cyai

Manages issues via the br CLI (beads), a local-first tracker stored in .beads/ (SQLite + JSONL). Use when capturing issues, finding ready work, claiming issues, managing dependencies, or syncing changes. Triggers: "br", "beads", "issue tracking".

Review, rewrite, and debug LLM prompts. Use when asked to: (1) improve an existing prompt, (2) design a new system or developer prompt, (3) add few-shot examples, (4) define output schemas and success criteria, (5) diagnose prompt failures from transcripts. Not for: model policy workarounds, producing domain answers without context, or guaranteeing model-specific behavior.

Creates or updates mala.yaml project configuration files for the local mala orchestrator. Use when asked to initialize, generate, write, edit, validate, fix, or explain a mala.yaml config, including presets, commands, coverage, evidence checks, validation triggers, or review settings.

Simplifies and refines code for clarity, consistency, and maintainability while preserving all functionality. Focuses on recently modified code unless instructed otherwise. Triggers: simplify, refine, clean up code.

Automates browser interactions for web testing, form filling, screenshots, and data extraction. Use when the user needs to navigate websites, interact with web pages, fill forms, take screenshots, or extract information from web pages.

Executes SQL queries on Dune Analytics and writes results as CSV to /tmp. Use when the user needs blockchain data from Dune or wants to run a saved Dune query by ID. Triggers: "dune query", "dune sql", "query dune", "blockchain data"

Explore Python import graphs and enforce layered architecture using grimp.

Search and analyze mala orchestrator and Claude session logs. Use when searching for session logs, debugging agent runs, finding tool errors, analyzing mala run history, or investigating issue-specific logs. Triggers on queries like "find logs for issue X", "what went wrong in the last run", "show tool errors", "list recent sessions".

Execute SQL queries against Databricks SQL Warehouses. Use when the user wants to: - Run ad-hoc SQL queries on Databricks - Explore table data or run analytics - Execute DDL/DML statements Triggers: "run sql", "query databricks", "select from", "databricks sql", "execute query"

PySpark code style and best practices for DataFrame API. Use when: (1) Writing or reviewing PySpark/Python code (2) Refactoring Spark transformations Triggers: "pyspark", "spark dataframe", "code review", "style", "etl code"

Manage Databricks Asset Bundles (DABs) for infrastructure as code. Use when user wants to: (1) Initialize a new bundle project from templates (2) Deploy jobs, pipelines, or apps to workspaces (3) Run jobs/pipelines from bundle definitions (4) Generate bundle config from existing resources (5) Manage multi-environment deployments (dev/staging/prod) Triggers: "bundle", "DAB", "deploy to databricks", "init project", "databricks.yml"

Manage Databricks Jobs via CLI. Use when user wants to: (1) Create, update, or delete job definitions (2) Run jobs or submit one-time runs (3) List jobs or get job details (4) Monitor runs, check status, or cancel Triggers: "databricks job", "create job", "run job", "job status", "list jobs", "cancel run"

Manage Unity Catalog via Databricks CLI. Use when user wants to: (1) Create/list/manage catalogs, schemas, tables, or volumes (2) Set up or manage grants and permissions (3) Explore the three-level namespace (catalog.schema.table) Triggers: "unity catalog", "catalog", "schema", "table permissions", "grants", "volumes", "list tables"