207 skills · sorted by relevance
Run Scenic traffic scenarios on a CARLA server. First test whether a valid scene can be generated, then simulate with limits on runs and steps, record the outcome, and restore the world's asynchronous setting afterward.
Turn a written traffic situation into a Scenic file, which describes possible scenes using placement rules and constraints. Select suitable maps and actors, then check that the file compiles and can generate at least one scene.
Clean, combine, summarize, and reshape tabular data with pandas DataFrames, Python's table-like data structures. Produces transformation code and validation checks, including time series processing and memory-conscious approaches for large datasets.
Coordinate bulk contract clause extraction with Luminance or Kira, prepare loading requests, and check returned results according to your team's review settings. Assess flagged clauses against the transaction and organize findings and required consents.
Analyze Axiom data ingestion and query usage to identify unused columns and field values. Build cost dashboards and spike monitors, then summarize recommendations for dropping or sampling data with estimated savings.
Research websites, extract page content, and interact with sites using search tools or an existing browser session. Handles login-dependent and dynamically loaded pages, with browser controls for navigation, forms, screenshots, and media inspection.
Design charts and dashboards that show data distributions, uncertainty, missing values, and sample sizes clearly. Choose visual forms that preserve meaningful variation and explain where averages, aggregation, or interval choices could mislead readers.
Design live monitoring dashboards with clear priorities, linked charts, and predictable update behavior. Covers mobile interactions, connection failures, and rendering performance so users can scan current conditions, spot anomalies, and explore details as data changes.
Analyze actual GA4 visits from AI services such as ChatGPT and Perplexity. Compare traffic trends, landing pages, and conversions, then identify page patterns and specific content changes that may improve visibility in AI search.
Biohub ESMFold2 / ESMFold2-Fast all-atom co-folding (Candido et al. 2026, github.com/Biohub/esm). Single-sequence and MSA modes; protein, DNA, RNA, ligand (CCD/SMILES), modified residues. FoldBench Ab-Ag 50-55%, PPI 70-77% DockQ-pass. Also covers the ESMC-{300M,600M,6B} protein language models from the same release: masked-LM logits, hidden states, mutation scoring, contact prediction, and the SAE interpretability head. MIT-licensed weights on HuggingFace org `biohub`. Use this skill when: (1) Predicting complex structures with single-sequence input, (2) Validating designed binders with ESMFold2-Fast, (3) Running ESMFold2 with MSA input, (4) Getting ESMC embeddings or per-residue mutation scores, (5) Choosing kernel backend and sampling-step settings for paper-faithful throughput.
The English summary is being prepared. Showing the original description.
Opinionated Bayesian modeling workflow with PyMC and ArviZ. Contains critical guardrails (nutpie sampler, prior/posterior predictive checks, LOO-PIT calibration, prior sensitivity checks, 94% HDI, non-centered parameterizations, reproducible seeds) that agents won't apply unprompted — always consult before writing Bayesian model code. Trigger on: building probabilistic/Bayesian models, prior elicitation, MCMC inference, convergence diagnostics (divergences, R-hat, ESS), model comparison (LOO-CV, ELPD, stacking weights), hierarchical/multilevel models, count regressions, logistic regression with uncertainty, prior sensitivity analysis, reporting Bayesian results, or mentions of PyMC, ArviZ, InferenceData, credible intervals, posterior distributions, shrinkage, uncertainty quantification. Also trigger for model comparison, diagnosing sampling problems, choosing priors, or presenting stats to non-technical audiences.
The English summary is being prepared. Showing the original description.
Use this skill when the user is deploying or operating the DOCA Argus Service — the packaged BlueField-side runtime-security container that watches the BlueField and attached host for suspicious activity, integrity violations, and operational anomalies, and forwards findings to a SIEM (Splunk / ELK / Sentinel / syslog). Covers the four-axis config (detection policy, forwarding, sampling, host coverage), running the NGC container on BlueField Arm, and wiring the forwarder. Trigger even without "DOCA Argus" by name — typical implicit phrasings: "container green but no findings arrive", "false-positive flood in Splunk", or "runtime security on a fleet of BlueField-3s". Refuse and route elsewhere for installing DOCA, SIEM-side ingest stanzas, pre-baked detection-rule packs, and metrics observability (DOCA Telemetry). Argus is NVIDIA's currently- promoted runtime-security framework, superseding the older App Shield library; name it first for new runtime-security work.
The English summary is being prepared. Showing the original description.
Run ProteinMPNN inverse folding via NVIDIA NIM to design protein sequences for a target backbone. Sends user-provided PDB files and design parameters to NVIDIA's hosted API, authenticated with an environment API key, or to a user-selected local NIM. Use for sequence design, backbone redesign, fixed chains and residues, omit_AAs, sampling temperature, soluble model, local Docker, and multi-FASTA output.
The English summary is being prepared. Showing the original description.
Use this skill for MolMIM, NVIDIA's BioNeMo NIM microservice for small-molecule latent-space generation and optimization. Invoke for MolMIM, molecular embeddings, hidden states, latent decoding, sampling around a seed SMILES, CMA-ES guided molecule generation, QED or plogP optimization, hosted NVIDIA API calls, or local Docker deployment.
The English summary is being prepared. Showing the original description.
Design unbiased survey instruments — question wording, scales, and sampling — to measure attitudes at scale. Use when you need quantitative breadth. For behavioural experiments, use `a-b-test-design` (prototyping-testing).
