Loading...
Loading...
Found 3,019 Skills
Guides hands-on actuarial analyst work for insurance, reinsurance, and pension—reserving and loss development (IBNR, triangles, chain-ladder diagnostics), pricing and rate indication support (experience, trend, credibility, basic GLM at spec level), data validation and model I/O review, reporting packs and workpapers, assumption application under actuary direction, and statutory tie-outs at analyst depth. Use when the user mentions actuarial analyst, loss development, IBNR, reserve analysis, rate indication, pricing support, actuarial workpaper, triangle analysis, credibility, experience study, actuarial reporting, or reserve roll-forward—not actuary sign-off (actuary), consulting engagements (actuarial-consulting), assumption governance (assumption-setting), ALM strategy (asset-liability-management), P&C legal depth (property-casualty-insurance), charts only (data-visualization), or ETL-only pipelines (data-scrubbing).
Guides advanced short-term actuarial mathematics aligned with SOA ASTAM and P&C/health-adjacent modeling—severity and frequency distributions, aggregate and compound loss models, Bühlmann and Bühlmann-Straub credibility, ratemaking and experience rating, short-term reserving at the math level, MLE and goodness-of-fit, and risk measures (VaR, TVaR). Tool-agnostic and concept-first. Use when the user mentions advanced short-term actuarial mathematics, ASTAM, severity model, frequency model, aggregate loss, compound distribution, Bühlmann credibility, experience rating, ratemaking, pure premium, negative binomial frequency, tail factor, TVaR, or short-term actuarial models—not life contingencies (life-health-insurance), Excel workpapers only (actuarial-analyst), appointed actuary sign-off (actuary, appointed-chief-actuary), assumption governance (assumption-setting), P&C legal/operations depth (property-casualty-insurance), or general ML (data-scientist, quantitative-researcher).
This skill should be used when the user asks to forecast aggregate sentiment and opinion dynamics over time—sentiment indices from text streams; temporal rollups; leading/lagging KPI links; time-series and sequence models (ARIMA, Prophet, state-space, ML); nowcasting; spikes, bots, and bias; walk-forward backtests; intervals and scenarios; volume/velocity/topic features; BI or brand dashboards. Triggers: sentiment forecasting, forecast sentiment, sentiment index, opinion trend forecast, social sentiment time series, brand sentiment trajectory, nowcast sentiment, sentiment leading indicator, aggregate polarity forecast, sentiment backtest, walk-forward sentiment, sentiment spike prediction. Not for per-text labeling (sentiment-analysis-engineer), demand forecasting without sentiment (predictive-logistics-developer, data-scientist), trade advice (methodology only), marketing copy (content-creator), macro without text sentiment (financial-analyst partial).
Use this skill whenever the user wants to integrate Loops from application code, backend services, webhook handlers, or server-side automation. This includes the Loops HTTP API and official SDKs for server-side contact, contact-property, mailing-list, event, API-key-validation, and transactional-email workflows. Trigger on phrases like "Loops API", "Loops SDK", "send a Loops event from my app", "add a contact to Loops in a webhook", "send a transactional email from backend code", or any time the user wants to integrate Loops into their app, backend, webhook, or automation. Do not trigger for CLI or shell-only requests.
Calculate agreement between human ground truth and machine labels for a text LLM judge metric, then analyze transcripts and reviewer notes to propose an improved metric prompt. One metric at a time.
Autonomously set up an OpenClaw bot on a fresh Yandex Cloud VM in Kazakhstan (kz1-a, Karaganda). Asks the user for exactly two things — a Telegram bot token and one of three LLM access options (Anthropic API key, OpenRouter API key, or OpenAI Codex OAuth via ChatGPT Plus/Pro subscription) — then handles VM creation, hardening, OpenClaw install, CEO AI OS workspace seeding, Telegram pairing, chat_id auto-detection, and bot-reply verification on its own. The only other actions the user performs are pressing /start in Telegram once and (if Codex) confirming a device code on auth.openai.com. Use when the user says install OpenClaw to Yandex Cloud, deploy OpenClaw to YC Kazakhstan, set up my CEO bot in YC KZ, I am at OpenClaw workshop and need my own bot, create a Yandex Cloud VM for OpenClaw, or any close paraphrase. Targets a ~15-minute end-to-end run for non-DevOps users (founders, CEOs, marketing leads). Supports two modes of accessing Yandex Cloud — Plan A (the user's own YC Kazakhstan account via OAuth) and Plan B (a workshop-key bundle provided by the workshop organizer, for participants without their own YC account). The mode is auto-detected from the inputs. For local-machine OpenClaw install, use openclaw/install.sh in this repo instead. Companion skill openclaw-guide is required; prepare-yc-workshop is the matching organizer-side skill that produces the bundles consumed in Plan B; openclaw-user-onboarding is auto-invoked after Step 5 to collect the five basic facts about the user (identity, focus, style, tools, anti-patterns) and write them into USER.md so the bot is useful from message one.
Expert cuTile programming assistant. Write high-performance GPU kernels using cuTile's tile-based programming model with proper validation and optimization. Supports deep agent orchestration for complex multi-kernel tasks.
Evaluates accuracy of quantized or unquantized LLMs using NeMo Evaluator Launcher (NEL). Triggers on "evaluate model", "benchmark accuracy", "run MMLU", "evaluate quantized model", "accuracy drop", "run nel". Handles deployment, config generation, and evaluation execution. Not for quantizing models (use ptq) or deploying/serving models (use deployment).
After solving a non-trivial problem, detect generalizable learnings and propose skill updates so future interactions benefit automatically. Always active — applies to every interaction.
Turns a codebase into EventCatalog documentation through an evidence-based interview. Scans the code first, proposes an architectural model (domains, services, messages, channels), grills the user on the structural decisions, produces a reviewable plan file, then hands off to catalog-documentation-creator. Use when user says "document my codebase in EventCatalog", "turn this repo into a catalog", "model my code as a catalog", "grill me on my architecture", "update my catalog from the code", "reconcile my catalog with my code", or "I don't know where to start documenting this codebase". Works for brand-new catalogs AND for updating existing catalogs that have drifted from the code.
Airbnb-DLS-aligned design system engineering for Expo / React Native apps targeting both web and native iOS, built on Unistyles v3, Reanimated, Skia, and FlashList. Use whenever building, reviewing, or refactoring shared UI — design tokens, theming, variant-driven component APIs, typography, spacing, cross-platform web/iOS parity, native-feel performance, or complex surfaces like calendars and drawing canvases (examples use a clinic app). Covers token architecture, theming, component API contracts (variants over style props), web/iOS parity (Unistyles `_web` hover/focus/cursor, Platform splits, one shared theme), the Unistyles styling engine, and governance. Trigger even when the user does not say "design system" but is creating or changing reusable React Native components, tokens, theme code, or making a component behave natively on both web and iOS. Teaches how to BUILD the design system; pair with expo-react-native-coder for features and expo-ios-hig for iOS native-feel decisions.
Run a Bayesian A/B test on conversion data using PyMC. Use when the user wants to compare two variants (landing pages, emails, pricing, UI changes) and decide which to ship using posterior probabilities and expected loss instead of p-values. Covers Beta-Binomial model, ROPE, expected loss, sample-size guidance, and ArviZ diagnostics.