5d-verify
Multi-layer verification of implementation against spec and intent. Use when: (1) After BUILD phase in 5D-SDD workflow, (2) Implementation is complete and needs validation, (3) User asks to 'test,' 'verify,' or 'check' the implementation, (4) Before considering a feature done. This phase catches errors at multiple levels and routes fixes appropriately.
What this skill does
# VERIFY Phase Verify implementation at multiple levels and route failures appropriately. ## Verification Layers ### Layer 1: Technical Correctness - Does it build/compile without errors? - Do tests pass? - Does linting pass? - Does it run without crashing? **Failure routing:** Return to BUILD ### Layer 2: Spec Fidelity - Does implementation match spec interfaces? - Are all spec requirements addressed? - Do outputs match spec definitions? **Failure routing:** Return to BUILD (if code error) or SPEC (if spec error) ### Layer 3: Plan Validity - Does this solve the problem stated in the plan? - Does user testing confirm expected behavior? - Are the original assumptions holding? **Failure routing:** Return to PLAN or SPAR ### Layer 4: Epistemic Update (Depth + Time) - Did we learn anything that changes our assumptions? - Are there new risks or opportunities? - Should the spec be updated for future work? - What patterns emerged that apply to future projects? - What should we "transcend and include" going forward? **Failure routing:** Document for REFLECT phase ### Layer 5: Multi-Dimensional Check **Quadrant coverage:** - Individual Outer: Are artifacts complete and correct? - Individual Inner: Is understanding documented? - Collective Outer: Are system integrations verified? - Collective Inner: Is stakeholder alignment confirmed? **Height (Skill Dependencies):** - Did capability gaps cause failures? - What skills were developed during implementation? - What remains blocked by missing capabilities? **Identity Trap:** - Are we declaring success to avoid examining failures? - Are failures being minimized because they threaten assumptions? - What are we not looking at? ## Verification Process 1. Run automated checks (build, lint, test) 2. Manual spec comparison 3. User acceptance testing (if applicable) 4. Collect all failures and discoveries ## Failure Diagnosis When something fails, identify which layer: | Symptom | Likely Layer | Action | |---------|--------------|--------| | Code doesn't run | Layer 1 | Fix in BUILD | | Works but wrong output | Layer 2 | Check spec, fix in BUILD or SPEC | | Works but users confused | Layer 3 | Return to PLAN | | Works but solves wrong problem | Layer 3-4 | Return to SPAR | **Critical:** Don't keep fixing code if the spec is wrong. Don't keep fixing spec if the understanding is wrong. ## Output Format ``` ## Verification Report ### Layer 1: Technical - Build: ✓/✗ - Tests: ✓/✗ ([pass]/[total]) - Lint: ✓/✗ ### Layer 2: Spec Fidelity - [Spec item]: ✓/✗ - [Spec item]: ✓/✗ ### Layer 3: Plan Validity - User testing: [results] - Problem solved: [yes/no/partial] ### Layer 4: Learnings - [Discovery or assumption update] ### Failures Requiring Action | Issue | Layer | Routing | |-------|-------|---------| | [issue] | [1-4] | [phase to return to] | **Verification status:** pass / fail-minor / fail-major ``` ## Exit Criteria Feature complete when: - All Layer 1-3 checks pass - No unresolved failures - User confirms acceptance Proceed to REFLECT when feature is complete or iteration is ending.
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.