Agent skill pack · 24 skills
Addy Osmani's Agent Skills
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.
Works with
- Claude Code
- Any agent via the skills CLI
- Codex
- Gemini CLI
- Antigravity CLI
- Command Code
What problems it solves
- The agent skips specs and testsEach 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 headA constraints skill interviews you once, writes CONSTRAINTS.md and wires each threshold to a real command.
- Confident answers that turn out wrongDoubt-driven development sends each non-trivial decision to a fresh reviewer told to find faults, not approve.
- Agents talk themselves out of stepsEvery skill lists the usual excuses for cutting corners and a short rebuttal the agent is expected to follow.
The core workflow
These skills are built to be used one after another.
- 1
/interview-meAsks you single questions, offering its own guessed answer for each, until it can state your real goal and you confirm it. - 2
/spec-driven-developmentWrites a reviewed spec covering objectives, commands, structure, style, testing and boundaries before any code exists. - 3
/planning-and-task-breakdownMaps dependencies in read-only mode and turns a spec into small, ordered tasks with acceptance criteria in tasks/plan.md. - 4
/incremental-implementationBuilds a change in thin vertical slices, testing, verifying and committing each one before starting the next. - 5
/test-driven-developmentFinds the repo's own test commands, then runs a red-green-refactor loop and reproduces bugs with a failing test first. - 6
/code-review-and-qualityReviews a change for correctness, readability, architecture, security and performance, labelling each finding by severity. - 7
/shipping-and-launchRuns a pre-launch checklist across quality, security, performance and accessibility, then plans staged rollout and rollback.
Skill guides
Explained step by step on this site
/browser-testing-with-devtoolsLet the agent check a real browser instead of guessingInspects a live page through Chrome DevTools MCP: DOM, console, network, performance traces and the accessibility tree.Read the guide →/code-review-and-qualityFive-axis code review with clear severity labelsReviews a change for correctness, readability, architecture, security and performance, labelling each finding by severity.Read the guide →/constraint-driven-developmentWrite down your quality bar and stop agents quietly lowering itSets a written quality bar in CONSTRAINTS.md with default thresholds and flags diffs that skip tests or silence checks.Read the guide →/doubt-driven-developmentHave a fresh reviewer try to break each risky decisionHands each non-trivial decision to a fresh-context reviewer prompted to find faults, with an optional second model.Read the guide →/interview-meFind out what you actually want before anything is builtAsks you single questions, offering its own guessed answer for each, until it can state your real goal and you confirm it.Read the guide →
All 24 skills
Skill names are shown as /name: depending on your agent, a skill runs when it is relevant or when you call it by name, and plugin installs may add a prefix. Highlighted skills have a guide on this site; the others open their folder on GitHub.
/api-and-interface-designDesigns the contract before the code, applying Hyrum's Law, a one-version rule and clear error semantics to interfaces.↗/browser-testing-with-devtoolsInspects a live page through Chrome DevTools MCP: DOM, console, network, performance traces and the accessibility tree.→/ci-cd-and-automationSets up a pipeline where lint, types, tests, build, audit and bundle checks must all pass before review.↗/code-review-and-qualityReviews a change for correctness, readability, architecture, security and performance, labelling each finding by severity.→/code-simplificationCuts complexity in working code while keeping every input, output, side effect and error exactly the same.↗/constraint-driven-developmentSets a written quality bar in CONSTRAINTS.md with default thresholds and flags diffs that skip tests or silence checks.→/context-engineeringSets up rules files and decides which specs, source files and error output the agent should load for each task.↗/debugging-and-error-recoveryHalts feature work on any failure and walks a reproduce, localize, reduce, fix and guard checklist to the root cause.↗/deprecation-and-migrationDecides whether old code should go, then plans compulsory or advisory deprecation and migrates consumers off it.↗/documentation-and-adrsRecords significant decisions as ADRs in the project's existing format and spots docs that no longer match the code.↗/doubt-driven-developmentHands each non-trivial decision to a fresh-context reviewer prompted to find faults, with an optional second model.→/frontend-ui-engineeringBuilds accessible, responsive components with composition-first patterns and checks them with the project's own tooling.↗/git-workflow-and-versioningKeeps main deployable with short-lived branches and small atomic commits that act as save points.↗/idea-refineExpands a rough idea into variations, stress-tests them and saves a one-page proposal with MVP scope and a not-doing list.↗/incremental-implementationBuilds a change in thin vertical slices, testing, verifying and committing each one before starting the next.↗/interview-meAsks you single questions, offering its own guessed answer for each, until it can state your real goal and you confirm it.→/observability-and-instrumentationLists the questions on-call will ask, then adds structured logs, metrics, traces and symptom-based alerts to answer them.↗/performance-optimizationMeasures a baseline against Core Web Vitals targets, fixes the proven bottleneck and measures again before keeping it.↗/planning-and-task-breakdownMaps dependencies in read-only mode and turns a spec into small, ordered tasks with acceptance criteria in tasks/plan.md.↗/security-and-hardeningStarts from a quick STRIDE threat model, then applies always, ask-first and never rules for input, auth and secrets.↗/shipping-and-launchRuns a pre-launch checklist across quality, security, performance and accessibility, then plans staged rollout and rollback.↗/source-driven-developmentDetects exact framework versions, fetches the official docs and cites them for each framework-specific decision.↗/spec-driven-developmentWrites a reviewed spec covering objectives, commands, structure, style, testing and boundaries before any code exists.↗/test-driven-developmentFinds the repo's own test commands, then runs a red-green-refactor loop and reproduces bugs with a failing test first.↗
No skill matches that filter.
Install
Pick your agent; commands come from the author’s README.
Claude CodeAdds 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-skillsAny agent via the skills CLIInstalls all skills into Claude Code, Cursor, Codex, Copilot, Cline and many other agents.
npx skills add addyosmani/agent-skillsCodexNeeds 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-skillsGemini CLIInstalls the skills for auto-discovery.
gemini skills install https://github.com/addyosmani/agent-skills.git --path skillsAntigravity CLIInstalls as a native plugin; some releases need the namespaced skills invoked directly.
agy plugin install https://github.com/addyosmani/agent-skills.gitCommand CodeThe first form installs per project, the second for all projects.
cmd skills add addyosmani/agent-skills
cmd skills add addyosmani/agent-skills --globalOn 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. Check the author’s README for changes before you run a command.
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.
This page is trendhub’s own summary of a public repository. The skills, their text and every update live in addyosmani/agent-skills by Addy Osmani; we do not host or modify the files.