Browse skills

Write type-safe SQL with Kysely query builder. Use when a user asks to write raw SQL with TypeScript safety, build queries without an ORM, use a lightweight SQL builder, or migrate from Knex with type safety.

Open-source data labeling and annotation platform for ML projects. Supports text, image, audio, video, and time-series data. Features configurable labeling interfaces, ML-assisted labeling, team collaboration, and API integration for automated workflows.

Build LLM-powered applications with LangChain. Use when a user asks to create AI chains, build RAG pipelines, implement agents with tools, set up document loaders, create vector stores, build conversational AI, implement prompt templates, chain LLM calls, add memory to chatbots, or orchestrate language model workflows. Covers LangChain v0.3+ with LCEL (LangChain Expression Language), structured output, tool calling, retrieval, and production deployment patterns.

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.

Use when testing valid model configuration

Monitor, trace, debug, and evaluate LLM applications with LangSmith. Use when a user asks to trace LLM calls, debug chain executions, evaluate AI output quality, set up LLM observability, monitor agent performance, run prompt experiments, compare model outputs, create evaluation datasets, track token usage and latency, or build LLM testing pipelines. Covers tracing, datasets, evaluators, annotation queues, prompt hub, and production monitoring.

You are an expert in Laravel, the most popular PHP framework for building web applications and APIs. You help developers build production systems with Eloquent ORM, Blade templating, Artisan CLI, queues, events, middleware, authentication (Sanctum/Breeze), Livewire for reactive UI, and a rich ecosystem of first-party packages — enabling rapid development without sacrificing code quality.

Manage feature flags with LaunchDarkly. Use when a user asks to implement feature flags, roll out features gradually, do A/B testing, control feature access by user segment, or implement kill switches for features.

Build interactive maps with Leaflet.js. Use when a user asks to create map-based applications, add markers and popups, draw shapes, handle geolocation, or integrate tile layers in web applications.

Fast Git hooks manager written in Go. Use when a user asks to set up Git hooks without Node.js dependency, run parallel pre-commit checks, or find a faster alternative to Husky.

You are an expert in Leptos, the full-stack Rust web framework that combines server-side rendering with client-side interactivity via WebAssembly. You help developers build reactive web applications using Leptos's fine-grained signal system, server functions, islands architecture, and compile-time optimizations — getting React-like DX with Rust's performance and type safety.

libSQL — a fork of SQLite with replication, HTTP API, and embedded replicas (used by Turso). Use when you need embedded SQLite with remote sync, an edge-compatible database, or a Turso cloud database. Covers the @libsql/client SDK, local/in-memory/cloud connections, embedded replicas, batch queries, and transactions.

Automate Lighthouse audits in CI with Lighthouse CI. Use when a user asks to track Core Web Vitals, prevent performance regressions, audit accessibility in CI, or set performance budgets for web apps.

Manage projects and issues with Linear. Use when a user asks to set up Linear workspaces, create issues and projects, automate workflows, build Linear integrations, sync issues with GitHub, manage sprints and cycles, set up triage processes, build custom views, use Linear's GraphQL API, create webhooks, automate issue transitions, or build tools on top of Linear. Covers workspace configuration, team workflows, API automation, and integration patterns.

Linkerd lightweight service mesh for Kubernetes. Use when the user needs automatic mTLS, traffic splitting, retries, and observability with minimal resource overhead and operational complexity.

Expert guidance for Liveblocks, the platform for adding real-time collaboration features to web applications. Helps developers implement live cursors, presence indicators, collaborative editing, comments, and notifications using Liveblocks' React hooks and APIs.

Expert guidance for llamafile, the tool that packages LLMs into single executable files that run on any OS (Linux, macOS, Windows, FreeBSD) without installation. Helps developers create portable AI applications, run models offline, and distribute LLMs as self-contained binaries with built-in web UI and OpenAI-compatible API.

Offload tasks to local LLMs via LM Studio. Use when a user asks to run local models with LM Studio, save API costs by using local LLMs, create subagents with local models, offload summarization or classification to a local model, or use LM Studio's API for batch processing. Covers local model inference, task delegation, and cost optimization.

Expert guidance for LocalAI, the open-source drop-in replacement for OpenAI's API that runs locally. Helps developers self-host LLMs, image generators, audio transcription, and text-to-speech models with an OpenAI-compatible API — no GPU required, completely offline and private.

Analyze application logs, server logs, and error traces to identify root causes, patterns, and anomalies. Use when debugging production incidents, investigating error spikes, parsing crash reports, or correlating events across multiple log sources. Trigger words: logs, errors, stack trace, crash, exception, debug, incident, 500 errors, timeout, latency spike.