Explorar skills

Use when first setting up lark-cli, running auth login, switching user/bot identity (--as), handling permission denied or scope errors, needing to update lark-cli, or seeing _notice in JSON output.

Expert guidance for Fully Sharded Data Parallel training with PyTorch FSDP - parameter sharding, mixed precision, CPU offloading, FSDP2

Audit public sector and government resource allocation systems for budget optimization algorithms (zero-based, incremental, performance-based), service demand forecasting (ARIMA, Prophet, regression), equity-based distribution scoring (CDC SVI, environmental justice indices, disparate impact analysis), GIS geographic coverage and service gap analysis, workload-based staffing models, grant drawdown

Write state-restoration documents for passing tasks between agents or engineers.

Guidance for building and running a B2B conversion rate optimization program — covering research frameworks, testing strategy, CTA design, metrics, reporting, and organizational setup. Trigger when a user asks about improving conversion rates, CRO program structure, landing page optimization, email CTAs, or testing methodology.

Audit credit risk modeling software for scoring algorithm accuracy, regulatory compliance (ECOA, FCRA, SR 11-7), bias and disparate impact testing, model governance lifecycle, and explainability. Covers logistic regression, GBM, neural net evaluation, protected class proxy detection, adverse action notice generation, SHAP/LIME explainability, champion-challenger frameworks, and PSI drift monitorin

Use when optimizing agent runtime loops, card packs, MCP session lifecycle, tool-call count, or multi-agent orchestration patterns.

Analyze franchise expansion plans, model new market entry, score site selection candidates, map territory density, assess cannibalization risk, and build multi-year growth scenarios. Covers market feasibility scoring, Huff gravity models, trade area overlap analysis, white space identification, and unit-level investment returns for franchise development teams.

Analyze insurance underwriting systems for risk assessment accuracy, pricing adequacy, and portfolio exposure management. Evaluates predictive models (GLM, GBM), rating algorithms, loss ratio performance by line of business, guideline automation engines, regulatory compliance (NAIC, SERFF filings), and model governance following SR 11-7 standards across personal, commercial, and specialty lines.

Connect to a running NeuroSkill instance and incorporate the user's real-time cognitive and emotional state (focus, relaxation, mood, cognitive load, drowsiness, heart rate, HRV, sleep staging, and 40+ derived EXG scores) into responses. Requires a BCI wearable (Muse 2/S or OpenBCI) and the NeuroSkill desktop app running locally.

Polishes UI primitives one at a time using 2026 research-backed patterns — adds loading/icon states to buttons, replaces inline skeletons with primitives, adds secondary actions to errors, ensures 48px touch targets and visible focus indicators, applies a standard motion token ladder. Use when: 'make the UI feel more polished', 'add attention to detail', 'reduce component duplication', 'tighten th

Use when the user needs ideas or a name — brainstorming, naming, developing an idea further, hybridizing ideas, stress-testing candidates, reframing a problem, or picking a final direction. Ideas persist in a per-topic logbook across sessions.