sasonov/shipshape
Tool-gated front-end QA & pre-deploy hardening skill for Claude Code — Lighthouse, axe, Playwright, semgrep, gitleaks. Proves every finding with tool output.
Tool-gated front-end QA & pre-deploy hardening skill for Claude Code — Lighthouse, axe, Playwright, semgrep, gitleaks. Proves every finding with tool output.
npx add-skill sasonov/shipshapeTool-gated front-end QA & pre-deploy hardening skill for Claude Code — Lighthouse, axe, Playwright, semgrep, gitleaks. Proves every finding with tool output.
Agent Loom is a repo-local truth system for coding agents
📊 把 Agent Skill 变成可测、可比、可改进的系统 · 35 个核心概念系统学习 OpenAI Agent Skills Evals 方法论
Automate Securitytrails tasks via Rube MCP (Composio). Always search tools first for current schemas.
🧩 Enhance Claude Code behavior with clear guidelines inspired by Andrej Karpathy's insights on common pitfalls in LLM coding practices.
A production-ready framework for secure AI-assisted software engineering. Features auto-discovery rules, CI/CD quality gates, and strict compliance with the Karpathy Principles for Cursor, Claude, and Copilot.
封装 MiniMax 语音、图片、视频和音乐能力为 4 个技能，方便快速接入生成与编辑工作流