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.
-
hainamchung Bundle LLM WikiBuild and maintain a git-based markdown wiki for software teams. Use when user mentions wiki, knowledge base, llm-wiki, ingest documents, compile sources, or query project knowledge.
-
zocomputer Bundle Clarion Value ScreenerRun a value-quality screen and write a watchlist file. The script accepts either a list of tickers (fundamentals fetched from yfinance) or a JSON input file the chat agent prepared from a screener site (multpl.com, finviz, Yardeni, etc.). Computes the 8-factor composite score (P/E, P/FCF, ROE, ROIC, Operating Margin, D/E, Profit Margin, Insider) per docs/ALLOCATION-POLICY.md, applies regime-tightened thresholds, and produces a sector-capped Top-10 watchlist. Saves to ~/clarion/watchlists/sp500-screen-YYYY-MM-DD.md. Use when the user asks "run a value screen", "screen the S&P 500", "screen these tickers <list>", or after market drawdowns / regime changes. Requires clarion-setup to have been run.
- zocomputer Bundle Clarion Single Stock Eval
Evaluate a single stock using the Buffett lens. Pulls a quality snapshot from yfinance, current SPY/TLT regime context, and snippets from the indexed SEC filings across four dimensions (moat, management, financial trends, risks). The chat agent reasons over the structured output to produce a written evaluation. Use when the user says "evaluate <TICKER>", "is <TICKER> a buy?", "Buffett evaluation of <TICKER>", "what's <TICKER>'s moat?", or asks about a specific company's management, financials, or risks. Requires clarion-setup to have been run, and the ticker to be indexed first via clarion-sec-research.
-
bjornmelin Skill Claude Subagent CreatorAuthor, validate, and install custom Claude Code subagents as .claude/agents Markdown files. Use when the user asks to create a subagent, custom agent, or .claude/agents role; define a reusable reviewer, explorer, planner, or worker persona; set an agent's model or tool allowlist; or turn a recurring workflow into a delegatable role. Produces Markdown agent files with YAML frontmatter (name, description, model, tools) plus a focused system-prompt body, scoped to the smallest tool surface that does the job (read-only by default). Covers naming, description wording for autonomous delegation, model policy (Opus for reasoning/review, inherit for scans), tool scoping, project vs user scope, and a smoke test. Pairs with fan-out, which delegates to these roles. Not for one-off ad-hoc delegation (use fan-out) or authoring Agent Skills (SKILL.md files).
-
timequity Bundle MCP BuilderGuide for creating high-quality MCP (Model Context Protocol) servers that enable LLMs to interact with external services through well-designed tools. Use when building MCP servers to integrate external APIs or services, whether in Python (FastMCP) or Node/TypeScript (MCP SDK).
-
happy-technologies-llc Bundle Happy Platform SkillsReusable enterprise platform instructions - 184 skills across 23 categories with a versioned Happy Platform MCP v5.1 contract
- happy-technologies-llc Skill Script Sync
Explicit pull, local edit, freshness check, and push workflow for ServiceNow scripts with Happy Platform MCP 5.1
- happy-technologies-llc Skill Agent Miner
Mine agent interactions to find automation opportunities by analyzing repetitive patterns, identifying common resolutions, and discovering handoff points for bot candidates
- happy-technologies-llc Skill Build Agent
Build custom AI agents for ServiceNow including agent capabilities, knowledge sources, tool access, conversational flows, and guardrails
-
athola Skill Glimmer DelegationDelegates tasks to a locally served Muse Glimmer via ollama. Use when delegation-core selects glimmer or the prompt must not leave the machine.
- happy-technologies-llc Skill AI Search RAG
Configure retrieval-augmented AI search, including sources, indexing, ranking, answer generation, and search quality tuning.
- happy-technologies-llc Bundle Fluent Sdk
Hybrid ServiceNow development using the three-tier approach - NowSDK Fluent for metadata-as-code, MCP REST for runtime operations, and fix scripts as manual fallback
- happy-technologies-llc Skill MCP Server
Set up ServiceNow as an MCP (Model Context Protocol) server defining tool capabilities, authentication, resource endpoints, and integration patterns for AI agents
- happy-technologies-llc Skill Skill Kit Custom
Create custom Now Assist skills using Skill Kit including skill input/output definition, prompt configuration, skill testing with ATF, deployment, and building custom AI capabilities
- happy-technologies-llc Skill Workflow Creation
Programmatic workflow creation via API/MCP - build complete workflows without the UI editor
- athola Bundle Night Market Model And Harness Updates
Sweep plugins, skills, agents, commands, and hooks after a model release or Claude Code version bump. Use when upstream ships. Do not use for routine edits; use night-market-change-control.
- happy-technologies-llc Skill Instance Management
Manage and safely route Happy Platform MCP v5.1 operations across ServiceNow instances
-
gitwalter Bundle Using ToolsTool design, binding, and error handling patterns for LangChain agents
- gitwalter Bundle Browsing Web
Web scraping with agents, browser automation, content extraction, and ethical scraping practices
- gitwalter Bundle Selecting MCP
Guide users through selecting appropriate MCP servers during project generation
- gitwalter Bundle Analyzing Code
Static code analysis with AST parsing, complexity metrics, dependency graphs, and quality scoring
- gitwalter Bundle Configuring Pm
Configure project management system with backend and methodology selection
- gitwalter Bundle Developing Bdd
Behavior-driven development with Gherkin feature files, scenario outlines, and step definitions
- gitwalter Skill Git Governance
Automated governance, hook installation, pre-commit validation, branch isolation, and safe commit operations.
- gitwalter Bundle Managing State
LangGraph state schemas, reducers, checkpointing, and persistence
- gitwalter Bundle Create Task
Create implementation task from story or description
- gitwalter Bundle Serving Models
Production model serving with vLLM, TGI, Ollama, Triton, FastAPI endpoints, batching, and GPU optimization
- gitwalter Bundle Testing Agents
Unit testing with mocks, integration testing, LangSmith evaluation, benchmarking
- gitwalter Skill Writing Plans
Use when you have a spec or requirements for a multi-step task, before touching code. Enforces bite-sized task granularity.
- gitwalter Bundle Handling Errors
Retry strategies with tenacity, fallback patterns, circuit breakers, graceful degradation
- gitwalter Bundle Integrating MCP
Model Context Protocol overview, server creation, tool exposure, and common integrations
- gitwalter Bundle Create Story
Create user story from description with acceptance criteria
- gitwalter Bundle Verifying Links
Verify internal and external links in project documentation
- gitwalter Bundle Defining Purpose
Guide users through articulating why their agent system should exist, who it serves, and how success will be measured
- happy-technologies-llc Skill Playbook Generation
Generate Process Automation Designer playbooks from natural language descriptions including activities, lanes, conditions, data gathering steps, and both standard and agent-facing playbooks
- gitwalter Bundle Selecting Axioms
Interactive guidance for selecting appropriate trust verification tier
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 llm-wiki, claude-subagent-creator, happy-platform-skills. 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.