Essential command-line tools and system utilities.
Large Language and Vision Assistant. Enables visual instruction tuning and image-based conversations. Combines CLIP vision encoder with Vicuna/LLaMA language models. Supports multi-turn image chat, visual question answering, and instruction following. Use for vision-language chatbots or image understanding tasks. Best for conversational image analysis.
Multi-cloud orchestration for ML workloads with automatic cost optimization. Use when you need to run training or batch jobs across multiple clouds, leverage spot instances with auto-recovery, or optimize GPU costs across providers.
Autonomous AI agent platform for building and deploying continuous agents. Use when creating visual workflow agents, deploying persistent autonomous agents, or building complex multi-step AI automation systems.
Manage Unstract connectors - add, remove, or modify database, filesystem, and queue connectors. This skill handles backend code, JSON schemas, tests, logo fetching, and dependency management. Use when the user wants to create a new connector, delete an existing one, or modify connector behavior.
Check CI status, analyze failures, and explain skips for a Dynamo PR
Best practices for using the stagewise built-in JavaScript sandbox. Explains how to access APIs for browser debugging/interaction, use external dependencies, file system access, running mini-apps, etc.
Stagewise UI theming, design tokens, derived utilities, and component library reference. Use when creating, editing, or reviewing UI in apps/browser, implementing new screens or components, or styling with Tailwind in the stagewise codebase.
Sink short link API operations via OpenAPI. Use when managing short links: creating, querying, updating, deleting, listing, importing, or exporting links. Also covers AI-powered slug generation and link analytics. Triggers: "create short link", "shorten URL", "delete link", "edit link", "list links", "export links", "import links", "link analytics", "AI slug".
Check and optimize MetaDescription frontmatter fields in VS Code documentation. Use when auditing, adding, or improving page descriptions for SEO and discoverability. Apply this when making content changes to markdown articles.
Create new commands for the code-forge application. Commands are stored as .md files in the <cwd>/.forge/commands directory with YAML frontmatter (name, description) and markdown body containing command steps. Use when users need to add new commands, modify existing commands, or understand the command file structure. Supports special command tags like <lint> and <test> for automated workflows.
Resolve inline code review comments on a GitHub PR. Use when asked to "resolve review comments", "address PR feedback", "fix PR comments", or "work through review comments". Fetches every inline comment with its surrounding code context, then applies each change systematically.
Find all FIXME comments across the codebase and attempt to resolve them. Use when the user asks to fix, resolve, or address FIXME comments, or when running the "fixme" command. Runs a script to locate every FIXME with surrounding context (2 lines before, 5 lines after) and then works through each one systematically.
Query patterns including pagination, search, filtering, and specifications for FSH. Use when implementing GET endpoints that return lists or need filtering.
Create a domain entity with multi-tenancy, auditing, soft-delete, and domain events. Use when adding new database entities to a module.
Add, modify, or debug benchmark scenarios for measuring Materialize performance. Covers three frameworks: Feature Benchmark (single-operation micro-benchmarks), Scalability Test (SQL throughput under concurrency), and Parallel Benchmark (sustained latency over time via scenarios.py). Trigger on "benchmark", "feature benchmark", "scalability test", "parallel benchmark", "performance regression", "micro-benchmark", "TPS", "latency test", or when editing files in feature_benchmark/scenarios/, scalability/workload/workloads/, or parallel_benchmark/scenarios.py. Note: this is about benchmark measurement frameworks, not the parallel-workload stress-testing framework (which tests for panics under concurrency, not performance).
Investigate CI failures on a PR using gh and bk CLI tools. Trigger when the user asks about failing checks, Buildkite failures, or CI issues — including casual phrases like "why is CI red", "build broken", "checks failing", "what went wrong in CI", "nightly broke", "tests failing on this PR", or pastes a Buildkite URL. Also trigger when the user mentions a specific PR number and wants to understand why it's failing.
Extend the parallel-workload stress-testing framework, which runs random SQL actions concurrently to catch panics and unexpected errors (not performance measurement — see mz-benchmark for that). Trigger when the user mentions "parallel workload", "parallel-workload", "action.py" in the context of parallel workload, or wants to test for panics or unexpected query errors under concurrency. Use this skill even if the user just says "add this to parallel workload" or references a bug that panics under concurrent DDL/DML.
This skill should be used when the user wants to "profile Materialize", "check memory usage", "analyze binary size", "debug performance", or mentions profiling, samply, heaptrack, flame graphs, memory checking, binary size analysis, slow queries, or high CPU/memory usage in the Materialize repository. Use this skill even if the user just says something is "slow" or "using too much memory" without explicitly mentioning profiling.
Debug where time is spent during SQL execution using distributed tracing (OpenTelemetry / Tempo). Trigger when the user asks "why is this query slow", "where is the time going", "this SELECT takes forever", or wants a latency breakdown for any SQL statement. Also trigger on mentions of tracing queries, span analysis, Tempo traces, trace IDs, or opentelemetry_filter.
