AI Agent Skills

Med peer benchmarking: select actual biotech/pharma peers via the med universe (drug/indication overlap where possible) and compare med-relevant metrics — pipeline depth…

R performance best practices including profiling, benchmarking, vctrs, and optimization strategies. Use when optimizing R code.

Use when optimizing Go code, investigating slow performance, or writing performance-critical sections. Also use when a user mentions slow Go code, string concatenation i…

CRE Due Diligence analysis suite — 7 specialist skills for multifamily property analysis including rent roll validation, expense benchmarking, market study, physical ins…

Reviews an existing conjoint study for threats to inference and returns prioritized findings across five areas — design integrity (attributes, profile restrictions, task…

Query the CZ CELLxGENE Census (61M+ cells) programmatically via cellxgene-census and TileDB-SOMA, slicing expression by tissue, disease, or cell type and returning AnnDa…

Quickly creates new Claude Code skills or translates ChatGPT projects into Claude Code skills. Handles skill scaffolding, frontmatter, directory structure, and ChatGPT-t…

Use when scoping a competitive landscape — identifying, categorising, and score-filtering a competitor set before any benchmarking begins. Decides who counts as

Use after benchmark-methodology has produced scored competitor profile cards. Assembles findings into a decision-grade report: landscape map, competitor profile

Helps the user design a lab workflow by asking questions, working through steps together, and writing the result to a plan.md file. Use when planning a new lab run, benc…

Use when exporting or deploying Ultralytics YOLO models in Platform or code — the Platform Export tab and yolo export/model.export() for ONNX, TensorRT, CoreML, Core AI,…

Always invoke for training, validating, tuning, benchmarking, or claiming readiness of a predictive model. Covers leakage audits, spatial and grouped splits, me