# Addy Osmani's Agent Skills

Source: https://trendhub.net/skills/addyosmani-agent-skills
Repository: https://github.com/addyosmani/agent-skills
Author: Addy Osmani (https://github.com/addyosmani)
License: MIT
GitHub stars: 118,372

Agent Skills is Addy Osmani's pack of 24 lifecycle skills that walk a coding agent from idea and spec through tests, review and launch, with written checkpoints and evidence at each stage. It adds slash commands such as /spec, /plan, /build and /ship, and suits developers who want production habits from their agent on Claude Code, Codex, Gemini CLI, Cursor and similar tools.

## What problems it solves

- **The agent skips specs and tests**: Each phase from definition to launch has its own skill with steps that must produce evidence before the agent moves on.
- **Quality standards live only in someone's head**: A constraints skill interviews you once, writes CONSTRAINTS.md and wires each threshold to a real command.
- **Confident answers that turn out wrong**: Doubt-driven development sends each non-trivial decision to a fresh reviewer told to find faults, not approve.
- **Agents talk themselves out of steps**: Every skill lists the usual excuses for cutting corners and a short rebuttal the agent is expected to follow.

## Install

### Claude Code

Adds the skills plus nine lifecycle slash commands; use /agent-skills:review where a built-in command shares the name.

```
/plugin marketplace add addyosmani/agent-skills
/plugin install agent-skills@addy-agent-skills
```

### Any agent via the skills CLI

Installs all skills into Claude Code, Cursor, Codex, Copilot, Cline and many other agents.

```
npx skills add addyosmani/agent-skills
```

### Codex

Needs Codex CLI v0.122 or later; skills are then called with @ in chat.

```
codex plugin marketplace add addyosmani/agent-skills
codex plugin add agent-skills@agent-skills
```

### Gemini CLI

Installs the skills for auto-discovery.

```
gemini skills install https://github.com/addyosmani/agent-skills.git --path skills
```

### Antigravity CLI

Installs as a native plugin; some releases need the namespaced skills invoked directly.

```
agy plugin install https://github.com/addyosmani/agent-skills.git
```

### Command Code

The first form installs per project, the second for all projects.

```
cmd skills add addyosmani/agent-skills
cmd skills add addyosmani/agent-skills --global
```

On Claude Code the plugin marketplace is the fullest route, because it brings the slash commands, reviewer personas and shared checklists; a single-skill npx install leaves out the repo-level references folder. If the marketplace step fails over SSH, use the HTTPS URL shown in the README.

## Skills

Skill names are shown as /name. Depending on the agent, a skill runs when it is relevant or when you call it by name; plugin installs may add a prefix.

