CommunityProduktivität & Zusammenarbeitgithub.com

alirezarezvani/eval

Bewertet und ordnet Agentenergebnisse nach Metriken oder LLM-Bewertung für eine AgentHub-Sitzung. Verwende diese Fähigkeit, wenn der Benutzer /hub:eval ausführt oder darum bittet, abgeschlossene AgentHub-Agenten zu bewerten, zu vergleichen oder einen Gewinner auszuwählen.

Was ist eval?

Die Fähigkeit `alirezarezvani/eval` ermöglicht es, Ergebnisse von verschiedenen KI-Agenten in einer AgentHub-Sitzung systematisch zu bewerten und zu vergleichen. Sie ist besonders nützlich, wenn du mehrere Agenten dieselbe Aufgabe ausführen lässt und die Ergebnisse anhand von Metriken (z. B. Genauigkeit, Geschwindigkeit) oder mittels eines LLM-Richters beurteilen möchtest. Die Fähigkeit wird durch den Befehl `/hub:eval` aktiviert und kann dazu verwendet werden, die beste Lösung zu identifizieren, eine Rangliste der Agenten zu erstellen oder einfach eine Punktzahl für jeden Agenten zu generieren. Sie unterstützt gängige AgentHub-Plattformen, indem sie die Ergebnisse aus der aktuellen Sitzung auswertet und eine strukturierte Bewertung zurückgibt. Dadurch erhält der Entwickler eine klare Übersicht über die Leistungsfähigkeit der getesteten Agenten und kann fundierte Entscheidungen treffen, welcher Agent für eine bestimmte Aufgabe am besten geeignet ist.

Funktioniert mit~Claude Code~Codex CLI~Cursor
Part ofAgent Workflows
npx skills add https://github.com/alirezarezvani/claude-skills/tree/main/skills/eval

Installed? Explore more Produktivität & Zusammenarbeit skills: steipete/gemini, steipete/gh-issues, steipete/skill-creator · View all 6 →

Original anzeigen→Alle Skills durchsuchen

In Ihrer bevorzugten KI fragen

Öffnet einen neuen Chat, in dem dieser Agent-Skill bereits geladen ist.

OpenAIChatGPTClaudeClaudeGeminiGeminiGrokGrokPerplexityPerplexityDeepSeekDeepSeek

Dokumentation

Was macht eval?

Bewertet und ordnet Agentenergebnisse nach Metriken oder LLM-Bewertung für eine AgentHub-Sitzung. Verwende diese Fähigkeit, wenn der Benutzer /hub:eval ausführt oder darum bittet, abgeschlossene AgentHub-Agenten zu bewerten, zu vergleichen oder einen Gewinner auszuwählen.

Funktionsweise

Die Fähigkeit analysiert die Ausgaben der Agenten aus der aktuellen AgentHub-Sitzung und wendet entweder vordefinierte Metriken (z. B. Antwortlänge, Korrektheit) oder eine Bewertung durch ein LLM an, um eine Rangliste zu erstellen.

Verwendung

  • Befehl: /hub:eval – löst die Bewertung aller abgeschlossenen Agenten in der Sitzung aus.
  • Optionen: Du kannst optional angeben, welche Metrik oder welcher LLM-Richter verwendet werden soll.

Beispiel

# In der AgentHub-Sitzung:
Agent A: "Lösung A"
Agent B: "Lösung B"

# Führe aus:
/hub:eval

# Ergebnis:
1. Agent B (Punktzahl: 9/10)
2. Agent A (Punktzahl: 7/10)

Unterstützte Plattformen

  • AgentHub (Standard)

Hinweise

  • Stelle sicher, dass alle Agenten ihre Ausführung abgeschlossen haben, bevor du /hub:eval aufrufst.
  • Die Bewertung basiert auf dem Sitzungskontext und den bereitgestellten Metriken.

Individual skills in this repo

This repo contains 20 individual skills — each has its own dedicated page.

alirezarezvani/aws-solution-architect

Design AWS architectures for startups using serverless patterns and IaC templates. Use when asked to design serverless architecture, create CloudFormation templates, optimize AWS costs, set up CI/CD pipelines, or migrate to AWS. Covers Lambda, API Gateway, DynamoDB, ECS, Aurora, and cost optimization.

alirezarezvani/board

Read, write, and browse the AgentHub message board for agent coordination. Use when the user runs /hub:board or asks to post, read, or inspect coordination messages between competing AgentHub agents.

alirezarezvani/board-prep

Board meeting preparation for the adversarial scenario, not the friendly one. Forces numbers-cold mastery, anticipates hard questions, builds a narrative that acknowledges weakness without losing the room. Use when preparing for a board meeting, an investor update, fundraising presentation, or any high-stakes adversarial review where every number must live in your head not just on a slide.

alirezarezvani/browserstack

Run tests on BrowserStack. Use when user mentions "browserstack", "cross-browser", "cloud testing", "browser matrix", "test on safari", "test on firefox", or "browser compatibility".

alirezarezvani/business-growth-skills

Router/index for the 4 business & growth skills bundled in this plugin: customer-success-manager (health scoring, churn risk, expansion), sales-engineer (RFP analysis, competitive matrices, PoC planning), revenue-operations (pipeline, forecast accuracy, GTM efficiency), and contract-and-proposal-writer. Use when a growth/revenue request doesn't obviously match one skill and you need to pick the right one (e.g., 'which accounts are at risk', 'should we bid on this RFP').

