Agent Skills by Addy Osmani
Agent Skills
25 engineering skills across the development lifecycle: spec, plan, build, test, review and ship
- 111,542 ★ on the repository
- Last commit
- MIT
Install
- Works in
In your terminal, with SkillFoxx CLI
npx skillfoxx add skills/agent-skillsDetects the agents on your machine, shows the access level and pins the version.
Other ways to install
Access and checks
How we reviewMinimal accessThe tool runs nothing and makes no network calls.
- Skills are markdown instructions
This is third-party code. Review the repository files before installing.
What it does
The skills encode the workflows and quality gates senior engineers use, so the agent follows them consistently. Nine slash commands, including /spec, /plan, /build, /test, /review and /ship, map to lifecycle phases and activate the right skills. Each skill has steps, checkpoints and a table of common agent excuses with counter-arguments. They draw on practices from Software Engineering at Google.
Who it is for. Developers and tech leads who want the agent to stop skipping specs, tests and reviews.
Good fit when
- You are starting a feature and want a spec first
- You want test-driven development with red-green-refactor
- You need a five-axis review before merge
- You are designing an API or module boundaries
Not a fit when
- Quick prototypes where a formal process only slows you down
- Tiny one-line fixes
Example request
/spec add CSV export for reports, then /plan and /buildLimitations
A per-skill npx install copies only that skill folder without shared checklists from references, so those paths break. For Cursor and Windsurf skills are set up manually following the docs.
How to disable. Remove the agent-skills plugin in Claude Code or delete the skill folders from the agent's skills directory.
FAQ
What if the plugin install fails with SSH errors?
Add the marketplace via https://github.com/addyosmani/agent-skills.git or configure git to rewrite GitHub SSH URLs to HTTPS.
What does /build auto do?
It generates the plan and implements every task in one approved pass, keeping the verification steps.
Discussion
No questions or reviews yet.
Related
SkillsSkills for real engineers by Matt Pocock
Skills For Real Engineers
Small composable skills for engineering with agents: plan grilling, TDD, bug diagnosis, code review and architecture
Tech Leads Club Agent Skills
Agent Skills
A vetted skill registry with a CLI that installs into twenty-plus agents and an MCP server for on-demand skill lookup
Builder Skills
Skills for agents
A set of small skills from Builder.io for agent work habits: visual plans and diff recaps, docs-first checks, cross-agent review and clean status updates
Dimillian Skills
Skills
A set of 16 engineering skills for agents: Apple platform work, macOS packaging, React performance, code review and refactoring
A skills library that gives coding agents a development process: brainstorming, planning, TDD, subagents and code review
Two skills for coding agents: wtf audits a project before shipping, better-codex keeps the agent disciplined while working on code
Comparison with similar tools
Entries that share the main search query, and how they differ.
| Entry | Official | Authentication | Repository stars | Main difference |
|---|---|---|---|---|
| Agent Skills by Addy Osmani (this entry) | no | 111,542 | ||
| Copilot MCP | no | 506 | VS Code extension for finding and installing MCP servers and skills | |
| HeyClaude MCP | no | not required | 304 | a read-only MCP server for the HeyClaude registry |
README in short
A set of production engineering skills for agents, organized from defining work to shipping it. The README covers installation for Claude Code, Cursor, Antigravity, Gemini CLI, Windsurf, OpenCode, Copilot, Kiro, Codex and Command Code. It describes review personas, reference checklists and principles: process over prose, mandatory verification, progressive disclosure. A comparison with Superpowers and Matt Pocock's skills is linked.
README badge
Original SKILL.md
---
name: api-and-interface-design
description: Guides stable API and interface design. Use when designing APIs, module boundaries, or any public interface. Use when creating REST or GraphQL endpoints, defining type contracts between modules, or establishing boundaries between frontend and backend.
---
# API and Interface Design
## Overview
Design stable, well-documented interfaces that are hard to misuse. Good interfaces make the right thing easy and the wrong thing hard. This applies to REST APIs, GraphQL schemas, module boundaries, component props, and any surface where one piece of code talks to another.
## When to Use
- Designing new API endpoints
- Defining module boundaries or contracts between teams
- Creating component prop interfaces
- Establishing database schema that informs API shape
- Changing existing public interfaces
## Core Principles
### Hyrum's Law
> With a sufficient number of users of an API, all observable behaviors of your system will be depended on by somebody, regardless of what you promise in the contract.
This means: every public behavior — including undocumented quirks, error message text, timing, and ordering — becomes a de facto contract once users depend on it. Design implications:
- **Be intentional about what you expose.** Every observable behavior is a potential commitment.
- **Don't leak implementation details.** If users can observe it, they will depend on it.
- **Plan for deprecation at design time.** See `deprecation-and-migration` for how to safely remove things users depend on.
- **Tests are not enough.** Even with perfect contract tests, Hyrum's Law means "safe" changes can break real users who depend on undocumented behavior.
### The One-Version Rule
Avoid forcing consumers to choose between multiple versions of the same dependency or API. Diamond dependency problems arise when different consumers need different versions of the same thing. Design for a world where only one version exists at a time — extend rather than fork.
### 1. Contract First
Define the interface before implementing it. The contract is the spec — implementation follows.
```typescript
// Define the contract first
interface TaskAPI {
// Creates a task and returns the created task with server-generated fields
createTask(input: CreateTaskInput): Promise<Task>;
// Returns paginated tasks matching filters
listTasks(params: ListTasksParams): Promise<PaginatedResult<Task>>;
// Returns a single task or throws NotFoundError
getTask(id: string): Promise<Task>;
// Partial update — only provided fields change
updateTask(id: string, input: UpdateTaskInput): Promise<Task>;
// Idempotent delete — succeeds even if already deleted
deleteTask(id: string): Promise<void>;
}
```