Agent skill · Addy Osmani's Agent Skills
/code-review-and-quality Five-axis code review with clear severity labels
This skill has the agent review any change, whether written by you, another model or itself, for correctness, readability, architecture, security and performance. It reads the tests first, checks them by flipping a condition, labels each comment as required, critical, optional, nit or FYI, proposes a concrete restructuring for structural problems and reviews dependency upgrades one package at a time.
Works with
- Claude Code
- Any agent via the skills CLI
- Codex
- Gemini CLI
- Antigravity CLI
- Command Code
Used forCode review
When to use it
- A pull request or local diff needs a verdict before merge.
- Another agent or model wrote code you have not examined.
- A bulk dependency bump or a refactor claims to make things cleaner.
How it works
- 1Understand intent
The agent works out what the change is meant to do and which spec or task it implements before reading code.
- 2Test the tests
It reads the tests first, then inverts a condition the change adds and reruns the suite; a test that stays green is reported as a gap.
- 3Walk five axes
Each changed file is checked for correctness, readability, architecture, security and performance, including size of the diff and of the file.
- 4Label and order findings
It drops findings that callers or tests rule out, separates old defects from new regressions, tags severity and puts the highest-impact issues first.
- 5Check verification
It confirms which tests and builds were run and lists any now-unused code, asking before deleting it.
What it steers the agent away from
- Approving with LGTM and no evidence of review
- Refactors that move complexity around without removing any
- Merging a mass version bump without reading changelogs or the lockfile diff
Install this skill
It installs with the Addy Osmani's Agent Skills pack.
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 --globalCommands come from the author’s README; check it for changes before you run them.
Questions
Is a review with no findings acceptable?
Yes. The skill says zero findings is a valid result and the agent should not invent issues to fill the report.
How large should a change be?
It treats about 100 changed lines as ideal, about 300 as acceptable for one logical change, and around 1000 as a signal to split.
More guides from Addy Osmani's Agent Skills
/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 →/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 →
Also in this pack
/api-and-interface-designDesigns the contract before the code, applying Hyrum's Law, a one-version rule and clear error semantics to interfaces.↗/ci-cd-and-automationSets up a pipeline where lint, types, tests, build, audit and bundle checks must all pass before review.↗/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.↗/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.↗/observability-and-instrumentationLists the questions on-call will ask, then adds structured logs, metrics, traces and symptom-based alerts to answer them.↗/planning-and-task-breakdownMaps dependencies in read-only mode and turns a spec into small, ordered tasks with acceptance criteria in tasks/plan.md.↗
Summary by trendhub. The skill itself lives in addyosmani/agent-skills/skills/code-review-and-quality by Addy Osmani (MIT); read the full, current text there.