# AI use cases for Agent Skills (addyosmani/agent-skills) Repo: [addyosmani/agent-skills](https://github.com/addyosmani/agent-skills) | Use cases: 3 | Page: https://dedupedai.com/use-cases/addyosmani-agent-skills/ Agent Skills is a set of 25 production-grade engineering skills for AI coding agents by Addy Osmani. Nine slash commands (/spec, /plan, /build, /test, /constraints, /review, /webperf, /code-simplify and /ship) map to the development lifecycle and activate the right skills, such as test-driven development and five-axis code review, so agents follow senior engineering workflows consistently. This file holds every use case of this repo. Each one starts with a "## " heading and ends with its URL. - Go from idea to tested feature with /spec, /plan and /build: https://dedupedai.com/use-cases/addyosmani-agent-skills/spec-plan-build-a-feature-with-agent-skills/ - Run a five-axis code review on every branch before merge: https://dedupedai.com/use-cases/addyosmani-agent-skills/five-axis-code-review-before-merge/ - Have your agent interview you before it writes any code: https://dedupedai.com/use-cases/addyosmani-agent-skills/interview-me-before-coding/ ## How to go from idea to tested feature with /spec, /plan and /build with Agent Skills Repo: [addyosmani/agent-skills](https://github.com/addyosmani/agent-skills) | Difficulty: Intermediate | Time: 1 hour | Basis: From the README Install the skills and run a feature through spec, plan and incremental build with tests at every step. **Who it is for:** A developer who wants an agent to build features in small, tested slices instead of one giant change. **The problem:** Agents jump straight to code, skip the spec and produce large changes that are hard to verify. **The outcome:** A written spec, a plan of small atomic tasks and code built one slice at a time, each test-driven and committed. ### Steps 1. Run `npx skills add addyosmani/agent-skills` to install all 25 skills into your agent 2. Run `/spec` and describe what to build; the spec comes before any code 3. Run `/plan` to break it into small, atomic tasks 4. Run `/build` to implement one slice at a time, or `/build auto` to implement every task after one plan approval 5. Run `/test` to prove it works before you merge ### Prompt to paste into your agent ```text Using addyosmani/agent-skills, run /spec for , then /plan, and show me the plan. After I approve, implement it with /build one slice at a time, test-driven, committing each task, and stop on any failing test. ``` ### Caveat /build auto still pauses on failures or risky steps; it removes the stepping between tasks, not the verification. Disclaimer: Third-party repos we don't own or vouch for. AI-generated use cases can be wrong: review everything and run at your own risk. Full text: https://dedupedai.com/disclaimer/ URL: https://dedupedai.com/use-cases/addyosmani-agent-skills/spec-plan-build-a-feature-with-agent-skills/ ## How to run a five-axis code review on every branch before merge with Agent Skills Repo: [addyosmani/agent-skills](https://github.com/addyosmani/agent-skills) | Difficulty: Beginner | Time: 15 minutes | Basis: From the README Install just the code review skill and have your agent review changes before you open the PR. **Who it is for:** A tech lead who wants consistent pre-merge review without reading every agent diff line by line. **The problem:** Agent written code often passes CI but slips on readability, design or health issues a human reviewer would catch. **The outcome:** A structured review of the branch against the skill's five axes, with fixes proposed before merge. ### Steps 1. Install only the review skill with `npx skills add addyosmani/agent-skills --skill code-review-and-quality` 2. In Claude Code, install the plugin with `/plugin install agent-skills@addy-agent-skills` if you prefer commands 3. Run `/review` on your branch; in Claude Code use `/agent-skills:review` since a built-in command has the same name 4. Run `/code-simplify` on anything the review flags as too clever 5. Use `/ship` when the review is clean ### Prompt to paste into your agent ```text Install the code-review-and-quality skill from addyosmani/agent-skills and review the changes on this branch against main. Group findings by severity, fix the obvious ones, and list anything that needs my decision before merge. ``` ### Caveat A per-skill npx install copies only that skill, not the shared references/ checklists; install the whole repo if you want them. Disclaimer: Third-party repos we don't own or vouch for. AI-generated use cases can be wrong: review everything and run at your own risk. Full text: https://dedupedai.com/disclaimer/ URL: https://dedupedai.com/use-cases/addyosmani-agent-skills/five-axis-code-review-before-merge/ ## How to have your agent interview you before it writes any code with Agent Skills Repo: [addyosmani/agent-skills](https://github.com/addyosmani/agent-skills) | Difficulty: Beginner | Time: 20 minutes | Basis: From the README Use the interview-me skill so the agent asks requirement questions one at a time before building. **Who it is for:** A product minded developer or PM who keeps getting the wrong feature because the prompt was vague. **The problem:** Vague requests get silent assumptions, and you only find the gaps after the code is written. **The outcome:** A clear set of requirements gathered one question at a time, ready to feed into /spec. ### Steps 1. Run `npx skills add addyosmani/agent-skills --skill interview-me` 2. Describe the feature in a sentence and ask the agent to use interview-me 3. Answer its questions one at a time until it has enough to write a spec 4. Run `/spec` with the answers so the spec reflects what you actually need 5. Add `/constraints` to record quality rules once so they are enforced everywhere ### Prompt to paste into your agent ```text Use the interview-me skill from addyosmani/agent-skills to interrogate me about , one question at a time. When you have enough, write the spec with /spec and list every assumption you still made. ``` ### Caveat Disclaimer: Third-party repos we don't own or vouch for. AI-generated use cases can be wrong: review everything and run at your own risk. Full text: https://dedupedai.com/disclaimer/ URL: https://dedupedai.com/use-cases/addyosmani-agent-skills/interview-me-before-coding/