olore-langfuse-latest
Local langfuse documentation reference (latest). Langfuse LLM observability documentation. Use for LLM tracing, evaluation, prompt management, datasets, experiments, OpenTelemetry integration, and SDK setup.
research-methodology
You must use this when matching research questions to appropriate designs, sampling strategies, or validity controls.
ab-test-stats
Calculate A/B test statistical significance. Use when: determining if test results are significant; calculating required sample size; estimating test duration; analyzing conversion experiments; making data-driven decisions
council-outcome
Record the outcome of a past Agent Council decision. Was the council right? Builds calibration data over time to learn which models are best at what.
qdrant-monitoring
Guides Qdrant monitoring and observability setup. Use when someone asks 'how to monitor Qdrant', 'what metrics to track', 'is Qdrant healthy', 'optimizer stuck', 'why is memory growing', 'requests are slow', or needs to set up Prometheus, Grafana, or health checks. Also use when debugging production issues that require metric analysis.
check-abstract-factory
Audits Abstract Factory pattern implementations. Checks family consistency, product hierarchy, factory method completeness, and cross-family compatibility.
autoresearch
Karpathy-style keep/revert experiment loop for Atris experiment packs. Use when improving prompts, tools, workers, or bounded repo targets.
mlops-engineer
Build comprehensive ML pipelines, experiment tracking, and model registries with MLflow, Kubeflow, and modern MLOps tools.
experiment-management
Use this skill when setting up ML experiment infrastructure. Covers wandb/tensorboard integration, hydra/omegaconf configuration management, experiment reproducibility, and results visualization.
backseat-driver-testing
Testing strategies for Calva Backseat Driver MCP tools. Use when: Testing Backseat Driver, validating tool updates, testing structural editing workflows, verifying REPL evaluation with who-tracking, testing output log filtering, smoke testing after dep bumps, or debugging tool behavior. Covers all Backseat Driver tool categories: structural editing, REPL eval, symbol info, bracket balancing, and output log.
lab-automation
Patterns for laboratory automation including liquid handling robotics, LIMS integration, protocol development, quality control, and high-throughput workflows. Covers both open-source (Opentrons) and commercial platforms. Use when ", " mentioned.
data-reproducibility
Infrastructure and practices for reproducible computational research. Covers environment management, data versioning, code documentation, and sharing protocols that enable others to reproduce your results. Use when ", " mentioned.
audit-readiness
Prepare for internal and external audits with SOX 404 control testing, sample selection, workpaper documentation, and deficiency evaluation. Use for SOX compliance, control testing methodology, audit sample selection, audit workpaper preparation, control deficiency classification, material weakness evaluation, ITGC testing, remediation tracking, or audit evidence standards.
experiment-provenance
Capture experiment provenance with reproducible run metadata, artifact pointers, and decision logs for scientific claims.
openspec-verify-change
Verify implementation matches change artifacts. Use when the user wants to validate that implementation is complete, correct, and coherent before archiving.
openspec-archive-change
Archive a completed change in the experimental workflow. Use when the user wants to finalize and archive a change after implementation is complete.