Agent Eval — Content & Marketing agent for Claude Code
Оценивает качество работы конкретного subagent'а на репрезентативной выборке его прошлых run'ов.
How to install Agent Eval
Installs to ~/.claude/agents/kamilibragimov7772-lab-orchestrator-agent-eval.md
mkdir -p ~/.claude/agents && curl -fsSL https://raw.githubusercontent.com/kamilibragimov7772-lab/orchestrator/HEAD/agents/agent-eval.md -o ~/.claude/agents/kamilibragimov7772-lab-orchestrator-agent-eval.md Restart Claude Code, or start a new session, for it to be picked up.
What Agent Eval does
name: agent-eval description: Оценивает качество работы конкретного subagent'а на репрезентативной выборке его прошлых run'ов. Применяется к доменным агентам (strategy-researcher, decision-analyst, ghostwriter, content-strategist, etc.) — НЕ к системным (brief-architect, knowledge-curator, document-compiler). На вход: имя агента + glob путей к артефактам, которые он создал; на выход: файл-отчёт в `_agent_evals/` с оценкой по 5 осям (соответствие брифу, методологическая опора, формат, бюджет,
Alternatives in Content & Marketing
- SEO Content Planner — You are an SEO content strategist creating comprehensive content plans and outlines 31.9k ★
- Blog Researcher 550 ★
- Mako Marketing — Use this agent when dealing with marketing activities 523 ★
Full documentation available on GitHub
View Source RepositoryRelated Agents
Behavior Strategist
Use when the decision depends on friction, uncertainty, choice architecture, social proof, risk, defaults, sal
Effectiveness Strategist
Use when the decision depends on short versus longer marketing horizons, demand capture versus brand effects,
SEO Analyst
SEO specialist for technical SEO audits, keyword research, on-page optimization, content optimization, and lin
Growth Marketer
Elite growth marketing strategist who deeply researches the domain before producing anything. Combines brand s
Agency SEO Strategist
Stratège SEO Agency OS. À lancer à l'étape SEO Keyword Strategy de tout build (landing page, site SEO, e-comme
Eval Failure Analyzer
Analyze Logic-Lens benchmark/eval failures. Use after running content-evals, or when pointed at a skills-works
Related Skills
Diagnostic
Lance un diagnostic carrière complet (Interviewer → Researcher → Knowledge Builder → Strategist → Critic) et p
Agentic Terminal
AI-powered hacker terminal — chat with 4 specialised Claude agents (Researcher, Coder, Creative, Analyst) righ
Strategist
Product strategist that challenges assumptions, asks forcing questions, and validates ideas before any code is