Claude Skills by opensite-ai

When the user wants to plan, design, or implement an A/B test or experiment, or build a growth experimentation program. Also use when the user mentions "A/B test," "split test," "experiment," "test this change," "variant copy," "multivariate test," "hypothesis," "should I test this," "which version is better," "test two versions," "statistical significance," "how long should I run this test," "growth experiments," "experiment velocity," "experiment backlog," "ICE score," "experimentation prog...

Run a comprehensive WCAG accessibility audit covering perceivable, operable, understandable, and robust principles. Use this skill whenever the user wants to audit accessibility, review WCAG compliance, fix accessibility issues, prepare for accessibility certification, address an accessibility lawsuit risk, or systematically improve a site's accessibility. Triggers on accessibility audit, WCAG audit, a11y audit, accessibility compliance, ADA compliance, screen reader test, keyboard navigation...

Repository-specific AGENTS.md authoring and maintenance workflow. Use when creating, refreshing, or expanding AGENTS.md coverage for a codebase, including deciding whether nested AGENTS.md files are needed for subsystems with distinct rules, workflows, or AI-sensitive constraints.

Deep research and AI workflow orchestration patterns for Octane. Use when working on brand guide generation, market analysis, competitive analysis, content brief, or any multi-step AI research pipeline. Covers the WorkflowBuilder/WorkflowStep orchestration system, Anthropic dual-model routing (Opus for research, Sonnet for generation), and the ai_tasks persistence pattern.

Retrieval architecture for AI applications — choosing and combining vector RAG, PageIndex (vectorless PDF tree-search), and precision embedding models. Covers the decision framework for matching retrieval strategy to document type and query characteristics, Milvus collection design, hybrid two-stage pipelines, the EmbeddingProvider abstraction, and the routing layer that ties it all together. Use when building semantic search, RAG pipelines, document Q&A, or any system where retrieval strateg...

When the user wants to set up, improve, or audit analytics tracking and measurement. Also use when the user mentions "set up tracking," "GA4," "Google Analytics," "conversion tracking," "event tracking," "UTM parameters," "tag manager," "GTM," "analytics implementation," "tracking plan," "how do I measure this," "track conversions," "Mixpanel," "Segment," "are my events firing," or "analytics isn't working." Use this whenever someone asks how to know if something is working or wants to measur...

Browser and system automation patterns for engineers building scripts that interact with Cloudflare-protected SPAs, React file upload flows, and session-authenticated dashboards. Also covers media automation tool selection (ffmpeg, ImageMagick, Sharp) and shell script best practices. Use when scripting any headless or headed browser interaction, file upload pipeline, or batch media processing task.

Executive leadership guidance for strategic decision-making, organizational development, and stakeholder management. Includes strategy analyzer, financial scenario modeling, board governance frameworks, and investor relations playbooks. Use when planning strategy, preparing board presentations, managing investors, developing organizational culture, making executive decisions, or when user mentions CEO, strategic planning, board meetings, investor updates, organizational leadership, or executi...

Client-side routing patterns using the History API — managing URL state without full page reloads, building provider-optional routing hooks, SSR-safe browser API access, scroll behavior, and parameter parsing. Covers both the architectural patterns (custom routechange events, popstate listeners) and practical hook design for zero-dependency routing libraries. Use when building or extending routing systems, debugging navigation bugs, or working with @page-speed/router patterns.

Security-focused code review for OpenSite/Toastability platform. Use when reviewing PRs for security issues, auditing new API endpoints, checking for HIPAA/SOC2 compliance violations, reviewing Rust unsafe code, or scanning for injection vulnerabilities, data leakage, or auth bypasses. Auto-activates when reviewing code changes involving auth, LLM calls, user data, or external API integrations.

Context virtualization skill for extending effective context window across all AI coding agents. Provides SQLite FTS5 indexing of large tool outputs, BM25 search for targeted snippet retrieval, deterministic output compression, and session checkpointing that survives context compaction. Use this skill when working in long sessions, when tool outputs are large (logs, diffs, snapshots), or when resuming after compaction. Essential for Codex CLI and other agents that lack hook-based automatic ou...

Run conversion rate optimization through hypothesis-driven testing including audit, hypothesis generation, test design, statistical analysis, and rollout decisions. Use this skill whenever the user wants to optimize conversion, run A/B tests, audit a funnel, generate test hypotheses, design experiments, or analyze test results. Triggers on conversion optimization, CRO, A/B test, split test, multivariate test, hypothesis, conversion funnel, funnel audit, experiment design, statistical signific...

