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 Always Commit Skill To RepoSANDBOX PERSISTENCE REMINDER for Claude Code on the Web. The sandbox filesystem is ephemeral — only files committed to a git repository AND pushed to the remote survive after the session ends. Read this skill before/during/after any work that creates, writes, edits, modifies, drafts, or saves a file intended to outlive the current session. Applies universally — to skills, configuration, scripts, documentation, code, notes, reports, plans, hooks, workflows, anything else. Also applies before declaring a task complete (verify everything is committed AND pushed AND a PR is open and current). The required working pattern is feature-branch + commit + push + pull-request, and the PR must be kept current until it is merged. Files written to `~/.claude/`, `/tmp`, `/root`, or any path outside the current git working tree are LOST when the session ends. Triggers broadly on file operations and on session start. Use when this capability is needed.
- tomevault-io Bundle Langcare Langcare MCP Fhir Discharge Summary Writer
Discharge Summary Writer
- tomevault-io Bundle Langcare Langcare MCP Fhir Renal Function Dashboard
Renal Function Dashboard
- tomevault-io Bundle Dde Ext Verification Loop
DDE subordinate extension. Execute verification loop (build/type/lint/test/security/diff) and return a structured quality report. Use when this capability is needed.
- tomevault-io Bundle Lenny Skillpack Creator
Convert a Refound/Lenny Skill into an agent-executable Skill Pack. Use when this capability is needed.
- tomevault-io Bundle Goravel Crud Model
Generate a Goravel model from an existing database table with post-generation fixes and automatic GORM test creation. Use after running migration. Use when this capability is needed.
- tomevault-io Bundle Goravel Type Check
Cross-reference Go structs (model, requests) with TypeScript interfaces to verify type consistency, field coverage, nullable handling, and JSON tag alignment. Use when this capability is needed.
- tomevault-io Bundle Playwright UI Test
Use the Playwright MCP to verify UI integrity and functionality of the Goravel Inertia app. Tests page rendering, navigation, forms, CRUD operations, global search, and responsive layout via browser automation. Use when this capability is needed.
- tomevault-io Bundle MCP JS Reverse Playbook
在使用 MCP 做前端 JavaScript 逆向时使用，适用于签名链路定位、页面观察取证、本地补环境复现、VMP 类插桩分析、AST 去混淆与证据化输出。 Use when this capability is needed.
- tomevault-io Bundle Lmql Constraints
LMQL constraint-guided generation DSL for type-safe prompting with grammar constraints and logical conditions. Use when building structured LLM outputs with guaranteed format compliance, implementing constrained decoding with logical operators, creating type-safe prompt templates, or combining neural generation with symbolic constraints for reliable AI outputs. Use when this capability is needed.
- tomevault-io Bundle Copilot Custom Instructions
How to write and organize VS Code Copilot custom instructions (.instructions.md) and agent skills (SKILL.md). Use when creating, editing, reorganizing, or debugging custom instruction or skill files, or when asked about applyTo glob syntax. Use when this capability is needed.
- tomevault-io Bundle Skillopt Evolve Skills
Evolve Codex skills and agent instructions with a SkillOpt-style loop. Use when creating, refining, or auditing local skills, AGENTS.md rules, prompt playbooks, or reusable agent workflows after repeated task experience, especially when the user asks to "improve your skills", "capture this lesson", "make this reusable", or "update agent instructions". Use when this capability is needed.
- tomevault-io Bundle Issue Resolver
Autonomous issue resolution agent that investigates, plans, and fixes issues using sub-agents and browser-based validation. Use when the user provides one or more issues to resolve autonomously, wants hands-off debugging and fixing, or needs an orchestrated investigate-plan-execute-validate workflow. Use when this capability is needed.
- tomevault-io Bundle Magento API Developer
Designs and implements REST and GraphQL APIs for Magento 2. Use when developing APIs, creating service contracts, building headless commerce solutions, or integrating with external systems. Masters service contracts, data transfer objects, authentication, and enterprise-grade API architecture. Use when this capability is needed.
- tomevault-io Bundle Magento Cache Analyst
Optimizes Magento 2 caching strategies for enterprise performance. Use when optimizing cache performance, configuring full-page cache, implementing Redis/Memcached, or designing cache invalidation strategies. Masters FPC, application cache, and distributed caching solutions. Use when this capability is needed.
- tomevault-io Bundle Magento Index Analyst
Optimizes Magento 2 indexing for search performance and database efficiency. Use when optimizing search performance, configuring Elasticsearch, designing database indexes, or improving reindexing strategies. Masters indexer optimization, Elasticsearch configuration, and database indexing. Use when this capability is needed.