The English summary is being prepared. Showing the original description.
Configures AWS WAF to filter web traffic: creating web access control lists (web ACLs) on CloudFront, Application Load Balancers, API Gateway, and AppSync; AWS Managed Rules tuned in Count mode; rate-based rules for HTTP floods; IP set and geographic match rules; Bot Control (Common and Targeted); turning bot labels into a confidence signal; stripping spoofed inbound x-amzn-waf-* headers; recovering the real client IP behind a CDN; Fraud Control (account takeover and account creation fraud prevention); and logging and request sampling. Use when the user wants to protect a web application or API from common exploits, bots, credential stuffing, fake-account creation, or HTTP floods at the application layer (layer 7). Routes to the right per-task procedure in references. Do NOT use for L3/L4 DDoS protection (shieldadvanced skill), multi-account WAF rollout (firewallmanager skill), CloudFront configuration (cloudfront skill), or Route 53 health checks or records (route53 skill).
The English summary is being prepared. Showing the original description.
Use BEFORE reading any data file that could be large (CSV/TSV, Parquet, HDF5, FITS, NetCDF, NDJSON, genomics FASTQ/FASTA/VCF/BAM, GRIB, ROOT, or big text/simulation logs like VASP OUTCAR). Returns a compact memory pointer — header/schema/shape/sample/key numbers — by introspection and sampling in bounded memory, so you never load a file bigger than the context window into the model. Reference data via the pointer; read specific ranges deterministically.
The English summary is being prepared. Showing the original description.
Use this skill when writing analytical SQL over time-series data with the TimescaleDB Toolkit (timescaledb_toolkit extension) hyperfunctions: approximate percentiles, statistical summaries, time-weighted averages, counter/gauge rates, uptime/heartbeat tracking, state durations, OHLC candlesticks, approximate distinct counts, top-N, and downsampling. **Trigger when user asks to:** - Compute percentiles/medians/p95/p99 over large or rolled-up time-series data - Compute rates or deltas from monotonic counters (Prometheus-style) or gauges - Compute time-weighted averages or integrals over irregularly sampled data - Track uptime/downtime from heartbeats, or time spent in each state - Build OHLC/candlestick or VWAP data for financial ticks - Store re-aggregatable summaries in continuous aggregates (two-step aggregation, rollup) - Approximate COUNT DISTINCT, find top-N / most frequent values, or downsample for charts **Keywords:** timescaledb_toolkit, hyperfunctions, percentile_agg, uddsketch, tdigest, approx_percentile, stats_agg, time_weight, counter_agg, gauge_agg, heartbeat_agg, state_agg, candlestick_agg, hyperloglog, approx_count_distinct, min_n, max_n, mcv_agg, lttb, asap_smooth, rollup, two-step aggregation
The English summary is being prepared. Showing the original description.
Data conditioning techniques for gravitational wave detector data. Use when preprocessing raw detector strain data before matched filtering, including high-pass filtering, resampling, removing filter wraparound artifacts, and estimating power spectral density (PSD). Works with PyCBC TimeSeries data.
The English summary is being prepared. Showing the original description.
Generate ideas in one shot using creative sampling
The English summary is being prepared. Showing the original description.
Draft a structured preregistration document (OSF, AsPredicted, or AEA RCT Registry style) from a research spec or free-form study description. Output is a Markdown file with hypotheses, design, sampling plan, analysis plan, exclusions, and inference criteria — annotated with MUST / SHOULD / MAY clarity flags. Use when user says "preregister", "draft a preregistration", "OSF preregistration", "AsPredicted", "AEA RCT registry", "PAP", "preanalysis plan", or before launching an experiment / data collection / analysis on data the analyst has not yet seen. NOT a registry submission tool — produces a document the user uploads to OSF / AsPredicted / AEA themselves.
The English summary is being prepared. Showing the original description.
Create diverse synthetic test inputs for LLM pipeline evaluation using dimension-based tuple generation. Use when bootstrapping an eval dataset, when real user data is sparse, or when stress-testing specific failure hypotheses. Do NOT use when you already have 100+ representative real traces (use stratified sampling instead), or when the task is collecting production logs.
The English summary is being prepared. Showing the original description.
Specify the tracing, metrics, and alerting for an AI agent or LLM feature in production. Use when asked what to log for an LLM app, design agent tracing or spans, define quality and cost monitors, or answer 'how do we know if the agent is misbehaving?'. Produces an observability spec with a trace schema, metric definitions with owners and alert thresholds, sampling and retention policy, and a privacy note for logged content.
The English summary is being prepared. Showing the original description.
Tracks ctDNA across serial liquid-biopsy timepoints for molecular residual disease (MRD) and treatment-response monitoring, treating MRD as a binary integrated detection call across the patient's full variant set (with a defined LoD95 and per-sample specificity) rather than a per-timepoint VAF threshold, and handling undetectable samples as left-censored at the per-sample limit of detection rather than true zeros. Covers tumor-informed bespoke vs tumor-naive design, landmark vs surveillance sampling, molecular-response definitions and their non-standardization, censoring-aware clearance kinetics, and the multiple-testing structure of repeated surveillance. Use when monitoring ctDNA during therapy, calling molecular relapse before imaging, or estimating clearance half-life from serial samples.
The English summary is being prepared. Showing the original description.