agent-eval基于Karpathy AutoResearch和多Agent复盘的闭环量化评估体系，实现任务自动yes/no评判与持续优化升级。
Install via ClawdBot CLI:
clawdbot install luaqnyin/agent-evalGrade Limited — based on market validation, documentation quality, package completeness, maintenance status, and authenticity signals.
Generated Aug 4, 2026
An organization uses Agent Eval to automatically score all outgoing communications (e.g., reports, memos, press releases) against a checklist for format compliance, absence of AI-sounding phrases, data verifiability, and role appropriateness. The system flags underperforming documents for human review and tracks quality trends over time, enabling continuous improvement.
A legal department deploys Agent Eval to evaluate AI-generated contract reviews. Each review is scored on completeness of risk clause identification, citation of legal references, actionable recommendations, and coverage of critical clauses. Low-scoring reviews are escalated to senior lawyers, and the feedback loop refines the review agent's performance.
An academic journal uses Agent Eval to assist in the peer-review process. Each manuscript is evaluated against criteria such as identification of substantive flaws, evidence support, bias detection coverage, statistical rigor, and constructive feedback. This helps editors triage submissions and provides authors with structured feedback.
A healthcare AI system generates clinical recommendations that are scored by Agent Eval for policy compliance, data timeliness, clinical relevance, evidence grading (e.g., GRADE), and awareness of potential biases. High-scoring recommendations are automatically accepted, while others are flagged for clinician review, ensuring patient safety and regulatory alignment.
Offer Agent Eval as a cloud-based service where companies subscribe to evaluate their AI agents' outputs. Revenue comes from monthly or annual subscription fees based on the number of agents evaluated and usage volume.
Provide expert consulting to tailor the eval checklists to specific industries and integrate with existing workflows. Revenue from consulting fees, implementation services, and ongoing maintenance contracts.
Charge clients based on the improvements in their agent performance scores, with a base fee plus a percentage of the value added. Revenue model aligns with outcome, pricing based on score improvement metrics.
💬 Integration Tip
Integrate Agent Eval with your existing memory/pattern storage (e.g., Phoenix Memory) to automatically feed eval results back into agent configuration for continuous improvement.
Scored Apr 19, 2026
Meta-skill for AI agent self-improvement. Analyzes runtime logs to detect error patterns, regressions, and inefficiencies, then generates structured improvem...
Stop waiting for prompts. Keep working.
Turn OpenClaw into a learning-loop agent with seeded workspace rules, skill promotion, reflective memory, and proactive maintenance.
Meta-agent skill for orchestrating complex tasks through autonomous sub-agents. Decomposes macro tasks into subtasks, spawns specialized sub-agents with dynamically generated SKILL.md files, coordinates file-based communication, consolidates results, and dissolves agents upon completion. MANDATORY TRIGGERS: orchestrate, multi-agent, decompose task, spawn agents, sub-agents, parallel agents, agent coordination, task breakdown, meta-agent, agent factory, delegate tasks
Complete toolkit for creating autonomous AI agents and managing Discord channels for OpenClaw. Use when setting up multi-agent systems, creating new agents, or managing Discord channel organization.
Billions decentralized identity for agents. Link agents to human identities using Billions ERC-8004 and Attestation Registries. Verify and generate authentic...