abtesting
Root A/B testing: experiment design, statistical significance, sample size power analysis, launch criteria
What this skill does
## abtesting
### Purpose
This skill enables A/B testing workflows, including experiment design, statistical significance testing, sample size power analysis, and defining launch criteria. Use it to optimize decisions based on data-driven experiments.
### When to Use
Apply this skill when designing experiments for feature rollouts, website changes, or product variations. Use it for scenarios requiring statistical validation, such as comparing conversion rates or user engagement metrics, to ensure reliable results before full deployment.
### Key Capabilities
- Design A/B experiments with parameters like variants, metrics, and duration.
- Perform power analysis to calculate required sample sizes using formulas like Cohen's d.
- Test statistical significance with t-tests or chi-squared tests on experiment data.
- Define launch criteria based on p-values, confidence intervals, and effect sizes.
- Integrate with data sources for real-time analysis.
### Usage Patterns
Start by initializing an experiment object with required parameters. Use CLI for quick calculations or API for programmatic access. Always set the API key via environment variable `$ABTEST_API_KEY` before operations. For example, chain commands to design, run analysis, and decide on launch. Handle asynchronous API calls by polling for results.
### Common Commands/API
Use the OpenClaw CLI for A/B testing commands. Set up with `export ABTEST_API_KEY=your_key`. Example API endpoint: `POST https://api.openclaw.ai/abtesting/experiments`.
- CLI command for sample size calculation:
`abtest calculate-sample-size --effect-size 0.2 --power 0.8 --alpha 0.05`
This outputs the minimum sample per group.
- API call for significance test:
`curl -H "Authorization: Bearer $ABTEST_API_KEY" -d '{"control': [50, 55], 'treatment': [60, 65], 'metric': 'mean'}" https://api.openclaw.ai/abtesting/significance`
Returns JSON with p-value and confidence interval.
- Config format for experiment design (JSON):
`{ "name": "email-variant-test", "variants": ["A", "B"], "metric": "click-rate", "duration_days": 7 }`
Save as `experiment.json` and run: `abtest design --config experiment.json`.
- Power analysis via code snippet (Python):
`import openclaw.abtesting`
`result = openclaw.abtesting.power_analysis(effect_size=0.1, alpha=0.05, power=0.8)`
Print result for required sample size.
### Integration Notes
Integrate this skill into your codebase by importing the OpenClaw SDK and setting `$ABTEST_API_KEY`. For web apps, use it in CI/CD pipelines to validate experiments before merges. Ensure data sources (e.g., databases) are accessible via the SDK's `connect` method, like `openclaw.abtesting.connect(db_url="postgres://user:pass@host/db")`. If using in a microservice, handle retries for API calls with exponential backoff.
### Error Handling
Check for errors in every command; CLI returns exit codes (e.g., 1 for invalid input). For API, parse HTTP responses: 400 for bad requests, 401 for auth failures. Example:
`try:
response = requests.post(url, headers={"Authorization": f"Bearer {os.environ['ABTEST_API_KEY']}"}))
response.raise_for_status()
except requests.exceptions.HTTPError as e:
log_error(e)`
Handle common issues like insufficient sample size by validating inputs upfront, e.g., use `abtest validate --config experiment.json` to catch errors early.
### Concrete Usage Examples
1. **Design and calculate sample size for a website variant test:**
First, create a config: `{ "name": "homepage-test", "variants": ["original", "new"], "metric": "bounce-rate" }`.
Run: `abtest calculate-sample-size --effect-size 0.05 --power 0.8 --alpha 0.05`.
Use the output (e.g., 500 per group) to set up: `abtest design --config config.json`.
This ensures your experiment has enough power.
2. **Analyze significance and decide launch for an email campaign:**
Collect data: control clicks = [100, 120], treatment = [140, 150].
Run: `curl -H "Authorization: Bearer $ABTEST_API_KEY" -d '{"control": [100,120], "treatment": [140,150], "metric": "mean"}' https://api.openclaw.ai/abtesting/significance`.
If p-value < 0.05, proceed with launch criteria: `abtest launch-check --p-value 0.03 --min-effect 0.1`.
This automates decision-making based on results.
### Graph Relationships
- Related to cluster: abtesting (direct parent).
- Connected to tags: ab-testing, experiments, statistics.
- Links to other skills: analytics (for data processing), data-science (for advanced stats).
