test-assumption
Identify hidden assumptions about users in code that could exclude or harm. A focused analysis asking "What am I assuming about the person using this?"
What this skill does
# Test of Assumption A focused analysis to identify hidden assumptions about users that could exclude or harm them. ## Philosophy Every line of code makes assumptions about who will use it. Most assumptions are invisible to the people making them because they match the developer's own experience. > "What am I assuming about the person using this?" This skill makes the invisible visible. Not to judge—but to **see** who we might be leaving out. ## Scope The user may specify a file path, glob pattern, or directory. If not specified, ask what they'd like to analyze. ## Config Integration Before starting, follow the migration preflight in `references/config-migration.md`, then read `.assistant-config.md` from the project root. If it exists: 1. **Read** scope decisions and acknowledged findings 2. **Skip** acknowledged findings (note them in output) 3. **Respect** scope decisions (e.g., if US-only, certain location assumptions are intentional) 4. **Note** at the top of output: "Config loaded: .assistant-config.md" Core dignity checks always run regardless of config. ## Process ### 1. Read and Understand First, **read the code** to understand: - What does this code do? - Who sees or uses this? (developers? end users? both?) - What's the context? (onboarding? checkout? settings?) ### 2. Identify Assumptions Look for assumptions about users in these categories: **Ability** - Physical: Can use mouse, can see screen, can hear audio - Cognitive: Can read quickly, can remember steps, understands jargon - Technological: Has fast internet, has modern device, has webcam **Identity** - Gender: Binary options, gendered language, assumptions about presentation - Age: Tech-savvy defaults, references that assume generation - Culture: Western holidays, specific foods, cultural norms **Circumstance** - Economic: Has credit card, can afford premium, has bank account - Family: Has parents, is married, has children - Location: In US, has stable address, speaks English - Employment: Has job, has work email, available during business hours **Experience** - No trauma history (showing "memories" or throwbacks) - No grief (Mother's/Father's Day reminders) - Positive associations (holidays are joyful) ### 3. Evaluate Each Assumption For each assumption identified: | Question | If Yes | If No | |----------|--------|-------| | Is this necessary for the feature to work? | Document why | Flag for removal | | Could it exclude or harm someone? | Note who | Lower priority | | Could the feature work without this assumption? | Suggest how | Document constraint | ### 4. Prioritize **Remove** - Unnecessary and potentially harmful **Redesign** - Can work differently to be more inclusive **Mitigate** - Necessary but add opt-out or alternatives **Document** - Unavoidable with clear justification ## Output Format ```markdown ## Assumption Analysis: [Target] [1-2 sentences: What is this? Who uses it? Key finding?] --- ### Assumptions Found | # | Assumption | Category | Who's Excluded | Priority | |---|------------|----------|----------------|----------| | 1 | Binary gender required | Identity | Non-binary users | Remove | | 2 | Credit card required | Circumstance | Unbanked users | Redesign | | 3 | Can click buttons | Ability | Keyboard users | Mitigate | ### Detailed Analysis #### 1. [Assumption] **Location**: `file.tsx:27` **Category**: [Ability / Identity / Circumstance / Experience] **Who's excluded**: [Specific user groups] **Is it necessary?** [Yes/No with reasoning] **Recommendation**: Remove / Redesign / Mitigate / Document **Suggested change**: [Specific alternative approach] --- ### Summary **[X] assumptions found**: [breakdown by priority] **Pattern**: [What underlying assumption connects these?] **Priority action**: [Single most impactful change to make] ``` ## The Guiding Question When in doubt: > "If this were my first experience with this product, and I didn't match the 'default user', would I feel welcome?" Design for the margins. What works for users with the most constraints usually works better for everyone.
Related in Code Review
gstack
IncludedFast headless browser for QA testing and site dogfooding. Navigate pages, interact with elements, verify state, diff before/after, take annotated screenshots, test responsive layouts, forms, uploads, dialogs, and capture bug evidence. Use when asked to open or test a site, verify a deployment, dogfood a user flow, or file a bug with screenshots. (gstack)
startup-due-diligence
IncludedLegal due diligence review for seed-stage and Series A startups (US, Delaware C-Corp focus). Supports both investor and founder perspectives. Capabilities include: (1) Interactive document review and issue spotting; (2) Document request list generation; (3) Cap table and SAFE/convertible note analysis; (4) Red flag identification with severity ratings; (5) Diligence report generation. TRIGGERS: due diligence, DD, startup investment, cap table review, Series A, seed round, investor diligence, legal review startup, SAFE analysis, convertible note, 409A, founder vesting.
interview-master
IncludedThis skill should be used when the user asks to "generate interview questions", "prepare for interview", "optimize resume", "conduct mock interview", "analyze git commits for resume", "generate resume from code", "review my resume", or mentions interview preparation, career assistance, or extracting project experience from git history. Provides comprehensive interview and career development guidance for both job seekers and interviewers.
fix-issue
IncludedFixes GitHub issues using parallel analysis agents for root cause investigation, code exploration, and regression detection. Reads issue context from gh CLI, searches codebase and memory for related patterns, generates a fix with tests, and links the resolution back to the issue via PR. Includes prevention analysis to avoid recurrence. Use when debugging errors, resolving regressions, fixing bugs, or triaging issues.
sf-apex
IncludedGenerates and reviews Salesforce Apex code with 150-point scoring. TRIGGER when: user writes, reviews, or fixes Apex classes, triggers, test classes, batch/queueable/schedulable jobs, or touches .cls/.trigger files. DO NOT TRIGGER when: LWC JavaScript (use sf-lwc), Flow XML (use sf-flow), SOQL-only queries (use sf-soql), or non-Salesforce code.
swift-development
IncludedComprehensive Swift development for building, testing, and deploying iOS/macOS applications. Use when Claude needs to: (1) Build Swift packages or Xcode projects from command line, (2) Run tests with XCTest or Swift Testing framework, (3) Manage iOS simulators with simctl, (4) Handle code signing, provisioning profiles, and app distribution, (5) Format or lint Swift code with SwiftFormat/SwiftLint, (6) Work with Swift Package Manager (SPM), (7) Implement Swift 6 concurrency patterns (async/await, actors, Sendable), (8) Create SwiftUI views with MVVM architecture, (9) Set up Core Data or SwiftData persistence, or any other Swift/iOS/macOS development tasks.