Loading...
Loading...
Found 2,762 Skills
Build and validate HelixDB dynamic inline-query requests for POST /v1/query. Use when the task involves dynamic queries, inline query JSON, the inline AST (steps, predicates, expressions, projections), parameter_types, DateTime coercion, query warming, or debugging a request body sent directly to the Helix gateway. See REFERENCE.md for every AST variant and EXAMPLES.md for copy-pasteable payloads.
Shell script development workflow. Use when modifying files in scripts/ directory or any *.sh files.
Code review requires technical evaluation, not emotional performance.
Generates production-ready Python code following PEP standards, type hints, and clean code principles. Use when user requests Python implementation of classes, functions, services, or modules. Triggers on "implement", "write", "Python code", "create class", "create function", "code for".
Extract, validate, and categorize invoice data against purchase orders and GL codes
Comprehensive citation management for academic research. Search Google Scholar and PubMed for papers, extract accurate metadata, validate citations, and generate properly formatted BibTeX entries. This skill should be used when you need to find papers, verify citation information, convert DOIs to BibTeX, or ensure reference accuracy in scientific writing.
Canonical built-in iii trigger config and call payload shapes. Use when generating or validating HTTP, cron, queue, pubsub, state, stream, or log trigger registrations and handler input types.
Enforces vendor-neutral UTM naming conventions by validating marketing links and generating a normalized, policy-compliant output.
Apply after completing a task, before declaring done. Verify against the real artifact (run the feature, read the actual value, inspect the diff), not a proxy, self-report, or 'it compiles.'
Use when importing a new model architecture into MAX from a Hugging Face model ID. Triggers on: "import a model into MAX", "add model to MAX", "bring up <HF model> in MAX". Workflow: inspect Hugging Face config and modeling code, scaffold from a similar MAX architecture, implement each graph layer to match HF, serve, then debug against the Hugging Face reference until outputs match.
Continuously question users about their plan or design. Suitable for scenarios where users want to stress-test their plan before building, or when using any "grill" trigger phrases.
Structured guide for setting up A/B tests with mandatory gates for hypothesis, metrics, and execution readiness.