Go from idea to tested feature in Claude Code or Cursor with /spec, /plan and /build

Developer Addy Osmani released agent-skills, a set of 25 skills for Claude Code, Cursor and Codex that installs via a single npx command and forces coding agents through a spec-plan-build-test workflow. The skills add /spec, /plan, /build and /test commands so agents define requirements and break work into atomic tasks before writing code, with an optional /build auto mode that still pauses on failures and risky steps. A per-skill install copies only that skill and omits the shared checklists.

Agents are fast at writing code and equally fast at writing the wrong code. addyosmani/agent-skills https://github.com/addyosmani/agent-skills is a set of 25 skills that put a spec, a plan and tests between your idea and the diff. It works with Claude Code, Cursor and Codex, and installs with one command. Here is the short path from a vague feature idea to a tested change. Left alone, a coding agent jumps straight to code, skips the spec and hands you a large change that is hard to verify. The skills push the agent through the same order a careful engineer would use: define what to build, break it into small tasks, build one slice at a time, test, then ship. npx skills add addyosmani/agent-skills This installs all 25 skills into your agent. You need Node.js for npx skills . If you only want one skill, add --skill <name to the same command, for example --skill interview-me . A per-skill install copies only that skill, not the shared checklists, so install the whole repo if you want those. Run: /spec Describe what you want to build. The spec comes before any code. If your idea is still fuzzy, install and use the interview-me skill first, so the agent asks requirement questions one at a time instead of silently guessing. /plan The plan breaks the spec into small, atomic tasks. Read it. This is the cheapest moment to catch a wrong assumption, because nothing has been built yet. /build This implements one slice at a time, test-driven. If you trust the plan, /build auto implements every task after a single plan approval. Be clear about what that means: it removes the stepping between tasks, not the verification. It still pauses on failures and risky steps. /test Run it before you merge. When you want a review pass, the repo also has /review in Claude Code use /agent-skills:review , because a built-in command shares the name and /code-simplify for anything that came out too clever. "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." Step-by-step card: 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/?utm source=devto&utm medium=article&utm campaign=howto agentskills . Everything else people do with this repo: agent-skills use cases https://dedupedai.com/use-cases/addyosmani-agent-skills/?utm source=devto&utm medium=article&utm campaign=howto agentskills . For the wider category, see AI use cases for Cursor https://dedupedai.com/use-cases/a/cursor/?utm source=devto&utm medium=article&utm campaign=howto agentskills . Source repo: addyosmani/agent-skills https://github.com/addyosmani/agent-skills . Want the setup commands for 50 AI repos people actually ship with? Get the free AI Repos That Actually Ship pack: https://dedupedai.com/ship-pack/?utm source=devto&utm medium=article&utm campaign=shippack https://dedupedai.com/ship-pack/?utm source=devto&utm medium=article&utm campaign=shippack Get one email every Monday with the week's hottest AI repos and exactly how to use them: subscribe free at dedupedai.com https://dedupedai.com/join/?utm source=devto&utm medium=article&utm campaign=howto agentskills