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 Auth0 MigrationUse when migrating or switching from an existing auth provider (Firebase, Cognito, Supabase, Clerk, custom auth) to Auth0 - covers bulk user import, gradual migration strategies, code migration patterns, and JWT validation updates.
-
tomevault-io Bundle With Context AgentUse when testing valid context and agent configuration
-
tomevault-io Bundle Thrunt List Phase AssumptionsSurface the agent's assumptions about a phase approach before planning Use when this capability is needed.
-
tomevault-io Bundle Skill EnhanceGuide for enhancing and improving existing skills based on conversation analysis and usage feedback. This skill should be used when the Skill Sub-Agent needs to update or strengthen an existing skill by adding new patterns, fixing issues, or improving content quality based on observed usage. Use when this capability is needed.
-
tomevault-io Bundle Mobile App FlowsUnderstand and explore the Omi Flutter mobile app's UI flows, navigation patterns, and widget architecture. Use when developing features, fixing bugs, or verifying changes in app/lib/ Dart files. Provides agent-flutter commands to explore the live app, understand how screens connect, and verify your work. Use when this capability is needed.
-
tomevault-io Bundle Chatgpt2api SearchUse when current web search is needed through this chatgpt2api server. Call the configured HTTP search endpoint with a prompt and return the answer with source URLs.
-
tomevault-io Bundle Code Review EvalCompare bramble code-review output across reviewer configs (cursor with composer-2, codex with gpt-5.4-mini, gemini with gemini-3.1-flash-lite-preview). Runs each config three times against the same branch — turn 1 fresh, turn 2 resumed with default follow-up prompt, turn 3 resumed with fresh prompt — to also characterize backend resume behavior, then compares findings side-by-side and logs results. Use when this capability is needed.
-
tomevault-io Bundle Bdfinst Agentic Dev Team Agent AddAgent Add
-
tomevault-io Bundle Setup EnvWhen given a Python project codebase, this skill helps the agent to set up virtual environments, install dependencies, and run scripts. Use when this capability is needed.
-
tomevault-io Bundle Feature Developer负责 NoMoreDay Track 的落地执行与收尾。严格按 feature-planner 产出的 Spec/Plan 推进,并遵循当前五阶段工作流:Context(先读 memory MCP)-> Implement(最小改动实现)-> Verify(先 build.bat,再按需 CTest)-> TrackSync(同步 plan/validation/metadata/tracks 与 bug_registry)-> Closeout(归档、提交、git notes、memory 收尾)。当方案已确定,需要进入编码、验证、文档同步和闭环交付时激活。 Use when this capability is needed.
-
tomevault-io Bundle Blockscout MCP Server Consult SpecSPEC.md Consultation Skill
-
tomevault-io Bundle Gh Issue BugGenerate a structured bug report for GitHub issues based on conversation context about bugs, errors, or broken functionality Use when this capability is needed.
-
tomevault-io Bundle Gas FakesThis skill is used to maintain and update the `gf_agent` (Google Apps Script Local Automation Agent). It ensures the agent's internal skills, index, and documentation stay synchronized with the latest implementations in `gas-fakes`. Use when this capability is needed.
-
tomevault-io Bundle Vibe CodingLLM-readable code standards. Functions ≤50 lines, files ≤200 lines, nesting ≤3 levels. SRP, DRY, KISS, Early Return. Use when this capability is needed.
-
tomevault-io Bundle Malo Find SkillsHelps users discover and install agent skills when they ask questions like "how do I do X", "find a skill for X", "is there a skill that can...", or express interest in extending capabilities. This skill should be used when the user is looking for functionality that might exist as an installable skill. Use when this capability is needed.
-
tomevault-io Bundle Mcaf Adr WritingCreate or update an ADR under `docs/ADR/` for architectural decisions, dependency changes, data-model changes, or cross-cutting policy shifts. Use when the user asks to write, update, or document an ADR, record a design decision, capture architecture trade-offs, or justify a repo-wide technical policy. Use when this capability is needed.
-
tomevault-io Bundle Comfyui NodesUse this skill when creating, modifying, or debugging ComfyUI custom nodes. Triggers on: 'ComfyUI custom node', 'ComfyUI node development', 'ComfyUI plugin', 'INPUT_TYPES', 'NODE_CLASS_MAPPINGS', 'RETURN_TYPES', 'define_schema', 'io.ComfyNode', or any request to build a new node for ComfyUI. Covers both V1 (current) and V3 (new) node APIs.
