Loading...
Loading...
Found 877 Skills
Guides rollout configuration for experiments: variant splits, overall rollout percentage, and the critical disambiguation when a user mentions a specific percentage. Covers both initial setup and mid-experiment changes. TRIGGER when: user mentions a rollout percentage, asks about variant splits, wants to change distribution on a running experiment, or asks 'who sees what variant?' DO NOT TRIGGER when: user is asking about metrics, analytics, or experiment results.
Convert an Omni Analytics topic into a Databricks Metric View definition in Unity Catalog. Use this skill whenever someone wants to export Omni metrics to Databricks, create a Metric View from an Omni topic, harden BI metrics into Unity Catalog, or bridge Omni's semantic layer with Databricks AI/BI dashboards and Genie spaces.
Use when improving performance, latency, throughput, memory usage, or general efficiency. Start by defining target metrics, measuring comprehensively, attributing bottlenecks, validating with static analysis, and prioritizing macro-optimizations before micro-optimizations.
On-chain data analysis framework — covers active addresses, whale behaviour, TVL (total value locked), DEX liquidity, and on-chain valuation metrics: MVRV (market cap / realised value), NVT (network value / transaction volume), SOPR. Longbridge provides spot crypto quotes (.HAS); raw on-chain data requires external sources (Glassnode / Dune Analytics). Triggers: "链上数据", "链上分析", "MVRV", "NVT", "活跃地址", "鲸鱼地址", "TVL", "SOPR", "链上指标", "链上估值", "鏈上數據", "鏈上分析", "活躍地址", "鯨魚地址", "鏈上指標", "鏈上估值", "on-chain data", "on-chain analysis", "MVRV ratio", "NVT ratio", "active addresses", "whale activity", "TVL", "SOPR", "on-chain valuation", "DeFi TVL", "crypto on-chain".
Retrieve and analyze AlphaFold predicted structures for a protein. Use when the user provides a specific UniProt Accession ID and wants structural confidence metrics (pLDDT), domain boundary analysis, or disorder assessment. Do not use if the user only has a protein name, gene name, or amino acid sequence — ask for a UniProt ID first.
Guides quantitative research for markets and finance—research question framing, data sourcing and quality checks, descriptive and inferential statistics, time series and panel methods (high level), factor and signal research, backtest design and pitfalls (lookahead, survivorship), risk metrics (volatility, drawdown, Sharpe limitations), regime and stress analysis, and reproducible notebooks or reports with explicit limitations and uncertainty communication. Use when the user mentions "quantitative research", "quant researcher", "factor research", "signal backtest", "time series analysis", "panel regression", "alpha research", "Sharpe ratio analysis", "survivorship bias", "lookahead bias", "econometric analysis", or "risk factor model". Not for production ML pipelines (data-scientist, ml-research-engineer), equity narrative reports (equity-research skills), SOX accounting (financial-statements), legal investment advice, or trading execution systems (senior-software-engineer).
Guides failure-prevention culture and operational excellence for mission-critical engineering— zero-defect aspiration vs error budgets; HRO principles; defense-in-depth; fail-safe/fail-closed; verification gates and independent checks; redundancy and graceful degradation; pre-mortems and FMEA; stop-the-line; defect escape, near-miss, and repeat-incident metrics; leadership against normalization of deviance—not blame culture. Use for failure-prevention programs, HRO practices, verification gates, fail-safe design, pre-mortem/FMEA, stop-the-line, near-miss reporting, or defect-escape metrics—not SRE error budgets only (site-reliability-engineer), incident command only (incident-management-engineer), backup/restore only (cyber-resilience-engineer), CI lint only (build-validator), agile coaching, HR discipline, or classified ATO without ops-excellence lens (classified-cyber-security-senior-manager).
Pull usage metrics, check subscription status, view invoices, and manage credits using the Cargo CLI. Use when the user wants billing analytics, usage reports, credit usage, cost analysis, subscription details, or invoice history for their Cargo workspace.
Create and manage Oodle log-based metric rules — extract metrics from log streams using filter expressions and groupBy labels.
Use this skill when reading video-analytics metrics, incidents, alerts, and sensor data via the VA-MCP server (port 9901). Not for live VLM or incident-range narrative reports.
Deploy, operate, and integrate the VSS 3.2 GA RT-Embed Video Embedding microservice. Covers Docker Compose bring-up, GPU and storage prerequisites, the `/v1` REST API (file uploads, text and video embeddings, live RTSP streams, health and metrics), Redis/Kafka/OTel integration, common failure modes, and teardown.
Use when a user needs a staged working-backwards interview to clarify the customer problem, audience, value proposition, business case, MVP, requirements, risks, and success metrics before any PRFAQ is written. Supports `--quick-flow` for fast assumption-driven execution and `--full-flow` for question-driven verified execution. Explicit full or end-to-end spec refinement requests continue through the existing 18-stage refinement cascade.