evidence-retrieval
Retrieve and organize evidence for key claims using available tools, with source URLs and confidence tags.
Retrieve and organize evidence for key claims using available tools, with source URLs and confidence tags.
When the user wants to solve complex optimization problems using metaheuristics, apply genetic algorithms, simulated annealing, or other nature-inspired algorithms. Also use when the user mentions "genetic algorithm," "simulated annealing," "tabu search," "ant colony," "particle swarm," "evolutionary algorithms," "nature-inspired optimization," "heuristic search," or when exact optimization methods are too slow for large-scale problems. For exact methods, see optimization-modeling. For multi-objective, see multi-objective-optimization.
Clinical data modeling covering healthcare terminology systems (ICD-10, SNOMED CT, LOINC, RxNorm, CPT, NDC), clinical document architecture, patient data normalization, temporal clinical data patterns, and clinical decision support data models.
Research-focused autonomous agent for evidence collection.
Computational system taxonomy for classifying systems by their computational properties. Load when analyzing or categorizing system architectures.
Run a simulation example and analyze the output
When the user wants to solve the Traveling Salesman Problem (TSP), find the shortest route visiting all cities, or optimize tour sequences. Also use when the user mentions "TSP," "shortest tour," "Hamiltonian cycle," "tour optimization," "route sequencing," "optimal visit order," "traveling salesperson," or "minimum distance tour." For vehicle routing with capacities, see vehicle-routing-problem.
Morph, blend, and transform faces using each::sense AI. Create face morphs, celebrity blends, family resemblance predictions, gender swaps, and animated transitions between faces.
Comprehensive framework for evaluating AI vendors and solutions to avoid costly mistakes. Use this skill when assessing AI vendor proposals, conducting due diligence, evaluating contracts, comparing vendors, or making build-vs-buy decisions. Helps identify red flags, assess pricing models, evaluate technical capabilities, and conduct structured vendor comparisons.
Create thought leadership content including long-form articles, essays, and opinion pieces. Use when the user needs authoritative content, wants to establish expertise, or needs to articulate a unique perspective on industry topics.
Analyze media content structure, narrative flow, key themes, and important moments from videos, podcasts, and articles. Use when you need to understand content organization before documenting.
Comprehensive verification of project documentation for completeness, accuracy, consistency, and quality. Use this skill when you need to verify documentation alignment with code, check for missing or outdated content, assess documentation quality, or ensure all major code aspects are properly documented. Explicitly triggered by user commands like /doc-verification or when asked to "check documentation", "verify docs", or "review documentation".
Router for simulation math - ODEs, state-space, stability, control, numerics, chaos, stochastic
Conduct comprehensive, multi-source research on any topic using the 7-phase Deep Research protocol with Graph of Thoughts. Use when user needs thorough research with verified claims, citations, and source triangulation. Triggers on "deep research [topic]", "research [topic] thoroughly", "I need comprehensive research on...", or "investigate [topic]".
Deep content analysis for structure, themes, narrative flow, key moments, and important quotes. Use before content-documenter.
Use when adding a new geologic data source to the underfoot project — creating the required three-file structure, writing citation.json, and calling process_usgs_source with the correct parameters for GAM or USGS shapefile sources.
Deep research skill for systematic exploration. Auto-triggered for research, analysis, investigation tasks. Ensures data accuracy and research depth.
Verify that an ML experiment meets reproducibility requirements: random seeds, library versions, data hashes, environment capture. Use when reviewing experiments before shipping.
Standard format for logging ML experiments including hypothesis, config, results, and learnings. Use when running experiments to maintain a consistent record.