472 skills · sorted by relevance
Evaluate model performance — check for accuracy drops, data drift, and error patterns. Use when asked about "model accuracy dropped", "evaluate the model", "check for drift", or "model performance".
The English summary is being prepared. Showing the original description.
Advanced multi-agent reasoning system for complex questions requiring maximum accuracy. Uses adaptive technique selection, adversarial validation, multi-agent debate, and deep analysis. Trigger phrases "ai board", "expert panel", "deep analysis", "maximum accuracy", "thorough reasoning". Use for critical medical decisions, theological questions, philosophical analysis, complex technical problems, high-stakes decisions, or any question requiring 95%+ confidence.
The English summary is being prepared. Showing the original description.
Fit cognitive drift-diffusion models (Ratcliff DDM) to reaction time and accuracy data with parameter estimation (drift rate, boundary separation, non-decision time), model comparison, and parameter recovery validation. Use when modeling binary decision-making with reaction time data, estimating cognitive parameters from experimental data, comparing sequential sampling model variants, or decomposing speed-accuracy tradeoff effects into latent cognitive components.
The English summary is being prepared. Showing the original description.
Feed actual task results back into agent memory for calibration. Compares predicted vs actual outcomes, records accuracy scores, and tracks estimation quality, prediction quality, and decision quality over time to improve future agent performance.
The English summary is being prepared. Showing the original description.
Use when a task needs the judgment of a Cartographer/Photogrammetrist — designing an aerial or LiDAR acquisition flight plan against a stated accuracy class, running an NSSDA checkpoint accuracy test on a delivered orthophoto or DTM, choosing a horizontal/vertical datum and geoid model for a georeferencing project, diagnosing why a state-plane grid distance disagrees with a field-surveyed ground distance, or specifying LiDAR point-density and classification requirements for a bare-earth deliverable.
The English summary is being prepared. Showing the original description.
Use when constructing the forecast call — commit / best-case / pipeline categorisation, deal-level evidence test, accuracy retro-loop. Triggers on 'build the forecast', 'why does our commit miss'.
The English summary is being prepared. Showing the original description.
Patient safety evaluation harness for healthcare application deployments. Automated test suites for CDSS accuracy, PHI exposure, clinical workflow integrity, and integration compliance. Blocks deployments on safety failures. Use when a healthcare deployment must be gated on patient-safety tests for CDSS accuracy, PHI exposure, and workflow integrity.
The English summary is being prepared. Showing the original description.
Diagnostic test / biomarker accuracy — sensitivity, specificity, PPV, NPV, likelihood ratios, accuracy from a 2x2 table; ROC curve, AUC, and the optimal cutoff (Youden) for a continuous biomarker; and post-test probability via Bayes. Use when you have test results vs a gold standard (binary 2x2, or a continuous score + true labels) and need to judge how good the test is, pick a threshold, or compute the probability of disease given a result. Emphasizes the prevalence-dependence of PPV/NPV.
The English summary is being prepared. Showing the original description.
Activation-aware weight quantization for 4-bit LLM compression with 3x speedup and minimal accuracy loss. Use when deploying large models (7B-70B) on limited GPU memory, when you need faster inference than GPTQ with better accuracy preservation, or for instruction-tuned and multimodal models. MLSys 2024 Best Paper Award winner.
The English summary is being prepared. Showing the original description.
Design text extraction for forms, invoices, and quizzes using regex, rules that match text patterns. Check extraction confidence and send uncertain items to an LLM for review, with guidance on testing and tracking processing costs.
Track machine learning experiments in W&B, record training settings and metrics, and compare results in dashboards. Automate searches for training settings and keep version histories for models and datasets.
Create reusable agent skills from recurring tasks, or improve existing ones through test prompts and user feedback. Compare outputs with and without a skill, measure performance, and refine descriptions so skills are invoked for the right requests.
Build a room-specific sensing model by recording an empty room and occupants performing activities, then training small specialized models. The workflow continues into live monitoring of presence, posture, and breathing in the calibrated room.
Check code and agent outputs, track reliability scores, and roll back changes that fail a chosen threshold. Includes quality reports, live monitoring, and integration with automated build and deployment workflows.
Start using RuView by choosing a Docker demo, a source build, or a live ESP32 setup. The skill guides the next concrete step, distinguishing sample data playback from sensing an actual room with WiFi signals.
Train and evaluate models that estimate human poses from WiFi signals. Compare results against a model that always predicts the average pose, check for data leakage, and report measured improvements with clear evaluation conditions.
Turn a repeatable workflow into a skill, or improve an existing one through test prompts and feedback. Compare results with and without the skill, review performance measurements, and refine its description so it triggers appropriately.
Guide market prediction workflows with LSTM, Transformer, and N-BEATS models using neural-trader commands and result storage. It explicitly identifies version 2.8.11 outputs as placeholders, so they cannot be treated as fitted models or evidence of prediction accuracy.
Audit AI-generated articles for factual accuracy, original value, and a natural voice. Suggest revisions grounded in original research or experience, and inspect rendered HTML, metadata, and response headers to identify issues in search-facing pages.
Fact-check finished OpenSpec documentation with a separate reviewer that checks commands, examples, and behavior against source files and actual output. Receive prioritized findings, suggested fixes, verification evidence, and a list of claims that remain unverified.
Evaluate an Agent Skill bundle before release by checking structure, activation conditions, output quality, scripts, safety, file integrity, and host compatibility. Receive a detailed JSON report that distinguishes local evidence checks from production readiness backed by external attestation.
Create and improve agent skills by defining tasks, writing instructions, and testing realistic requests. Compare outputs, success rates, time, and token use, then refine the skill and its description so it triggers appropriately.
Review Appwrite blog posts for search visibility and clear answers that answer engines can extract. Measure titles and content, assess structure and links, and receive evidence-based findings with prioritized fixes and suggested replacements.
Create product comparison and alternative pages that help buyers evaluate options. Organize pricing, features, use cases, and migration details, and audit existing competitive claims for outdated information, missing evidence, or wording that overstates the facts.