Explore skills

Create scalable, containerized bioinformatics pipelines with Nextflow DSL2 supporting Docker, Singularity, and cloud execution. Use when building portable pipelines with container support, running workflows on cloud platforms (AWS, Google Cloud), or leveraging nf-core community pipelines.

Use when working with incident response incident response

Reproduces the full prefill sensitivity analysis pipeline for reward hacking indicators. Use when evaluating how susceptible model checkpoints are to exploit-eliciting prefills, computing token-based trajectories, or comparing logprob vs token-count as predictors of exploitability.

Unified Azure OpenAI model deployment skill with intelligent intent-based routing. It handles quick preset deployments, fully customized deployments (version/SKU/capacity/RAI policy), and capacity discovery across regions and projects.

Advanced skill for SnowTower infrastructure administrators. Use for SnowDDL operations, user provisioning, role management, CI/CD deployments, troubleshooting, and Snowflake administration. Triggers on mentions of snowddl, deploy, user creation, role grants, infrastructure changes, or admin operations.

Automate repetitive development workflows: release notes generation, changelog updates, dependency management, environment setup, data migrations, and cross-system synchronization. Use when the user says 'automate this', 'I keep doing this manually', 'generate release notes', 'update the changelog', 'sync these systems', 'batch process', 'automate onboarding', 'script this workflow', or 'create a

This skill should be used at the start of any computationally intensive scientific task to detect and report available system resources (CPU cores, GPUs, memory, disk space). It creates a JSON file with resource information and strategic recommendations that inform computational approach decisions such as whether to use parallel processing (joblib, multiprocessing), out-of-core computing (Dask, Za

Use when user has a stake or perspective in a decision and wants to participate in discernment rather than receive advice - facilitates user alongside agent voices with participatory discipline teaching

Code quality standards, linting rules, and CI/CD principles.

Species abundance estimation using Bracken with Kraken2 output. Redistributes reads from higher taxonomic levels to species for more accurate estimates. Use when accurate species-level abundances are needed from Kraken2 classification output.

Guides users on creating mock implementations for testing with traits, providing test doubles, and avoiding tight coupling to test infrastructure. Activates when users need to test code with external dependencies.

Use when facing 2+ independent tasks that can be worked on without shared state or sequential dependencies