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 Security Github ReviewSecurity review workflow for GitHub repositories using the Security MCP (OWASP ASVS + NIST 800-53) as the primary reference and mapping layer. Use when asked to security review a repo, produce an OWASP/NIST-aligned checklist, map findings to ASVS/NIST controls, generate a prioritized vulnerability report, or create security requirements/acceptance criteria from repo code/config. Use when this capability is needed.
- tomevault-io Bundle Benchmark And Docs Refresh
Run or continue model benchmarks, collect measured results, and refresh README/docs benchmark sections from generated artifacts. Use when benchmark tables in model docs need to be created, updated, or corrected. Use when this capability is needed.
- tomevault-io Bundle Toggle Proactive
Toggle proactive messaging mode. When enabled, Agent proactively sends greetings, task reminders, and key recaps via IM channel. Use when user asks to enable/disable proactive messages. Use when this capability is needed.
- tomevault-io Bundle Openhands Software Agent Sdk Linting
Python Linting Skill
- tomevault-io Bundle Orxaq Autonomy Agent
Run resilient autonomous software-delivery cycles with protocol-driven prompts, optional MCP context injection, and cross-platform non-admin supervision. Use when this capability is needed.
- tomevault-io Bundle Multi Agent Vcs
This skill should be used when dispatching subagents for parallel development, coordinating multi-branch implementations, or when "parallel agents", "orchestrator commits", "subagent filesystem only", "multi-agent git", or "prevent stack corruption" are mentioned. Prevents stack corruption through orchestrator-only git policy. Use when this capability is needed.
- tomevault-io Bundle Plugin Engineer
Transforms external repositories (CLIs, libraries, MCP servers) into Claude Code plugins with skills. Use when "build plugin for", "create skills for CLI", "package as plugin", "repo to plugin", or "turn into plugin" are mentioned. Use when this capability is needed.
- tomevault-io Bundle Stack Templates
Templates for creating handlers, CLI commands, MCP tools, and daemon services following Outfitter Stack conventions. Use when scaffolding new components, creating handlers, adding commands, or when "create handler", "new command", "add tool", "scaffold", "template", or "daemon service" are mentioned. Use when this capability is needed.
- tomevault-io Bundle Agno
Agno AI agent framework. Use for building multi-agent systems, AgentOS runtime, MCP server integration, and agentic AI development. Use when this capability is needed.
- tomevault-io Bundle Testing Browser Manual
Manual browser UI verification via MCP snapshots with reproducible steps and observed behavior; not automation design Use when this capability is needed.
- tomevault-io Bundle Sindri Extension Guide
Guide users through creating Sindri extensions. Use when creating new extensions, understanding extension.yaml structure, validating extensions against schemas, or learning about extension installation methods (mise, apt, binary, npm, script, hybrid). Includes NEW capabilities system for project-init, authentication (multi-method API key + CLI auth), lifecycle hooks, and MCP integration. Helps with extension development, registry updates, and category assignment. Use when this capability is needed.
- tomevault-io Bundle Pjt222 Agent Almanac Use GRAPHQL API
GraphQL-API verwenden
- tomevault-io Bundle Pjt222 Agent Almanac Version Ml Data
Version ML Data
- tomevault-io Bundle Covariant Modification
Unified skill modification with covariant transport, Darwin Gödel Machine evolution, and MCP Tasks self-rewriting. GF(3) conserved. Use when this capability is needed.
- tomevault-io Bundle Rust Android Telemetry
Telemetry and observability discipline for the RIPDPI Android Rust stack — control-plane vs data-plane channel selection (android_logger vs tracing), bounded event ring choice (broadcast vs ArrayQueue), atomic counters, pull-model 1Hz polling, deterministic JSON serialization for goldens. Use when authoring or modifying telemetry emission code, the bounded event ring, the Kotlin-side telemetry consumer, or any per-packet logging. Use when this capability is needed.
- tomevault-io Bundle Workflow Manager
Coordinate the multi-agent workflow across planning, validation, implementation, and verification. Use when this capability is needed.
- tomevault-io Bundle People Research
People research using Exa search. Finds LinkedIn profiles, professional backgrounds, experts, team members, and public bios across the web. Use when searching for people, finding experts, or looking up professional profiles. Use when this capability is needed.
