YoavLax/AgentEval
Cross-agent quality gate for SKILL.md and agent.md files. Spec validation, description scoring, reference checks, and cross-platform compatibility warnings — all in one tool. Based on the agentskills.io specification.
Cross-agent quality gate for SKILL.md and agent.md files. Spec validation, description scoring, reference checks, and cross-platform compatibility warnings — all in one tool. Based on the agentskills.io specification.
npx skills add YoavLax/AgentEvalCross-agent quality gate for SKILL.md and agent.md files. Spec validation, description scoring, reference checks, and cross-platform compatibility warnings — all in one tool. Based on the agentskills.io specification.
Score your repo's AI-agent harness — CLAUDE.md, AGENTS.md, skills, rules — then remediate the findings. Install: npx skills add paniolo-ai/scan
Provide a curated set of tools and resources to secure Claude Code and its AI coding environment for production deployment and threat management.
Governed shared memory for AI agent fleets — multi-agent, multi-tenant, MCP-native. Trust tiers, keystone policies, audit trails, knowledge graph, self-improving retrieval. Apache 2.0.
Open-source AI agent. Lives in your terminal.
23 位专家 + 9 个圆桌的三层 AI 专家技能体系（Claude Code / Agent Skills）
让 Coding Agent 自己负责 git。一个 Claude Code Skill。