Explore Agent Skills

Score and compare covariance estimates with precise's assessor panel. Use when you need to judge an estimate out-of-sample or rank competing estimators — and especially in high dimensions, where the plain held-out likelihood is misleading.

Maintain an online covariance over named series whose set changes over time (e.g. assets entering and leaving). Use when observations arrive as dicts keyed by name rather than fixed-length vectors. Wraps precise's keyed / FixedUniverse / DynamicUniverse adapters.

Estimate a covariance / correlation / precision matrix incrementally with precise. Use when data arrives as a stream and you want the matrix updated per observation, or when you want an online (partial_fit) drop-in for sklearn.covariance, which is batch-only.

Pick which precise covariance estimator to use for a given dataset. Use when you have data X and are unsure which estimator fits its dimension, conditioning, or tail behavior. Wraps precise.suggest() and covariance_features().

Rigorously and honestly assess a NEW or proposed covariance / correlation / precision estimator, or a new covariance scoring rule, using precise. Use when someone proposes, asks to evaluate, or wants to compare a covariance methodology. Covers implementing it to the contract, conformance, benchmarking against the registry, out-of-sample validation, and statistically defensible inference.

Persistent compounding memory for AI agents. 5 default MCP tools: session_start, session_end, remember, recall, check. Full surface (18 tools) available with --full flag. Two-verb model: inhale (session_start) and exhale (session_end). Correction-first memory with decision trail tracking, watch_for warnings, palace rooms with salience scoring, cross-project insight matching, same-day journal merging, ambient recall hooks. Local markdown only. Zero cloud, zero telemetry, Obsidian-compatible. Optional Supabase backend: when configured via `ar setup supabase`, recall() uses pgvector cosine similarity on OpenAI/Voyage embeddings instead of keyword search — same API, semantic understanding. Gracefully degrades to local search if not configured.

Implement Zero Trust security model with identity verification, microsegmentation, least privilege access, and continuous monitoring. Use when building secure cloud-native applications.

Prevent Cross-Site Scripting (XSS) attacks through input sanitization, output encoding, and Content Security Policy. Use when handling user-generated content in web applications.

Create wireframes and interactive prototypes to visualize user interfaces and gather feedback early. Use tools and techniques to communicate design ideas before development.

Implement real-time bidirectional communication with WebSockets including connection management, message routing, and scaling. Use when building real-time features, chat systems, live notifications, or collaborative applications.

Implement secure webhook systems for event-driven integrations, including signature verification, retry logic, and delivery guarantees. Use when building third-party integrations, event notifications, or real-time data synchronization.

Implement webhook systems for event-driven integration with retry logic, signature verification, and delivery guarantees. Use when creating event notification systems, integrating with external services, or building event-driven architectures.

Optimize web application performance using code splitting, lazy loading, caching, compression, and monitoring. Use when improving Core Web Vitals and user experience.

Conduct comprehensive web performance audits. Measure page speed, identify bottlenecks, and recommend optimizations to improve user experience and SEO.

Automated vulnerability detection using OWASP tools, CVE databases, and security scanners. Use when performing security audits, compliance checks, or continuous security monitoring.

Structure Vue 3 applications using Composition API, component organization, and TypeScript. Use when building scalable Vue applications with proper separation of concerns.

Detect unintended visual changes in UI by comparing screenshots across versions. Use for visual regression, screenshot diff, Percy, Chromatic, UI testing, and visual validation.

Write effective user stories that capture requirements from the user's perspective. Create clear stories with detailed acceptance criteria to guide development and define done.

Analyze user research data to uncover insights, identify patterns, and inform design decisions. Synthesize qualitative and quantitative research into actionable recommendations.

Create detailed user personas based on research and data. Develop realistic representations of target users to guide product decisions and ensure user-centered design.

Create comprehensive user guides, tutorials, how-to documentation, and step-by-step instructions with screenshots and examples. Use when writing user documentation, tutorials, or getting started guides.

Implement uptime monitoring and status page systems for tracking service availability. Use when monitoring application uptime, creating status pages, or implementing health checks.

Write comprehensive unit tests with high coverage using testing frameworks like Jest, pytest, JUnit, or RSpec. Use when writing tests for functions, classes, components, or establishing testing standards.

Create comprehensive troubleshooting guides, FAQ documents, known issues lists, and debug guides. Use when documenting common problems, error messages, or debugging procedures.