본문으로 건너뛰기
cccskills
무료GitHub에 공개

11-star-framework

Rate any product, feature, or experience on the 11-star scale (Brian Chesky's Airbnb thought experiment). Use when user says "rate this experience", "11-star", "star rating", "experience audit", "how good is this", "experience rating", "product audit", "quality assessment", or wants to evaluate product quality and identify improvement paths. Also trigger when user wants to benchmark a feature, assess where a product stands, or map out what "great" looks like - even if they don't explicitly say "11-star".

한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.

설치 방법 보기

포함된 파일(1)

  • SKILL.md5.2 KB

SKILL.md(원문)

설치하기 전에 에이전트에게 전달되는 지시 내용을 확인할 수 있습니다.

11-Star Experience Framework

Brian Chesky (Airbnb) thought experiment: "What would a 1-star through 11-star experience look like?"

Forces teams to think beyond "good enough" and imagine transformative experiences.

The Scale

Star LevelDefinition
1-starBroken, unusable
2-starBarely functional
3-starMeets basic need
4-starReliable, useful
5-starDelights
6-starMemorable
7-starMagical
8-starPersonalized magic
9-starScience fiction
10-starImpossible today
11-starTransforms the domain

How to Use

Step 1: Rate Your Feature

Describe what each star level looks like for THIS specific feature or product.

Example - E-Commerce Checkout:

StarExperience
1-starPage crashes; payment fails silently; user gives up
3-starCheckout works; basic form fields; no saved payment methods
5-starOne-click checkout; saved cards; instant confirmation with ETA
7-starPredicts what you want before you search; auto-applies best discount; delivery arrives same day
9-starKnows you need something before you do; orders it; perfect every time
11-starCommerce friction doesn't exist - things you need appear when you need them

Step 2: Choose Target

  • Below 5-star: Acceptable for MVP, communicate clearly
  • 5-7 star: Sweet spot for v1 release
  • Above 7-star: Aspirational; roadmap for future

Step 3: Use as Scope Filter

  • "4-star to 5-star?" - Worth it
  • "5-star to 5.2-star?" - Probably not
  • "Gets us to 7-star" - Realistic for current phase?

Common Benchmarks

These benchmarks apply across product categories. Adapt the specific examples to your domain.

Domain3-star5-star7-star
OnboardingBasic docs with commandsGuided walkthrough, validation at each step, troubleshootingInteractive course, adapts to user's level
DocumentationSingle page covering basicsMulti-page docs, examples, architecture guideInline help, contextual guidance, video walkthroughs
Output qualityRaw data dumpRich formatting, severity indicators, actionable next stepsTrend tracking, executive summaries, copy-paste actions
ExtensibilityHardcoded defaultsConfig file, multiple output formatsPlugin system, custom extensions, API access
Trust & safetyNo explanation of what runsPermissions documented, read-only by defaultDry-run default, full audit trail, airgapped mode

Output Format

When rating a project or feature:

Star LevelExperience DescriptionRealistic Now?
1-star[broken version]--
3-star[basic version]--
5-star[delightful version]Yes/No
7-star[magical version]Yes/No
9-star[sci-fi version]No
11-star[transformative version]No

Target Star Level: {N} - {rationale}

Dimension-by-Dimension Rating

For a thorough audit, rate each dimension independently:

DimensionRatingEvidence
OnboardingX.X[specific evidence]
DocumentationX.X[specific evidence]
Output qualityX.X[specific evidence]
Trust & safetyX.X[specific evidence]
ExtensibilityX.X[specific evidence]
Code qualityX.X[specific evidence]

Then identify:

  • Strengths that push above 5-star (numbered list with evidence)
  • Remaining gaps to next star level (table with gap, impact)
  • Path to next star level (prioritized action items)

Anti-Patterns

1. Rating everything 3-star Bad: Defaulting every dimension to "meets basic need" without investigating actual behavior Good: Test the real experience, check edge cases, rate based on evidence not assumptions

2. Skipping dimensions Bad: Rating only the dimensions you feel confident about, ignoring the rest Good: Rate every dimension. Gaps in your knowledge are themselves evidence of a lower rating (if you can't tell, the user probably can't either)

3. Aspirational scoring Bad: "We plan to add X next sprint" bumps the rating from 3 to 5 Good: Rate what exists today. Plans are roadmap items, not current-state evidence

4. Flat improvement list Bad: "Improve onboarding, improve docs, improve output" with no priority Good: Rank by impact - which gap, if closed, moves the overall experience up a full star level?

