mikeparcewski/design
skills/delivery/design/SKILL.md
Design statistically rigorous A/B tests and experiments. Formulate hypotheses, select metrics, calculate sample sizes. Discovers analytics and feature flag tools via capability detection. Use when: "design experiment", "A/B test", "hypothesis", "sample size", "what metrics", "test my feature", "should we experiment"
$ install --global
skillsauthnpx skillsauth add mikeparcewski/wicked-garden designInstall this skill globally with one command. Works with Claude Code, Cursor, and Windsurf.
Security Scan Results
3 of 9 scanners reported clean
Some scanners were skipped, did not run, or reported a non-clean status. Review each row below.
3
Scanners Passed
9
Scanners in report
Clean
TrivyContainer and dependency vulnerability scanner
95%
Clean
SemgrepStatic code analysis for vulnerabilities
95%
Clean
mcp-scan (Snyk)Model Context Protocol security validation
95%
Skipped
Snyk (dep)Open source security scanning
50%
Skipped
Socket.devSupply chain security analysis
50%
Skipped
VirusTotalMulti-engine malware detection
50%
Skipped
CrowdStrikeAdvanced threat intelligence
50%
Skipped
OSV-ScannerOpen Source Vulnerability database check
50%
Skipped
OWASP Dep-Check
50%
Last scanned: May 7, 2026, 6:25 AM149.2s3 files scanned
SKILL.md
- name:
- design
- description:
- |
- Use when:
- design experiment", "A/B test", "hypothesis", "sample size",
- phase_relevance:
- ["build", "review", "operate"]
- archetype_relevance:
- ["*"]
Design Skill
Design experiments with statistical rigor.
Quick Start
# Design experiment from hypothesis
/wicked-garden:delivery:experiment "Blue CTA increases clicks by 10%"
# Design with context file
/wicked-garden:delivery:experiment feature-spec.md
# Discover available tools
/wicked-garden:delivery:experiment --discover
What This Skill Does
- Formulates clear, testable hypotheses
- Selects appropriate success metrics
- Calculates required sample sizes
- Plans instrumentation strategy
- Defines success criteria
Hypothesis Formulation
Template:
[Action] will [increase/decrease] [Metric] by [Amount] because [Reason]
Good: "Adding social proof to checkout will increase conversion by 8% because it reduces purchase anxiety"
Bad: "New design will be better" (not specific or measurable)
Metric Selection
Hierarchy:
- Primary: The ONE metric determining success
- Secondary: Supporting metrics for context
- Guardrail: Metrics that must not degrade
Example for checkout optimization:
- Primary: Purchase completion rate
- Secondary: Time to purchase, cart value
- Guardrail: Page load time, error rate
Sample Size Calculation
Quick estimates (95% confidence, 80% power):
- 5% effect: ~3,200 per variant
- 10% effect: ~800 per variant
- 20% effect: ~200 per variant
See statistics.md for detailed formulas.
Variant Design
Best practices:
- Start with 2 variants (control + treatment)
- Make ONE clear change per variant
- Ensure variants are mutually exclusive
- Document variant details clearly
Instrumentation Planning
Required tracking:
// Variant assignment
trackEvent('experiment_viewed', {
experiment: 'checkout_social_proof',
variant: 'control' | 'treatment',
user_id: '...'
})
// Primary metric
trackEvent('purchase_completed', {
experiment: 'checkout_social_proof',
variant: '...',
value: 49.99
})
Success Criteria
Statistical:
- Significance: p < 0.05
- Confidence: 95%
- Power: 80%
Business:
- Minimum effect worth shipping
- Resource constraints
- Timeline limitations
Output Format
The skill emits a markdown experiment design with sections: Hypothesis, Metrics (Primary / Secondary / Guardrail), Variants, Sample Size, Statistical Parameters, Instrumentation, Success Criteria, Risks & Mitigations.
Full template with substitutable placeholders: refs/output-template.md.
Capability Discovery
Discovers available tools automatically via capability detection:
Capabilities needed:
feature-flags: Feature toggle and flag managementanalytics: Event tracking and metrics collectionexperiment-platform: Dedicated A/B testing platforms
Discovery methods:
- CLI tools presence (check for commands)
- API configuration (config files, environment variables)
- SDK detection (package.json, requirements.txt, go.mod)
Asks "Do I have analytics capability?" not "Do I have Amplitude?"
