Explore skills

QA testing for Streamlit applications — locally or on Hugging Face Spaces. Covers app startup, UI rendering, Streamlit-specific checks (session state, widgets, forms, caching), clinical content accuracy, HF Spaces compatibility, and accessibility. Produces a structured QA report with PASS/FAIL/PARTIAL status.

Analyze the outcome of a product experiment using control and test results, effect size, and statistical evidence. Use this skill when the user has experiment results and needs a clear readout of what happened.

Clinical product direction review from a UK nursing perspective. The CQAI equivalent of /plan-ceo-review — asks the hard clinical questions before any technical planning. Reviews NMC Standards alignment, patient safety classification, health equity impact, and the "Ward Test". Use this INSTEAD of /plan-ceo-review for any nursing or clinical tool.

Define the primary metric, secondary metrics, guardrails, and success criteria for a product experiment. Use this skill when the user has a hypothesis or planned test but has not yet defined how success should be measured.

Clinical safety code review against DCB0129/DCB0160 and NHS Digital standards. This is NOT a general code review — it is a clinical safety audit for tools handling clinical data, calculations, decision support, or patient-facing information. Produces a hazard register, required mitigations, and a release recommendation.

TypeScript and Angular coding best practices. Use when working with TypeScript, Angular, or Node.js files: implementation, testing, refactoring, RxJS Observables, type system, strict mode, generics, and async patterns.

Go coding best practices and patterns. Use when working with Go or Golang files: implementation, testing, refactoring, architectural review, goroutines, channels, interfaces, error handling, memory management, and API development.

Turn a product problem, idea, observation, or business goal into a clear testable experiment hypothesis. Use this skill when the user has an idea or problem but not yet a properly structured hypothesis for an A/B test or product experiment.

Check and strengthen the alignment between team-level goals (OKRs, KPIs) and company strategy. Use this skill when goals have been set but their connection to strategy is unclear, inconsistent, or contested.

Multi-agent parallel code review of staged git changes. Launches two independent reviewer agents (Security/Bugs + Architecture/Quality), runs a code simplification pass, cross-references findings, and produces a consolidated verdict.

Archived source pointer. The canonical GitHub repo design skill now lives in claude-code-skills/development/github-repo-design.

Test accountability policy. All failures belong to the current changeset. Commits must include test results. No failures on main.