Loading...
Loading...
Found 2,054 Skills
Use this skill whenever deciding what features to extract from raw marketplace assets — listing photos, owner-entered listing metadata, sitter wizard responses — to power item-to-item (similar listings), user-to-item (homefeed ranking), or user-to-user (mutual-fit matching) recommenders in a two-sided trust marketplace. Covers asset auditing, first-principles feature decomposition from the decision the user is making, vision-feature extraction (CLIP, room-type classification, amenity detection, aesthetic and quality scoring), listing text and metadata encoding (categoricals, multi-hot amenities, H3 geo-hashing, sentence-transformer description embeddings, structured pet triples), sitter wizard design (information-gain ordering, multiple-choice over free text, genuine skippability, hard constraint versus soft preference), derived-composition patterns for i2i / u2i / u2u (precomputed ANN shelves, multi-modal fusion, two-tower affinity, symmetric mutual-fit scoring, interpretable subscores), feature quality governance (single registry, training-serving parity, coverage and drift alarms, PII scrubbing, schema versioning), and incremental value proof (one feature at a time, ablation A/B, kill reviews, exploration slice, permanent feature-free baseline). Trigger even when the user does not explicitly say "feature engineering" but is asking how to get more signal out of listing photos, listing metadata, or the sitter onboarding wizard, or how to improve i2i / u2i / u2u quality without blindly ingesting a new model.
Use this skill when creating and configuring a PixiJS v8 Application. Covers new Application() + async app.init() options (width, height, background, antialias, resolution, autoDensity, preference, resizeTo, autoStart, sharedTicker, canvas, useBackBuffer, powerPreference, eventFeatures, accessibilityOptions, gcActive, bezierSmoothness, webgl/webgpu/canvasOptions per-renderer overrides), app.stage/renderer/canvas/screen/domContainerRoot access, ResizePlugin, TickerPlugin, CullerPlugin (cullable, cullArea), custom ApplicationPlugin creation via ExtensionType.Application, start/stop lifecycle, and app.destroy() with releaseGlobalResources. Triggers on: Application, app.init, app.stage, app.renderer, app.canvas, app.screen, app.domContainerRoot, ApplicationOptions, ApplicationPlugin, ExtensionType.Application, resizeTo, preference, autoStart, sharedTicker, useBackBuffer, powerPreference, skipExtensionImports, preferWebGLVersion, preserveDrawingBuffer, cullable, CullerPlugin, app.start, app.stop, app.destroy, releaseGlobalResources.
Use when generating videos from images with DashScope Wan 2.7 image-to-video model (wan2.7-i2v). Use when implementing first-frame video generation, first+last frame interpolation, video continuation, or audio-driven video synthesis via the video-synthesis async API.
k6 performance and load testing. Covers writing test scripts in JavaScript/TypeScript, all test types (load/stress/spike/soak/smoke/breakpoint), thresholds, checks, scenarios, executors, extensions, result analysis, k6 Cloud execution, and CI/CD integration. Use when writing k6 tests, debugging test failures, setting up load testing pipelines, choosing executors/scenarios, or interpreting k6 results.
Whatfix platform help — Digital Adoption Platform (DAP), in-app Flows, Smart Tips, Beacons, Task Lists, Self Help widget, Product Analytics (funnels, Sankey charts, cohorts), Mirror sandbox training, NPS/custom surveys, Integration Hub. Use when Whatfix flows aren't triggering, users skip walkthroughs, Self Help widget isn't surfacing right content, product analytics look wrong, Mirror sandbox needs setup, Whatfix surveys have low completion, Integration Hub data isn't syncing, need help with Whatfix API or content tagging, setting up Whatfix for a new enterprise app, or comparing Whatfix to WalkMe or Pendo. Do NOT use for in-app messaging strategy across platforms (use /sales-in-app-messaging) or general customer feedback strategy (use /sales-customer-feedback).
Configurable grid trading bot for Hyperliquid DEX with TypeScript/Node.js primary implementation, supporting perpetuals and spot markets with risk management features.