- tomevault-io Bundle Cyanheads Mailchimp MCP Server Release And Publish
Preconditions
- tomevault-io Bundle Mental Models
Apply Charlie Munger's latticework of mental models to any problem. Use when user requests decision analysis, says "help me think", "apply mental model", mentions model names (inversion, bottlenecks, second-order thinking), or needs structured thinking frameworks. Use when this capability is needed.
- tomevault-io Bundle Claude Code Litellm Gateway
Configure Claude Code to use an existing LiteLLM gateway safely, including both a low-risk wrapper path and an optional main-command switch so Claude Code can route to Gemini or other non-Anthropic models through LiteLLM. Use when this capability is needed.
- tomevault-io Bundle Davila7 Claude Code Templates Agent Memory Systems
Agent Memory Systems
- tomevault-io Bundle Google Docs Automation
Use when automating Google Workspace (Docs, Sheets, Slides) operations - covers authentication, common patterns, and best practices for gspread and googleapiclient
- tomevault-io Bundle Patterns Entity Modeling
This skill MUST be invoked when the user says "extract entities", "define data model", "model relationships", "entity modeling", or "domain model". SHOULD also invoke when user mentions "relationship", "cardinality", "state machine", or "data attributes". Use when this capability is needed.
- tomevault-io Bundle Autonomous Agent
CreditNexus x402 agent. Use when the user wants stock predictions, backtests, bank linking, or agent/borrower scores. Payment-protected MCP tools (run_prediction, run_backtest, link_bank_account, get_agent_reputation_score, get_borrower_score, and by-email variants) with x402 flow (Aptos + Base). Agent handles 402 → pay → retry autonomously. Supports wallet attestation (signing) for onboarding. Use when this capability is needed.
- tomevault-io Bundle Ghl Open Account
Guides agents through opening GoHighLevel (GHL) developer accounts, creating marketplace apps, and connecting via OAuth. Use when the user or agent needs to sign up for GHL, create a GHL app, get API credentials, or connect clawdbot/moltbot/open claw to GoHighLevel. Use when this capability is needed.
- tomevault-io Bundle Polymarket Agent
Install Python dependencies and poly CLI Use when this capability is needed.
- tomevault-io Bundle Didit Protocol Didit Agent Skills Didit Face Match
Didit Face Match API
- tomevault-io Bundle Claude Guide
Navigate Claude Code documentation and get quick answers about configuration, MCP, plugins, and best practices. Use when this capability is needed.
- tomevault-io Bundle Digitarald MCP Apps Playground MCP Apps Playground
MCP Apps Development
- tomevault-io Bundle Dotcreativeagency Claude Plugins Chain Enforcement
Mandatory Agent Chain Enforcement
- tomevault-io Bundle Checkout Customization
Customize Shopify checkout with UI extensions and functions. Use this skill for building checkout UI extensions, adding custom fields, implementing payment customizations, creating post-purchase experiences, and extending customer accounts. Covers Checkout UI Extensions API and checkout branding. Use when this capability is needed.
- tomevault-io Bundle Dev Context Engineering
Context-driven AI development with Claude Code and Codex. Use when transitioning teams to AGENTS.md workflows or multi-repo AI setups. Use when this capability is needed.
- tomevault-io Bundle X Ranking Engine
Use this skill when you need to reason about the machine learning models that determine the final order of the "For You" timeline. It is essential for tasks involving model feature engineering, tuning engagement weights, or understanding the internal mechanics of the Heavy Ranker (Navi).
- tomevault-io Bundle Eaa Label Taxonomy
GitHub label taxonomy reference for the Architect Agent. Use when designing architecture, identifying components, or recommending labels. Trigger with architecture label requests. Use when this capability is needed.
- tomevault-io Bundle Eaa Session Memory
Architecture decision and design pattern persistence. Use when preserving architectural context across sessions or creating design handoffs. Trigger with session start. Use when this capability is needed.
- tomevault-io Bundle Ecos Label Taxonomy
Use when applying or checking GitHub labels for agent assignment and status tracking. GitHub label taxonomy reference for the Chief of Staff Agent. Trigger with `/ecos-label-taxonomy`.
- tomevault-io Bundle Eia Quality Gates
Quality gate enforcement for PR integration. Use when verifying code through pre-review, review, pre-merge, or post-merge checkpoints. Trigger with /eia-enforce-gates. Use when this capability is needed.
Audited
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 always-commit-skill-to-repo, langcare--langcare-mcp-fhir--discharge-summary-writer, langcare--langcare-mcp-fhir--renal-function-dashboard. 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.