engineering-methodology

IOSM v1.0 specification: reproducible methodology for continuous system improvement. Reference runtime implementation → github.com/rokoss21/iosm-cli

Provide a terminal-based AI tool to perform controlled, measurable engineering tasks directly on real codebases.

A reusable AI-first development framework for building software with AI agents.

任务架构通用智能体能力包 · 跨 Codex/Claude/Trae/Cursor 等 9+ 平台

One engineering workflow across Claude Code, Codex, Copilot, and Gemini CLI. A portable persona canon, process skills, and safety guardrails, kept in sync by design.

Let your AI agent review any software project with evidence, adaptive scoring, and actionable next steps. 让你的 AI Agent 基于真实证据审查任意软件项目，并给出自适应评分与可执行的下一步建议。

Metodología portable y agnóstica de agentes para desarrollar software con IA de forma estructurada, verificable y transferible entre herramientas como Claude Code, Codex y OpenSpec.

How I run AI coding agents: the ticket that binds them, the policy that constrains them, and the second signature that lets their work merge.

A constructional approach to engineering AI-powered workflow applications using TypeScript, SvelteKit, AWS CDK, Lambda, and a shared domain model.

Local-first authenticated browser automation for Claude Code — the Tap MCP server + skills. Record a logged-in browser task once; replay it forever in your own Chrome at zero LLM tokens.

A Claude Code harness and a knowledge-base format for building software with an AI assistant: rules, skills, hooks, and evidence-dated facts, derived from real installations.

A governed methodology for AI-assisted software engineering built around explicit context, task contracts, deterministic verification, evidence, durable memory, reconciliation, and human control.

A proof-driven, AI-accelerated method for taking infrastructure from idea to production — distilled from 3 production systems into drop-in templates (CLAUDE.md, rules, skills, commands, agents, hooks) for any project.