Boring Is All You Need: a Codex Desktop workflow replacement with transactional migration, audit-only managed hooks, risk-based review, scoped checkpoint commits, and release evidence.
ZeroSpec is a zero-dependency Markdown framework that helps AI agents understand your repository structure, rules, and source of truth before coding.
《阿里巴巴Java开发手册(黄山版)》Coding Agent Skill —— 极致优雅的Java代码实现，拒绝屎山堆积。
Agent skills for coding CLIs, multi-agent runtimes, context engines, MCP extensions, and terminal tooling. Instead of using claude code's source code, give your agent skills to create your own!
Guided, user-approved AGENTS.md adoption and durable development-note workflows for Codex. | 面向通用 Agent 的基础开发准则，依据真实环境与用户偏好配置，涵盖子代理委派、工具使用、上下文管理、媒体处理、恢复与验证，并提供首次安装配置 Skill。
Windows operator workbench for running many AI coding agents across many projects with SAIPEN continuation, scheduling, workers, and routing.
Shared project memory across Codex, Claude Code, Kimi Code, Antigravity, and any coding-agent harness.
Local-first coding agent verification and adversarial review with frozen evidence, moderated findings, and human final acceptance.
Evidence-based Unreal Engine 5.8 benchmark for complete AI game-building systems using Epic Unreal MCP, playable tasks, packaging, and launch proof.
Workflow for building AI projects with Claude and auditing them with Codex. Claude builds, Codex audits, and Still configures the project.
Lightweight fast-path instruction package for AI coding agents: reduces unnecessary context loading and adds state-aware validation.
agent-toolkit is a shared, agent-agnostic AI development toolkit for Codex, Cline, and other coding agents. It combines reusable skills, engineering rules, frontend design standards, image-to-code workflows, Playwright testing, security and code reviews, and project-agnostic development workflows into a version-controlled toolkit.
给 AI 编程立规矩的契约驱动开发系统：10 份契约 + 强制执行守卫（T0-T3 分级、自检、PCS），解决 AI 失忆、重复造轮子、上下文爆炸与返工。Contracts + enforcement skill for reliable AI coding.
Shared-memory operating environment for AI coding agents. The repo is the memory: agents wake severed from private context and start from the same record.
For people who keep Agent Skills on their machine or team drive. Switch repos without dragging the same pack everywhere: keep one local catalog, then use kit to pick and install the right skills per project so your coding AI gets what that repo needs, without a cloud marketplace.
A portable Agent Skill for generating safe, valid, and version-aware native Windows PowerShell commands across AI coding agents.
Versioned engineering rules, sync tooling, and evals for reliable coding-agent workflows across Git repositories.
Build curated agent skills for coding CLIs, terminal tools, context engines, remote bridges, and multi-agent runtimes
Open-source starter kit for agentic AI development. Includes Docker-based dev environment, MCP servers, local and cloud LLM support, VS Code Dev Containers, automation scripts, and AI coding workflows.
Public evidence for AIC coding-agent evaluations: frozen patches, canonical verifier scores, integrity hashes, cost, timing, and task context.
To associate your repository with the coding-agents topic, visit your repo's landing page and select "manage topics."