When the user wants to optimize, improve, or increase conversions on any marketing page or form — including homepage, landing pages, pricing pages, feature pages, lead capture forms, or contact forms. Also use when the user says 'CRO,' 'conversion rate optimization,' 'this page isn't converting,' 'improve conversions,' 'why isn't this page working,' 'my landing page sucks,' 'form abandonment,' 'nobody's converting,' 'low conversion rate,' or 'this page needs work.' Use this even if the user j...

Design Forge's Phase 4B deep-research subsystem so every claim in a generated report traces to a fetched source. Load when building or reviewing a multi-source research agent, planner/executor separation, parallel subagent fan-out, source adapters over src/scraping/ tiers, citation verification, claim-level entailment or faithfulness checks, hard-fail on unverifiable citations, report artifacts in Tigris, context-budget management for long syntheses, per-request cost caps for research aliases...

Language- and framework-agnostic process for upgrading one or more dependencies safely and systematically. Resolves version and peer conflicts before touching code, uses search tools to read changelogs and migration guides to find the exact breaking changes between the installed and target versions, applies every required code change, and verifies with the project's own build, lint, and test gates. Use when asked to bump, upgrade, or update a package (or a batch of packages), migrate a major ...

Architecture and decision guidance for enterprise-grade, database-agnostic natural-language-to-SQL over client-owned Postgres, MSSQL, MySQL, Oracle, Snowflake, and BigQuery warehouses at hundreds-of-databases / tens-of-thousands-of-tables scale. Load when designing, reviewing, or debugging text-to-SQL, NL2SQL, schema linking, catalog/metadata harvesting, semantic-layer routing, SQLGlot qualify/transpile/lineage, EXPLAIN (TYPE VALIDATE), BigQuery dry run, LSH value indexes, candidate reranking...

Forces truth-first, anti-sycophantic behavior across all AI agents. Use when proposing a hypothesis, reviewing an architectural decision, evaluating code design, or any situation where honest critical analysis is more valuable than validation. Auto-activates on hypothesis framing, design proposals, and requests for opinion or evaluation. Overrides default approval-seeking training behavior.

A discipline for designing experiments (A/B tests, multivariate, holdouts) so the results actually answer the question you asked. Hypothesis writing, sample size, duration, segment analysis, running discipline, matching a result to a pre-committed decision rule, and the common failure modes that produce confidently wrong shipping decisions. Use this skill whenever the user is planning a test that has not run yet: framing a hypothesis, sizing the sample, setting duration, choosing guardrails, ...

Design forms that convert, validate well, resist spam, and integrate cleanly with downstream systems. Use this skill when designing or auditing any form (contact, signup, checkout, multi-step, embedded), planning validation logic, fighting spam, choosing form tooling, or improving form conversion. Triggers on form design, form validation, form conversion, multi-step form, form spam, captcha, honeypot, form abandonment, signup form, contact form. Also triggers when form completion rates are lo...

Architecting cross-tool conversion flows that match audience and stage. Landing page to lead magnet to nurture sequence to offer to advanced funnels. Honest about silo-funnels (every tool standalone), kitchen-sink-funnels (every audience squeezed through one path), and matched-funnels (architecture matched to audience-and-stage) patterns. Triggers on funnel design, conversion architecture, marketing funnel, growth funnel, lifecycle architecture, nurture sequence design, multi-tool funnel orch...

Git workflow, branch conventions, PR patterns, and release management for OpenSite/Toastability repositories. Use when creating branches, writing commit messages, opening pull requests, managing monorepo packages, or coordinating cross-repo changes. Covers GitHub Actions CI patterns for Rust, Rails, and Next.js.

Hugging Face Hub CLI (`hf`) for downloading, uploading, and managing repositories, models, datasets, and Spaces on the Hugging Face Hub. Replaces now deprecated `huggingface-cli` command.

Use when the user asks to generate or edit images via the OpenAI Image API (for example: generate image, edit/inpaint/mask, background removal or replacement, transparent background, product shots, concept art, covers, or batch variants); run the bundled CLI (`scripts/image_gen.py`) and require `OPENAI_API_KEY` for live calls.

Guardrails, protocols, and operating constraints for large-scale, long-running, or parallelized AI coding tasks — migrations, codebase-wide refactors, framework upgrades, and any task touching 50+ files. Prevents scope creep, context drift, silent compounding errors, and emergent behavior outside the defined task boundary. Use when refactoring across files, migrating frameworks, upgrading dependencies, replacing or renaming patterns throughout a codebase, or any task touching 50+ files.

