dave-wind/auto_train_skills
Apply ML training loops to prompt engineering — run evals, LLM-grade outputs, and track pass rates to iteratively improve Claude Code skills
Apply ML training loops to prompt engineering — run evals, LLM-grade outputs, and track pass rates to iteratively improve Claude Code skills
npx add-skill dave-wind/auto_train_skillsApply ML training loops to prompt engineering — run evals, LLM-grade outputs, and track pass rates to iteratively improve Claude Code skills
AI-powered GA4 + GTM event tracking — automates site analysis, event schema, GTM sync, preview verification, and publishing. Works with Cursor, Codex, and any AI agent.
Curated Claude Code plugin marketplace for quality engineering, test automation, and SDLC tooling — ELITEA Next MCP, QA agents, test framework skill bundles (qavajs, Vividus, Tosca, ServiceNow ATF), agent-evaluator, and sdlc-skills.
Detect, redact, and block crypto private keys and seed phrases in text. Prevent sensitive secrets from leaking to LLMs, AI agents, logs, and external services
全球最大的 Claude Code 技能聚合库 · 收录 3900+ 来自 12+ 来源的技能，提供在线搜索与趋势分析看板 / The world's largest Claude Code skill aggregation hub — 3900+ skills from 12+ sources with online search and trend dashboard
Second brain for AI agent: auto memory injection, FTS5/vector/code search, compounding, drift detection, MCP, and optional Obsidian export.
Four agent skills for Playwright and Cypress: generate E2E tests from scratch with live browser exploration, review existing specs against 19 anti-patterns (P0/P1/P2 severity), and debug failures from playwright-report/ or cypress/reports/. For Claude Code, Codex, and OpenCode.