AI Agent Skills

Turn a task, plan, or feature request into a ready-to-paste Claude Code /goal command — a single completion condition with a measurable end state, a demonstrable proof,…

CodexDB generates code for SQL query processing via OpenAI's GPT-3 Codex model.

This repo contains Kubernetes manifests for the below mentioned topics

re_data - fix data issues before your users & CEO would discover them 😊

Playwright TypeScript Framework: a robust solution for testing Web (Desktop & Mobile), API, and Electron apps. With customized utilities, linting, logging, webhooks, and…

将手动测试用例转为 Playwright E2E 测试并执行时使用；含写自动化前的业务熟悉踩点、Page Object/Helper 编写、执行中的 Bug 证据收集与报告条目记录。不用于：纯 API 接口测试（api-testing）、以理解系统为目的的独立探索会话（exploratory-testing）、已确认 Bug 的根因分析…

Run multiple TokenMax SEO/GEO sites as a resumable, fail-closed fleet. Use when Codex needs to audit a site queue, execute one isolated site at a time, preserve determin…

Write and improve programs that call Jev, TypeSafe's System One model. Use when designing TypeSafe questions (Choice, Score, Noul), structuring state, composing answers…

Code, datasets, and checkpoints for the paper "Improving Passage Retrieval with Zero-Shot Question Generation (EMNLP 2022)"

An IoT Dash Like Button using an esp8266, a push button and GitHub Actions. Tested on an Adafruit Huzzah, SparkFun Thing, and Wemos D1 Mini

Code base for the meta-labeling papers published with the Journal of Financial Data Science

Blimp: Develop with Docker Compose in the cloud

A drop-in replacement for playwright-python patched with rebrowser-patches. It allows to pass modern automation detection tests.

Audit a named AI agent config, system prompt, tool-definition or instruction file (YAML, JSON, Markdown, text, or Python) with the released LintLang CLI, on request. Use…

Mantis is a unified infrastructure as code framework that replaces Terraform and Helm

Workflows for automation of AWS services setup from Github CI/CD