Loading...
Loading...
Found 802 Skills
Identify and prevent sales practice violations under FINRA and SEC rules governing broker-dealer conduct. Use when the user asks about churning or excessive trading metrics, mutual fund breakpoint discounts, selling away or private securities transactions, outside business activities, unauthorized trading, supervisory procedure design, senior investor protections, trusted contact persons, variable annuity suitability, or options account approval. Also trigger when users mention 'turnover ratio is high', 'rep did trades without authorization', 'breakpoint abuse', 'trusted contact for elderly client', 'selling away from the firm', 'supervision failure', '1035 exchange review', 'marking the close', or ask whether a broker's conduct violates FINRA rules.
Use when designing or auditing computer science experiments, evaluation plans, baselines, metrics, ablations, datasets, statistical tests, benchmarks, validity threats, or reproducibility claims.
Interactively set up a first Coval AI evaluation. Guides users through installing the CLI, connecting an agent, creating personas, building test cases, selecting metrics, and launching their first eval run. Use when user says "onboard", "get started", "set up evaluation", "first eval", "new to coval", or wants help creating their first test run.
Code instrumentation for timing workloads. Two scenarios: (1) Training loop — inject manual timing to report per-iteration latency, throughput (samples/sec), and data load time. (2) Standalone kernel/op — write CUDA event timing code with warmup, per-iteration statistics, and anti-pattern avoidance. Also covers NVTX annotation for labeling profiler timelines. NOT for: running or analyzing profiler tools (nsys, ncu, Nsight Systems, Nsight Compute), writing kernels (Triton, CuTe, CUDA), applying optimizations (CUDA Graphs, gradient checkpointing, fusion), or interpreting roofline/SOL% metrics. Triggers: "measure throughput", "benchmark this function", "time my training loop", "samples per second", "NVTX annotate", "instrument my dataloader", "data load time", "kernel timing", "how do I time".
Head-to-head comparison of coding agents (Claude Code, Aider, Codex, etc.) on custom tasks with pass rate, cost, time, and consistency metrics
Create and manage Oodle log-based metric rules — extract metrics from log streams using filter expressions and groupBy labels.
This skill should be used when the user asks to "set up oodle integration", "onboard to oodle", "integrate kubernetes with oodle", "connect AWS to oodle", "install oodle collector", or mentions setting up observability with Oodle. Discovers the environment, recommends matching integrations from available setup specs, and executes step-by-step installation. Not for querying existing metrics, logs, or traces (use /oodle-metrics-query, /oodle-logs, /oodle-traces instead).
Build clinical/healthcare deep-learning pipelines with PyHealth — loading EHR/signal/imaging datasets (MIMIC-III/IV, eICU, OMOP, SleepEDF, ChestXray14, EHRShot), defining tasks (mortality, readmission, length-of-stay, drug recommendation, sleep staging, ICD coding, EEG events), instantiating models (Transformer, RETAIN, GAMENet, SafeDrug, MICRON, StageNet, AdaCare, CNN/RNN/MLP), training with the PyHealth Trainer, computing clinical metrics, and using medical code utilities (ICD/ATC/NDC/RxNorm lookup and cross-mapping). Use this skill whenever the user mentions PyHealth, MIMIC, eICU, OMOP, EHR modeling, clinical prediction, drug recommendation, sleep staging, medical code mapping, ICD/ATC codes, or any healthcare ML pipeline that fits the dataset → task → model → trainer → metrics pattern, even if "PyHealth" isn't named explicitly.
Use this skill when the user wants to analyze social media performance, content metrics, engagement quality, channel ROI, post patterns, audience response, reporting, or what to post more or less of. Trigger phrases include "social media analysis," "analyze my social posts," "social ROI," "content performance," "engagement analysis," "post metrics," "social media report," and "what worked on social."
Pull Bigdata.com (RavenPack) financial and news data through the official `bigdata-client` SDK and its public `/v1/*` REST endpoints when the Bigdata MCP server returns only pre-synthesized tearsheets but you need the machine-readable substrate underneath. MCP search returns prose chunks (text + relevance only — no per-chunk sentiment, no entity spans); its tearsheets give only aggregate values, not computable time series or per-field JSON. This skill bundles a verified, cost-guarded toolkit over the official REST API: annotated chunk search, entity/ISIN resolution, analyst estimates, calendar/surprise/ ratings/targets, financial statements, TTM metrics & ratios, prices, dividends, revenue segments, a daily entity-sentiment series, co-mention graph, screener, and batch search. Use it whenever the user mentions Bigdata.com, RavenPack, a `bd_v2_` key, the bigdata MCP, rp_entity_id, chunk/query_unit cost, or wants structured financials, fundamentals, prices, sentiment, or annotated news.
Performs deep Root Cause Analysis (RCA) on NVIDIA TAO Visual ChangeNet classification experiments with image-evidence-driven investigation. Use when analyzing ChangeNet model failures, investigating poor recall / FAR / PASS-NO_PASS metrics, auditing visual inspection pipeline quality, or running an RCA report for an AOI defect-detection model. Trigger phrases include "RCA on my ChangeNet model", "why is my AOI model failing", "audit ChangeNet predictions", "investigate FAR regressions", "root cause analysis on visual-changenet".
Structured guide for setting up A/B tests with mandatory gates for hypothesis, metrics, and execution readiness.