Data & AI

GitFlow automation and PR policy enforcement for MoAI-ADK workflows.

Planning and architecture decision domain expert.Knows about:- Creating ADRs (Architecture Decision Records)- Creating technical specifications- Listing and discovering planning artifacts- Transforming plans into executable VTM tasks- Integrating with research tools (thinking-partner)Use when:- User wants to document an architectural decision- User needs to create a technical specification- User wants to explore or list existing ADRs/specs- User is ready to convert planning docs into tasks- User needs research before making a decision

Parse and structure information from screenshots, meeting notes, or text, then save to Second Brain Supabase database. Extracts contacts, tasks, and ideas automatically. Use when user wants to save information for later.

Container operations - build, deploy, compose, logs, debugging

Database migration workflow helper. Use when creating database migrations, modifying SQLAlchemy models, or managing Alembic migrations. Automatically handles model changes, migration creation, and database upgrades.

Configure, manage, update and review Claude Code permissions, sandboxing, and tool access. Use when user wants to set up permissions, configure sandboxing, update allowed tools, manage settings.json permissions, or review permissions in skills or commands or agents or settings.json. When user writes a new skill, command, agent, or updates settings.json, they should use this skill to manage permissions.

Define and structure database models with proper naming conventions, data integrity constraints, and relationship definitions. Use this skill when creating or modifying database model files, defining table schemas, setting up model relationships (one-to-many, many-to-many, one-to-one), working with ORM model files (schema.prisma, models/*, app/models/*, entities/*), implementing data validation at the model level, adding timestamps and audit fields, defining foreign keys and indexes, choosing appropriate data types, configuring cascade behaviors, or balancing database normalization with query performance. Apply this skill when designing database schemas, creating new models, refactoring existing model structures, or reviewing data integrity and relationship configurations.

Write comprehensive test coverage across unit, integration, regression, end-to-end, and manual tests. Watch for deprecation warnings in test output and address them immediately. Use when writing tests, implementing features, or before creating pull requests.

Use when planning software development tasks, before writing code or implementation plans - refines rough technical ideas into fully-formed designs through collaborative questioning, alternative exploration, and incremental validation. For software architecture, components, data flow, and technical design decisions. Don't use during clear 'mechanical' coding processes

Gather examples for the acceptance test; use when we are about to start development of a new feature

Persist task state across sessions using .claude/ files. Resume work with 'continue'. Never use TodoWrite - use tasks.md, requirements.md, session.md instead.

Reference and maintain documentation of the project's technical stack including frameworks, languages, databases, testing tools, and third-party services. Use this skill when choosing technologies for implementation, adding new dependencies or libraries, setting up project infrastructure, configuring build tools and package managers, integrating third-party services (authentication, email, monitoring), selecting appropriate frameworks for features, ensuring consistency with existing technology choices, documenting technology decisions, reviewing technology compatibility, or onboarding team members to the tech stack. Apply this skill when making technology decisions, adding new tools or services, documenting the stack, or ensuring new code aligns with the project's established technical architecture.

Data engineering, machine learning, AI, and MLOps. From data pipelines to production ML systems. ML algorithms, deep learning, and AI.

Execute tests following TDD cycle: RED (verify test fails) → GREEN (implement to pass) → REFACTOR.Interprets tests.json and performs steps using available tools (browser MCP, API, CLI, etc.).WHEN TO USE:- Starting implementation of a ticket with TDD: yes- After writing test spec (3-spec.md) and tests.json- When user says "run tests", "test this", "TDD cycle"- After fixing a failing testREQUIRES:- Ticket with 3-spec.md- tests.json in .pmc/docs/tests/tickets/T0000N/

Validation rules, schema checks, duplicate detection, and coverage analysis for golden dataset integrity

Workflow for processing large Things3 inboxes (100+ items) using LLM-driven confidence matching and intelligent automation. Integrates with personal taxonomy and MCP tools for efficient cleanup with self-improving pattern learning.

GPU-aware PPO training configuration for A100/H100. Trigger when training is slow or GPU utilization is low.

Use when implementing new features. Enforces TDD workflow - write tests FIRST, then implementation. Ensures AAA pattern, proper coverage, and quality test design.

Complete product launch workflow coordinating 15+ specialist agents across research, development, marketing, sales, and operations. Uses sequential and parallel orchestration for 10-week launch timeline.

Automatically retrieve relevant information from the organization's CustomGPT.ai knowledge base when answering questions about documented topics, policies, procedures, or technical specifications.