Related in Design
contribute
IncludedLocal-only OSS contribution command center. Auto-refreshes the user's in-flight PR and issue state on invoke so conversations start with full context — no need to brief Claude on what's in flight. Helps the user find issues to contribute to on GitHub, builds per-repo dossiers of what each upstream expects (CLA, DCO, branch convention, AI policy, draft-first, review bots, issue templates), runs deterministic gates before any external action so AI-assisted contributions don't reach maintainers as slop. State is markdown-only: candidate files at ~/.contribute-system/candidates/, repo dossiers at ~/.contribute-system/research/, append-only event log at ~/.contribute-system/log.jsonl. No database, no cloud calls. Use when the user asks about their PRs / issues / contributions, wants to find new work to take on, claim an issue, build/refresh a repo's dossier, or draft a Design Issue or PR. Trigger with "/contribute", "what's my PR status", "find a contribution", "claim issue X", "draft a Design Issue for Y", "refresh dossier for Z".
architectural-analysis
IncludedUser-triggered deep architectural analysis of a codebase or scoped subtree across eight modes — information architecture, data flow, integration points, UI surfaces, interaction patterns, data model, control flow, and failure modes. This skill should be used when the user asks to "diagram this codebase," "map the architecture," "show the data flow," "give me an ERD," "trace control flow," "find the integration points," "verify the layout pattern," "audit the UX architecture," or any similar request whose primary deliverable is mermaid diagrams plus cited reports under docs/architecture/. Dispatches haiku/sonnet sub-agents in parallel for per-mode exploration, then verifies every citation mechanically before any node lands in a diagram. Not for one-off prose explanations of code (use code-explanation) or for high-level system design from scratch (use system-design).
mcp
IncludedModel Context Protocol (MCP) server development and tool management. Languages: Python, TypeScript. Capabilities: build MCP servers, integrate external APIs, discover/execute MCP tools, manage multi-server configs, design agent-centric tools. Actions: create, build, integrate, discover, execute, configure MCP servers/tools. Keywords: MCP, Model Context Protocol, MCP server, MCP tool, stdio transport, SSE transport, tool discovery, resource provider, prompt template, external API integration, Gemini CLI MCP, Claude MCP, agent tools, tool execution, server config. Use when: building MCP servers, integrating external APIs as MCP tools, discovering available MCP tools, executing MCP capabilities, configuring multi-server setups, designing tools for AI agents.
react-native-skia
IncludedDesign, build, debug, and optimise high-polish animated graphics in React Native or Expo using @shopify/react-native-skia, Reanimated, and Gesture Handler. Use when the user wants canvas-driven UI, shaders, paths, rich text, image filters, sprite fields, Skottie, video frames, snapshots, web CanvasKit setup, or performance tuning for custom motion-heavy elements such as loaders, hero art, cards, charts, progress indicators, particle systems, or gesture-driven surfaces. Also use when the user asks for fluid, glow, glass, blob, parallax, 60fps/120fps, or GPU-friendly animated effects in React Native, even if they do not explicitly say "Skia". Do not use for ordinary form/layout work with standard views.
plaid
IncludedProduct Led AI Development — guides founders from idea to launched product. Six capabilities: Idea (discover a product idea), Validate (pressure-test the idea against fatal flaws, problem reality, competition, and 2-week MVP feasibility), Plan (vision intake + document generation), Design (translate image references into a design.md spec), Launch (go-to-market strategy), and Build (roadmap execution). Use when someone says "PLAID", "plaid idea", "help me find an idea", "product idea", "idea from my business", "idea from my expertise", "plaid validate", "validate my idea", "pressure-test", "is this idea good", "find fatal flaws", "validate the problem", "plan a product", "define my vision", "generate a PRD", "product strategy", "plaid design", "design from image", "translate image to design", "create design.md", "extract design tokens", "plaid launch", "go-to-market", "launch plan", "GTM strategy", "launch playbook", "plaid build", "build the app", "start building", or "execute the roadmap".
nextjs-framer-motion-animations
IncludedAdds production-safe Motion for React or Framer Motion animations to Next.js apps, including reveal, hover and tap micro-interactions, whileInView, stagger, AnimatePresence, layout and layoutId transitions, reorder, scroll-linked UI, and lightweight route-content transitions. Use when the user asks to add, refactor, or debug Motion or Framer Motion in App Router or Pages Router codebases, especially around server/client boundaries, reduced motion, LazyMotion, bundle size, hydration, or route transitions. Avoid for GSAP-style timelines, WebGL or 3D scenes, heavy scroll storytelling, or CSS-only effects unless Motion is explicitly requested.