productivity▌

Automated learning capture in CI pipelines that deduplicates failure patterns and proposes prevention rules. \n \n Inspects PR check results and CI failures to identify recurring patterns tracked by stable pattern_key , promoting only when recurrence thresholds are met (3+ occurrences across 2+ distinct runs within 30 days) \n Ingests learning candidates from simplify-and-harden-ci and emits machine-readable YAML output without interactive prompts, suitable for headless GitHub Actions workflows

Behavioral testing and reliability metrics for LLM agents, catching production failures benchmarks miss. \n \n Covers five core evaluation areas: agent testing, benchmark design, capability assessment, reliability metrics, and regression testing \n Emphasizes statistical test evaluation (multiple runs, result distribution analysis) and behavioral contract testing over single-run or string-matching approaches \n Includes adversarial testing patterns to actively probe agent failure modes and ident

Use this skill when the user needs metadata definition or org metadata discovery: custom objects, fields, validation rules, record types, page layouts, permission sets, or schema inspection with sf CLI.

Simplify code while preserving behavior, public contracts, and side effects. Favor explicit code and local clarity over clever or compressed constructs.

A systematic approach to building a scalable, predictable B2B sales machine. Pioneered the outbound prospecting system that helped Salesforce add $100M in recurring revenue.

Complete observability and tracing for LLM applications with prompt management, evaluation, and cost tracking. \n \n Automatic tracing of LLM calls, spans, and traces with user/session grouping; supports OpenAI SDK as drop-in replacement and integrates with LangChain via callback handlers \n Built-in prompt versioning, A/B testing, dataset management, and scoring for evaluation and quality monitoring \n Cost and performance tracking across traces with metadata tagging for production debugging an

Flutter development with Riverpod state management, Freezed immutable models, go_router navigation, and mocktail testing. \n \n Riverpod provider ecosystem covers simple values, mutable state, async operations, streams, and parameterized data with family modifiers; AsyncValue pattern handles loading, error, and data states uniformly \n Freezed generates immutable data classes and union types for sealed state modeling; integrates with JSON serialization via json_serializable \n go_router provides

Unix-style shell commands for navigating and querying web pages as a filesystem. \n \n Navigate URLs with cd , list links with ls , extract content with cat , and filter with grep —all operating on cached page content locally and instantly \n Supports natural language inference: commands like \"show me the first 5 links\" or \"what forms are on this page?\" are automatically interpreted without formal syntax \n Asynchronous architecture with background prefetching: user gets their prompt back im

Interactive migration from Cypress or Selenium to Playwright with file-by-file conversion.

Configure Astronomer Cosmos for dbt Fusion projects on Snowflake, Databricks, BigQuery, or Redshift with local execution. \n \n Requires Cosmos 1.11.0+, dbt Fusion binary installed separately in the Airflow runtime, and ExecutionMode.LOCAL with subprocess invocation \n Supports three parsing strategies: dbt_manifest (fastest for large projects), dbt_ls (for complex selectors), or automatic (simple setups) \n Covers ProfileConfig setup for warehouse connections, ProjectConfig for dbt project path