Explorar skills

Create new skills, modify and improve existing skills, and measure skill performance. Use when users want to create a skill from scratch, edit, or optimize an existing skill, run evals to test a skill, benchmark skill performance with variance analysis, or optimize a skill's description for better triggering accuracy.

Inspect changed dbt assets, estimate blast radius, identify missing tests, and recommend the narrowest safe validation plan.

Audit pharmaceutical yield prediction systems and process analytical technology -- evaluate critical process parameter (CPP) to critical quality attribute (CQA) relationships, design space characterization per ICH Q8(R2) Quality by Design, PAT sensor readiness (NIR, Raman, FBRM) for real-time release testing, scale-up modeling from lab to pilot to commercial with dimensional analysis, and raw mate

Audit the methodology used to split data into train, validation, and test sets.

Activates SyntheticDataGen — a specialist in generating high-quality synthetic datasets for ML training, testing, and privacy-safe data sharing. Use when you need tabular data generation, time-series synthesis, privacy-preserving data (differential privacy), GAN/VAE-based image data, realistic test fixtures, or bias-controlled training sets.

Use when implementing any feature or bugfix, before writing implementation code

Goal-driven smoke test for the feature just implemented. Drives a browser (UI) or hits the running service (backend) — both, when full-stack. Tests every behaviour acceptance criteria define plus exploratory edges, catches console errors / network failures / a11y issues / contract violations / auth leaks / missing observability, fixes every gap or bug it finds, then re-runs until clean. Captures t

Comprehensive regression model diagnostics and assumption checking. Use when validating regression models, checking assumptions (linearity, homoskedasticity, normality, independence), detecting outliers/influence, testing multicollinearity, or when user mentions residuals, heteroskedasticity, VIF, Cook's distance, or diagnostic plots.

Methodically walks a running app — every public route, every interactive control, every state (empty/loading/error/auth/un-auth) — to find real bugs, then root-causes, fixes, adds a regression test, and verifies each one before moving to the next. Use when: 'find bugs in the app', 'sweep for regressions', 'methodically hunt and fix bugs', 'audit user flows', 'find broken buttons / forms / links'.

Analyze nonprofit fundraising software for RFM donor segmentation, campaign performance modeling with A/B testing, recurring giving retention and failed payment recovery, major gift prospect scoring using capacity-affinity-propensity frameworks, event ROI calculation, multi-touch channel attribution, gift officer portfolio management, and donor data quality hygiene.

Complete testing pipeline — full test suite, test everything, automated and manual tests.

Run a complete mobile app pre-launch verification — chains performance audit, QA testing, OWASP mobile security review, App Store and Play Store compliance checks, and store listing optimization into a single launch-ready report. Use before submitting to TestFlight, App Store, or Google Play.