Install and wire the AI toolchain on a Linux dev machine: local LLM inference (Ollama, llama.cpp, vLLM, SGLang, TabbyAPI) with VRAM-based model selection, AI coding agents and CLIs (Claude Code, Codex, aider, OpenCode) with MCP servers, ML frameworks (PyTorch/JAX, Jupyter, HuggingFace) and GPU containers, and cloud/remote GPU workflows (RunPod, Vast.ai, Lambda, remote dev over SSH and Tailscale). Use when someone wants to run local models, set up or connect AI coding agents, configure MCP ser...

Configure a senior-grade Linux development environment on the machine: GPU drivers and compute stacks (NVIDIA CUDA, AMD ROCm, Intel XPU, Apple Silicon/Asahi), shell and terminal (zsh/fish, starship, modern CLI tools, tmux/zellij), advanced editor setup (Neovim/Vim, VS Code, Zed), language toolchains for Rust, Python, Ruby, and JavaScript/TypeScript via mise/uv/pixi, Docker/Podman containers, reproducible declarative setup (chezmoi, Ansible, Nix/home-manager), and security hardening (SSH keys,...

Choose the right Linux distribution for a developer or AI/ML workstation and confirm the hardware will work before installing. Use when someone asks which Linux distro to pick; is comparing Ubuntu, Fedora, Arch, NixOS, Pop!_OS, Mint, or atomic/immutable distros; is switching from Windows or macOS and unsure what to install; needs a distro matched to a use case (maximum stability, bleeding-edge GPU/AI work, reproducibility, laptop battery life, or a server); or wants to check whether a GPU, Wi...

Generate a safe, step-by-step runbook for installing Linux on a physical machine (replacing Windows, dual-booting, or a clean install) for a human sitting at the computer. Use when someone needs instructions to wipe Windows and install Linux, create bootable USB media, enter UEFI/BIOS, disable Secure Boot or Fast Startup, handle BitLocker or Intel RST, partition and encrypt a disk with LUKS, walk through a distro installer, or finish first-boot setup (drivers, firmware, power management). It ...

Runs a background maintenance agent that consolidates, deduplicates, decays confidence, and compresses old sessions in the memory store. Run this skill periodically (weekly or monthly) to keep the memory store lean and high-signal. Also useful after large batches of memory-write operations. Prevents the store from growing stale or bloated over time.

Deploys a background sub-agent to search the memory store and inject all relevant historical context before work begins. Use this skill at the start of any non-trivial session, when the user says "do you remember", when picking up previous work, or when starting a task on a named project. Returns a structured context brief covering project knowledge, architecture decisions, conventions, technology notes, and the current working memory state.

Deploys a background sub-agent to extract and persist important information from the current conversation into the long-term memory store. Invoke this skill at the end of a work session, after major architectural decisions, after fixing a non-trivial bug, or whenever the user says "save this", "remember this", or "store to memory". The agent analyzes the conversation for decisions, preferences, patterns, and facts then writes them to the correct memory layer automatically.

The OpenSite persistent long-term memory store. Provides a hierarchical filesystem tree for all agent memories across four cognitive layers: episodic (session history), semantic (project/tech/user knowledge), procedural (decisions, workflows, conventions), and working (active session state). Use this skill to directly read, write, search, or inspect memory entries. For automated session capture use memory-write; for context retrieval before a task use memory-recall; for periodic maintenance u...

Mobile-first design thinking and decision-making for iOS and Android apps. Touch interaction, performance patterns, platform conventions. Teaches principles, not fixed values. Use when building React Native, Flutter, or native mobile apps.

Designing forms with multiple steps, progress indicators, conditional logic, and save-and-resume mechanics. The discipline of breaking complex data collection into stages that respect cognitive load while maintaining completion intent. Honest about kitchen-sink-single-page (overwhelms before the user starts), progress-theater (steps without genuine staging), and genuinely-staged (each step earns its own page) patterns. Triggers on multi-step form, multi-page form, form wizard, signup wizard, ...

When the user wants to optimize post-signup onboarding, user activation, first-run experience, or time-to-value. Also use when the user mentions "onboarding flow," "activation rate," "user activation," "first-run experience," "empty states," "onboarding checklist," "aha moment," "new user experience," "users aren't activating," "nobody completes setup," "low activation rate," "users sign up but don't use the product," "time to value," or "first session experience." Use this whenever users are...

