Eval
alirezarezvani/claude-skills/engineering/agenthub/skills/evalby alirezarezvani19392f7a0826No license27K starsListed Oct 8, 2026Updated Oct 8, 2026Repository updated 5 weeks ago
Evaluate and rank agent results by metric or LLM judge for an AgentHub session. Use when the user runs /hub:eval or asks to score, compare, or pick a winner among completed AgentHub agents.
- 19392f7a0826Currentcommit 19392f7Published Oct 8, 2026
Source and attribution
Source:alirezarezvani/claude-skillsinengineering/agenthub/skills/evalat commit19392f7
License: No license
Content belongs to its original authors. SourceWeft indexes it from a public repository.
More from alirezarezvani/claude-skills
Chaos Engineering
alirezarezvani
Designs safe chaos engineering experiments with hypotheses, blast-radius estimates, abort criteria and postmortems.
Feature Flags Architect
alirezarezvani
Guides feature flag lifecycle: classify flags, plan rollouts, audit kill switches, and scan for flag debt.
Slo Architect
alirezarezvani
Defines, reviews and operates SLOs, SLIs and error budgets with three stdlib Python tools and reference guides.
General Counsel Advisor
alirezarezvani
Startup general counsel advisory: contract risk review, IP strategy, term sheet decoding and regulatory exposure mapping.
Run
alirezarezvani
Runs one manual autoresearch experiment iteration: review history, make one change, commit, evaluate, keep or discard.
Ux Researcher Designer
alirezarezvani
UX research toolkit for generating data-driven personas, journey maps, usability test plans, and research synthesis.
More in AI & Agents
Ppt Template Creator
anthropics
Turns a user's PowerPoint template into a reusable skill that generates branded presentations.
Skill Development
anthropics
Guides creation of Claude Code plugin skills, covering structure, descriptions, progressive disclosure and validation.
Plugin Structure
anthropics
Guides the structure, manifest, and component layout of Claude Code plugins.
Command Development
anthropics
Guides creation of Claude Code slash commands, covering structure, YAML frontmatter, arguments and plugin features.
Claude Md Improver
anthropics
Audits CLAUDE.md files in a repository, scores their quality, and applies approved targeted improvements.
Find Skills
vercel-labs
Guides discovery, quality checking and installation of agent skills via the npx skills CLI.