5. Ignoring the 1-star description Bad: Jumping straight to 5-star and above Good: Describing the 1-star experience grounds the team in what "broken" actually looks like and makes higher ratings more calibrated

리뷰

아직 리뷰가 없습니다. 사용해 본 소감을 남겨 주세요.

댓글

로그인 없이 쓸 수 있습니다. 사용 후기, 질문, 작동하지 않은 환경 등을 편하게 남겨 주세요.

아직 댓글이 없습니다. 첫 댓글을 남겨 보세요.

보내면 바로 공개됩니다. 이메일 주소나 전화번호 같은 개인 정보는 쓰지 마세요. URL은 2개까지입니다.

0 / 1,000자

이 양식은 reCAPTCHA로 보호되며 Google 개인정보처리방침 및 서비스 약관이 적용됩니다.

같은 저장소의 스킬

Generate A/B copy variants grounded in Eugene Schwartz's awareness and market-sophistication stages and John Caples' tested-headline discipline. Every variant declares its angle, the awareness stage it targets, and a falsifiable hypothesis, and the skill recommends which pair to test first and what delta counts as signal. Use when the user says "A/B test this", "write variants", "give me options", "test different angles", "copy variants", "ab copy", "test this headline", "multiple versions", "which version is better", or wants to test copy before publishing. For reviewing copy that already exists, see copy-review. For sample size and stopping rules, see growth-experiment. For diagnosing a page rather than its words, see page-cro. For full paid ad sets by platform, see ad-campaign-writer.

한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.

qa-aman/claude-skills212026년 10월 19일 업데이트

Design statistically rigorous experiments to test data science hypotheses. Use when the user says "design an A/B test", "run an experiment", "test this hypothesis", "is this difference significant", "how many samples do I need", "randomized controlled trial", "causal inference", "uplift test", "holdout group", "significance test", "power calculation", "avoid p-hacking", or needs to determine whether an observed effect is real before making a product or model decision. For lean build-measure-learn product experiments without the statistics, use experiment-design instead.

한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.

qa-aman/claude-skills212026년 10월 19일 업데이트

Write measurable acceptance criteria for requirements or user stories. Use when the user says "write acceptance criteria", "definition of done", "how do we test this", "fit criteria", "given when then", "Gherkin scenarios", "what does done look like", "testable conditions", "how will we know this works" - even if they don't explicitly say "acceptance criteria".

한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.

qa-aman/claude-skills212026년 10월 19일 업데이트

Build a strategic account plan for winning, retaining, or expanding a named account. Use when the user says "build an account plan", "strategic account planning", "how do I grow this account", "account expansion strategy", "whitespace analysis", "QBR prep", "key account review", "map the stakeholders in this account", "land and expand plan", "how do I break into [company]", or wants a structured strategy for a specific account.

한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.

qa-aman/claude-skills212026년 10월 19일 업데이트

Write paid ad copy for LinkedIn, Google, Meta, and YouTube. Produces multiple variants per platform, each targeting a different Eugene Schwartz awareness level and Cialdini persuasion principle. Use when the user asks for ad copy, ad variants, "write LinkedIn ads", Google ads, Meta ads, paid social copy, ad headlines, or wants creative for a paid campaign. Reads brand voice, ICP, and positioning from knowledge/. For organic social posts, see linkedin-post or social-calendar. For the landing page the ad points at, see landing-page-writer. For testing variants, see ab-copy-writer.

한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.

qa-aman/claude-skills212026년 10월 19일 업데이트

Design clean and consistent APIs. Use when the user says "design an API", "API design review", "design these endpoints", "REST API for X", "GraphQL schema", "API contract", "how should this endpoint work", "review my API design", or wants to create or improve an API interface - even if they don't explicitly say "API design".

한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.

qa-aman/claude-skills212026년 10월 19일 업데이트

qa-aman의 스킬 모두 보기

이 스킬의 문제 신고