tiny-cats-model

Enhance session checkpoints with git context and diff summaries. Use after completing significant work to enrich checkpoint.md files with repository state, recent commits, and code change summaries. Triggers include "enhance checkpoint", "update checkpoint with git", "add git context to checkpoint", or when finishing a multi-file change session.

Use for model training, hyperparameter tuning, and Modal GPU training.

Use when invoking training, evaluation, and dataset preparation via CLI. Provides all standard commands for this project.

Multi-perspective code analysis using three AI personas (RYAN, FLASH, SOCRATES) for comprehensive decision-making. Use when complex code decisions need analysis from multiple viewpoints, or when avoiding single-perspective blind spots is critical.

Use for authentication management, token validation, and credential troubleshooting.

Use for secrets management, credentials handling, and security best practices.

Guide for creating effective skills. This skill should be used when users want to create a new skill (or update an existing skill) that extends Claude's capabilities with specialized knowledge, workflows, or tool integrations.

Token-aware wrappers around build, test, lint, and format commands to prevent context window overflow. Centralizes command execution through scripts that truncate noisy logs while preserving actionable error information.

Create, update, and maintain AGENTS.md and agents-docs/ for best practices. Handles documentation structure, skill creation, and reference management.

Monitor GitHub Actions CI runs, identify failures, and coordinate specialist agent fixes using GOAP/ADR workflow

Use for branch management, commits, PRs, and git operations via gh CLI.

Research topics using web search and content fetching to find accurate, current information. Use when you need modern information, official documentation, best practices, technical solutions, or comparisons beyond your training data.

Use when verifying CI, tests, and training integration. Runs the full test and lint suite and reports results.

Use for GOAP (Goal-Oriented Action Planning) and ADR (Architecture Decision Records) management. Handles project planning, issue tracking, and architectural decisions.

Use when interacting with GitHub Actions CI/CD automation. Covers workflow status, triggering, debugging, and configuration.

Use for linting, formatting, and type checking with ruff, black, flake8, mypy.