Programmatic security management in Neo4j — RBAC/ABAC, user lifecycle (CREATE/ALTER/DROP USER), role lifecycle (CREATE/GRANT ROLE/DROP ROLE), privilege grants and denies (GRANT/DENY/REVOKE on graph, database, DBMS), property-level access control, sub-graph access control, SHOW PRIVILEGES inspection, and auth provider config reference (LDAP, OIDC/SSO). Use when an agent needs to manage users, roles, or privileges programmatically via Cypher on the system database. Does NOT handle Cypher query writing — use neo4j-cypher-skill. Does NOT handle cluster ops or backups — use neo4j-cli-tools-skill. Property-level security and ABAC require Enterprise Edition.
Complete Hyperliquid playbook — perpetuals and spot trading, margin/leverage, TWAP, real-time WebSocket data, and historical candles. Use for any Hyperliquid task. Trading triggers: place perp/spot orders (Gtc/Ioc/Alo), market-like fills, take-profit/stop-loss grouping, modify or cancel orders, batch cancels, TWAP orders (place/track fills/terminate), change leverage (cross vs isolated), adjust isolated margin, transfer USDC between spot and perp accounts (usd_class_transfer), get the EVM deposit address to fund Hyperliquid. Data triggers: read account summary (perp margin, positions, liquidation price, unrealized PnL), spot balances, portfolio, open orders, historical orders, single order status, fills (latest or by time window), funding history, rate limits, market metas (perp + spot, szDecimals), perp-only metas, spot-only metas, mid prices for all coins, L2 orderbook per coin, spot token details, allDexsAssetCtxs snapshot (funding/OI/mark prices across assets). Real-time WebSocket: wss://api.hyperliquid.xyz/ws with channels allMids, allDexsAssetCtxs (backend manages a shared subscription — agent can subscribe/unsubscribe and read the cached snapshot), l2Book, trades, candle, orderUpdates, userFills, userFundings. Historical OHLCV candles via direct POST https://api.hyperliquid.xyz/info {type: 'candleSnapshot'} — supports 1m/3m/5m/15m/30m/1h/2h/4h/8h/12h/1d/3d/1w/1M intervals up to 5000 candles. Covers all routes under /agent/trading/* (market/metas|mids|perp-metas|spot-metas|l2-book|token|all-dexs-asset-ctxs, deposit-address, account, account/spot, portfolio, rate-limit, orders, orders/details, orders/history, orders/:oid/status, twap, twap/fills, twap/:id, fills, fills/by-time, funding, leverage, margin, transfer). Triggers on mentions of Hyperliquid, "HL", perp, perpetual, funding rate, TWAP, isolated margin, cross margin, "deposit to Hyperliquid", "HIP-3", "HLP", or "HL vault". Prerequisite: openfin-setup.
Evaluates ML models for performance, fairness, and reliability. Use for metric selection, cross-validation strategies, overfitting/underfitting diagnosis, hyperparameter tuning, LLM evaluation, A/B testing, and production monitoring for model drift.
Systematic ACMG/AMP variant classification using ToolUniverse tools. Given a genetic variant (HGVS, rsID, or gene+change), applies all 28 ACMG criteria (PVS1, PS1-4, PM1-6, PP1-5, BA1, BS1-4, BP1-7) through automated database queries and computational predictions. Produces a final 5-tier classification (Pathogenic / Likely Pathogenic / VUS / Likely Benign / Benign) with evidence summary. Use when asked to classify a variant, interpret a VUS, apply ACMG criteria, assess pathogenicity, or determine clinical significance of a germline variant.
Guides structured security log analysis across authentication, network, endpoint, and cloud audit log sources. Auto-invoked when the user shares log data, asks about suspicious events, needs help interpreting Windows Event IDs or Linux auth logs, or is establishing baselines for anomaly detection. Produces log source taxonomy, anomaly identification, baseline recommendations, and correlation findings mapped to MITRE ATT&CK v16 techniques.
SEO & content marketing command suite with keyword research, content audits, SERP analysis, technical SEO workflows, and structured progress tracking