- tomevault-io Bundle Update Agent
Create, update, or manage universal-ai-config agent templates. Handles finding existing agents, deciding whether to create or modify, and writing the template. Use when this capability is needed.
- tomevault-io Bundle Agent Card Hooks
Guide for implementing fast-agent hooks. Use when adding hook functions to agent cards or Python code for tasks like history compaction, saving sessions, modifying tool calls, or managing agent lifecycle. Use when this capability is needed.
- tomevault-io Bundle Workspace Surface Audit
Audit the active repo, MCP servers, plugins, connectors, env surfaces, and harness setup, then recommend the highest-value EGC-native skills, hooks, agents, and operator workflows. Use when the user wants help setting up Gemini Code or understanding what capabilities are actually available in their environment. Use when this capability is needed.
- tomevault-io Bundle Django Create Model
Steps for creating or modifying a Django model Use when this capability is needed.
- tomevault-io Bundle Arcanea Coding Agent
Arcanea creative agent integration for opencode Use when this capability is needed.
- tomevault-io Bundle Crafting Rules
Use when creating or modifying OpenCode rules (.md/.mdc files) that customize agent behavior. Trigger when user wants to create a rule, codify repeated instructions, persist guidance across sessions, or scope rules to specific files, prompts, environments, or workflows.
- tomevault-io Bundle Jira Management
This skill should be used when the user asks about Jira issues, tickets, projects, sprints, or bug tracking. Activates for creating, updating, searching, or commenting on Jira issues. Use when this capability is needed.
- tomevault-io Bundle Baml Codegen
Generates production-ready BAML applications from natural language requirements. Creates complete type definitions, functions, clients, tests, and framework integrations for data extraction, classification, RAG, and agent workflows. Queries official BoundaryML repositories via MCP for real-time patterns. Supports multimodal inputs (images, audio), 6 programming languages (Python, TypeScript, Ruby, Java, Go, C#), 10+ frameworks, 50-70% token optimization, and 95%+ compilation success.
- tomevault-io Bundle Stable Diffusion
Stable Diffusion image generation models. Use for image AI. Use when this capability is needed.
- tomevault-io Bundle Gamekit CLI
Creating pickups, collectibles, coins, power-ups, and items Use when this capability is needed.
- tomevault-io Bundle Geq1fan Prompt Optimizer Skill Skills
提示词优化器
- tomevault-io Bundle Workiq Copilot
Guides the Copilot CLI on how to use the WorkIQ CLI/MCP server to query Microsoft 365 Copilot data (emails, meetings, docs, Teams, people) for live context, summaries, and recommendations. Use when this capability is needed.
- tomevault-io Bundle Mnemo Cortex
Installs and wires Mnemo Cortex (local-first persistent memory) into OpenClaw and other MCP-capable agents. Use for cross-session recall, decision history, or multi-agent shared memory. Use when this capability is needed.
- tomevault-io Bundle Aesthetic
Create aesthetically beautiful interfaces following proven design principles. Use when building UI/UX, analyzing designs from inspiration sites, generating design images, implementing visual hierarchy and color theory, adding micro-interactions, or creating design documentation. Integrate localized specialized skills (chrome-devtools, ImageMagick) with native vision intelligence to achieve premium aesthetic standards. Use when this capability is needed.
- tomevault-io Bundle Senior QA
Comprehensive QA and testing skill for quality assurance, test automation, and testing strategies for ReactJS, NextJS, NodeJS applications. Includes test suite generation, coverage analysis, E2E testing setup, and quality metrics. Use when designing test strategies, writing test cases, implementing test automation, performing manual testing, or analyzing test coverage. Use when this capability is needed.
- tomevault-io Bundle Hershate Meta Skill Deepwiki AI Agent
DeepWiki AI Agent
- tomevault-io Bundle Model Health Check
AI model health monitoring and diagnostics Use when this capability is needed.
- tomevault-io Bundle Huggingface AI Deadlines AI Deadlines
Install: `curl -LsSf https://hf.co/cli/install.sh | bash -s`.
- tomevault-io Bundle Add Or Fix Type Checking
Fixes broken typing checks detected by ty, make typing, or make check-repo. Use when typing errors appear in local runs, CI, or PR logs. 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 update-agent, security-github-review, benchmark-and-docs-refresh. 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.