agent-skills vs AIWG
AI coding-agent workflows compared
agent-skills and aiwg both provide reusable workflows and guidance for AI coding agents. agent-skills centers on structured engineering practices across the development lifecycle, while aiwg also organizes project context and artifacts for reuse across sessions and supports workflows beyond software development.
agent-skills: Production-Grade Workflows for AI Coding Agents
A portable pack of Markdown engineering skills that helps AI coding agents follow senior-engineer workflows from scoping through shipping. It supports a range of agents, including Claude Code, Cursor, Codex, Copilot, and Gemini CLI.
AIWG: Reusable Workflows for AI Coding Tools
AIWG provides reusable project context, specialist agents, and workflows for tools including Claude Code, Codex, Copilot, and Cursor. Its TypeScript CLI deploys these assets across providers and supports persistent project artifacts, reviews, and optional decision support.
| agent-skills | AIWG | |
|---|---|---|
| Language | JavaScript | TypeScript |
| License | MIT | MIT |
| Stars | 109k | 224 |
| Forks | 11.3k | 34 |
| Last analyzed | Oct 20, 2026 | Oct 20, 2026 |
Key differences
- agent-skills focuses on 25 lifecycle skills, nine slash commands, verification checklists, and four specialist personas; aiwg provides agents, skills, rules, commands, templates, and workflow utilities across software and other domains.
- agent-skills packages portable Markdown skills and native integrations; aiwg deploys shared assets into provider-readable locations through its CLI and stores project artifacts in `.aiwg/`.
- agent-skills is written in JavaScript, while aiwg is written in TypeScript and requires Node.js 20 or newer.
- Both projects use the MIT license.
- The supplied figures list agent-skills at 101k stars and 10.6k forks, compared with aiwg at 224 stars and 34 forks.
- agent-skills describes an opinionated engineering process that teams can adapt; aiwg emphasizes retaining project decisions and context between sessions, with some behaviors dependent on provider and environment support.
Choose agent-skills if you…
- want structured, lifecycle-wide engineering workflows with explicit verification and shared quality checklists.
- need to introduce agent workflows incrementally or use portable skills across different coding-agent tools.
- prefer a focused engineering workflow pack with requirements, planning, implementation, testing, review, and shipping guidance.
Choose AIWG if you…
- need project requirements, decisions, plans, and reviews retained as artifacts for work across sessions.
- want reusable specialist workflows, multi-agent review patterns, or domain frameworks beyond software development.
- need CLI-based deployment of shared assets and optional utilities for indexing, diagnostics, memory, or MCP integration.
Compare the numbers side by side, or add more projects
This comparison is generated with AI from the OSRepos analyses of both projects. Always check each project's repository and documentation before choosing.