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 Layer 08 Data StoreExpert knowledge for Data Store Layer modeling in Documentation Robotics Use when this capability is needed.
- tomevault-io Bundle Thinking Model Selection
Choose the right mental model for the problem at hand. Use when facing new problems, when current approaches fail, or when you need to match tool to context. Use when this capability is needed.
- tomevault-io Bundle Kiro Custom Agents
Create and configure Kiro CLI custom agents (JSON config files). Use when user asks to "create a kiro agent", "make a custom agent", "configure agent tools", "set up MCP servers in an agent", "add hooks to an agent", "troubleshoot agent config", or any task involving kiro-cli agent JSON configuration, tool permissions, resources, hooks, steering, MCP integration, or code intelligence setup. Use when this capability is needed.
- tomevault-io Bundle AI Agent Onboarding Bootstrap
Creates and maintains environment-specific compatibility surfaces, a normalized MCP catalog, and a local bootstrap flow to prepare AI coding assistants (Cursor, Claude Code, Codex, Antigravity, or similar) for a repository.
- tomevault-io Bundle AI Agent Financial Analyst
SaaS financial modeling engine that generates unit economics models, feature ROI calculators, pricing scenario analyses, TAM/SAM/SOM sizing, build-vs-buy comparisons, and revenue projections from natural language inputs. Use when building business cases, calculating LTV/CAC/payback, modeling pricing changes, estimating feature revenue impact, running sensitivity analyses, or preparing financial justifications for product investments. Produces actual calculations with explicit assumptions and sensitivity ranges. Use when this capability is needed.
- tomevault-io Bundle Detecting Information Disclosure
Detects information disclosure vulnerabilities including sensitive data in logs, error message exposure, and memory leaks. Use when analyzing logging practices, error handling, or investigating data leakage issues. Use when this capability is needed.
- tomevault-io Bundle Project Status Reporter
Read-only progress reporter. Produces a structured status snapshot from existing project/task artifacts (project hub + dev-docs), can include semantic focus extracted from LLM-authored feature briefs, and includes an actionable next command; never modifies repo files. Use when this capability is needed.
- tomevault-io Bundle Implement Agent Teams
Set up and validate Claude agent team configurations, collaboration flows, and operator guidance for team-based execution. Use when this capability is needed.
- tomevault-io Bundle Techdoc Search And Orchestrate
【强制】所有技术文档查询必须使用本技能，禁止在主对话中直接使用 mcp__context7-mcp 工具。触发关键词：查询/学习/了解某个库或框架的文档、API用法、配置参数、错误解释、版本差异、代码示例、最佳实践。本技能通过 context7-researcher agent 执行查询，避免大量文档内容污染主对话上下文，保持 token 效率。 Use when this capability is needed.
- tomevault-io Bundle Delegation Prompt Crafter
Transform clarified user requests into structured delegation prompts optimized for specialist agents (cto-architect, strategic-cto-mentor, cv-ml-architect). Use after clarification is complete, before routing to specialist agents. Ensures agents receive complete context for effective work. Use when this capability is needed.
- tomevault-io Bundle Create Beads Orchestration
Bootstrap lean multi-agent orchestration with beads task tracking. Use for projects needing agent delegation without heavy MCP overhead. Use when this capability is needed.
- tomevault-io Bundle Flutter Project Detector
Routes Flutter work to the correct specialist skill by reading pubspec.yaml. Activate this skill whenever the user is working in a Flutter project (any .dart file, pubspec.yaml, lib/ folder, or mention of Flutter, Dart, Riverpod, Provider, BLoC). It detects the project's stack (Firebase vs Supabase, Riverpod vs others, navigation, monetization) and tells the model which sibling skills to consult next. Trigger this skill BEFORE writing any Flutter code so the resulting code matches the project's existing patterns instead of imposing new ones. Critical for solo founders maintaining multiple Flutter apps with different stacks. Use when this capability is needed.
- tomevault-io Bundle Balneario De Cofrentes Notion CLI Agent Notion CLI Agent
Notion Workspace Onboarding
- tomevault-io Bundle Codex Intent Context Analyzer
Analyze code-change prompts into structured intent JSON with goal, constraints, missing info, normalized prompt, complexity, and confirmation gating. Use before implementation for build, fix, debug, review, and docs tasks. Use when this capability is needed.
- tomevault-io Bundle Generate Path Instructions
Generates path-specific instruction files (.github/instructions/*.md) with JIT loading via applyTo glob patterns. Performs LLM-driven repository analysis to discover file patterns and extract scope-specific rules. Use when the user requests scoped, framework-specific, or directory-specific rules for testing, components, docs, config files, or language-specific files to prevent context pollution. Works for code, documentation, configuration, and data files.
- tomevault-io Bundle Generate Repo Instructions
Generates the global repository constitution file (.github/copilot-instructions.md). Works for code repositories, documentation repositories, data repositories, and mixed repos. Performs LLM-driven deep repository analysis including docs, code patterns, build systems, documentation generators, and data schemas. Generates constitutional rules following context economics (under 1000 lines). Enforces positive constraints and no hardcoded secrets.
