AI & ML
AI & ML agent skills cover the machine-learning workflow itself: writing and evaluating prompts, building RAG pipelines, running evals, and wiring up model APIs. Each one is a SKILL.md file your agent loads on demand, so the know-how travels across Claude Code, Cursor, and 60+ agents.
-
majiayu000 Bundle Gemini Research Subagent 2Delegates large-context code analysis to Gemini CLI. Use when analyzing codebases, tracing bugs across files, reviewing architecture, or performing security audits. Gemini reads, Claude implements.
567 -
majiayu000 Bundle Context Degradation 2Recognize, diagnose, and mitigate patterns of context degradation in agent systems. Use when context grows large, agent performance degrades unexpectedly, or debugging agent failures.
567 -
majiayu000 Bundle Output Meta Project Context 2Comprehensive guide to Output.ai Framework for building durable, LLM-powered workflows orchestrated by Temporal. Covers project structure, workflow patterns, steps, LLM integration, HTTP clients, and CLI commands.
567 -
majiayu000 Bundle Model Context Protocol 2Model Context Protocol (MCP) - Open standard for connecting AI applications to external data sources, tools, and systems. Use for building MCP servers (tools, resources, prompts), clients, understanding protocol architecture, and implementing AI integrations.
567 -
majiayu000 Bundle 141 Java Refactoring With Modern Features 3Use when you need to refactor Java code to adopt modern Java features (Java 8+) — including migrating anonymous classes to lambdas, replacing Iterator loops with Stream API, adopting Optional for null safety, switching from legacy Date/Calendar to java.time, using collection factory methods, applying text blocks, var inference, or leveraging Java 25 features like flexible constructor bodies and module import declarations. This should trigger for requests such as Review Java code for modern Java development; Apply best practices for modern Java development in Java code. Part of cursor-rules-java project
567 -
majiayu000 Bundle Context Optimization 8Apply optimization techniques to extend effective context capacity. Use when context limits constrain agent performance, when optimizing for cost or latency, or when implementing long-running agent systems.
567 -
majiayu000 Bundle Quality Gates Parallel 2Launch 4 quality subagents in parallel using Claude Code 2.1+ native Task tool. Reads results post-analysis for orchestrator decision-making.
567 -
majiayu000 Bundle Ln 012 MCP Configurator 4Use when installing MCP packages and configuring Claude-side MCP registration, hooks, permissions, IDE extension mode, and migrations.
567 -
majiayu000 Bundle Cursor Mem 2Accesses the claude-mem MCP server from Cursor to search session history and record observations. Triggers: memory search, claude-mem, past decisions, record this. Do NOT load for: normal coding, temporary notes, or implementation work.
567 -
majiayu000 Bundle Flow Convert Prompts To Files 2Convert inline prompts and prompt arrays to .prompt files with YAML frontmatter. Use when migrating prompts from Flow SDK format to Output SDK prompt files.
567 -
majiayu000 Bundle Ln 310 Multi Agent Validator 4Validates Stories, plans, or context via parallel multi-agent review with GO/NO-GO verdict. Use when changes need cross-agent validation before proceeding.
567 -
majiayu000 Bundle Gemini Extension Development 2Expert guide for building and managing Gemini CLI Extensions. Covers extension anatomy, GEMINI.md context, commands, MCP integration, and publishing. Use when creating Gemini extensions, linking local extensions, packaging MCP servers, or installing extensions from GitHub. Delegates to gemini-cli-docs.
567 -
majiayu000 Bundle Ln 813 Optimization Plan Validator 4Use when validating optimization plans through the evaluation platform with mandatory research, parallel agent evidence, sequential merge, and bounded refinement.
567 -
neuralblitz Bundle Go 2Go Skills
1 -
neuralblitz Bundle JqJq Skills
1 -
neuralblitz Skill K6K6 Skills
1 -
neuralblitz Skill JWTJwt Skills
1 -
neuralblitz Skill PHP 2Php Skills
1 -
neuralblitz Skill SqsSqs Skills
1 -
neuralblitz Skill SreSite reliability engineering practices
1 -
neuralblitz Skill SsgStatic Site Generation for fast, pre-rendered web pages
1 -
neuralblitz Bundle VimVim Skills
1 -
neuralblitz Bundle FluxFlux Skills
1 -
neuralblitz Skill Java 2Java Skills
1 -
neuralblitz Skill SurrealdbSurrealDB multi-model database, document-graph hybrid, and real-time capabilities
1 -
neuralblitz Skill MonolithicMonolithic Architecture
1 -
neuralblitz Skill Pwa 2PWA (Progressive Web Apps)
1 -
neuralblitz Skill Ssr 2SSR (Server-Side Rendering)
1 -
neuralblitz Bundle Computer Graphics Based DesignComputer Graphics Based Design Skill
1 -
neuralblitz Bundle Cryptography Cs Based AnalysisCryptography Cs Based Analysis Skill
1 -
neuralblitz Bundle Cybersecurity Based EstimationCybersecurity Based Estimation Skill
1 -
neuralblitz Bundle Cybersecurity Based PredictionCybersecurity Based Prediction Skill
1 -
neuralblitz Bundle Cybersecurity Based SimulationCybersecurity Based Simulation Skill
1 -
neuralblitz Bundle Data Structures Based AnalysisData Structures Based Analysis Skill
1 -
neuralblitz Bundle Botany Design Advanced 2Botany Design Advanced Skill
1 -
neuralblitz Bundle Botany Modeling Expert 2Botany Modeling Expert Skill
1
Frequently asked questions
What are AI & ML agent skills?
AI & ML agent skills cover the machine-learning workflow itself: writing and evaluating prompts, building RAG pipelines, running evals, and wiring up model APIs. Each one is a SKILL.md file your agent loads on demand, so the know-how travels across Claude Code, Cursor, and 60+ agents.
Which AI & ML skills are most installed?
Popular AI & ML skills on SkillMD right now include Gemini Research Subagent, context-degradation, output-meta-project-context. Rankings shift as installs change; sort this page by "Most installs" for the live list.
Do AI & ML skills work with Claude Code and Cursor?
Yes. Every skill here ships as a SKILL.md file, an open format that works in Claude Code, Claude.ai, Cursor, Codex, Windsurf, and 60+ other agents. Install one with npx skillmds@latest add <owner>/<name>, or copy the file into your agent's skills directory.