機器學習
1913 skills in 數據與 AI > 機器學習
swimlane-visualization
Design swimlane UI patterns for visualizing ADW execution. Use when building observability dashboards, monitoring agent workflows, or creating real-time status displays.
data-classification
Data classification framework including sensitivity levels, handling requirements, labeling, and data lifecycle management
data-processing
Process JSON with jq and YAML/TOML with yq. Filter, transform, query structured data efficiently. Triggers on: parse JSON, extract from YAML, query config, Docker Compose, K8s manifests, GitHub Actions workflows, package.json, filter data.
skill-development
Comprehensive meta-skill for creating, managing, validating, auditing, and distributing Claude Code skills. Provides skill templates, creation workflows, validation patterns, audit checklists, naming conventions, YAML frontmatter guidance, progressive disclosure examples, and best practices lookup. Use when creating new skills, validating existing skills, auditing skill quality, understanding skill architecture, needing skill templates, learning about YAML frontmatter requirements, progressive disclosure patterns, tool restrictions (allowed-tools), skill composition, skill naming conventions, or troubleshooting skill activation issues. Delegates to docs-management skill for official documentation.
brand-typography-systems
Provides brand typography selection and hierarchy development frameworks including the Brand-First Typography Selection Process, Modular Scale System, Font Classification Matrix, Serif vs. Sans-Serif Decision Framework, Typeface Evaluation Criteria, Font Pairing Principles, WCAG accessibility requirements, and typography design tokens. Auto-activates during brand typography development, font selection, type hierarchy creation, and typography system work. Use when discussing brand typography, font selection, font pairing, type hierarchy, modular scale, typography accessibility, WCAG typography, or typography guidelines.
python-regression-statistics
Expert guidance for regression analysis, statistical modeling, and outlier detection in Python using statsmodels, scikit-learn, scipy, and PyOD - includes model diagnostics, assumption checking, robust methods, and comprehensive outlier detection strategies
law-machine-readable-interpreter
Interprets legal text in regelrecht YAML files and generates machine-readable execution logic with parameters, operations, outputs, and cross-law references. Use when user wants to make a law executable, add machine_readable sections, or interpret legal articles for computational execution.
dependency-management
Enforces fixed version dependency installation across all package managers. Ensures reproducible builds, supply chain security, and stability.Use when: installing packages, updating dependencies, working with package.json/requirements.txt/go.mod/Cargo.toml/pom.xml/build.gradle/composer.json/Gemfile/.csproj, reviewing dependency configurations, configuring CI/CD pipelines
lint
Development: Pre-commit hooks and linting for code quality. Validatesshell scripts, YAML, markdown, TOML, and justfiles. Run from repositoryroot with 'just lint'. Use when developers need to validate code beforecommitting or set up pre-commit hooks.
architecture-diagram
Create professional, dark-themed architecture diagrams as standalone HTML files with SVG graphics. Use when the user asks for system architecture diagrams, infrastructure diagrams, cloud architecture visualizations, security diagrams, network topology diagrams, or any technical diagram showing system components and their relationships.
wp-wpcli-and-ops
Use when working with WP-CLI for WordPress operations: safe search-replace, db export/import, plugin/theme management, cron, cache flushing, multisite, and automation with wp-cli.yml.
test
Overlay testing session management for bazzite-ai development. Enables liveediting of justfiles via symlinks to /usr on immutable OS (OSTree) or traditionalLinux systems. Use when users need to test ujust changes, enable overlay mode,troubleshoot testing sessions, or run VM/install tests.
expertise-file-design
Design YAML expertise file structures for agent experts. Use when creating mental models for domain-specific agents, defining expertise schema, or structuring knowledge for Act-Learn-Reuse workflows.
skill-builder
Create new Skills for Claude Code including YAML frontmatter, descriptions, instructions, and structure. Use when creating, building, or designing skills, or when asked about skill creation, structure, best practices, or debugging skills that don't activate properly.
dutch-law-downloader
Downloads Dutch official legal publications including national laws (wetten, ministeriele regelingen, koninklijk besluiten), local regulations (lokale verordeningen, gemeentelijk beleid), and implementation policies (uitvoeringsbeleid) from government databases (BWB, CVDR) and converts them to YAML format with textual content only. Use when user wants to download, fetch, or import any Dutch regulation by name or type.
sysml-modeling
Systems Modeling Language (SysML) for systems engineering and complex system design
event-modeling
Adam Dymitruk's Event Modeling methodology with swimlanes
validate-journey
Validates CDP journey YAML configurations against tdx schema requirements. Use when reviewing journey structure, checking step types and parameters, verifying segment references, or troubleshooting journey configuration errors before pushing to Treasure Data.
toml-command-builder
Guide for building Gemini CLI TOML custom commands. Covers syntax, templates, argument handling, shell injection, and file injection. Use when creating Gemini TOML commands, adding {{args}} argument handling, injecting shell output with !{}, or troubleshooting command issues.
policy-engine-builder
Guide for creating Gemini CLI policy engine TOML rules. Covers rule syntax, priority tiers, conditions, and MCP wildcards. Use when restricting Gemini tools, creating security policies, controlling MCP server permissions, or setting up approval workflows.