OpenSite UI component library patterns. Use when creating, editing, or reviewing components in @opensite/ui (opensite-ai/opensite-ui), the Semantic UI Engine, page-speed-* libraries, or the ui-library showcase (opensite-ai/ui-library). Covers component registration patterns, Tailwind CSS v4, Radix UI, framer-motion, ShadCN conventions, and the block/skin architecture.

page-speed-* library development patterns. Use when creating or modifying @page-speed/* packages (blocks, router, forms, img, video, skins, maps, icon, lightbox, pdf-viewer, venn-diagram, hooks, social-share, humanizer) or the opensite-hooks and pressable libraries. Covers tsup bundling, peer dependency management, and the sub-library architecture.

pgvector performance optimization: HNSW vs IVFFlat index selection and tuning, ef_search / m / ef_construction parameters, iterative scanning for filtered queries, scalar and binary quantization for memory reduction, and dimensionality compression. Embedding-model-agnostic — applies to any float32 vector workload. Use when vector search queries are slow, recall is poor, or index memory footprint is too large.

PostgreSQL performance engineering beyond basic indexing: query plan instability, statistics staleness, EXPLAIN ANALYZE interpretation, GIN index pending list management, extended statistics for correlated columns, PgBouncer connection pooling modes, and autovacuum tuning. Use when investigating slow queries, debugging inconsistent query performance, or tuning PostgreSQL for high-write production workloads.

Strategic product leadership toolkit for Head of Product including OKR cascade generation, market analysis, vision setting, and team scaling. Use for strategic planning, goal alignment, competitive analysis, and organizational design.

Advanced Rails query optimization: diagnosing N+1 beyond simple includes, the cartesian product trap with multiple has_many eager loads, CTEs and lateral joins via Arel and raw SQL, reading EXPLAIN ANALYZE output, and counter cache patterns. Use when investigating slow Rails endpoints, optimizing ActiveRecord queries, or designing queries for high-traffic production endpoints.

Zero-downtime database migration patterns for Rails 6.1+ on PostgreSQL with Heroku deployments. Covers the hot-compatibility principle, concurrent index creation, multi-step column operations, constraint validation strategies, and Heroku-specific release phase coordination. Use when adding columns, indexes, constraints, or renaming/removing any database object on a live production database.

React 19+ rendering performance: React Compiler diagnostics, profiler-driven optimization, useTransition for non-blocking updates, the new Activity and ViewTransition components, resource preloading APIs, and when to actually reach for useMemo/useCallback vs letting the Compiler handle it. Use when debugging slow renders, optimizing user-perceived performance, or implementing smooth navigation transitions in React 19+ applications.

Senior-level async Rust patterns: Future Send bound failures, Rust 2024 lifetime capture rules, task cancellation with CancellationToken, blocking/async boundary design, and timeout composition. Use when debugging async compilation errors, structuring long-lived tasks, or designing services that mix async and CPU-bound work.

Idiomatic Rust error handling design for libraries and applications: thiserror vs anyhow boundary decisions, error hierarchy design, context chain propagation, HTTP handler error mapping, and the common patterns that prevent error type proliferation. Use when designing error types for a new module, deciding between thiserror and anyhow, or debugging opaque error messages in production.

OpenSite Semantic UI Builder patterns. Use when working on the AI-powered site builder (handlers/semantic_builder.rs, handlers/semantic_ui_agent.rs in Octane), the component registry service, the Toastability/app CMS dashboard's site builder views, or any task related to AI-driven UI generation, block selection, skin application, or the v0-clone-inspired builder interface.

Comprehensive software architecture skill for designing scalable, maintainable systems using ReactJS, NextJS, NodeJS, Express, React Native, Swift, Kotlin, Flutter, Postgres, GraphQL, Go, Python. Includes architecture diagram generation, system design patterns, tech stack decision frameworks, and dependency analysis. Use when designing system architecture, making technical decisions, creating architecture diagrams, evaluating trade-offs, or defining integration patterns.

World-class data science skill for statistical modeling, experimentation, causal inference, and advanced analytics. Expertise in Python (NumPy, Pandas, Scikit-learn), R, SQL, statistical methods, A/B testing, time series, and business intelligence. Includes experiment design, feature engineering, model evaluation, and stakeholder communication. Use when designing experiments, building predictive models, performing causal analysis, or driving data-driven decisions.

Production-grade Sidekiq job design covering idempotency, database-level locking, transient vs permanent error classification, dead job management, and version-aware API differences across Sidekiq 6.5.x through 8.x. IMPORTANT: Before writing any Sidekiq job code, check the exact version in Gemfile.lock and load the docs via Context7 — the API changed significantly between major versions.

When the user wants to optimize signup, registration, account creation, or trial activation flows. Also use when the user mentions "signup conversions," "registration friction," "signup form optimization," "free trial signup," "reduce signup dropoff," "account creation flow," "people aren't signing up," "signup abandonment," "trial conversion rate," "nobody completes registration," "too many steps to sign up," or "simplify our signup." Use this whenever the user has a signup or registration f...