athola

Provisions the oracle ML inference daemon with onnxruntime via uv. Use when setting up local ONNX model inference for skill quality evaluation.

Applies microkernel architecture with minimal core and plugin extensibility. Use when building platforms where third parties extend core functionality.

Audits the DSA problem bank for coverage gaps and proposes new YAML entries. Use when refreshing the problem bank during update-plugins runs.

Provide reusable patterns for validation, error handling, scaffolding. Use for skill consistency.

Updates documentation after code changes with quality gates, slop detection, and accuracy checks. Use when code changes require corresponding doc updates.

Establishes CPU/GPU baselines before resource-intensive operations. Use before builds, training runs, or any task that pins cores or GPUs for over a minute.

Applies Functional Core, Imperative Shell to isolate logic from side effects. Use when business logic is entangled with I/O or unit tests are slow and brittle.

Generates phased, dependency-ordered implementation tasks from specifications. Use after spec is complete and before starting implementation.

Applies stewardship virtues (Care, Curiosity, Humility, Diligence) to plugin work. Use when authoring plugins or reviewing code quality.

Routes multi-tool workflows through MCP servers for large datasets and pipelines. Use when Bash tool overhead is limiting throughput on data-heavy tasks.

Processes external resources into stored knowledge with quality scoring and routing. Use when ingesting articles, papers, or docs into a memory palace.

Convenes a multi-LLM expert panel to pressure-test hard-to-reverse decisions. Use when reversibility score is low and adversarial review is warranted.