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.
-
tomevault-io Bundle Retrieving RAG ContextSpecialized skill for retrieving rag context Use when this capability is needed.
- tomevault-io Bundle Hackermanishackerman Claude Skills Vault Prompt Compressor
---
- tomevault-io Bundle Helixdevelopment Helixagent Building Classification Models
Classification Model Builder
- tomevault-io Bundle Heyu 233 Engineering Figure Agent Engineering Figure Agent
Engineering Figure Agent For Claude Code
- tomevault-io Bundle Background Researcher Agent
Deep research specialist for background tasks. Investigates technologies, analyzes patterns, documents findings, and provides comprehensive research reports. Use for technology research, codebase analysis, or documentation synthesis. Use when this capability is needed.
- tomevault-io Bundle Prp Codebase Explorer Agent
Comprehensive codebase exploration - finds WHERE code lives AND shows HOW it is implemented. Use when you need to locate files, understand directory structure, AND extract actual code patterns. Documents existing code without suggesting improvements. Use when this capability is needed.
- tomevault-io Bundle Review Doc
指定された章のドキュメント（index.md）を見直し、ソースコードとの差分チェック・内容の加筆修正・構成の整合性確認を行う。 Use when this capability is needed.
- tomevault-io Bundle Creating Claude Code Skills
Guide for creating effective Claude Code Agent Skills. Use when users want to create, improve, or troubleshoot Skills that extend Claude's capabilities with specialized workflows, domain expertise, or tool integrations. Use when this capability is needed.
- tomevault-io Bundle Story Breakdown
Activate when user presents a large story or epic that needs decomposition. Activate when a task spans multiple components or requires coordination across specialists. Creates work items in .agent/queue/ for execution. Use when this capability is needed.
- tomevault-io Bundle Packetscope
This skill enables LLM to interact with the PacketScope Monitor module API for network packet analysis, function call tracking, and socket monitoring. Use when this capability is needed.
- tomevault-io Bundle Harness Engineering
Bootstrap or migrate a repository into an agent-first harness-engineering knowledge store modeled on OpenAI's Harness engineering article. Use when Codex needs to set up AGENTS.md plus a structured docs/ system of record for a new repository, or audit an existing repository's documentation against the real codebase, rewrite mismatched docs, retire stale docs, and re-home surviving docs into a predictable agent-readable structure. Use when this capability is needed.
- tomevault-io Bundle Cc Schedule Recurring Cron And Execute Immediately Compact
Instructions for creating a recurring cron job, confirming the schedule with the user, and immediately executing the parsed prompt without waiting for the first cron fire Use when this capability is needed.
- tomevault-io Bundle Git History Analyzer
Use this agent when understanding the historical context and evolution of code changes, tracing the origins of specific code patterns, identifying key contributors and their expertise areas, or analyzing patterns in commit history. Triggers on requests like "git history analysis", "why was this written", "who owns this code".
- tomevault-io Bundle Kart Rc Dataobservability Agents Telemetry Validator Agent
Telemetry Validator Agent
- tomevault-io Bundle Joeseesun Qiaomu Feishu Lark Agent Qiaomu Feishu Lark Agent
Feishu Lark Agent
- tomevault-io Bundle Data Migration Expert
Use this agent when reviewing database migrations, schema changes, or data transformations. Specializes in validating ID mappings, checking for swapped values, and verifying rollback safety. Triggers on requests like "migration review", "schema change validation".
- tomevault-io Bundle Juandelossantos Another Agent Skills Documentation And Adrs
Documentation and ADRs
- tomevault-io Bundle Deployment Strategy Blue Green
Design blue-green deployment strategy with explicit cutover checks, rollback triggers, and state/data compatibility safeguards. Use when release risk requires fast rollback and environment-level switch control; do not use for canary-percentage experimentation policy design. Use when this capability is needed.
- tomevault-io Bundle Langcare Langcare MCP Fhir Allergy Adverse Reaction Summary
Allergy & Adverse Reaction Summary
- tomevault-io Bundle Local Code Review
Working-tree (uncommitted diff) code review with cross-model adversarial pass — Gemini reviews, Codex challenges false positives, surviving findings get applied. Use BEFORE commit. For PR-level review, use the official `/code-review:code-review` plugin instead. Use when this capability is needed.
