Loading...
Loading...
Found 62 Skills
Running and fine-tuning LLMs on Apple Silicon with MLX. Use when working with models locally on Mac, converting Hugging Face models to MLX format, fine-tuning with LoRA/QLoRA on Apple Silicon, or serving models via HTTP API.
Optimizes Snowflake query performance using query ID from history. Use when optimizing Snowflake queries for: (1) User provides a Snowflake query_id (UUID format) to analyze or optimize (2) Task mentions "slow query", "optimize", "query history", or "query profile" with a query ID (3) Analyzing query performance metrics - bytes scanned, spillage, partition pruning (4) User references a previously run query that needs optimization Fetches query profile, identifies bottlenecks, returns optimized SQL with expected improvements.
Wallets for AI agents with x402 payment signing, referral rewards, and policy-controlled actions.
Strategies for managing LLM context windows effectively in AI agents. Use when building agents that handle long conversations, multi-step tasks, tool orchestration, or need to maintain coherence across extended interactions.
Refine user stories into sprint-ready backlog items using INVEST checks, gap analysis, Gherkin acceptance criteria, edge cases, dependencies, and structured refinement questions.
Patterns and architectures for building AI agents and workflows with LLMs. Use when designing systems that involve tool use, multi-step reasoning, autonomous decision-making, or orchestration of LLM-driven tasks.
Infrastructure as Code best practices for Terraform, Docker, Ansible, and CloudFormation. Covers secure-by-default configurations, multi-stage builds, state management, and modular patterns. Use when working with .tf, Dockerfile, docker-compose.yml, .yaml/.yml Ansible files, CloudFormation templates, or when asking about IaC, containers, or infrastructure automation.
Use when the user wants to turn a PRD requirement (FR-N or similar ID) into an executable development plan. Locates the requirement in docs/prd/, investigates the surrounding code, asks clarifying questions, and produces docs/plans/<FR-N>.md as a markdown checkbox list of independent, vertical-slice tasks. Triggers on "make a plan for FR-001", "generate a plan for this requirement", "break this PRD into tasks", "plan the implementation of FR-N", "create a dev plan", "/plan FR-N".
Safely refactors dbt models with downstream impact analysis. Use when restructuring dbt models for: (1) Task mentions "refactor", "restructure", "extract", "split", "break into", or "reorganize" (2) Extracting CTEs to intermediate models or creating macros (3) Modifying model logic that has downstream consumers (4) Renaming columns, changing types, or reorganizing model dependencies Analyzes all downstream dependencies BEFORE making changes.
Adds schema tests and data quality validation to dbt models. Use when working with dbt tests for: (1) Adding or modifying tests in schema.yml files (2) Task mentions "test", "validate", "data quality", "unique", "not_null", or "accepted_values" (3) Ensuring data integrity - primary keys, foreign keys, relationships (4) Debugging test failures or understanding why dbt test failed Matches existing project test patterns and YAML style before adding new tests.
Debugs and fixes dbt errors systematically. Use when working with dbt errors for: (1) Task mentions "fix", "error", "broken", "failing", "debug", "wrong", or "not working" (2) Compilation Error, Database Error, or test failures occur (3) Model produces incorrect output or unexpected results (4) Need to troubleshoot why a dbt command failed Reads full error, checks upstream first, runs dbt build (not just compile) to verify fix.
Memory-efficient fine-tuning with 4-bit quantization and LoRA adapters. Use when fine-tuning large models (7B+) on consumer GPUs, when VRAM is limited, or when standard LoRA still exceeds memory. Builds on the lora skill.