Research

Phase 1 of disciplined development. Deep problem understanding before design.Maps existing systems, identifies constraints, surfaces risks, and producesa research document for human approval before proceeding.

Create web pages and UI components using the Neuphorism design system—a soft, tactile neumorphic aesthetic with extruded/pressed shadows, muted surface colors, and refined typography. Use when the user requests neuphorism/neumorphic styling, soft UI, or references this design system for any web page, component, dashboard, or application. Framework-agnostic (works with vanilla HTML/CSS, React, Vue, Tailwind, etc.).

Machine learning in Python with scikit-learn. Use when working with supervised learning (classification, regression), unsupervised learning (clustering, dimensionality reduction), model evaluation, hyperparameter tuning, preprocessing, or building ML pipelines. Provides comprehensive reference documentation for algorithms, preprocessing techniques, pipelines, and best practices.

Manages long-term memory for users across conversations. Automatically queries relevant memories when starting a new topic, and saves important personal information, habits, schedules, and user-requested memories. Use this when: discussing user background, preferences, or plans; starting a new task or project; users mention personal details or ask to remember something.

Complete knowledge domain for Cloudflare Workers KV - global, low-latency key-value storage on Cloudflare's edge network.Use when: creating KV namespaces, storing configuration data, caching API responses, managing user preferences,implementing TTL expiration, handling KV metadata, or encountering "KV_ERROR", "429 too many requests","kv rate limit", cacheTtl errors, or eventual consistency issues.Keywords: kv storage, cloudflare kv, workers kv, kv namespace, kv bindings, kv cache, kv ttl, kv metadata,kv list, kv pagination, cache optimization, edge caching, KV_ERROR, 429 too many requests, kv rate limit,eventually consistent, wrangler kv, kv operations, key value storage

AWS Polly TTS CLI for text-to-speech synthesis

LMS-ESID core architecture including one-class-three-teachers system, course structure, grade levels, role permissions, and database schema. Use this skill when understanding teacher types (LT/IT/KCFS/HT), course relationships, class naming conventions, academic year data, or table relationships.

Generate API documentation from TypeScript source code for RSPress. Use when documenting package APIs, extracting types from source code, or creating function/class reference pages.

Research external information using web search and codebase exploration. Activate when user requests research or asks about libraries, APIs, external repos, current events, or needs up-to-date information. Delegates to subagents to preserve context window.

Generate AI agent personas with authentic backstories, demographics, and personality traits for TraitorSim. Use when creating new characters, generating personas, building character libraries, or when asked about persona generation, backstory creation, or character development. Orchestrates Deep Research + Claude synthesis pipeline.

Use when building context-dependent animations - duration that changes based on device, distance, user preference, or interaction context

Personal research backlog. Quick-capture ideas for later exploration. Check when you have unstructured time.

Always use Context7 MCP to fetch up-to-date library/API documentation before generating code that depends on external libraries or config. Use when the user asks for setup steps, configuration, or code involving third-party libraries. Prefer Context7 docs over memory. Include citations to the retrieved docs when possible.

Pure Data reference documentation for audio patch development. Use when writing .pd patches, working with OSC/audio/sampling, or implementing Pure Data code.

Creates and tests Pangea Ruby function resources with synthesis testing. Use when creating new resources, writing synthesis tests, generating test coverage for Terraform DSL resources, or filling test gaps for AWS/Cloudflare/Hetzner resources.

Advanced meta-skill for generating complete, production-ready skills for any domain. Use when the user wants to create a new skill, needs help designing a skill, wants to generate specialized skills for specific workflows, or requests "make me a skill for X". Automatically analyzes requirements, designs optimal skill architecture, generates all resources (scripts/references/assets), validates output, and packages distributable .skill files. Handles technical skills (API integrations, file processing), domain expertise skills (finance, legal, medical), workflow skills (multi-step processes), and creative skills (writing, design, content generation).

Heme/Onc consultant: Rapid clinical decision support for hematology and oncology with multi-level analysis. Provides immediate guidance followed by deep adversarial validation, tumor board simulation with multiple specialties, evidence-based research, and risk-benefit analysis. Use for diagnostic dilemmas, treatment planning, complex cases, or when uncertain about clinical decisions in hematology/oncology.

Use this skill when setting up or running autonomous stock trading operations. The system continuously researches stocks, makes trading decisions without human input, executes trades on Alpaca paper trading, and sends Telegram notifications. Based on AI-Trader's autonomous agent pattern.

AI-powered research skill with five workflows - chat (single-model conversation), consensus (multi-model synthesis), thinkdeep (systematic investigation), ideate (creative brainstorming), and deep (multi-phase web research). Supports persistent threads and research sessions.

Reference for the buy box optimization pricing algorithm. Use when understanding pricing decisions, debugging price changes, or investigating buy box behavior. Covers the core optimization loop, buy box detection, and edge cases like multiple buy box winners.