Loading...
Loading...
Found 19 Skills
Use when asked to compare multiple ML models, perform cross-validation, evaluate metrics, or select the best model for a classification/regression task.
Conduct multi-round in-depth research on any research question, requiring iterative searching, full-text reading, cross-validation of independent sources, presentation of contradictions, and honest gaps; the domain mapping mode simultaneously explores both the stable knowledge structure and the latest status as of the current date. Use this skill when users request in-depth research, systematic study, fact-checking, research reports, or evidence preparation for domain maps. Quick one-time searches are not within the scope of this skill.
Reason about ML experiment design for healthcare and life sciences data. Use when the user asks to design an ML study, choose a model for clinical/biomedical data, set up cross-validation, pick evaluation metrics, audit fairness, plan a regulatory submission, or critique an ML pipeline on EHR, medical imaging, genomics, molecules, or clinical text. Triggers include "design an ML experiment", "which model for this clinical data", "how should I split", "nested CV", "class imbalance", "AUROC vs AUPRC", "calibration", "decision curve", "net benefit", "TRIPOD+AI", "PROBAST", "CLAIM", "FDA SaMD", "PCCP", "GMLP", "site generalization", "temporal leakage", "scaffold split", "foundation model evaluation", "subgroup fairness", "is this model ready for deployment".
Reason about biomarker discovery and validation in HCLS — classifying biomarker intent, choosing feature-selection and cross-validation strategies, avoiding leakage, and planning external replication. Use when the user asks to discover, develop, or validate a biomarker; select features from high-dimensional omics or clinical data; design a validation study; choose evaluation metrics; justify sample size; combine multi-omics signals; or assess clinical utility. Triggers include "discover a biomarker", "validate biomarker", "prognostic vs predictive", "feature selection", "LASSO vs elastic net", "nested cross-validation", "data leakage", "C-index", "time-dependent AUC", "decision curve analysis", "external validation cohort", "events per variable", "optimism-corrected", "multi-omics integration", "clinical utility of a biomarker", "is this biomarker ready".
Extract comprehensive, production-ready JSON design specifications from visual inputs using a 7-pass serial architecture with cross-validation. Use when converting screenshots, mockups, or design exports into structured design tokens, component specs, accessibility analysis, and developer handoff artifacts.
Interact with Google's Gemini model via CLI. Use when needing a second opinion from another LLM, cross-validation, or leveraging Gemini's Google Search grounding. Supports multi-turn conversations with session management.
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.
Google Gemini CLI orchestration for AI-assisted development. Capabilities: second opinion/cross-validation, real-time web search (Google Search), codebase architecture analysis, parallel code generation, code review from different perspective. Actions: query, search, analyze, generate, review with Gemini. Keywords: Gemini CLI, second opinion, cross-validation, Google Search, web research, current information, parallel AI, code review, architecture analysis, gemini prompt, AI comparison, real-time search, alternative perspective, code generation. Use when: needing second AI opinion, searching current web information, analyzing codebase architecture, generating code in parallel, getting alternative code review, researching current events/docs.
Use the @steipete/oracle CLI to bundle a prompt plus the right files and get a second-model review (API or browser) for debugging, refactors, design checks, or cross-validation.
Detect the divergence phenomenon where commodity prices rise but the holdings of corresponding physical ETFs/trusts decline, and use multi-indicator cross-validation to assess the risk of physical supply tightness/delivery pressure.
Chat with web AI agents (ChatGPT, Gemini, Claude, Grok, NotebookLM) via browser automation. Use when stuck, need cross-validation, or want a second-model review.
SEO/GEO Agent Operations SOP v2 — Rebuilt based on real-world operations (analook.com from 0 to launch, GSC incident, DataForSEO monitoring, gingiris.tools post-migration recovery). What's new in v2: • Step-by-step onboarding (Q1→Q6), multiple-choice questions wherever possible — no lengthy forms • Mandatory daily SEO log — the first item is always GSC token status check • Data cross-validation rule: any external metric must come from ≥2 sources before being used • Backlink progress tracking (6-week waiting period → check → alert if not indexed) • New vs. established site strategy matrix (new site <6 months: KD≤20; mature site: KD up to 35+) Real incidents incorporated: GSC token expired silently for 2 weeks (analook.com), P0 keywords dropped out of Top 100 after domain migration (gingiris.tools), traffic data had a 17× discrepancy from single-source DataForSEO. Triggers: "SEO agent" | "SEO daily report" | "GSC monitoring" | "DataForSEO" | "GEO agent" | "backlink tracking" | "IndexNow" | "competitor comparison page" | "SEO SOP" | "autonomous SEO" | "GEO triple combo" 🇨🇳 SEO/GEO Agent Operations SOP v2 — Rewritten based on real operational experience (analook.com from scratch + 2-week GSC outage + DataForSEO monitoring + gingiris.tools post-migration authority recovery). Conversational onboarding, mandatory daily report (GSC token check as the first item), strict data cross-validation rule, backlink progress tracking, differentiated strategies for new and established sites.