dlaw

Read project context (CLAUDE.md, TODO.md, README.md, DEVELOPER.md, recent git changes) to catch up on current state.

Generate implementation notes for today's session — reviews conversation history, documents decisions, files changed, and next steps.

Show a concise bullet list of open TODO items from TODO.md.

Organize TODOs into a phased roadmap structure (Next, Backlog, Completed) and ensure all items are up to date.

Before clearing the conversation, update TODO.md with any progress made during this session:

Interface contracts, versioning, REST/GraphQL patterns. Use when: new API endpoints, API modifications, integration work, external-facing services, contract changes.

Best practices, consistency, edge cases, readability. Use when: any code changes, new feature implementation, refactoring work, code quality improvements, style/consistency enforcement.

Resource efficiency, cloud spend, waste reduction. Use when: infrastructure provisioning, cloud resource selection, data storage decisions, high-volume operations, cost optimization initiatives.

Schema design, query optimization, migrations, indexing. Use when: schema changes, new data models, query performance issues, database migrations, data integrity concerns, reporting/analytics features.

Root cause analysis, systematic debugging, logging. Use when: bug investigations, production issues, error handling improvements, logging enhancements, monitoring setup.

This skill MUST be used before writing any implementation code — feature work, bug fixes, pipeline stages, data processing, API handlers, K8s manifests, or integration code. Enforces fail-loud patterns, input/output validation, connection verification, and pre-commit gates. Triggered automatically on any code writing task. Also use when user says "defensive", "fail-fast", "validate", "check failures", "harden".

Analyze code for simplification opportunities. Use when user says "simplify", "reduce complexity", "clean up code", "remove duplication", "too complicated", or wants to reduce technical debt.

Deploy ssmd components to GKE prod. Handles git tagging, GitHub Actions image builds, manifest updates, and Flux reconciliation. Use when deploying connector, archiver, parquet-gen, DQ, data-ts, CLI, operator, worker, or other ssmd images after code changes.

Catalog of ssmd DQ checks — what each measures, pass/fail criteria, common failure modes and fixes, fanout rules, and accountability SLOs. Use when investigating DQ failures, understanding check behavior, or adding new checks.

How to run ssmd DQ checks locally and in-cluster, interpret scores, trigger email reports, and verify results. Use when running data quality checks, re-sending DQ emails, or verifying pipeline health after deployments or backfills.

2 hooks across 2 events