-
tomevault-io Bundle Prp GeneratorAuto-activates when generating Product Requirements Prompt (PRP) documents Use when this capability is needed.
-
tomevault-io Bundle Grill With DocsGrilling session that challenges your plan against the existing domain model, sharpens terminology, and updates documentation (CONTEXT.md, ADRs) inline as decisions crystallise. Use when user wants to stress-test a plan against their project's language and documented decisions. Use when this capability is needed.
-
tomevault-io Bundle Sub Agent CreatorGuide for creating effective OpenKosmos sub-agents. Use when users want to create a new sub-agent (or update an existing sub-agent) that can be delegated specialized tasks by a parent agent. Covers AGENT.md file format, YAML front-matter configuration, system prompt writing, tool/MCP/skill configuration, context access modes, and Claude Code compatibility. Use when this capability is needed.
-
tomevault-io Bundle Millionco Debug Agent Debug AgentWeb Performance
-
tomevault-io Bundle Commit Docsデプロイ不要な変更をコミット([skip-cd]付きでAmplifyデプロイをスキップ) Use when this capability is needed.
-
tomevault-io Bundle Sync IssuesGitHubのissueとdocs/todo.mdを双方向同期する。新規issueをTODOに追加し、完了したTODOのissueをクローズする。 Use when this capability is needed.
-
tomevault-io Bundle Native Web SearchTrigger native web search. Use when you need quick internet research with concise summaries and full source URLs. Use when this capability is needed.
-
tomevault-io Bundle Agent DelegateDelegate tasks to other AI agents — Moltis for deep research/analysis, TG-Kombain for complex multi-step automation. Use ONLY for inter-agent delegation where another agent's reasoning is needed. Do NOT use for system commands (publish, music, status) — use n8n-api skill instead. Do NOT use for data queries — use tg-kombain skill instead. Requires N8N_BASE_URL environment variable. Use when this capability is needed.
-
tomevault-io Bundle Modbender Skill Library MCP CI CD---
-
tomevault-io Bundle Motosan AIHelp developers use the motosan-ai SDK (Python and Rust) and the codex-oauth crate — LLM chat, streaming, tool use, ThinkStripper, multi-provider setup, Gemini HTTP/Code Assist providers, and Codex OAuth login. Use when code imports motosan_ai or codex_oauth, or user asks how to integrate Anthropic/OpenAI/Ollama/MiniMax/Gemini via motosan-ai, implement streaming, handle tool calls, filter <think> tags, or get an OpenAI Codex access token. Use when this capability is needed.
-
tomevault-io Bundle Mthines Agent Skills Code QualityCode Quality Skill
-
tomevault-io Bundle Mthines Agent Skills Rum TrackingRUM Tracking
-
tomevault-io Bundle Forensics Disk磁盘取证分析技术,涵盖 NTFS/FAT/ext 文件系统解析、文件恢复、时间线分析、日志挖掘等实战技能。 Use when this capability is needed.
-
tomevault-io Bundle Nayuta Agent Skills Security ScanSecurity Scan
-
tomevault-io Bundle Lens MCP DesktopInstall the lens MCP server and register it with Claude Desktop Use when this capability is needed.
-
tomevault-io Bundle Spec BuilderGenerate comprehensive specification documents including requirements, technical design, and detailed task breakdown from any feature request. Use when the user asks to create specs, requirements docs, design docs, or needs to break down a feature into implementation tasks. Perfect for planning new features, understanding system architecture, or preparing work for AI coding agents. Use when this capability is needed.
-
tomevault-io Bundle ShopifyShopify Admin & Storefront GraphQL APIs via curl. Products, orders, customers, inventory, metafields. Use when this capability is needed.
-
tomevault-io Bundle OrchestrationMulti-agent orchestration for complex tasks. Use when tasks require parallel work, multiple agents, or sophisticated coordination. Triggers include requests for features, reviews, refactoring, testing, documentation, or any work that benefits from decomposition into parallel subtasks. This skill defines how to orchestrate work using cc-mirror tasks for persistent dependency tracking and TodoWrite for real-time session visibility. Use when this capability is needed.
-
tomevault-io Bundle Create Agent SkillCreate a new Agent Skill following project standards and templates. Use this when you need to encapsulate a new capability or workflow. 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 auth0-migration, with-context-agent, thrunt-list-phase-assumptions. 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.