Skill profile
Agent Skills
Production engineering skills for AI coding agents from Addy Osmani.
Why builders use this
Agent Skills is worth studying because it gives builders a concrete engineering skills pattern with visible GitHub demand. Use the profile to decide whether to install it for your own AI agent workflow.
Before you use it
Agent Skills is an external open-source repo, not a first-party Build Lean SaaS skill. Review the source, license, permissions, and maintenance signal before you install or adapt it.
Expected outcomes
- Identify whether Agent Skills fits your agent stack
- Borrow a concrete pattern without copying unrelated assumptions
- Compare source quality, maintenance signal, license, and permissions before adoption
What it includes
- Engineering skills source and examples
- Shell implementation or reference material
- README guidance, issues, releases, or community discussion to review
Best for
- Builders evaluating engineering skills for practical agent work
- Teams that want to install a proven public repo before inventing their own pattern
- Operators who need visible source, examples, and tradeoffs before trusting an agent workflow
Use this if
- You want production-minded engineering skills for AI coding agents.
- You need review, testing, debugging, and implementation routines more than broad inspiration.
- You want a skill pack that can be installed or adapted incrementally.
Skip this if
- You are looking for marketing, design, or non-engineering operator skills.
- You cannot inspect shell scripts and local permissions before use.
- You need a framework for multi-agent orchestration rather than coding-agent skills.
How to evaluate it
- Run one skill on a disposable repo with tests.
- Compare the agent plan and final diff to your engineering standards.
- Review scripts for file, shell, and network behavior before adding them to a default environment.
Best first task
Try one bounded workflow before adding it to your agent stack.
Install or copy one engineering skill into a sandbox coding-agent setup and ask it to fix a small failing test.
Before you trust it
- Read the README, license, and setup path end to end
- Run it first with low-risk data or a sandbox repository
- Keep changes reviewable and remove assumptions that do not match your stack
Related repos
Comparable alternatives
GStack
Agent skill stack · 109k stars
Role-based CEO, design, engineering, release, docs, and QA workflows for agentic coding.
Awesome CursorRules
Cursor rules · 39.9k stars
A collection of Cursor rule files that shape AI editor behavior across frameworks and workflows.
Aider
Coding agent · 37.9k stars
AI pair programming in the terminal with Git-aware code edits.
Marketing Skills
Marketing skills · 32.8k stars
Marketing skills for Claude Code and AI agents across CRO, copywriting, SEO, analytics, and growth engineering.
Shared by / maintained by
Shared by Addy Osmani. Maintained at addyosmani/agent-skills. BuildLeanSaaS curates the profile for discovery and evaluation, not as an endorsement claim from the maintainer.
Daily X highlights
Building a related agent skill repo?
Submit it for review. Strong fits can get a directory profile like this one, a BuildLeanSaaS X highlight, and a spot in future blog roundups for builders comparing real workflows.
Submit yours for X highlightSuggested install path
Review the source, then test it on a real task.
Open addyosmani/agent-skills and review the README, license, and relevant files.
Adapt the smallest useful workflow instead of copying the entire repo blindly.
Run it on one low-risk task and keep the changes reviewable before making it part of your default agent workflow.
Builder learning path
Want help turning these repo ideas into working agent systems?
BuildLeanSaaS teaches builders how to evaluate public examples, design safer workflows, and ship agent-backed product systems with review loops.
Explore the skills marketplace