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.
-
darthlinuxer Bundle Sequential Thinking 3Apply structured, reflective problem-solving for complex tasks requiring multi-step analysis, revision capability, and hypothesis verification. Use for complex problem decomposition, adaptive planning, analysis needing course correction, problems with unclear scope, multi-step solutions, and hypothesis-driven work.
- darthlinuxer Skill Code Review Checklist 3
Code review guidelines covering code quality, security, and best practices.
- darthlinuxer Bundle Documentation Templates 3
Documentation templates and structure guidelines. README, API docs, code comments, and AI-friendly documentation.
-
megastep Bundle Axiom SwiftdataUse when working with SwiftData - @Model definitions, @Query in SwiftUI, @Relationship macros, ModelContext patterns, CloudKit integration, iOS 26+ features, and Swift 6 concurrency with @MainActor — Apple's native persistence framework
- megastep Bundle Axiom Realm Migration Ref
Use when migrating from Realm to SwiftData - comprehensive migration guide covering pattern equivalents, threading model conversion, schema migration strategies, CloudKit sync transition, and real-world scenarios
-
harshahosur81 Skill Debug WorkflowGlobal Debugging agent skill for AG
-
troykelly-claude-skills Bundle Hook DevelopmentThis skill should be used when the user asks to "create a hook", "add a PreToolUse/PostToolUse/Stop hook", "validate tool use", "implement prompt-based hooks", "use ${CLAUDE_PLUGIN_ROOT}", "set up event-driven automation", "block dangerous commands", or mentions hook events (PreToolUse, PostToolUse, Stop, SubagentStop, SessionStart, SessionEnd, UserPromptSubmit, PreCompact, Notification). Provides comprehensive guidance for creating and implementing Claude Code plugin hooks with focus on advanced prompt-based hooks API.
- troykelly-claude-skills Skill Sentry Setup AI Monitoring
Setup Sentry AI Agent Monitoring in any project. Use this when asked to add AI monitoring, track LLM calls, monitor AI agents, or instrument OpenAI/Anthropic/Vercel AI/LangChain/Google GenAI. Automatically detects installed AI SDKs and configures the appropriate Sentry integration.
-
bybren-llc Bundle Vault Sync 2Detect and repair drift between an OKF knowledge vault and the code it describes. Use after merging significant changes (schema, interfaces, workflows, agent config), when a staleness review is due, or when the user asks to sync, refresh, or update the knowledge vault.
- bybren-llc Bundle Agent Coordination 2
Agent assignment matrix, blocker escalation, and TDM coordination patterns. Use when assigning work to specialists, managing blockers, or coordinating multi-agent workflows.
- bybren-llc Bundle Orchestration Patterns 2
Agentic orchestration patterns for long-running tasks. Implements evidence-based delivery and iterative agent loops. Use when managing multi-step work, coordinating workflows, or orchestrating PR workflows.
-
futurewithvibe Skill Model UsageTrack and report model usage and costs
-
hnabyz-bot Bundle MoaiMoAI super agent - unified orchestrator for autonomous development. Routes natural language or explicit subcommands (plan, run, sync, fix, loop, project, feedback) to specialized agents. Use for any development task from planning to deployment.
- hnabyz-bot Bundle Moai Library Mermaid
Enterprise Mermaid diagramming skill for Claude Code using MCP Playwright. Use when creating architecture diagrams, flowcharts, sequence diagrams, or visual documentation.
- hnabyz-bot Bundle Moai Foundation Claude
Canonical Claude Code authoring kit covering Skills, sub-agents, plugins, slash commands, hooks, memory, settings, sandboxing, headless mode, and advanced agent patterns. Use when creating Claude Code extensions or configuring Claude Code features.
-
razbakov Skill Daily DigestDaily Digest — Chief-of-Staff role consolidates the six top-managers into one Telegram message to the Commander, instead of six. Implements the protocol from agent-proactivity.md.
- razbakov Skill Daily Review
Daily Review (Meta-Skill) — orchestrates child skills: gather browser history, AI transcripts, app usage, process Telegram inbox, process Chrome bookmarks, snapshot portfolio DAU, sync all projects, suggest agent tasks, suggest today's plan, sync to calendar, and save the review.
- razbakov Skill Suggest Tasks
Scan all projects, OKRs, open PRs, Notion board, and calendar to propose prioritized agent tasks. Creates 'Suggested' cards in Notion Control Center with S3 analysis and agent assignment (Viktor/Luna/Marco/Kai/Maya). Part of Maya's operational loop.
- razbakov Skill Dispatch Approved
Dispatch all approved agent tasks from Notion Control Center. Picks up cards where Status='To do' and Assigned Agent is set, then launches each via the /inbox pattern (worktree + tmux). Always manual — never auto-runs.
- razbakov Bundle Install Local MCP Service
Install a self-hosted / community MCP server on macOS and make it durable — clone, build (fixing stale pinned deps that break at runtime), register in BOTH Claude Code and the Claude desktop app, handle interactive auth (QR/OAuth), and if it has a long-running daemon, wrap it in a launchd service. Use when the user asks to install a local/community MCP server (e.g. a GitHub project like lharries/whatsapp-mcp), especially one with a background bridge/daemon that must survive reboots.
-
bobmatnyc Skill Mpm 2Access Claude MPM functionality and manage multi-agent orchestration
71 - bobmatnyc Skill Mpm Ticket View 2
Orchestrate ticketing agent for project management workflows
71 - bobmatnyc Skill Pm Git File Tracking 2
Protocol for tracking files immediately after agent creation
71 - bobmatnyc Skill Pm Delegation Patterns
Common delegation patterns for PM agent
71 - bobmatnyc Skill Mpm Agent Update Workflow 3
PM Skill: Agent Update Workflow
71 - bobmatnyc Bundle Test Driven Development 3
Write the test first, watch it fail, write minimal code to pass
71 - harshahosur81 Skill Multi Agent Debug Review
Use when working with error debugging multi agent review
-
peparhugo Skill Humanizer 2Wave 5 migration placeholder for `softaworks-agent-toolkit/humanizer` imported from antigravity-awesome-skills manifest.
- peparhugo Skill Commit Work
Wave 5 migration placeholder for `softaworks-agent-toolkit/commit-work` imported from antigravity-awesome-skills manifest.
- peparhugo Skill Skill Judge
Wave 5 migration placeholder for `softaworks-agent-toolkit/skill-judge` imported from antigravity-awesome-skills manifest.
- peparhugo Skill QA Test Planner
Wave 5 migration placeholder for `softaworks-agent-toolkit/qa-test-planner` imported from antigravity-awesome-skills manifest.
- peparhugo Skill Session Handoff
Wave 5 migration placeholder for `softaworks-agent-toolkit/session-handoff` imported from antigravity-awesome-skills manifest.
- peparhugo Skill Ship Learn Next
Wave 5 migration placeholder for `softaworks-agent-toolkit/ship-learn-next` imported from antigravity-awesome-skills manifest.
- peparhugo Skill Feedback Mastery
Wave 5 migration placeholder for `softaworks-agent-toolkit/feedback-mastery` imported from antigravity-awesome-skills manifest.
- peparhugo Skill Reducing Entropy
Wave 5 migration placeholder for `softaworks-agent-toolkit/reducing-entropy` imported from antigravity-awesome-skills manifest.
- peparhugo Skill Dependency Updater
Wave 5 migration placeholder for `softaworks-agent-toolkit/dependency-updater` imported from antigravity-awesome-skills manifest.
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 qa-test-planner, ship-learn-next, feedback-mastery. 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.