> browse/registry

> kaggle-finetune

End-to-end workflow for fine-tuning LLMs using Kaggle datasets. Use when downloading datasets from Kaggle for model training, preparing conversation/customer service data for chatbot fine-tuning, or building domain-specific AI assistants. Covers dataset discovery, download, preprocessing into chat format, and integration with PEFT/LoRA training.

> feedback-analysis

Collect, categorize, and synthesize user feedback from multiple channels into actionable product insights. Use when tasks involve analyzing support tickets, app store reviews, NPS survey responses, social media mentions, user interviews, feature request prioritization, sentiment analysis, churn prediction from feedback patterns, or building voice-of-customer reports. Covers multi-channel feedback aggregation and data-driven product decisions.

> ffmpeg

Transcode, convert, edit, and process audio and video with FFmpeg. Use when a user asks to convert video formats (webm to mp4, mkv to mp4), extract audio from video, compress video files, trim or cut clips, concatenate videos, add subtitles, create thumbnails, apply filters, change resolution or bitrate, re-encode media, create GIFs from video, add watermarks, normalize audio, stream media, or build automated media processing pipelines.

> unity

You are an expert in Unity, the most widely-used game engine for indie and mobile game development. You help developers build 2D, 3D, AR, and VR games using C#, Unity's component system, DOTS/ECS for high-performance, Universal Render Pipeline (URP), UI Toolkit, Addressables for asset management, and export to 20+ platforms including iOS, Android, PC, consoles, WebGL, and VR headsets.

> data-validator

Validate data quality in CSV, JSON, and database exports by checking for missing values, type mismatches, duplicates, outliers, and schema violations. Use when building ETL pipelines, auditing data imports, checking data freshness, or ensuring data contracts between teams. Trigger words: data quality, validation, null values, duplicates, schema check, data contract, ETL, pipeline, data drift.

> flask

Flask is a lightweight Python micro web framework that provides the essentials for web development without imposing structure. It uses Jinja2 templates and Werkzeug WSGI toolkit, with a rich ecosystem of extensions for databases, auth, and more.

> malloy

Expert guidance for Malloy, the experimental data language from Google that replaces SQL for analytics with a composable, reusable, and more readable syntax. Helps developers write Malloy models, build nested queries, and explore data with Malloy's VS Code extension and notebook interface.

> knex

You are an expert in Knex.js, the flexible SQL query builder for Node.js that supports PostgreSQL, MySQL, SQLite, and MSSQL. You help developers write type-safe queries with a chainable API, manage database migrations and seeds, build complex joins and subqueries, and use transactions — providing direct SQL control without the overhead of a full ORM.

> vitest

You are an expert in Vitest, the Vite-native testing framework. You help developers write and run unit tests, integration tests, and component tests with native TypeScript support, Jest-compatible API, built-in mocking, code coverage, snapshot testing, and watch mode — leveraging Vite's transform pipeline for instant test execution without separate compilation.

> agent-memory

Add persistent memory to AI coding agents — file-based, vector, and semantic search memory systems that survive between sessions. Use when a user asks to "remember this", "add memory to my agent", "persist context between sessions", "build a knowledge base for my agent", "set up agent memory", or "make my AI remember things". Covers file-based memory (MEMORY.md), SQLite with embeddings, vector databases (ChromaDB, Pinecone), semantic search, memory consolidation, and automatic context injection.

> traceloop

You are an expert in Traceloop and its OpenLLMetry SDK, the open-source observability framework that extends OpenTelemetry for LLM applications. You help developers instrument AI pipelines with automatic tracing for OpenAI, Anthropic, Cohere, LangChain, LlamaIndex, vector databases, and frameworks — exporting to any OpenTelemetry-compatible backend (Grafana Tempo, Jaeger, Datadog, Honeycomb, Traceloop Cloud).

> agent-swarm-orchestration

Coordinate multiple AI agents working together on complex tasks — routing, handoffs, consensus, memory sharing, and quality gates. Use when tasks involve building multi-agent systems, coordinating specialist agents in a pipeline, implementing agent-to-agent communication, designing swarm architectures, setting up agent orchestration frameworks, or building autonomous agent teams with supervision and quality control. Covers hierarchical, mesh, and pipeline topologies.

> langgraph

Build stateful, multi-step AI agents and workflows with LangGraph. Use when a user asks to create AI agents with complex logic, build multi-agent systems, implement human-in-the-loop workflows, create state machines for LLMs, build agentic RAG, implement tool-calling agents with branching logic, create planning agents, build supervisor/worker patterns, or orchestrate multi-step AI pipelines with cycles, persistence, and streaming.

> langtrace

You are an expert in Langtrace, the open-source observability platform for LLM applications built on OpenTelemetry. You help developers trace LLM calls, RAG pipelines, agent tool use, and chain executions with automatic instrumentation for OpenAI, Anthropic, LangChain, LlamaIndex, and 20+ providers — providing cost tracking, latency analysis, token usage, and quality evaluation in a self-hostable dashboard.

> mintlify

Create beautiful developer documentation with Mintlify — AI-powered docs platform. Use when someone asks to "create documentation site", "Mintlify", "developer docs", "API documentation", "beautiful docs like Stripe", or "documentation platform with AI search". Covers page creation, API reference generation, components, analytics, and AI chat.

> programmatic-seo

When the user wants to create SEO-driven pages at scale using templates and data. Also use when the user mentions "programmatic SEO," "template pages," "pages at scale," "directory pages," "location pages," "[keyword] + [city] pages," "comparison pages," "integration pages," or "building many pages for SEO." For auditing existing SEO issues, see seo-audit.

> confluence

Manage knowledge bases and documentation with Confluence Cloud. Use when a user asks to create or manage Confluence spaces, pages, and blogs, build documentation systems, automate page creation from templates, use Confluence REST API v2, manage page trees and hierarchies, set up permissions, integrate Confluence with Jira or other tools, generate reports from Confluence data, build macros or Forge apps, or migrate content between spaces. Covers content management, API automation, templates, and

> github-actions

Build CI/CD pipelines with GitHub Actions — workflows, jobs, steps, triggers, caching, artifacts, matrix builds, secrets, environments, reusable workflows, and custom actions. Use when tasks involve automating tests, builds, deployments, code quality checks, or any GitHub-triggered automation.

> billing-automation

Automate invoice generation, billing workflows, payment tracking, and revenue recognition for SaaS and service businesses. Use when building billing pipelines, usage-based invoicing, subscription management, payment reminders, or financial reporting. Trigger words: invoice, billing, payment, subscription, usage billing, revenue recognition, accounts receivable, payment reminder, overdue invoice, billing cycle, proration, Stripe billing.

> coolify

Deploy and manage applications, databases, and services on Coolify. Use when a user asks to deploy an app to Coolify, manage Coolify deployments, check deployment logs, sync environment variables, create or manage databases on Coolify, trigger a deployment, manage Coolify servers, or troubleshoot Coolify issues. Covers the Coolify CLI and REST API. For infrastructure provisioning on Hetzner, see hetzner-cloud.