abtesting-design
Hypothesis formation, null/alternative, control/variant setup, randomization hash-based, stratification
What this skill does
# abtesting-design
## Purpose
This skill enables precise A/B test design for OpenClaw, covering hypothesis formulation (e.g., null and alternative), setup of control/variant groups, hash-based randomization, and stratification to ensure balanced experiments.
## When to Use
Use this skill when designing experiments for feature comparisons, such as testing website layouts, app features, or marketing campaigns, to validate hypotheses with statistical rigor and minimize bias.
## Key Capabilities
- Formulate hypotheses: Define null (e.g., "No difference in click rates") and alternative (e.g., "Variant increases clicks by 10%").
- Set up groups: Configure control and variant setups with parameters like sample sizes and metrics.
- Implement randomization: Use hash-based methods (e.g., SHA-256 on user IDs) for assignment to reduce selection bias.
- Apply stratification: Divide users into strata (e.g., by demographics) to balance groups, using algorithms like stratified sampling.
## Usage Patterns
Always start by defining your hypothesis and groups. Use CLI for quick designs or API for programmatic integration. Provide all required inputs (e.g., hypothesis strings, variant names) in a single command or request. For repeated use, store configurations in JSON files and reference them via flags. Validate inputs before execution to avoid runtime errors.
## Common Commands/API
- CLI Command: Run `openclaw abtesting-design --hypothesis-null "No effect on conversion" --hypothesis-alt "Variant increases conversion" --variants control,variantA --randomize hash --stratify age,gender` to design a test. Use `--config path/to/config.json` for JSON configs like {"variants": ["control", "variantA"], "strata": ["age", "gender"]}.
- API Endpoint: Send a POST request to `/api/abtesting/design` with a JSON body, e.g., {"hypothesis_null": "No difference", "hypothesis_alt": "Increase in engagement", "variants": ["control", "variantB"], "randomization": "hash", "stratification": ["device_type"]}. Set auth via header: `Authorization: Bearer $OPENCLAW_API_KEY`.
- Code Snippet (Python):
```python
import requests
headers = {'Authorization': f'Bearer {os.environ["OPENCLAW_API_KEY"]}'}
data = {"hypothesis_null": "No effect", "variants": ["control", "variant"]}
response = requests.post('https://api.openclaw.com/api/abtesting/design', json=data, headers=headers)
```
- Code Snippet (CLI in Script):
```bash
export OPENCLAW_API_KEY=your_key_here
openclaw abtesting-design --hypothesis-null "Baseline equal" --variants control,testVariant --output results.json
```
## Integration Notes
Integrate by setting `$OPENCLAW_API_KEY` as an environment variable for authentication. For multi-service setups, chain this skill with data tools (e.g., via OpenClaw's workflow API at `/api/workflows/add`). Use JSON configs for consistency, e.g., {"api_endpoint": "/api/abtesting/design", "auth_env": "OPENCLAW_API_KEY"}. Ensure your application handles asynchronous responses by polling `/api/abtesting/status/{job_id}`.
## Error Handling
Check for errors by parsing response codes: HTTP 400 for invalid inputs (e.g., missing hypothesis), 401 for auth failures. In code, use try-except blocks:
```python
try:
response = requests.post(url, json=data, headers=headers)
response.raise_for_status()
except requests.exceptions.HTTPError as e:
print(f"Error: {e.response.status_code} - {e.response.text}")
# Retry with corrected inputs, e.g., add missing fields
```
For CLI, capture output and check for strings like "Error: Invalid hypothesis format" then adjust flags accordingly.
## Concrete Usage Examples
1. **Email Subject Line Test**: To compare two email subjects, run `openclaw abtesting-design --hypothesis-null "Open rates are equal" --hypothesis-alt "Subject B increases opens" --variants control,subjectB --randomize hash --stratify location` then use the output JSON to assign users via their IDs in your email system.
2. **App Feature A/B Test**: For testing a new login button, use the API: Send POST to `/api/abtesting/design` with {"hypothesis_null": "No change in login time", "variants": ["old_button", "new_button"], "stratification": ["user_type"]} and apply the returned randomization function (e.g., hash-based) in your app code to segment users.
## Graph Relationships
- Related Cluster: abtesting (e.g., links to skills like abtesting-analysis for post-design steps).
- Related Tags: experiment-design (connects to data-collection skills), hypothesis (ties to statistical-modeling tools), randomization (integrates with user-segmentation utilities).
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.