claude

evals-ai

Evaluate AI skills with static-quality scoring, real trigger checks, isolated with/without comparisons, blind judging, and self-contained local reports.

2 on GitHubby [email protected]v1.0.1Apache-2.0updated 6 days ago
/

Plugin evals-ai from marketplace zivi-development-marketplace in LiorZivi/ZiviDevelopmentMarketplace. Commands read from the repo's manifest — 5 days ago.

What it installs

Skills (1)

  • skill-eval

    Evaluate how good an existing skill is. Run a one-shot quality sweep over a target skill that (1) scores how well it is written, (2) checks whether its description triggers on the right requests, and (3) measures whether it adds real value versus no skill at all — then write a local JSON result and

Subagents (2)

  • skill-eval-analyzer

    Internal text evaluator for evals-ai:skill-eval. Reads a skill's authored text (never executes it) and scores it against the static-quality rubric, emitting strict JSON. Use only when the skill-eval workflow delegates static analysis.

  • skill-eval-judge

    Internal blind grader for evals-ai:skill-eval. Given one task output plus expectations, grades each expectation and emits strict JSON without knowing which configuration produced the output. Use only when the skill-eval workflow delegates value grading.

View source on GitHub

More from LiorZivi/ZiviDevelopmentMarketplace

All 13 plugins →

ads-commercials

claude

Vendored subset of coreyhaines31/marketingskills for paid ads and commercials: ads, ad-creative, attribution, analytics, cro, signup, paywalls, pricing, video, and product-marketing.

10 skills

2

agentic-ai

claude

Agentic engineering plugin with complex and simplified architecture planning, workspace-grounded onboarding, agent-memory workflows, and visual HTML explainers for PRs and local code changes.

6 skills · 3 agents

2

general-mcp

claude

Bundles user-wide MCP servers for Excalidraw, Playwright, Azure DevOps/ADO, Azure (azmcp), MongoDB (read-only), Meta Ads (read-only tools), and Microsoft Clarity (read-only analytics). Local servers launch via npx; ADO and Azure reuse your Azure CLI sign-in, MongoDB, Meta Ads, and Clarity read credentials from environment variables, and Excalidraw and Meta Ads use remote HTTP.

7 MCP servers

2

general-ops

claude

Bidirectional Copilot CLI remote-control bridges — step away from the terminal and keep the agent running by chatting with it from Microsoft Teams or Telegram. Progress, questions, completion markers, and requested file attachments post outbound; your replies auto-inject back into the session.

2 skills · hooks

2

content-ai

claude

AI-powered content generation plugin with skills for deep-dive research, branded presentations, and LinkedIn publishing.

2 skills

2

code-simplifier

claude

Agent that simplifies and refines code for clarity, consistency, and maintainability while preserving functionality. Focuses on recently modified code.

1 agent

2

Similar plugins

mattpocock-skills

claude

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

nextjs

claude

Official Next.js skills: adopt and optimize Cache Components, adopt Partial Prefetching, and verify runtime behavior against a running dev server.

6 skills

vercel/next.js 143,495

Taste Skill

claudecodex

tasteskill 2.5.1: professional company websites at the figma.com and x.ai level, with one section per screen, real photographs, real product UI, effects kept for tech and gaming pages, and a real-browser checker and finish gate.

1 skill

Leonxlnx/taste-skill 114,391

career-ops

claudecodex

Open-source AI job search that runs locally in your AI coding CLI: scan job portals, evaluate listings into a structured A-H report with a 1-5 score, tailor your CV, track applications

5 skills · hooks

career-ops-hq/career-ops 82,253

academic-research-skills

claude

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

Maintain evals-ai?

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 plugins13 plugins