- tomevault-io Bundle Agent Capability Assessor
Assesses agent capabilities by analyzing agent files and determining what tasks they can handle. Use when you need to evaluate if an existing agent can handle a task or if a new agent is needed. Reviews agent descriptions, skills, and workflows to determine capability match. Use when this capability is needed.
- tomevault-io Bundle Langgraph State Management
Design state schemas, implement reducers, configure persistence, and debug state issues for LangGraph applications. Use when users want to (1) design or define state schemas for LangGraph graphs, (2) implement reducer functions for state accumulation, (3) configure persistence with checkpointers (InMemorySaver/MemorySaver, SqliteSaver, PostgresSaver), (4) debug state update issues or unexpected state behavior, (5) migrate state schemas between versions, (6) validate state schema structure, (7) choose between TypedDict and MessagesState patterns, (8) implement custom reducers for lists, dicts, or sets, (9) use the Overwrite type to bypass reducers, (10) set up thread-based persistence for multi-turn conversations, or (11) inspect checkpoints for debugging. Use when this capability is needed.
- tomevault-io Bundle Prompt Solve Next Todo Item
Codex-native counterpart of `/home/projekty/copilot-instructions/prompts/Solve_next_todo_item.prompt.md`. Use when this capability is needed.
- tomevault-io Bundle Gemini MCP Integration
Expert guide for Model Context Protocol (MCP) integration with Gemini CLI. Covers MCP server configuration (HTTP, SSE, Stdio), connection management, and tool permissions. Use when adding MCP servers to Gemini, configuring transports, troubleshooting MCP connections, or managing tool permissions. Delegates to gemini-cli-docs. Use when this capability is needed.
- tomevault-io Bundle Minimum Viable Agentic
Guide creation of minimum viable agentic layer for a codebase. Use when starting agentic coding in a new project, bootstrapping essential components, or creating the minimal scaffolding for agent success. Use when this capability is needed.
- tomevault-io Bundle Prompt Level Selection
Guide selection of appropriate prompt level for a task. Use when choosing between simple prompts and complex workflows, applying the seven levels framework, or matching task complexity to prompt investment. Use when this capability is needed.
- tomevault-io Bundle Swimlane Visualization
Design swimlane UI patterns for visualizing ADW execution. Use when building observability dashboards, monitoring agent workflows, or creating real-time status displays. Use when this capability is needed.
- tomevault-io Bundle User Config Management
Central authority for managing Claude Code user configuration directories (~/.claude/ and ~/.claude.json). Covers storage cleanup, backup/restore, reset workflows, MCP server preservation, history management, plan management, session statistics, and configuration health auditing. Delegates to docs-management skill for official documentation. Use when managing user config, cleaning up storage, backing up settings, resetting Claude Code, or auditing configuration health. Use when this capability is needed.
- tomevault-io Bundle Troubleshooting Authentication
Provides authentication troubleshooting for MSAL, JWT, and Entra ID. Use when debugging 401 errors, token issues, MSAL configuration problems, or credential failures in this repository.
- tomevault-io Bundle Human In The Loop
Instrument human approval workflows, feedback loops, and escalations Use when this capability is needed.
- tomevault-io Bundle Prompt Versioning
Track prompt versions, A/B test variants, and measure prompt performance Use when this capability is needed.
- tomevault-io Bundle Discord List Channels
List all channels in a Discord guild/server via the Discord API. Use this skill when the user wants to see all channels, find specific channels, or audit server structure. Use when this capability is needed.
- tomevault-io Bundle Omer Metin Skills For Antigravity Multi Agent Orchestration
---
- tomevault-io Bundle Orcaqubits Agentic Commerce Skills Plugins Nlweb MCP Server
NLWeb MCP Server
- tomevault-io Bundle Pablo Lozano Gil Battletested Agent Skills Skill Propagator
Skill Propagator
- tomevault-io Bundle Adding Orchestrator Workflow
Adds new workflow endpoints to the QuAIA orchestrator. Use when creating new FastAPI endpoints that coordinate agent tasks, handle webhooks, or expose new API functionality. Use when this capability is needed.
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 retrieving-rag-context, hackermanishackerman--claude-skills-vault--prompt-compressor, helixdevelopment--helixagent--building-classification-models. 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.