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 Test ValidationRuns the standard test sequence (smoke, unit, api, integration, then ui). UI uses --skip-playwright-js (pytest tests/ui only; no npx tests/playwright). Agent/workflow config-mutating tests stay excluded by run_tests.py ui defaults. Parses pass counts; does not fix failures.
- tomevault-io Bundle Ezcater Research
This skill should be used when the user asks to "investigate ezCater systems", "research architectural decisions", "understand code evolution", "find historical context", "analyze project history", "search internal documentation", or needs to understand why technical decisions were made at ezCater. Use this for lighter research where the user doesn't explicitly request "deep research" (which triggers the agent). Use when this capability is needed.
- tomevault-io Bundle Skill Reinforcement
Always and Automatically improve skills after each use by capturing learnings and anti-patterns Use when this capability is needed.
- tomevault-io Bundle Test Staging Branch
Test feature branches on Vercel preview deployments using Chrome automation and Gmail OTP Use when this capability is needed.
- tomevault-io Bundle Webinar Script Writing
This skill enables the agent to create high-converting webinar scripts using the frameworks of Jason Fladlien and Jon Penberthy. It covers the entire process from introduction and content structure to offer presentation, objection handling, and closing sequences. Use this skill for webinar script creation, webinar strategy, and improving webinar performance. Use when this capability is needed.
- tomevault-io Bundle Smart Bug Fix
Intelligent bug fixing workflow combining root cause analysis, multi-model reasoning, Codex auto-fix, and comprehensive testing. Uses RCA agent, Codex iteration, and validation to systematically fix bugs. Use when this capability is needed.
- tomevault-io Bundle Managing Database Migrations
AI agent implements safe database migrations with zero-downtime strategies, rollback plans, and expand-contract patterns. Use when creating migrations, deploying schema changes, or implementing zero-downtime database updates. Use when this capability is needed.
- tomevault-io Bundle Tracing Root Causes
AI agent performs systematic root cause analysis using 5 Whys, Fishbone diagrams, and evidence-based investigation. Use when debugging, conducting post-mortems, or investigating incidents. Use when this capability is needed.
- tomevault-io Bundle Optimizing Tokens
AI agent maximizes efficiency and minimizes costs through strategic token usage while maintaining output quality. Use when managing AI interactions, designing prompts, or reducing costs. Use when this capability is needed.
- tomevault-io Bundle Sdlc Workspace Init
Initialize a new repository with SDLC workspace files — MCP config, copilot-instructions.md, quality instructions, and prompt files. Use when setting up a new project, bootstrapping SDLC, onboarding a repo, or when Harness detects missing workspace files. Use when this capability is needed.
- tomevault-io Bundle Model Selection
Select appropriate AI/ML models based on capability matching, benchmarks, cost-performance tradeoffs, and deployment constraints. Use when this capability is needed.
- tomevault-io Bundle IOS Security
Reviews iOS/Swift code for security vulnerabilities, data protection issues, and privacy compliance including OWASP Mobile Top 10 Use when this capability is needed.
- tomevault-io Bundle Agent Troubleshooting
Diagnoses Buildkite agent issues like stuck jobs and queue mismatches. Use when this capability is needed.
- tomevault-io Bundle Melsaeed276 Flutter Agent Skills Navigation
Skill: Navigation (go_router + Navigator 1.0)
- tomevault-io Bundle Mguinada Agent Skills Phoenix Observability
Phoenix - AI Observability Platform
- tomevault-io Bundle Michaelsvanbeek Personal Agent Git Workflow
Git Workflow Standards
- tomevault-io Bundle Tom Operations
Guide for working with the TOM (Tabular Object Model) wrapper. Use this when modifying semantic models programmatically. Use when this capability is needed.
- tomevault-io Bundle Managing Claude Code Meta
MUST be loaded when setting up, installing, migrating, reviewing, auditing, or checking CLAUDE.md files in projects. Covers installing the promode CLAUDE.md into new projects, migrating existing CLAUDE.md content to AGENT_ORIENTATION.md (progressive disclosure), and auditing projects for conformance. Invoke PROACTIVELY when user mentions CLAUDE.md, project setup, agent configuration, or code meta files. Use when this capability is needed.
