stancsz/skills-flow
Gradient descent for agent skills. An ML-style execute→evaluate→refine loop that trains a SKILL.md + scripts against labeled scenarios to a target pass rate on a held-out split.
Gradient descent for agent skills. An ML-style execute→evaluate→refine loop that trains a SKILL.md + scripts against labeled scenarios to a target pass rate on a held-out split.
npx skills add stancsz/skills-flowGradient descent for agent skills. An ML-style execute→evaluate→refine loop that trains a SKILL.md + scripts against labeled scenarios to a target pass rate on a held-out split.
Automate Grafbase tasks via Rube MCP (Composio). Always search tools first for current schemas.
A full-stack AI Red Teaming platform securing AI ecosystems via OpenClaw Security Scan, Agent Scan, Skills Scan, MCP scan, AI Infra scan and LLM jailbreak evaluation.
Manage and sync AI skills and MCP servers for coding tools with Git-based updates in one desktop interface.
飞书（lark）文档导出未 Markdown 格式，支持文档内的画板数据导出。AI 友好，支持 Agent Skill
A modular MCP server that provides commonly used developer tools for AI coding agents
Browser and V8 exploitation playbook. Use when exploiting JavaScript engine vulnerabilities including JIT type confusion, incorrect bounds elimination, and V8 sandbox bypass to achieve renderer RCE and sandbox escape in Chrome/Chromium.