Agent skill · Addy Osmani's Agent Skills
/interview-me Find out what you actually want before anything is built
Interview-me makes the agent write its best guess of your goal with a confidence percentage, then ask one question at a time with its own guess attached. It probes answers that sound like best-practice talk, restates your intent including what is out of scope, and waits for a clear yes before stopping and offering next steps.
Works with
- Claude Code
- Any agent via the skills CLI
- Codex
- Gemini CLI
- Antigravity CLI
- Command Code
Used forPlanning and specs
When to use it
- A request like build me a dashboard leaves out who it is for, why, or what success means.
- Two reasonable goals pull against each other and you have not said which matters more.
- You ask the agent to grill you or stress-test your thinking before starting.
How it works
- 1State a hypothesis
The agent writes a one-sentence read of what you want plus an honest confidence number, with a note on what is missing when it is under about 70 percent.
- 2Ask singly with a guess
It asks one focused question, adds its guessed answer and reasoning, and waits for your reaction before the next.
- 3Probe convention answers
When you reply with words like scalable or the standard way, it asks what you would want if you did not have to justify it.
- 4Restate intent
It writes back outcome, user, why now, success, constraint and out of scope in a few lines for you to correct.
- 5Confirm and stop
It accepts only an explicit yes, then offers to save the intent, draft a spec or plan, and ends its turn without starting work.
What it steers the agent away from
- Sending a batch of questions that invites skimmed answers
- Taking whatever you think is best as a decision
- Writing a spec or plan before you have confirmed the restated goal
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
When does the interview end?
When the agent can predict how you would answer its next three questions, or when several rounds pass without progress and it suggests stepping back.
Can it run in an automated pipeline?
No. It needs a live person, so in CI or scheduled runs it reports the unclear request as a blocker instead of guessing.
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 →/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 →
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.↗/code-simplificationCuts complexity in working code while keeping every input, output, side effect and error exactly the same.↗/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.↗/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.↗/performance-optimizationMeasures a baseline against Core Web Vitals targets, fixes the proven bottleneck and measures again before keeping it.↗
Summary by trendhub. The skill itself lives in addyosmani/agent-skills/skills/interview-me by Addy Osmani (MIT); read the full, current text there.