How code gets written and checked: architectural baselines, Python standards, and the defect and structure reviews that gate a finished change. Invoke as /craft:<skill-name>. The architecture-baseline skill requires the separately installed researcher agent.
Plugin craft from marketplace data-engineering-skills in victormacaubas/data-engineering-skills. Commands read from the repo's manifest — 8 days ago.
architecture-baselineTurn a design doc into a project's architectural constraints before any feature work — layer map, runtime dependencies and libraries, identity model, injected seams, error taxonomy, machine-enforced import contracts, testing conventions, a quality gate that checks all of it, and a reviewer-facing `d
code-auditProduces a non-destructive, language-agnostic code review as a machine-parseable JSON artifact under `./.code-audit/`, with a human markdown report rendered on request. Scores security, correctness, performance, architecture, error handling, and readability across six weighted dimensions with severi
python-engineering-standardsCanonical Python coding standards — layout, typing, docstrings and comments, class-vs-function, logging, error handling and retries, dependency injection, concurrency, security, testing, and the tells that make code read as machine-generated. Use whenever you write, review, or refactor Python of any
structure-reviewReviews finished changes for code and test structure, conformance to applicable plans, tasks, and documentation, applicable architecture conventions, and readability. Use after implementation and before merge or archive, or to assess module/test design, cohesion, state ownership, duplication, Clean
How work gets driven from an unformed idea to something tracked and built: exploring, pressure-testing, delegating implementation, ticketing, and capture. Invoke as /flow:<skill-name>. The scout skill requires the separately installed pathfinder and researcher agents; orchestrate requires implementer, pathfinder, researcher, structure-reviewer, and test-author.
6 skills
The warehouse surface: canonical SQL standards for trustworthy analytics, and Snowflake ACCOUNT_USAGE auditing for masking, row access, classification, tags, grants, logins, and query history. Invoke as /data:<skill-name>.
2 skills
Claude Code only. Optional. Denies the implementer agent file edits on the test tree and the test-author agent file edits on production code. Without it, both agents are bounded by their instructions only.
Claude Code only. Shows the SQL that the main session and its subagents run through the snowflake-raw MCP server in a pane, grouped by agent. Requires the snowflake-raw MCP server.
This page updates itself from your repo. Add the badge to your README, or get it Featured to pin it above the organic results with a followed link to your site.