- tomevault-io Bundle Chambear2809 Splunk Cisco Skills Splunk MCP Server Setup
Splunk MCP Server Setup
- tomevault-io Bundle Embedding Pdb In Exe
Embeds PDB debugging symbols into EXE/DLL files. Use when configuring embedded debug symbols, single-file deployment, Source Link integration, or dotnet publish settings. Use when this capability is needed.
- tomevault-io Bundle Comprehensive Research Agent
Ensure thorough validation, error recovery, and transparent reasoning in research tasks with multiple tool calls Use when this capability is needed.
- tomevault-io Bundle Jina AI
Use Jina AI APIs for converting URLs to LLM-friendly Markdown (Reader) and searching the web (Search). Use when this capability is needed.
- tomevault-io Bundle IOS Swift Patterns
SwiftUI, UIKit, MVVM, Combine, async/await, Core Data, and App Store submission patterns Use when this capability is needed.
- tomevault-io Bundle Copilot Studio Rocket
Analyse Microsoft Copilot Studio agent YAML files and score agent instructions using the ROCKET framework (Role, Objectives, Constraints, Knowledge, Execute, Tone). Use when reviewing, auditing, improving, or templating Copilot Studio agent instructions. Triggers on phrases like "score my agent", "review these instructions", "ROCKET framework", "framework details", "framework template", "template for agent instructions", "help with Role", "help with Constraints", or when a .yaml file containing Copilot Studio agent configuration is provided. Use when this capability is needed.
- tomevault-io Bundle 2026 Legal Research Agent
Expert legal research agent for finding and scraping expungement data state by state. Knows authoritative sources, URL patterns, Firecrawl configuration, and 2026 legal landscape. Activate Use when this capability is needed.
- tomevault-io Bundle Cost Verification Auditor
Audit LLM token cost estimates against actual API usage. Activate on 'cost verification', 'token estimate accuracy', 'API cost audit', 'estimation variance'. NOT for pricing lookups, budget Use when this capability is needed.
- tomevault-io Bundle GRAPHQL Data Federation Agent
Federates data from multiple GraphQL and REST APIs using Apollo Federation gateway. Implements schema stitching with automatic type merging and the DataLoader pattern for N+1 prevention. Use when this capability is needed.
- tomevault-io Bundle GRAPHQL Schema Registry Agent
Manages federated GraphQL schemas using Apollo Studio API and Hive Schema Registry. Validates schema composition, detects breaking changes, and enforces naming conventions across subgraph services.
- tomevault-io Bundle Prompt Factory
World-class prompt powerhouse that generates production-ready mega-prompts for any role, industry, and task through intelligent 7-question flow, 69 comprehensive presets across 15 professional domains (technical, business, creative, legal, finance, HR, design, customer, executive, manufacturing, R&D, regulatory, specialized-technical, research, creative-media), multiple output formats (XML/Claude/ChatGPT/Gemini), quality validation gates, and contextual best practices from OpenAI/Anthropic/Google. Supports both core and advanced modes with testing scenarios and prompt variations. Use when this capability is needed.
- tomevault-io Bundle Refactor With Confidence
Safe code refactoring combining Sherpa's refactor workflow, Julie's reference checking and safe renaming, and Goldfish's before/after checkpointing. Activates for code improvement with systematic testing, refactoring, and verification. Use when cleaning up or improving existing code. Use when this capability is needed.
- tomevault-io Bundle Atlassian Atlassian MCP Server Search Company Knowledge
Search Company Knowledge
- tomevault-io Bundle Runbook Creation
Create operational runbooks and standard operating procedures. Document troubleshooting guides and recovery procedures. Use when documenting operational knowledge. Use when this capability is needed.
- tomevault-io Bundle Super GRAPHQL Architect Skill
GraphQL and Apollo architecture guidance for schemas, resolvers, Apollo Server, Apollo Client, Federation, Router, Rover, connectors, dataloaders, and performance. Use when this capability is needed.
- tomevault-io Bundle Audit Agentsmd
Audit AGENTS.md (or CLAUDE.md) for length, attention-zone misplacement, and extraction opportunities. Produces a prioritized report with reordering and extraction recommendations. Use when AGENTS.md exceeds 400 lines, after major additions, or when agent instruction compliance is poor. Use when this capability is needed.
- tomevault-io Bundle Analyzing Machine Learning In Investing
Evaluates ML applications in investment with feature engineering, model selection, and implementation considerations for alpha generation. Use when evaluating ML for investing, designing ML pipelines, or assessing ML strategy feasibility. Use when this capability is needed.
- tomevault-io Bundle Alicloud AI Video Wan R2v Test
Minimal reference-to-video smoke test for Model Studio Wan R2V. Use when this capability is needed.
- tomevault-io Bundle Comeonoliver Skillshub Training Machine Learning Models
Ml Model Trainer
- tomevault-io Bundle Infrastructure Management
Manage network hosts and devices across all UniFi sites. Monitor host status, device configuration, and infrastructure health for comprehensive inventory management. 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 layer-08-data-store, thinking-model-selection, kiro-custom-agents. 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.