127 tagged ab testing, measured the same way as everything else here.
Browse within: experiments 62ai-analytics 60cdp 60data-warehouse 60marketing 20growth 16agent-evaluation 13ai-product-management 13attribution 12experimentation 6Optimization 5landing page 5landing-page-generator 5
Skill Claude CodeCodex
Implement and extend PostHog Data warehouse import sources. Use when adding a new source under products/warehousesources/backend/temporal/dataimports/sources, adding datasets/endpoints to an existing source, or adding incremental sync, resumable imports, webhook ingestion, pagination, credentials validation, and…
Skill Claude CodeCodex
Plan and execute product isolation migrations to a facade plus contract layer in PostHog, following the Visual review architecture. Use when a product still exposes internals (models/logic/views) across boundaries and needs migration toward contracts.py + facade/api.py + presentation separation, with a PR strategy…
Skill Claude CodeCodex
Guide for using the Grafana MCP to monitor and diagnose the Node.js ingestion pipeline workers in production. Use when investigating event lag, drops, pipeline errors, person/group processing, Kafka consumer health, Redis, Postgres, ClickHouse downstream health, or any ingestion worker question. Covers prod-us and…
Humblytics/humblytics-marketing-skills
Skill Claude CodeCodex
Reads page analytics and click data from Humblytics, generates A/B test hypotheses with element selectors, and launches no-code split tests via the Humblytics MCP. Use when creating A/B tests, split tests, multivariate tests, or when you need to test headlines, CTAs, layouts, or pricing. Triggers: A/B test, split…
Humblytics/humblytics-marketing-skills
Skill Claude CodeCodex
Expert in paid advertising across Meta (Facebook/Instagram), Google Ads, TikTok, LinkedIn, and YouTube. Specializes in ad ideation, creative concepting, copywriting, audience targeting, campaign structure, and performance optimization. Use when creating ad campaigns, writing ad copy, designing audience targeting…
Humblytics/humblytics-marketing-skills
Skill Claude CodeCodex
Revenue attribution specialist that connects Meta Ads, Google Ads, and Stripe revenue to show which campaigns actually pay back. Generates campaign-level ROAS breakdowns with waste detection and budget reallocation recommendations. Use when analyzing ad ROI, finding wasted ad spend, comparing channel performance, or…
Skill Claude CodeCodex
Data analysis workflow kit using the ALIVE loop (Ask, Look, Investigate, Voice, Evolve).
Skill Claude CodeCodex
Data analysis workflow kit using the ALIVE loop (Ask, Look, Investigate, Voice, Evolve).
Skill Claude CodeCodex
Data analysis workflow kit using the ALIVE loop (Ask, Look, Investigate, Voice, Evolve).
Skill Claude CodeCodex
A setup tool that installs a landing-page generation system into an existing Git project. The system includes tools for creating pages, running A/B tests, keeping an audit log, preparing ads, and related project files.
Skill Claude CodeCodex
A landing-page tool for creating A/B tests, where visitors see different versions of one page. It connects each version to analytics and records the experiment steps.
Skill Claude CodeCodex
A generator for self-contained static landing pages. Static means the page content is delivered in the HTML itself instead of being created in the browser after loading.
Skill Claude CodeCodex
Use when the user wants to autonomously search for the best AI/engineering approach across competing candidates (prompts, models, retrieval strategies, architectures, algorithms) — give it a goal + candidate arms + success threshold, it runs the experiment to a defensible ship-or-kill verdict. Autonomously handles…
Skill Claude CodeCodex
Run A/B tests that pick their own winner. Build a test from variants of one element or several at once (hero plus CTA), get URLs for email or web, and read results with real win probabilities instead of eyeballed conversion rates. Use when someone wants to test headlines, images, landing pages or email creative, or…
jackterror/social-demand-signal-agent
Skill Claude CodeCodex
Operates a human-reviewed social listening workflow that finds public customer pain, buying intent, product questions, competitor frustration, and unmet demand; routes risk; drafts governed A/B responses; and learns from observed outcomes. Use for social listening, demand-signal monitoring, public conversation…
Skill Claude CodeCodex
AI-powered growth marketing creative engine. Generates multi-variant ad creatives from a product positioning document + channel selection, runs structured A/B experiments, monitors for creative fatigue / CAC shifts / payback drift, allocates spend via Thompson Sampling, and feeds learnings into a persistent knowledge…
Skill Claude CodeCodex
A Chinese-language guide for producing growth strategies. It first classifies the request, then creates a plan using models, experiments, channels, metrics, and stored working notes.
Autter-dev/agentic-sales-skills
Skill Claude CodeCodex
Reviews and coaches your outreach with specific scoring, feedback, and rewrites.
Skill Claude CodeCodex
Use before any AI product messaging ships externally. Audits capability claims for accuracy, quantified claims for evidence, and "AI" labels for specificity. Blocks "10x productivity" without measurement and "AI-powered" without definition.
Skill Claude CodeCodex
Use before any campaign moves from strategy to execution. Transforms a growth strategy and offer into an executable brief — campaign objective, audience, offer, message, channel, creative requirements, landing destination, CTA, success metric, review gates, and launch checklist. Blocks "the team knows what we're going…
Skill Claude CodeCodex
Use before publishing or changing any pricing, packaging, or plan page. Reviews pricing clarity, plan differentiation, target customer per tier, CTA clarity, risk reversal, objections, comparison logic, anchoring, limitations, upgrade path, and trust/proof. Blocks "the pricing speaks for itself" completions.
aaronartistzhang-afk/DailyWork
Skill Claude CodeCodex
A workflow for comparing two versions of a prompt, skill, or piece of text without revealing which one is the new version. Separate agents create the versions, and a person scores them without seeing their labels.
aaronartistzhang-afk/DailyWork
Skill Claude CodeCodex
A read-only review checkpoint that asks another coding model to inspect a plan, code change, SQL query, or externally published numbers and return a GO or NO-GO decision.
aaronartistzhang-afk/DailyWork
Skill Claude CodeCodex
A tool that turns a Lark or Feishu meeting-minutes link into concise meeting notes, including @mentions for responsible people, and sends them to a group or direct message.