Integration
With native tasks: Stores design via TaskUpdate description append on the active task With qe: QE provides test scenarios for instrumentation With wicked-brain:memory: Recalls past experiment patterns With product: Uses product context for hypothesis
See Also
- statistics.md - Statistical concepts and formulas
/wicked-garden:delivery:report- Analyze experiment results/wicked-garden:delivery:rollout- Plan feature rollout
Related Skills
mikeparcewski/wicked-garden-engineering-conformance-reviewer
development
VerifiedTrustedCommunity
Pattern-conformance agent-half: evaluates a produced artifact or diff against a set of architectural/design pattern rules from the conformance-rule store (wicked_governance schema). Returns structured findings with rule ID, severity, and rationale — the deterministic half (mechanical rule recall) is done by the guard pipeline; this is the semantic evaluation step. Triggered by: the guard_pipeline `outgov_pattern` check (session-close), or explicitly by an engineering review when WICKED_OUTGOV_RULES_DIR is populated. NOT a replacement for the full `engineering` review skill — focuses only on conformance to stored Pattern rules; architecture and code-quality checks live in the `engineering` skill. Semantic evaluation reuses `wicked-garden-qe-semantic-reviewer` as the designated agent-half evaluator (per garden#983 spec). This skill is the orchestrating wrapper that loads applicable Pattern rules and delegates the per-rule semantic judgment to qe-semantic-reviewer.
8SKILL.mdUpdated Jul 22, 2026
mikeparcewski/wicked-garden-domain
tools
VerifiedTrustedCommunity
The FOUNDATIONAL domain-model capability: extract a codebase's domain — testable business rules (with confidence + provenance), entities, requirements — as a schema-conformant model on the estate graph. The workers annotate the store; wicked-core reads it and builds the requirements graph, coverage-gating fail-closed. Steers three fork workers. A shared substrate, not a modernization tool. The `modernize` archetype DERIVES from it; build / migrate / review / specify / explore consume the SAME domain model — none OWN it. Understanding a codebase's domain is upstream of almost everything else garden does. Use when: "extract the business rules / domain model from this codebase", "build a requirements graph from the code", "what does this system actually require", "reverse-engineer the domain before we build/port/migrate". Works on ANY codebase (modern or legacy) — the value is the domain model, not the porting. NOT the code transform itself (that is the archetype consuming this model). This skill produces the DOMAIN MODEL, not new code.
8SKILL.mdUpdated Jul 15, 2026
mikeparcewski/wicked-garden-domain-modeler
development
VerifiedTrustedCommunity
Domain-graph fork worker for the modernize archetype. Groups the estate's Louvain communities into business domains, attaches each requirement to its cluster (advisory cluster_id provenance), and invokes wicked-core's domain-graph build (which reads the annotated estate store, recomputes coverage fail-closed, and builds the requirements graph) — then validates core's output against the vendored schema. Use when: dispatched by wicked-garden-domain after rule extraction to turn a flat rule set into cluster-keyed domains; "group these into domains", "build the requirements graph", "translate clusters into a domain model". NOT for mining the rules themselves (that is domain-extractor) or threat-modeling (that is domain-coverage).
8SKILL.mdUpdated Jul 15, 2026
mikeparcewski/wicked-garden-domain-extractor
tools
VerifiedTrustedCommunity
Rule-extraction fork worker for the FOUNDATIONAL domain-model capability. Mines testable business rules from a codebase — each with a numeric confidence and a provenance{source, ref, source_kinds} — and annotates them into the estate store so wicked-core can build the domain-model requirements graph (coverage-gated). This is a substrate, not a modernization tool: the `modernize` archetype DERIVES from it, and build / migrate / review / specify / explore can consume the same domain model — none OWN it. Use when: dispatched by wicked-garden-domain to mine the business_rules of a codebase (or a module); "extract the domain rules", "what does this system require", building the requirements half of a domain model. NOT for grouping into domains (that is domain-modeler) or judging coverage (that is domain-coverage — a seat-distinct evaluator).
8SKILL.mdUpdated Jul 15, 2026