- `/api-and-interface-design`: Designs the contract before the code, applying Hyrum's Law, a one-version rule and clear error semantics to interfaces. (https://github.com/addyosmani/agent-skills/tree/main/skills/api-and-interface-design)
- `/browser-testing-with-devtools`: Inspects a live page through Chrome DevTools MCP: DOM, console, network, performance traces and the accessibility tree. (https://trendhub.net/skills/addyosmani-agent-skills/browser-testing-with-devtools.markdown)
- `/ci-cd-and-automation`: Sets up a pipeline where lint, types, tests, build, audit and bundle checks must all pass before review. (https://github.com/addyosmani/agent-skills/tree/main/skills/ci-cd-and-automation)
- `/code-review-and-quality`: Reviews a change for correctness, readability, architecture, security and performance, labelling each finding by severity. (https://trendhub.net/skills/addyosmani-agent-skills/code-review-and-quality.markdown)
- `/code-simplification`: Cuts complexity in working code while keeping every input, output, side effect and error exactly the same. (https://github.com/addyosmani/agent-skills/tree/main/skills/code-simplification)
- `/constraint-driven-development`: Sets a written quality bar in CONSTRAINTS.md with default thresholds and flags diffs that skip tests or silence checks. (https://trendhub.net/skills/addyosmani-agent-skills/constraint-driven-development.markdown)
- `/context-engineering`: Sets up rules files and decides which specs, source files and error output the agent should load for each task. (https://github.com/addyosmani/agent-skills/tree/main/skills/context-engineering)
- `/debugging-and-error-recovery`: Halts feature work on any failure and walks a reproduce, localize, reduce, fix and guard checklist to the root cause. (https://github.com/addyosmani/agent-skills/tree/main/skills/debugging-and-error-recovery)
- `/deprecation-and-migration`: Decides whether old code should go, then plans compulsory or advisory deprecation and migrates consumers off it. (https://github.com/addyosmani/agent-skills/tree/main/skills/deprecation-and-migration)
- `/documentation-and-adrs`: Records significant decisions as ADRs in the project's existing format and spots docs that no longer match the code. (https://github.com/addyosmani/agent-skills/tree/main/skills/documentation-and-adrs)
- `/doubt-driven-development`: Hands each non-trivial decision to a fresh-context reviewer prompted to find faults, with an optional second model. (https://trendhub.net/skills/addyosmani-agent-skills/doubt-driven-development.markdown)
- `/frontend-ui-engineering`: Builds accessible, responsive components with composition-first patterns and checks them with the project's own tooling. (https://github.com/addyosmani/agent-skills/tree/main/skills/frontend-ui-engineering)
- `/git-workflow-and-versioning`: Keeps main deployable with short-lived branches and small atomic commits that act as save points. (https://github.com/addyosmani/agent-skills/tree/main/skills/git-workflow-and-versioning)
- `/idea-refine`: Expands a rough idea into variations, stress-tests them and saves a one-page proposal with MVP scope and a not-doing list. (https://github.com/addyosmani/agent-skills/tree/main/skills/idea-refine)
- `/incremental-implementation`: Builds a change in thin vertical slices, testing, verifying and committing each one before starting the next. (https://github.com/addyosmani/agent-skills/tree/main/skills/incremental-implementation)
- `/interview-me`: Asks you single questions, offering its own guessed answer for each, until it can state your real goal and you confirm it. (https://trendhub.net/skills/addyosmani-agent-skills/interview-me.markdown)
- `/observability-and-instrumentation`: Lists the questions on-call will ask, then adds structured logs, metrics, traces and symptom-based alerts to answer them. (https://github.com/addyosmani/agent-skills/tree/main/skills/observability-and-instrumentation)
- `/performance-optimization`: Measures a baseline against Core Web Vitals targets, fixes the proven bottleneck and measures again before keeping it. (https://github.com/addyosmani/agent-skills/tree/main/skills/performance-optimization)
- `/planning-and-task-breakdown`: Maps dependencies in read-only mode and turns a spec into small, ordered tasks with acceptance criteria in tasks/plan.md. (https://github.com/addyosmani/agent-skills/tree/main/skills/planning-and-task-breakdown)
- `/security-and-hardening`: Starts from a quick STRIDE threat model, then applies always, ask-first and never rules for input, auth and secrets. (https://github.com/addyosmani/agent-skills/tree/main/skills/security-and-hardening)
- `/shipping-and-launch`: Runs a pre-launch checklist across quality, security, performance and accessibility, then plans staged rollout and rollback. (https://github.com/addyosmani/agent-skills/tree/main/skills/shipping-and-launch)
- `/source-driven-development`: Detects exact framework versions, fetches the official docs and cites them for each framework-specific decision. (https://github.com/addyosmani/agent-skills/tree/main/skills/source-driven-development)
- `/spec-driven-development`: Writes a reviewed spec covering objectives, commands, structure, style, testing and boundaries before any code exists. (https://github.com/addyosmani/agent-skills/tree/main/skills/spec-driven-development)
- `/test-driven-development`: Finds the repo's own test commands, then runs a red-green-refactor loop and reproduces bugs with a failing test first. (https://github.com/addyosmani/agent-skills/tree/main/skills/test-driven-development)

## Questions

### Is the pack free to use?

Yes. It is released under the MIT license, so you can use and adapt the skills in personal, team and commercial projects.

### Which agents does it work with?

The README covers Claude Code, Codex, Gemini CLI, Antigravity CLI, Command Code, Cursor, Windsurf, OpenCode, GitHub Copilot and Kiro, and notes that the plain Markdown works with any agent that reads instruction files.

### Do the slash commands work outside Claude Code?

Not everywhere. The lifecycle commands are Claude Code plugin commands with wrappers for Gemini CLI; in Copilot and some other hosts you call the skills by name instead.

### What do I lose installing just one skill?

Installing one skill at a time with npx brings over just that folder, so its links to the shared checklists in references/ break unless you clone the repo or copy those files too.

## Before you install

The skills are Markdown workflows that have the agent edit files, run tests, linters, scanners and git, and in some cases install tools such as gitleaks or Lighthouse. The Claude Code plugin also adds lifecycle hooks, and browser-testing-with-devtools drives Chrome through the DevTools MCP server, so review those before enabling them.