- tomevault-io Bundle Idea Reality
Pre-build reality check — scan GitHub, HN, npm, PyPI, Product Hunt for existing prior art before you build. Use when this capability is needed.
- tomevault-io Bundle Modbender Skill Library MCP AI Agent Helper
---
- tomevault-io Bundle Modbender Skill Library MCP AI Editor Rules
---
- tomevault-io Bundle Modbender Skill Library MCP Email Organizer
---
- tomevault-io Bundle Modbender Skill Library MCP Next Config Gen
---
- tomevault-io Bundle Modbender Skill Library MCP Nodejs Patterns
Node.js Backend Patterns
- tomevault-io Bundle Modbender Skill Library MCP Phoenix API Gen
---
- tomevault-io Bundle M5 Onboard
End-to-end onboarding for a freshly-plugged-in M5Stack ESP32 device — detect it on USB, identify the exact model, flash UIFlow 2.0 firmware, and install a MicroPython app bundle (e.g. the Claude Buddy + Hello + Snake payload) so the device boots into user software instead of UIFlow's pairing screen. Works on macOS, Linux, and Windows; Python, esptool, and pyserial are auto-installed by the skill if missing. The apps we ship run over BLE / USB. Use this skill whenever the user mentions an M5Stack, M5Core, M5Stick, Cardputer, Cardputer-Adv, CoreS3, Core2, UIFlow, "flashing" or "provisioning" an ESP32 dev board, or plugs in "a new device" after previously working with M5Stack hardware. Also use it if the user asks to push app .py files onto an already-flashed device, install "the games" or "buddy" onto a board, or reset one to factory UIFlow. Trigger even when the user doesn't explicitly name the skill — "I have another one of these", "same thing for this device", "put the game on this one too", "m5-onboard", or
- tomevault-io Bundle Python Packaging Uv
Use when building or publishing Python packages with uv, including dist artifacts and pre-publish checks.
- tomevault-io Bundle Gh Issue Dev
Dev agent workflow for implementing a GitHub issue end-to-end in a git worktree (code + tests + E2E + PR). Use as the Dev sub-agent. Use when this capability is needed.
- tomevault-io Bundle Paperless Search
Search documents in Paperless-ngx via REST API. Full-text search, tag/correspondent filtering, and direct links to documents. Use when this capability is needed.
- tomevault-io Bundle Nosmoht Review Claude Config Scaffold Agent
Agent Scaffolding
- tomevault-io Bundle Duckduckgo Search
Free web search via DuckDuckGo — text, news, images, videos. No API key needed. Prefer the `ddgs` CLI when installed; use the Python DDGS library only after verifying that `ddgs` is available in the current runtime. Use when this capability is needed.
- tomevault-io Bundle Touchdesigner MCP
Control a running TouchDesigner instance via twozero MCP — create operators, set parameters, wire connections, execute Python, build real-time visuals. 36 native tools. Use when this capability is needed.
- tomevault-io Bundle Nemo Mbridge Perf Hierarchical Context Parallel
Operational guide for enabling hierarchical context parallelism in Megatron-Bridge, including config knobs, code anchors, pitfalls, and verification. Use when this capability is needed.
- tomevault-io Bundle Hone
AI CLI configuration auditing and optimization agent. Collects official best practices for Codex CLI (~/.codex/), Gemini CLI (~/.gemini/), and Claude Code (~/.claude/) from the web, analyzes config.toml/settings.json/CLAUDE.md/GEMINI.md/AGENTS.md/permissions/commands/hooks/rules/MCP/extensions, and proposes improvements in Before/After diff format. Does not edit configurations directly. Use when this capability is needed.
Audited - tomevault-io Bundle Openhands Software Agent Sdk Python Linting
Python Linting Skill
- tomevault-io Bundle Paiml Apr Model QA Playbook Coverage Kaizen
Coverage Kaizen
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 test-validation, ezcater-research, skill-reinforcement. 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.