alirezarezvani/challenge

Pre-mortem plan analysis. Imagine the plan failed 12 months from now and work backwards to find the weaknesses. Surfaces assumptions, dependencies, and execution risks before committing resources. Use when before significant resource commitment, before presenting to a board or investors, when feedback has been one-sidedly positive, or when there is pressure to move fast and figure it out later.

alirezarezvani/claude-skills

Decision-grade entity research skill — produces a hypothesis-tested dossier on a specific company, person, nonprofit, or government org, not a generic profile. Forcing intake makes the user state their hypothesis upfront (what they already believe and want to verify or disprove) so the dossier tests it rather than confirms it. Output is an editable Word document (.docx) with verdict on the hypothesis, identity facts, 12-month activity timeline, network and reputation signals, red flags, conversation hooks tied to specific findings, and source-provenance audit log. Uses WebSearch + WebFetch + free APIs (SEC EDGAR, GitHub, ProPublica) as workhorses; optional BYOK MCPs enhance coverage. Use when the user asks for background research, diligence, or meeting prep on a specific entity (e.g., 'prep me for a meeting with [person/company]', 'due diligence on [company]'). Honors sensitivity exclusions for journalism + personal-vetting contexts.

alirezarezvani/c-level-advisor

10 C-level advisory agent skills and plugins for Claude Code, Codex, Gemini CLI, Cursor, OpenClaw. CEO, CTO, COO, CPO, CMO, CFO, CRO, CISO, CHRO, Executive Mentor. Multi-role board meetings, strategy routing, structured recommendations. For founders needing executive-level decision support.

alirezarezvani/coverage

Analyze test coverage gaps. Use when user says "test coverage", "what's not tested", "coverage gaps", "missing tests", "coverage report", or "what needs testing".

alirezarezvani/engineering-advanced-skills

Index of 37 advanced engineering agent skills for Claude Code, Codex, Gemini CLI, Cursor, OpenClaw. Use when browsing or choosing among the POWERFUL-tier engineering skills: agent design, RAG, MCP servers, CI/CD, database design, observability, security auditing, changelog/release automation, reliability (SLO/chaos/flags/operators), platform ops.

alirezarezvani/engineering-skills

Index of the engineering-team skills bundle for Claude Code, Codex, Gemini CLI, Cursor, OpenClaw, and 6 more tools. Architecture, frontend, backend, QA, DevOps, security, AI/ML, data engineering, Playwright, Stripe, AWS, MS365 (stdlib-only Python tools). Use when browsing or choosing among engineering-team role skills — load only the one specialist SKILL.md you need, never bulk-load the bundle.

alirezarezvani/extract

Turn a proven pattern or debugging solution into a standalone reusable skill with SKILL.md, reference docs, and examples. Use when the user runs /si:extract or asks to package a recurring solution from memory into a skill.

alirezarezvani/finance-skills

Router/index for the 2 finance skills bundled in this plugin: financial-analyst (ratio analysis, DCF valuation, budget variance, rolling forecasts) and saas-metrics-coach (ARR/MRR, churn, CAC/LTV, NRR, quick ratio). Use when a finance request doesn't obviously match one skill and you need to pick the right one (e.g., 'analyze these financials', 'how healthy are my SaaS metrics').

alirezarezvani/fix

Fix failing or flaky Playwright tests. Use when user says "fix test", "flaky test", "test failing", "debug test", "test broken", "test passes sometimes", or "intermittent failure".

alirezarezvani/generate

Generate Playwright tests. Use when user says "write tests", "generate tests", "add tests for", "test this component", "e2e test", "create test for", "test this page", or "test this feature".

alirezarezvani/hard-call

/em:hard-call — Framework for decisions with no good options. Use when every option is painful and a structured 10/10/10 + regret-minimization pass is needed — e.g. choosing between a layoff and a down round, or killing a beloved product line.

alirezarezvani/init

Set up Playwright in a project. Use when user says "set up playwright", "add e2e tests", "configure playwright", "testing setup", "init playwright", or "add test infrastructure".

alirezarezvani/loop

Start an autonomous experiment loop with user-selected interval (10min, 1h, daily, weekly, monthly). Uses CronCreate for scheduling. Use when the user runs /ar:loop or asks to run an autoresearch experiment continuously on a schedule.

alirezarezvani/marketing-skills

Directory and router for the marketing skills library. Use when you need to find the right marketing skill for a task, see what marketing capabilities exist, or get oriented in this plugin. 44 specialist skills across 8 pods (content, SEO + AEO, CRO, channels, growth, intelligence, sales enablement, ops), 59 stdlib Python tools. Routes to one skill — it does not execute marketing work itself.

alirezarezvani/merge

Merge the winning agent's branch into base, archive losers, and clean up worktrees. Use when the user runs /hub:merge or asks to land the winning AgentHub result and tidy the session.

Verwandte Skills

steipete/gemini

Gemini CLI one-shot prompts, summaries, generation, skills, hooks, MCP, or Gemma routing.

community

steipete/gh-issues

Fetch GitHub issues, select candidates, spawn background fix agents, open PRs, and optionally process PR review comments.

community

steipete/skill-creator

Create, edit, audit, tidy, validate, or restructure AgentSkills and SKILL.md files.

community

steipete/clawhub

Search, install, update, sync, or publish agent skills with the ClawHub CLI and registry.

community

steipete/coding-agent

Delegate coding work to Codex, Claude Code, or OpenCode as background workers; not simple edits or read-only code lookup.

community

steipete/mcporter

List, configure, authenticate, call, and inspect MCP servers/tools with mcporter over HTTP or stdio.

community
← More Produktivität & Zusammenarbeit skills