eval is an agent skill that ranks the results of agents working in an AgentHub session, so you can pick a winner. It supports three modes: a metric-based evaluation that runs a command you configure in each agent's worktree, an LLM judge that compares the diffs the agents produced, and a hybrid of the two. You can evaluate the latest session, a specific session by its ID, or force the LLM judge mode even if a metric is configured. The metric mode runs the evaluation command in each agent's worktree and scores the results against the criteria, while the judge mode reads the changes and compares them. The skill is triggered by the hub eval command, or when you ask to score, compare or pick a winner among agent results. It is useful when several agents have attempted the same task and you want an objective ranking before you merge one of them. It is part of the claude-skills collection by alirezarezvani and is listed on skills.sh, where its audit shows a warning from Gen Agent Trust Hub.

View evalAll AI Skills apps
Price
Free
Made by
alirezarezvani
Category
AI Skills
Website
github.com/alirezarezvani/claude-skills/eval